WO2022247515A1

WO2022247515A1 - Attitude detection method and apparatus, wireless earphone, and storage medium

Info

Publication number: WO2022247515A1
Application number: PCT/CN2022/087055
Authority: WO
Inventors: 龚勇
Original assignee: 中兴通讯股份有限公司
Priority date: 2021-05-27
Filing date: 2022-04-15
Publication date: 2022-12-01
Also published as: CN115412793A

Abstract

The present disclosure provides an attitude detection method and apparatus, a wireless earphone, and a storage medium. The method comprises: collecting first motion data of the head of a user; generating a motion curve of the head of the user according to the collected first motion data; and obtaining a comparison result between the motion curve and a standard motion curve, and sending an alarm prompt to the user according to the comparison result.

Description

Attitude detection method, device, wireless earphone and storage medium

Cross References to Related Applications

This disclosure claims the priority of the Chinese patent application CN202110584065.5 entitled "Attitude Detection Method, Device, Wireless Earphone and Storage Medium" filed on May 27, 2021, the entire content of which is incorporated into this disclosure by reference.

technical field

The present disclosure relates to but not limited to the technical field of wireless earphones, and specifically, relates to but not limited to an attitude detection method and device, a wireless earphone and a storage medium.

Background technique

The mobile phone is already the first tool for interaction in work and life, and the car is a tool that provides convenience for work and life. Reasonable use will improve work efficiency and enhance the happiness of life, but unreasonable use will bring very large risks, even life-threatening. Fatigue driving ranks first in highway traffic accidents, and the trend is still rising as automobiles become popular. During the driving process, hand-held calls are likely to cause unstable control due to hands leaving the steering wheel, thereby causing traffic accidents. Therefore, taking your hands off the steering wheel to make a phone call is prohibited by traffic rules. How to make drivers aware of fatigue and keep their hands on the steering wheel has become an important direction of automotive electronics research.

At present, the fatigue driving monitoring technology is mainly divided into the following types: the vehicle running track monitoring method, and the fatigue driving monitoring system based on human eyes.

It can be seen from the above technical description that these technical directions have not yet involved in solving the problem of safe communication during driving. Some vehicles are equipped with a vehicle-mounted Bluetooth communication system, but because the driver is far away from the microphone, the voice of the driver cannot be effectively distinguished from the noise inside the vehicle, making it impossible for the other party to hear the content that the driver needs to transmit, resulting in the abandonment of the vehicle-mounted Bluetooth communication system ; And, there is also a large part of vehicles that do not possess the vehicle-mounted Bluetooth intercom system. Therefore, how to monitor the driver's fatigue more accurately and provide a friendly and safe communication system at the same time is very necessary.

Contents of the invention

The posture detection method, device, wireless earphone and storage medium provided by the present disclosure at least solve the technical problem that the existing wireless earphones do not have abnormal posture detection functions such as user head fatigue posture.

The present disclosure provides a posture detection method, which is applied to wireless earphones, including: collecting first motion data of the user's head; generating a motion curve of the user's head according to the collected first motion data; Compare the results, and send an alarm prompt to the user according to the comparison results.

The present disclosure also provides a posture detection device, which is applied to wireless earphones, including: a posture acquisition unit, used to collect the first motion data of the user's head; a posture judgment unit, used to generate the user's head according to the collected first motion data The internal motion curve; and obtain the comparison result of the motion curve and the standard motion curve; the posture reminder unit is used to send an alarm prompt to the user according to the comparison result.

The present disclosure also provides a wireless earphone, including: a processor, a memory, and a communication bus; the communication bus is used to realize connection and communication between the processor and the memory; the processor is used to execute one or more computer programs stored in the memory, to The steps of the above attitude detection method are realized.

The present disclosure also provides a computer-readable storage medium, where one or more computer programs are stored in the computer-readable storage medium, and one or more computer programs can be executed by one or more processors, so as to realize the gesture detection as described above method steps.

Description of drawings

FIG. 1 is a schematic flow diagram of a posture detection method in Embodiment 1 of the present disclosure;

FIG. 2 is a schematic structural diagram of a wireless headset connected to the cloud in Embodiment 1 of the present disclosure;

3 is a schematic diagram of a model of a motion curve in Embodiment 1 of the present disclosure;

4 is a schematic structural diagram of an attitude detection device in Embodiment 2 of the present disclosure;

5 is a schematic structural diagram of an attitude detection device in Embodiment 3 of the present disclosure;

6 is a schematic structural diagram of another attitude detection device in Embodiment 3 of the present disclosure;

FIG. 7 is a schematic diagram of a refined process of a posture detection method in Embodiment 3 of the present disclosure.

