Ultrasonic adaptive sensing safety protection method, device and medium

Abstract

The present application relates to the field of ultrasonic sensor technology, and in particular to an ultrasonic adaptive sensing safety protection method, computer equipment and storage medium. It includes pre-acquiring the human body sensing signal of the current user detected by the ultrasonic sensor, and identifying the human body feature data based on the signal; then acquiring the real-time sensing signal and identifying the sensing feature data; then judging the human body condition within the current sensing range based on the sensing feature data and the human body feature data, and finally performing safety protection based on the human body condition within the sensing range. The present application achieves the effect of improving the reliability and security of the safety protection of the direct-drive steering wheel control driving simulation software, effectively avoiding misjudgment and missed detection, and ensuring the user experience.

Description

Technical Field

[0001] The present application relates to the technical field of ultrasonic sensors, and in particular to an ultrasonic adaptive sensing safety protection method, device and medium. Background Art

[0002] In the application of direct-drive steering wheel control driving simulation software, users usually need to fix the direct-drive steering wheel on a desktop or a dedicated bracket, and control the steering wheel with both hands, while using their feet to control the accelerator, brake and clutch pedals located below, so as to simulate the real driving scene. In the actual operation process, in order to more realistically simulate the actual racing operation scene, the direct-drive steering wheel will produce a relatively large operating resistance to fight against the hands of the game players. The user's hands need to exert force to fight against the resistance of the direct-drive steering wheel and complete the steering wheel control. At this time, if the user temporarily leaves or an emergency occurs and no one controls the steering wheel, the steering wheel will enter the idling state, and the direct-drive motor will still output the corresponding torque according to the simulation scene to drive the steering wheel to rotate. When encountering special scenes, such as continuous sharp turns, bumpy scenes, and scenes where the front of the car swings left and right, the direct-drive motor will output a larger torque to adapt to the above special scenes. If no one is operating at this time, the steering wheel is in an idling state with large torque and frequent and rapid forward and reverse rotation. If other people, especially children, accidentally put their hands into the steering wheel, it is easy to cause hand injuries or even finger fractures and other dangerous situations.

[0003] Therefore, in order to ensure the authenticity and safety of the user experience, it is usually necessary to detect the user's usage status in real time to achieve automatic safety protection functions. However, the methods of the prior art have obvious limitations in practical applications. For example, the user's body movement forward and backward during operation will cause misjudgment, and users of different body shapes will also affect the accuracy of detection. In addition, users wearing clothes of different thicknesses in different seasons and different types of chairs may make it impossible to accurately judge whether the user is in place, resulting in the problem of poor reliability and safety of the method of safety protection based on sensing. Summary of the invention

[0004] The purpose of this application is to provide an ultrasonic adaptive sensing safety protection method, device and medium to improve the reliability and safety of the safety protection of direct-drive steering wheel control driving simulation software.

[0005] In the first aspect, the ultrasonic adaptive sensing safety protection method provided by the present application adopts the following technical solution: An ultrasonic adaptive sensing safety protection method, comprising: Pre-acquire a human body sensing signal of a current user detected by an ultrasonic sensor; Identify human body feature data according to the human body sensing signal, wherein the human body feature data includes human body shape features and human body distance features; Acquire real-time sensing signals detected by ultrasonic sensors; Identify sensing feature data according to the real-time sensing signal; Determine the human body condition within the current sensing range according to the sensing feature data and the human body feature data, wherein the human body condition includes the human body existence condition and the human body movement condition; Provide safety protection based on the human body conditions within the sensing range.

[0006] By adopting the above technical solution, this application can accurately judge the user's usage status in complex environments through multi-level data collection and analysis, significantly reducing the misjudgment caused by factors such as user body movement and body shape differences. At the same time, through real-time monitoring and intelligent decision-making mechanisms, automated safety protection is achieved, improving the reliability and safety of the direct-drive steering wheel control driving simulation software safety protection.

[0007] Preferably, the identifying of human body characteristic data according to human body sensing signals comprises: Performing intensity analysis on human body sensing signals to obtain human body shape intensity characteristics and human body distance intensity characteristics; Performing Doppler effect analysis on human body sensing signals to obtain human body shape Doppler characteristics and human body distance Doppler characteristics; Performing signal pattern recognition on human body sensing signals to obtain human body shape pattern features and human body distance pattern features; The human body shape intensity feature, the human body shape Doppler feature and the human body shape mode feature are fused to obtain the human body shape feature; The human body distance intensity feature, human body distance Doppler feature and human body distance pattern feature are fused to obtain the human body distance feature.

[0008] Preferably, the intensity analysis of the human body sensing signal to obtain the human body shape intensity feature and the human body distance intensity feature specifically includes: According to the intensity change of the human body sensing signal, combined with the reflection area and reflectivity of different parts of the human body, the human body shape intensity characteristics are obtained; According to the strength of the human body sensing signal, combined with the transmitting power and receiving sensitivity of the ultrasonic sensor, the human body distance intensity characteristics are obtained.

[0009] Preferably, the performing of Doppler effect analysis on the human body sensing signal to obtain the human body shape Doppler characteristics and the human body distance Doppler characteristics specifically includes: Identify the tiny movements of the human body according to the human body sensing signal, and obtain the Doppler characteristics of the human body shape according to the tiny movements of the human body, wherein the tiny movements include breathing and heartbeat; The movement state of the human body is determined by analyzing the Doppler frequency shift of the human body sensing signal, and the human body distance Doppler characteristics are obtained.

[0010] Preferably, the signal pattern recognition of the human body sensing signal to obtain the human body shape pattern characteristics and the human body distance pattern characteristics specifically includes: Constructing and training a human body shape feature recognition model, and obtaining human body shape pattern features according to the human body shape feature recognition model; Construct and train a human body distance feature recognition model, and obtain human body distance pattern features based on the human body distance feature recognition model.

[0011] Preferably, judging the human body condition within the current sensing range according to the sensing feature data and the human body feature data includes: Judging whether there is a human body within the current sensing range according to the human body shape characteristics and sensing feature data; When there is a human body within the sensing range, it is determined whether the human body is currently moving based on the human body distance characteristics and the sensing characteristic data.

[0012] Preferably, the safety protection according to the human body condition within the sensing range includes: When there is no human body within the sensing range, the control device enters a sleep state or sends a pause signal; When the device enters the sleep state or sends a pause signal, it receives a wake-up signal and controls the device to enter the wake-up state; When the device enters the sleep state or sends a pause signal, if no wake-up signal is received within the preset time, the device is controlled to enter the shutdown state.

[0013] Preferably, the safety protection according to the human body condition within the sensing range also includes: When there is a human body within the sensing range and the human body is moving, the time difference change of the real-time sensing signal is continuously monitored, and the movement of the human body is determined by the time difference change; When the time difference changes to continue to increase, it is determined that the current human body continues to move far away, and when it continues to move far away after a preset time, the control device enters a sleep state or sends a pause signal.

[0014] In a second aspect, the present application provides a computer device that adopts the following technical solution: A computer device comprises a memory and a processor, wherein the memory stores an ultrasonic adaptive sensing safety protection method as described in the first aspect which can be loaded and executed by the processor.

[0015] In a third aspect, the present application provides a computer-readable storage medium that adopts the following technical solution: A computer-readable storage medium stores a computer program that can be loaded by a processor and execute an ultrasonic adaptive sensing safety protection method as described in the first aspect.