FIG. 8 is a schematic structural diagram of yet another attitude detection device in Embodiment 3 of the present disclosure.

FIG. 9 is a schematic diagram of a refined process of yet another attitude detection method in Embodiment 3 of the present disclosure;

FIG. 10 is a schematic structural diagram of a wireless earphone in Embodiment 4 of the present disclosure.

Detailed ways

In order to make the purpose, technical solutions and advantages of the present disclosure clearer, the present disclosure will be further described in detail below through implementation manners in conjunction with the accompanying drawings. It should be understood that the embodiments described here are only used to explain the present disclosure, not to limit the present disclosure.

Vehicle running trajectory monitoring method: This method installs a monitoring running trajectory device on the vehicle, which is used to determine whether the vehicle deviates from the lane through trajectory measurement so as to judge whether the driver is in a fatigue driving state. When the vehicle is running, once it deviates from the track, it means that an accident is about to occur. In the fast highway section, the time left for the driver to react and take control measures is very short. As a result, even if there is a fatigue driving warning system, the effect is not great. In addition, the vehicle does not keep moving in a straight line during driving, so the misjudgment rate is relatively high.

Fatigue driving monitoring system based on human eyes: This method uses cameras to monitor the state of human eyes, and judges the degree of fatigue according to the degree of opening of human eyes. This method has requirements for the environment. When the light is dark, or when the driver wears dark glasses, the photographing effect is so poor that it is impossible to accurately identify the state of the human eye. When the road is smooth and has no curvature, the vehicle is close to a uniform linear motion, and the driver is prone to visual fatigue and driving posture fatigue. The monitoring system cannot ideally identify these two fatigue levels.

Embodiment one

The present disclosure provides an attitude detection method applied to a wireless earphone, please refer to FIG. 1 , the attitude detection method includes steps S101 to S103.

S101: Collect first motion data of the user's head.

In some embodiments, before collecting the first motion data of the user's head, it further includes: detecting a wearing state of the wireless earphone.

In practical applications, when the wireless headset is not worn (that is, the wireless headset is in a non-wearing state), the wireless headset will enter a sleep state to reduce power consumption. Only when the wireless headset is in the wearing state, the posture detection function of the user's head will be turned on. In order to realize the wearing detection function, the wireless headset is built with an acceleration sensor and/or a distance sensor. The distance detector can be an infrared proximity sensor or a capacitive sensor. Among them, the infrared proximity sensor determines the distance between the person and itself according to the intensity of the infrared rays emitted by the infrared rays reflected back by the blocking of the person. The capacitive sensor uses the skin on the human body to approach the contact point to cause a change in capacitance, and the distance between the person and itself is determined according to the change in capacitance. In this regard, the manner of detecting that the wireless earphone is in the wearing state includes but is limited to the following manners 1 to 3.

Method 1: Collect the acceleration value of the wireless headset, and when the acceleration value changes within a preset time, it is determined that the wireless headset is in the wearing state.

Method 2: collect the distance value between the wireless headset and the user's head, and determine that the wireless headset is in the wearing state when the distance value is less than or equal to the preset distance threshold within a preset time.

Method 3: collect the acceleration value of the wireless earphone and the distance value between the wireless earphone and the user's head respectively. When the acceleration value changes within the preset time and the distance value is less than or equal to the preset distance threshold, it is determined that the wireless earphone is in the wearing state.

Regarding the above-mentioned ways 1 to 3, the way 3 is beneficial to eliminate the situation that the user touches the wireless earphone by mistake, so as to improve the accuracy of wearing detection.

In a practical application scenario, the wireless headset is in a dormant state, and the acceleration value of the acceleration sensor is acquired regularly, and when the acceleration value changes within a preset time, it is determined that the wireless headset is moved. Then start the distance detector (such as proximity infrared sensor or capacitive sensor) for further detection, and regularly obtain the distance value of the distance detector. When the distance value is less than or equal to the preset distance threshold within the preset time, it is determined that the wireless headset is worn . Wherein, the preset distance threshold can be reasonably selected according to the type of the distance detector and the degree of sensitivity required. As an example, the preset distance threshold may be 1mm, 1.5mm, 2.0mm, 2.5mm. In addition, after it is determined that the wireless earphone is worn, the distance detector is kept on, and the distance value of the distance detector is continuously acquired at regular intervals. When the distance values are greater than a preset threshold within a preset time, it is determined that the wireless earphone is taken off. When the wireless headset is taken off, it will enter a dormant state until it is worn next time.