[0016] In summary, the present application includes at least one of the following beneficial technical effects: 1. Through multi-level data collection and analysis, this application can accurately judge the user's usage status in complex environments, significantly reducing the misjudgment problem caused by factors such as user body movement and body shape differences; 2. This application realizes automated safety protection through real-time monitoring and intelligent decision-making mechanisms, and improves the reliability and safety of the safety protection of direct-drive steering wheel control driving simulation software; 3. This application obtains human body feature data in advance, and then determines the human body condition within the current sensing range based on the sensed feature data and the human body feature data, which can effectively solve the problem in the prior art that the detection results are affected by the user's body shape, clothing, and forward and backward movement. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a flow chart of the ultrasonic adaptive sensing safety protection method according to an embodiment of the present application; Figure 2 This is a specific method flow chart of step S2 of an embodiment of the present application. DETAILED DESCRIPTION

[0018] The following is combined with Figure 1-2 , the technical solution of the present application is clearly and completely described, and the described embodiments are only possible technical implementations of the present invention, not all possible implementations. Those skilled in the art can completely combine the embodiments of the present invention to obtain other embodiments without creative work, and these embodiments are also within the scope of protection of the present invention.

[0019] The inventor of the present application found that when users use a direct-drive steering wheel to control driving simulation software, they usually fix the direct-drive steering wheel on the edge of a table or a special bracket. Although it looks different, the basic operation method is the same: the user sits on a chair and controls the steering wheel with both hands, and the pedals are located under the feet and controlled by both feet. In order to ensure safety, an ultrasonic sensor is set on the base of the steering wheel to detect whether the user is in the seat and decide whether to stop the steering wheel motor. However, due to problems such as the user's body moving forward and backward, body shape differences, clothing changes, and different states of the chair, the ultrasonic sensor may misjudge. To this end, the present application mainly adopts the following ultrasonic adaptive sensing safety protection method, which achieves accurate judgment of the user's usage status through multi-level data collection and analysis, significantly reduces the problem of misjudgment, and improves the stability and safety of the system.

[0020] The embodiment of the present application provides an ultrasonic adaptive sensing safety protection method, which aims to detect the presence and movement of a user through an ultrasonic sensor, thereby realizing an automatic safety protection function. Figure 1 , the method steps of the embodiment of the present application include: S1. Pre-acquire a human body sensing signal of a current user detected by an ultrasonic sensor.

[0021] Specifically, the human body sensing signal of the current user is first acquired in advance through an ultrasonic sensor. The ultrasonic sensor here can be single or multiple. For example, two ultrasonic sensors can be installed on both sides of the steering wheel base to improve the accuracy of detection. These sensors can use high-frequency ultrasonic waves, such as 40 kHz, with higher resolution and lower interference.

[0022] S2. Identify human body feature data according to the human body sensing signal.

[0023] Specifically, the human body feature data includes human body shape features and human body distance features. For human body shape features, they can be obtained by analyzing the intensity of ultrasonic signals. For example, the reflection area and reflectivity of different parts of the human body will affect the intensity of ultrasonic signals. By comprehensively analyzing these parameters, more accurate human body shape features can be obtained. In addition, the Doppler effect can be used to analyze the tiny movements of the human body, such as breathing and heartbeat, to obtain more detailed human body shape Doppler features. Finally, through the signal pattern recognition technology, the corresponding human body shape feature recognition model is constructed and trained, and multiple features are further integrated to form the final human body shape feature. Similarly, for human body distance features, similar steps can also be used for identification. First, the distance intensity feature of the human body is calculated by combining the intensity change of the ultrasonic signal with the transmitting power and receiving sensitivity of the sensor. Then, the movement state of the human body is analyzed by the Doppler effect to obtain the human body distance Doppler feature. Finally, through the signal pattern recognition technology, the corresponding human body distance feature recognition model is constructed and trained, and multiple features are further integrated to form the final human body distance feature.

[0024] S3. Acquire the real-time sensing signal detected by the ultrasonic sensor.

[0025] S4. Identify sensing feature data according to the real-time sensing signal.

[0026] Specifically, after obtaining the preliminary human feature data, the ultrasonic sensor's sensing signal is detected in real time, and the sensing feature data is identified based on these real-time signals. This process also involves multiple steps such as intensity analysis, Doppler effect analysis, and signal pattern recognition to ensure that the user's real-time dynamics can be accurately captured.

[0027] S5. Determine the human body condition within the current sensing range according to the sensing feature data and the human body feature data.