S102: Generate a motion curve of the user's head according to the collected first motion data.

The wireless headset has a built-in angular velocity sensor (also called a gyroscope), and the angle and direction of the user's head can be collected through the angular velocity sensor in the wireless headset. In S102, the first exercise data includes: the angle, direction and frequency of the wireless earphone. Subsequently, the motion curve of the user's head can be constructed according to the first motion data, and after comparing the motion curve with the standard motion curve, it can be determined whether the posture of the user's head is a normal posture or an abnormal posture.

In practical applications, in order to accurately construct the motion curve of the user's head, it is necessary to collect enough motion data, and the processing process of the motion data is relatively complicated at this time. In an actual application scenario, as shown in Figure 2, a system can be composed of a wireless headset, a mobile terminal, and the cloud; wherein, the wireless headset is paired with the mobile terminal, and the wireless headset communicates with the cloud through the mobile terminal. In addition, when a specific chip is integrated in the wireless headset, the wireless headset can also directly communicate with the cloud. In this regard, in this disclosure, an appropriate execution subject can be selected according to actual application requirements to process the motion data of the user's head to generate a motion curve of the user's head; an appropriate execution subject can also be selected according to actual needs to compare the motion curves Compare with the standard motion curve to get the result. The aforementioned execution subject may be a wireless earphone or a third device, wherein the third party device may be a mobile terminal paired and connected with the wireless earphone, or a cloud communicated with the wireless earphone. For better understanding, several examples are provided below.

In an example, the motion curve of the user's head is generated through the wireless earphone according to the collected first motion data; the pre-stored standard motion curve is obtained from the wireless earphone, and the motion curve is compared with the standard motion curve through the wireless earphone to obtain Get the comparison result. When using this method, the wireless headset has a built-in standard motion curve, which is convenient for the wireless headset to quickly obtain the standard curve motion for subsequent processing. Even when the wireless headset cannot communicate with the mobile terminal and cannot access the cloud, or the wireless headset has no cloud service function and cannot access the cloud, the standard motion curve can be directly obtained from the wireless headset.

In addition, the wireless headset can also generate a standard motion curve based on the collected motion data through a local algorithm; the specific process is: S1, the first motion of the user's head is detected within a period of time and returns to the initial state, and the timing is reset to calibrate Acceleration sensor and gyroscope. S2, start the collection of head movement posture parameters. S3. When the head movement of the user is detected, the acceleration of the current head movement process is compared with the acceleration of the last valid head movement to obtain the acceleration change rate. S4. When the acceleration rate is less than or equal to the preset threshold, it indicates that the head movement monitoring is an effective monitoring; record the angle and direction of the head movement, and calculate the movement frequency according to frequency=1/time; follow-up execution S6. S5, when the rate of acceleration change exceeds the preset threshold, it indicates that the user's sudden head movement is caused by other circumstances, not a natural movement of neck muscle relaxation; follow-up execution of S6. S6, when the angle of the head movement returns to the initial state, the timer is reset to zero, and the next collection of head movement posture parameters is started, and the process returns to S3. A standard motion curve is constructed according to the collected effective head motion posture parameters. As shown in Figure 3, according to the angle and frequency in the effective head movement posture parameters, the user's head movement curve is constructed with forward bending, backward extension, left and right as anchor points.

In another example, the motion curve of the user's head is generated through the wireless earphone according to the collected first motion data; the standard motion curve sent by the third-party device is received, and the motion curve is compared with the standard motion curve through the wireless earphone to obtain Compare the results. When this method is adopted, the standard motion curve can be generated by a third-party device to obtain a more accurate standard motion curve, thereby improving the accuracy of posture detection.

In order to construct corresponding standard motion curves for different users to reduce the misjudgment rate, before receiving the standard motion curves sent by the third-party device, the method further includes: collecting second motion data of the user's head, the second motion data includes The acceleration value of the wireless earphone; when the acceleration value is less than or equal to the preset acceleration threshold within the preset time, the second motion data is sent to the third-party device, so that the third-party device can generate a standard motion curve according to the second motion data. For example, in a practical application scenario, a wireless headset is paired and connected to a mobile terminal through Bluetooth. When the wireless earphone is in the wearing state, the second motion data of the user's head is obtained through the wireless earphone, and the second motion data includes the acceleration value of the wireless earphone and the angle and frequency of the wireless earphone; When the acceleration threshold is set, it is determined that the posture of the user's head is in a normal posture; at this time, the second movement data of the user's head collected within a preset time can be sent to the mobile terminal, and then the mobile terminal constructs The standard motion curve of the user's head is fed back to the wireless headset; after the wireless headset receives the standard motion curve, it compares the motion curve of the user's head with the standard motion curve to determine whether the posture of the user's head is normal. In another practical application scenario, the wireless headset is paired and connected to the mobile terminal through Bluetooth, and the wireless headset is connected to the cloud through the mobile terminal. When the wireless earphone is in the wearing state, the second motion data of the user's head is obtained through the wireless earphone, and the second motion data includes the acceleration value of the wireless earphone and the angle and frequency of the wireless earphone; When the acceleration threshold is set, it is determined that the posture of the user's head is in a normal posture; at this time, the mobile terminal can be used to send the second movement data of the user's head collected within the preset time to the cloud, and then the artificial intelligence algorithm in the cloud will The second motion data constructs the standard motion curve of the user's head, and feeds it back to the wireless earphone through the mobile terminal; after the wireless earphone receives the standard motion curve, it compares the motion curve of the user's head with the standard motion curve to judge the motion of the user's head. Whether the posture is a normal posture.

It should be noted that the process of generating a standard motion curve based on the artificial intelligence algorithm in the cloud is as follows: after receiving n times of valid head motion posture data, according to the angle, frequency and acceleration rate of the head motion, a classification algorithm (such as the K nearest neighbor algorithm ) to find head motion curves. At the same time, predict the next head movement posture data according to the head movement curve. If k predictions out of the m predictions are accurate, the head motion curve is determined to be the standard motion curve of the current wearer's head motion posture. Among them, the values of m and k are set according to the accuracy.

In yet another example, the first motion data is sent to a third-party device; and the comparison result sent by the third-party device is received. When using this method, a third-party device is selected to process the motion data of the user's head to obtain the motion curve of the user's head, and the motion curve of the user's head is compared with the standard motion curve to judge the posture of the user's head. It is beneficial to improve the accuracy of posture detection.

S103: Obtain a comparison result between the motion curve and the standard motion curve, and send an alarm prompt to the user according to the comparison result.

When the wireless earphone is in the wearing state, the wireless earphone moves with the user's head, and at this time, the motion data of the wireless earphone can be regarded as the motion data of the user's head. In some practical scenarios, when the user's head is in a normal posture, the pulling torque of the neck muscles will make the motion posture of the user's head tend to be stable, and the acceleration of the user's head is very small at this time. When the user suffers from postural fatigue (that is, when the posture is abnormal), the torque of the pulling force of the neck muscles cannot be balanced with the gravity torque of the head and neck, resulting in changes in acceleration. At this time, the acceleration of the user's head is relatively large. In some other actual scenarios, when the user's head has posture fatigue (that is, abnormal posture), the acceleration of the user's head is small and the posture of the user's head remains unchanged for a long time. At this time, the movement of the user's head If both the frequency and the movement angle are small, the movement curve of the user's head tends to be gentle. It can be seen that when judging the current posture of the user's head, it can be determined based on any one or several parameters of the acceleration value, frequency and angle during the movement of the user's head. For a better understanding, the following further explains how to determine the posture of the user's head:

In an example, the first motion data includes: the angle and frequency of the wireless earphone. Generate the motion curve of the user's head according to the angle and frequency; also obtain the standard motion curve. Afterwards, obtaining the comparison result of the motion curve and the standard motion curve includes: obtaining the first frequency and the first angle of the motion curve and the second frequency and the second angle of the standard motion curve; when the first frequency is less than the second frequency and the first When the angle is smaller than the second angle, generate a comparison result that the user's head is in an abnormal posture; and/or, when the first frequency is greater than the second frequency and the first angle is greater than the second angle, generate that the user's head is in an abnormal posture comparison results.

In another example, the first motion data includes: the acceleration value of the wireless earphone and the angle and frequency of the wireless earphone. Generate the motion curve of the user's head according to the angle and frequency; also obtain the standard motion curve. If the acceleration value is greater than the preset acceleration threshold within the preset time and the acceleration value shows an increasing trend, an abnormal result that the user's head is in an abnormal posture will be generated, and an alarm prompt will be sent to the user according to the abnormal result; if the acceleration is within the preset time When the value is less than the preset acceleration threshold, compare the motion curve with the standard motion curve to obtain the comparison result. At this time, the process of comparing the motion curve with the standard motion curve to obtain the comparison result is as described above, and will not be repeated here. repeat.

It can be understood that when comparing the motion curve with the standard motion curve, the frequency and angle can be expressed in the form of interval values, the frequency can indicate the speed of the angle change of the motion curve or the standard motion curve, and the angle can indicate the motion curve or the standard motion Angle variation range of the curve.