[0028] Specifically, the human body condition includes the human body existence and human body movement. If the judgment result shows that there is a human body within the current sensing range, it is further judged whether the human body is in a moving state. If the human body exists and is moving, the system will continue to monitor the time difference change of the real-time sensing signal, and judge the movement direction and speed of the human body by the changing trend of the time difference. In the specific implementation process, by pre-acquiring human body feature data, and then judging the human body condition within the current sensing range based on the sensing feature data and human body feature data, it can effectively solve the problem that the detection results in the prior art are affected by the user's body shape, clothing, and forward and backward movement.

[0029] S6. Provide safety protection according to the human body conditions within the sensing range.

[0030] Specifically, if it is determined that no human body is sensed within the current sensing range for a certain period of time, or if it is sensed that the human body has left the current sensing range, the device is controlled to enter a sleep state or send a pause signal to save energy and reduce unnecessary operating risks. After the device enters a sleep state or sends a pause signal, if no wake-up signal is received within a predetermined time, the device is further controlled to enter a shutdown state. On the contrary, if a wake-up signal is received, the normal working state of the device will be quickly restored so that the user can continue to use it. In the specific implementation process, sending a pause signal can send a pause command to the driving simulation software or control the direct drive motor to pause.

[0031] like Figure 2 As shown, the specific steps of step S2 in the embodiment of the present application include: S21. Performing intensity analysis on the human body sensing signal to obtain human body shape intensity characteristics and human body distance intensity characteristics.

[0032] Specifically, according to the intensity change of the human body sensing signal, combined with the reflection area and reflectivity of different parts of the human body, the human body shape intensity characteristics are obtained, and according to the intensity of the human body sensing signal, combined with the transmitting power and receiving sensitivity of the ultrasonic sensor, the human body distance intensity characteristics are obtained.

[0033] S22. Performing Doppler effect analysis on the human body sensing signal to obtain human body shape Doppler characteristics and human body distance Doppler characteristics.

[0034] Specifically, the tiny movements of the human body are identified according to the human body sensing signal, and the Doppler characteristics of the human body shape are obtained according to the tiny movements of the human body. The tiny movements include breathing and heartbeat. The movement state of the human body is judged by analyzing the Doppler frequency shift of the human body sensing signal, and the human body distance Doppler characteristics are obtained.

[0035] S23, performing signal pattern recognition on the human body sensing signal to obtain human body shape pattern characteristics and human body distance pattern characteristics.

[0036] Specifically, a human body shape feature recognition model is constructed and trained, and human body shape pattern features are obtained according to the human body shape feature recognition model; a human body distance feature recognition model is constructed and trained, and human body distance pattern features are obtained according to the human body distance feature recognition model.

[0037] S24, fusing the human body shape intensity feature, the human body shape Doppler feature and the human body shape pattern feature to obtain the human body shape feature.

[0038] S25. Fusing the human body distance intensity feature, the human body distance Doppler feature and the human body distance pattern feature to obtain the human body distance feature.

[0039] Step S5 of the embodiment of the present application specifically includes: S51. Determine whether there is a human body within the current sensing range according to the human body appearance characteristics and sensing feature data.

[0040] S52: When there is a human body within the sensing range, determine whether the human body is currently moving based on the human body distance characteristics and the sensing characteristic data.

[0041] Step S6 of the embodiment of the present application specifically includes: S61. When there is no human body within the sensing range, the control device enters a sleep state or sends a pause signal.

[0042] S62: When the device enters a dormant state or sends a pause signal, it receives a wake-up signal and controls the device to enter a wake-up state.

[0043] S63: When the device enters a dormant state or sends a pause signal and does not receive a wake-up signal within a preset time, the device is controlled to enter a shutdown state.

[0044] S64: When a human body exists within the sensing range and is moving, continuously monitor the change in the time difference of receiving the real-time sensing signal, and determine the movement of the human body based on the change in the time difference.

[0045] S65. When the time difference changes to a continuously increasing state, it is determined that the current human body continues to move far away. When the human body continues to move far away for a preset time, the device is controlled to enter a sleep state or send a pause signal.

[0046] The implementation principle of this embodiment is: through multi-level data collection and analysis, it can accurately judge the user's usage status in complex environments, significantly reducing the misjudgment caused by factors such as user body movement and body shape differences. At the same time, through real-time monitoring and intelligent decision-making mechanisms, automated safety protection is achieved, improving the reliability and safety of the direct-drive steering wheel control driving simulation software safety protection.

[0047] In another embodiment, in addition to installing ultrasonic sensors on the steering wheel base, additional ultrasonic sensors can be added to the bottom of the seat and the pedal area to form a three-dimensional detection network, which greatly improves the comprehensiveness and accuracy of the detection. Specifically, the ultrasonic sensor on the steering wheel base is mainly used to detect the upper area of ​​the user's body, while the ultrasonic sensor at the bottom of the seat is used to detect the user's back and buttocks area, and the ultrasonic sensor in the pedal area is used to detect the user's legs and feet area. This layout design allows the system to capture the user's posture information from multiple angles and in all directions, and even if the user moves slightly during operation, it can accurately determine whether he or she exists.

[0048] In terms of hardware selection, you can choose a high-precision ultrasonic sensor, such as the MaxBotix MB1013, which has a maximum measurement distance of 5 meters and a resolution of 1 mm, suitable for both short-range and long-range detection needs. In addition, you can also consider using an MCU (microcontroller unit) with multi-channel input capabilities, such as the STM32F103C8T6, to support the synchronous data acquisition and processing of multiple ultrasonic sensors.

[0049] In terms of software algorithms, in order to better process data from multiple sensors, machine learning algorithms, especially clustering algorithms and support vector machines (SVMs), can be introduced. By training these algorithms, the user's posture and movement status can be more accurately identified. For example, the K-means clustering algorithm can be used to group data from multiple sensors to distinguish different activity states of the user, such as stillness, slow movement, and fast movement.

[0050] In addition, filtering algorithms, such as Kalman filters, can also be introduced to eliminate noise and jitter and improve the stability and reliability of the signal. Through these optimized designs, the system can not only judge the user's usage status more accurately, but also effectively cope with complex environmental changes, such as users wearing clothes of different thicknesses or different types of chairs. The implementation principle of this embodiment is: by increasing the number of ultrasonic sensors and optimizing the layout, the comprehensiveness and accuracy of the detection are greatly improved. Especially in complex environments, the advantages of multi-sensor collaborative work can be fully utilized, effectively solving the problem that a single sensor is easily interfered with. At the same time, by introducing advanced data processing algorithms, the system can process large amounts of data more efficiently, realize real-time and accurate user status judgment, and thus provide a more reliable security protection function.

[0051] In another embodiment, ultrasonic sensors can also be combined with other types of sensors to jointly realize comprehensive monitoring of the user's status. Specifically, in addition to ultrasonic sensors, infrared sensors and pressure sensors are also added to form a three-dimensional detection system. In the specific implementation process, infrared sensors can be installed on the steering wheel base and seat backs to detect the user's body temperature and heat distribution. This can not only assist in determining whether the user exists, but also help identify the user's fatigue level, because long-term driving can cause the user's body temperature to rise. Pressure sensors can be installed on the bottom of the seat and the pedals to detect the user's pressure distribution, thereby determining whether the user is in a comfortable sitting position.

[0052] In terms of hardware selection, the infrared sensor can be MLX90614, which is a non-contact temperature sensor with high accuracy and low power consumption, suitable for long-term monitoring scenarios. The pressure sensor can be FSR 400 series, a thin-film pressure sensor with good linearity and response speed, suitable as a tactile feedback element.

[0053] In terms of data fusion, a multimodal data fusion algorithm based on Bayesian reasoning can be used. By establishing a probability model, the data from different sensors are weighted and fused to obtain a more reliable user status assessment. For example, different weights can be assigned to the data from ultrasonic sensors, infrared sensors, and pressure sensors, and the final probability value can be calculated using the Bayesian formula to determine whether the user is present and his or her status.

[0054] In addition, deep learning algorithms, such as convolutional neural networks (CNNs), can be introduced to perform end-to-end learning and prediction of multimodal data. Through large-scale data set training, the system can gradually learn how to extract useful features from different types of data and make comprehensive judgments. The advantage of this method is that as data accumulates, the system's judgment accuracy will continue to improve.

[0055] The implementation principle of this embodiment is: by introducing multimodal sensing technology, this method can comprehensively utilize the information of multiple sensors to achieve comprehensive monitoring of the user's status. Each sensor has its unique advantages, such as the advantages of ultrasonic sensors in detecting object contours and distances, the advantages of infrared sensors in detecting temperature and heat distribution, and the advantages of pressure sensors in detecting pressure distribution. Through reasonable data fusion and the support of advanced algorithms, the system can more accurately judge the user's usage status, thereby providing more sophisticated and reliable security protection functions.

[0056] In another embodiment, an environmental perception module can also be introduced to dynamically adjust the detection strategy according to different environmental conditions. Specifically, the system can be equipped with an ambient light sensor, a temperature and humidity sensor, and a sound sensor for real-time monitoring of surrounding environmental conditions, such as light intensity, temperature, humidity, and noise level. In the specific implementation process, the ambient light sensor can be installed near the display to detect the surrounding lighting conditions. When the ambient light is strong, the system can appropriately reduce the operating frequency of the ultrasonic sensor to reduce sunlight interference. The temperature and humidity sensor can be installed in the room to detect indoor temperature and humidity. When the temperature is too high or the humidity is too high, the system can adjust the operating parameters of the ultrasonic sensor to prevent the high temperature and high humidity environment from affecting the performance of the sensor. The sound sensor can be installed inside the cockpit to detect the background noise level. When the noise is large, the system can enable a noise reduction algorithm to improve the quality of the ultrasonic signal.

[0057] In terms of hardware selection, the ambient light sensor can be BH1750, which is a digital light intensity sensor with an I2C interface, with high precision and low power consumption. The temperature and humidity sensor can be DHT22, which is an integrated temperature and humidity sensor with good stability and anti-interference ability. The sound sensor can be MAX4466, which is a high-performance microphone amplifier suitable for picking up and amplifying audio signals.

[0058] In terms of software algorithms, an environmental adaptation algorithm can be introduced to enable the system to dynamically adjust the detection strategy according to different environmental conditions. For example, when the ambient light is strong, the system can appropriately reduce the operating frequency of the ultrasonic sensor to reduce sunlight interference. When the temperature is high, the system can adjust the gain of the ultrasonic sensor to maintain the best detection effect. When the humidity is high, the system can enable the dehumidification algorithm to prevent the influence of moisture on the ultrasonic signal. When the background noise is large, the system can enable the noise reduction algorithm to improve the signal-to-noise ratio of the ultrasonic signal.

[0059] In addition, machine learning algorithms such as reinforcement learning can be introduced to enable the system to autonomously learn the optimal detection strategy. Through continuous trial and error and optimization, the system can gradually find the most suitable detection parameters for the current environment, thereby improving the accuracy and robustness of detection.

[0060] The implementation principle of this embodiment is: by introducing the environment perception module, this method can dynamically adjust the detection strategy according to different environmental conditions, thereby achieving more flexible and efficient user status detection. The addition of the environment perception module enables the system to respond to interference from various external factors in a timely manner, ensuring the stability and reliability of the detection. At the same time, with the support of intelligent algorithms, the system can continuously optimize its own detection strategy and adapt to more diverse application scenarios, thereby providing more complete security protection functions.

[0061] In another implementation, cloud platform support can also be introduced to achieve remote monitoring and data analysis. Specifically, it is possible to connect to the cloud server via Wi-Fi or Bluetooth, and upload the collected user status data to the cloud for centralized management and analysis. In the specific implementation process, the cloud server can deploy big data processing frameworks such as Hadoop and Spark to process massive amounts of user status data. Through distributed computing, the system can quickly analyze a large amount of historical data to find out the patterns and anomalies of user behavior. In addition, the cloud server can also provide a real-time monitoring interface for administrators to view the online status of each device and user usage.

[0062] In terms of hardware selection, you can choose an MCU with a Wi-Fi or Bluetooth module, such as ESP32, to achieve wireless communication functions. ESP32 has powerful processing capabilities and rich peripheral interfaces, which is very suitable for IoT scenarios. In addition, you also need to configure a suitable router and switch to ensure the stability and reliability of the network connection.

[0063] In terms of software architecture, a client-server model can be adopted, where the client is responsible for data collection and local processing, and the server is responsible for data storage and analysis. The client can send the collected data to the server regularly, and the server processes and stores the data after receiving it. In addition, the server can also provide an API interface to facilitate third-party application calls and integration.

[0064] In terms of data security, encrypted transmission protocols such as HTTPS can be used to protect the security of data during transmission. In addition, authentication mechanisms such as OAuth2.0 can be introduced to ensure that only authorized users can access sensitive data.

[0065] In terms of data analysis, machine learning algorithms such as random forests and support vector machines can be introduced to classify and predict user behavior. By training these algorithms, the system can identify common behavior patterns and potential risk points of users, so as to take preventive measures in advance. For example, when the system detects that a user frequently leaves his seat, it can remind the administrator to pay attention to the user's health or suggest that the user take a rest for a while.

[0066] The implementation principle of this embodiment is: by introducing cloud platform support, this method can realize remote monitoring and data analysis, thereby providing a more comprehensive and intelligent security protection function. The addition of the cloud platform enables the system to make full use of cloud computing resources, process and analyze massive historical data, and mine valuable information from it. At the same time, through real-time monitoring and early warning mechanisms, the system can promptly discover and deal with potential risks to ensure the safety of users. In addition, the open API interface also facilitates the integration of third-party applications and enhances the flexibility and scalability of the system.

[0067] The embodiment of the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and execute an ultrasonic adaptive sensing safety protection method, specifically including: S1. Pre-acquire a human body sensing signal of a current user detected by an ultrasonic sensor.

[0068] S2. Identify human body feature data according to the human body sensing signal.

[0069] S3. Acquire the real-time sensing signal detected by the ultrasonic sensor.

[0070] S4. Identify sensing feature data according to the real-time sensing signal.

[0071] S5. Determine the human body condition within the current sensing range according to the sensing feature data and the human body feature data.

[0072] S6. Provide safety protection according to the human body conditions within the sensing range.

[0073] The computer is a server, and the computer device includes a processor, a memory, a network interface and a database connected through a system bus. 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, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store human feature data, sensing feature data, human shape feature recognition model, human distance feature recognition model, etc. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an ultrasonic adaptive sensing safety protection method can be implemented.

[0074] The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: S1. Pre-acquire a human body sensing signal of a current user detected by an ultrasonic sensor.

[0075] S2. Identify human body feature data according to the human body sensing signal.

[0076] S3. Acquire the real-time sensing signal detected by the ultrasonic sensor.

[0077] S4. Identify sensing feature data according to the real-time sensing signal.

[0078] S5. Determine the human body condition within the current sensing range according to the sensing feature data and the human body feature data.

[0079] S6. Provide safety protection according to the human body conditions within the sensing range.

[0080] In addition, the processor in the computer device executes all the steps of the above-mentioned ultrasonic adaptive sensing safety protection method when executing the computer program.

[0081] 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 the memory, storage, database or other medium used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may 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).

[0082] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0083] The embodiments of this specific implementation are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. The same components are represented by the same figure marks. Therefore, any equivalent changes made based on the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. An ultrasonic adaptive sensing safety protection method, characterized in that: include: Pre-acquire a human body sensing signal of a current user detected by an ultrasonic sensor; Identify human body feature data according to the human body sensing signal, wherein the human body feature data includes human body shape features and human body distance features; Acquire real-time sensing signals detected by ultrasonic sensors; Identify sensing feature data according to the real-time sensing signal; Determine the human body condition within the current sensing range according to the sensing feature data and the human body feature data, wherein the human body condition includes the human body existence condition and the human body movement condition; Provide safety protection based on the human body conditions within the sensing range.

2. The ultrasonic adaptive sensing safety protection method according to claim 1, characterized in that: The method of identifying human body feature data according to the human body sensing signal, wherein the human body feature data includes human body shape features and human body distance features, includes: Performing intensity analysis on human body sensing signals to obtain human body shape intensity characteristics and human body distance intensity characteristics; Performing Doppler effect analysis on human body sensing signals to obtain human body shape Doppler characteristics and human body distance Doppler characteristics; Performing signal pattern recognition on human body sensing signals to obtain human body shape pattern features and human body distance pattern features; The human body shape intensity feature, the human body shape Doppler feature and the human body shape mode feature are fused to obtain the human body shape feature; The human body distance intensity feature, human body distance Doppler feature and human body distance pattern feature are fused to obtain the human body distance feature.

3. The ultrasonic adaptive sensing safety protection method according to claim 2, characterized in that: The intensity analysis of the human body sensing signal to obtain the human body shape intensity feature and the human body distance intensity feature specifically includes: According to the intensity change of the human body sensing signal, combined with the reflection area and reflectivity of different parts of the human body, the human body shape intensity characteristics are obtained; According to the strength of the human body sensing signal, combined with the transmitting power and receiving sensitivity of the ultrasonic sensor, the human body distance intensity characteristics are obtained.

4. The ultrasonic adaptive sensing safety protection method according to claim 2, characterized in that: The Doppler effect analysis of the human body sensing signal to obtain the human body shape Doppler characteristics and human body distance Doppler characteristics specifically includes: Identify the tiny movements of the human body according to the human body sensing signal, and obtain the Doppler characteristics of the human body shape according to the tiny movements of the human body, wherein the tiny movements include breathing and heartbeat; The movement state of the human body is determined by analyzing the Doppler frequency shift of the human body sensing signal, and the human body distance Doppler characteristics are obtained.

5. The ultrasonic adaptive sensing safety protection method according to claim 2, characterized in that: The signal pattern recognition of the human body sensing signal to obtain the human body shape pattern characteristics and the human body distance pattern characteristics specifically includes: Constructing and training a human body shape feature recognition model, and obtaining human body shape pattern features according to the human body shape feature recognition model; Construct and train a human body distance feature recognition model, and obtain human body distance pattern features based on the human body distance feature recognition model.

6. An ultrasonic adaptive sensing safety protection method according to any one of claims 1 to 5, characterized in that: The determining of the human body condition within the current sensing range according to the sensing feature data and the human body feature data includes: Judging whether there is a human body within the current sensing range according to the human body shape characteristics and sensing feature data; When there is a human body within the sensing range, it is determined whether the human body is currently moving based on the human body distance characteristics and the sensing characteristic data.

7. The ultrasonic adaptive sensing safety protection method according to claim 6, characterized in that: The safety protection is performed according to the human body condition within the sensing range, including: When there is no human body within the sensing range, the control device enters a sleep state or sends a pause signal; When the device enters the sleep state or sends a pause signal, it receives a wake-up signal and controls the device to enter the wake-up state; When the device enters the sleep state or sends a pause signal, if no wake-up signal is received within the preset time, the device is controlled to enter the shutdown state.

8. The ultrasonic adaptive sensing safety protection method according to claim 7, characterized in that: The safety protection according to the human body condition within the sensing range also includes: When there is a human body within the sensing range and the human body is moving, the time difference change of the real-time sensing signal is continuously monitored, and the movement of the human body is determined by the time difference change; When the time difference changes to continue to increase, it is determined that the current human body continues to move far away, and when it continues to move far away after a preset time, the control device enters a sleep state or sends a pause signal.

9. A computer device, characterized in that: It comprises a memory and a processor, wherein the memory stores an ultrasonic adaptive sensing safety protection method as described in any one of claims 1 to 8 which can be loaded and executed by the processor.

10. A computer-readable storage medium, characterized in that: A computer program is stored which can be loaded by a processor and execute an ultrasonic adaptive sensing safety protection method as described in any one of claims 1 to 8.

Images