The wireless headset has built-in speakers and motors; sending an alarm prompt to the user through the wireless headset includes: sending a voice prompt to the user's head through the speaker in the wireless headset, and/or sending a vibration prompt to the user's head through the motor in the wireless headset.

According to the posture detection method provided in the present disclosure, it is possible to obtain the posture data of the user's head with the help of wireless earphones, and when the user's head is in an abnormal posture (such as a fatigue state), an alarm prompt is sent to the user's head, so as to remind the user in time Be aware of the purpose of resting or adjusting for poor posture.

Embodiment two

The present disclosure provides an attitude detection device applied to wireless earphones. Please refer to FIG. 4 . The attitude detection device includes at least the following units: an attitude acquisition unit 201 , an attitude judgment unit 202 and an attitude reminder unit 203 .

Gesture acquisition unit 201 is used to collect the first motion data of the user's head; posture judgment unit 202 is used to generate the motion curve of the user's head according to the first motion data collected; posture reminder unit 203 is used to obtain the motion curve The comparison result with the standard motion curve, and an alarm prompt is sent to the user according to the comparison result.

In some embodiments, the attitude acquiring unit 201 is also used to acquire the acceleration value of the wireless earphone and/or acquire the distance value between the wireless earphone and the user's head. The posture detection device further includes a wearing detection unit. The wearing detection unit is used to determine that the wireless headset is in the wearing state when the acceleration value changes within a preset time; or, the wearing detection unit is used to determine that the wireless headset is in a wearing state when the distance value is less than or equal to a preset distance threshold within a preset time. In the wearing state; or, the wearing detection unit is used to determine that the wireless headset is in the wearing state when the acceleration value changes within a preset time and the distance value is less than or equal to the preset distance threshold.

In some embodiments, the gesture judging unit 202 is used to generate the motion curve of the user's head according to the collected first motion data through the wireless earphone; obtain the pre-stored standard motion curve from the wireless earphone, and use the wireless earphone to convert the motion curve Compare with the standard motion curve to get the comparison result. Alternatively, the posture judging unit 202 is used to generate the motion curve of the user's head according to the collected first motion data through the wireless earphone; receive the standard motion curve sent by the third-party device, and compare the motion curve with the standard motion curve through the wireless earphone to get the comparison result. Alternatively, the posture judging unit 202 is configured to send the first motion data to a third-party device; and receive a comparison result sent by the third-party device. Wherein, the third-party device can be a mobile terminal paired and connected with the wireless headset, or a cloud connected with the wireless headset.

In some embodiments, the posture acquisition unit 201 is further configured to collect second motion data of the user's head, and the second motion data includes the acceleration value of the wireless earphone. The posture judging unit 202 is also configured to send the second motion data to the third-party device when the acceleration value is less than or equal to the preset acceleration threshold within the preset time, so that the third-party device can generate a standard motion curve according to the second motion data.

In some embodiments, the posture judging unit 202 is also used to obtain the first frequency and the first angle of the motion curve and the second frequency and the second angle of the standard motion curve; when the first frequency is less than the second frequency and the first angle is less than At the second angle, generate the comparison result that the user’s head is in an abnormal posture; The comparison results of all parts in abnormal postures.

In some embodiments, when the first motion data includes the acceleration value of the wireless earphone, the posture judging unit 202 is further configured to generate a user head response when the acceleration value is greater than the preset acceleration threshold within a preset time and the acceleration value shows an increasing trend. An abnormal result in an abnormal posture; and when the acceleration value is less than a preset acceleration threshold within a preset time, comparing the motion curve with the standard motion curve to obtain a comparison result. The posture reminder unit 203 is also configured to send an alarm prompt to the user according to the abnormal result.

According to the posture detection device provided in the present disclosure, it is possible to obtain the posture data of the user's head with the help of wireless earphones, and when the user's head is in an abnormal posture (such as a fatigue state), an alarm prompt is sent to the user's head, so as to remind the user in time Be aware of the purpose of resting or adjusting for poor posture.

Embodiment Three

The present disclosure provides a gesture detection method and device. The wireless earphone may be an in-ear wireless Bluetooth earphone or a bone conduction wireless Bluetooth earphone. Please refer to shown in Fig. 5, the posture detection device in the wireless earphone includes the following units: posture tracking unit 301 (corresponding to posture acquisition unit 201), audio vibration unit 302 (corresponding to posture reminder unit 203), wearing detection unit 300, wireless connection unit 303 , power management unit 304 , storage unit 305 and management control unit 306 (corresponding to posture judging unit 202 ). The functions of each unit in the attitude detection device will be described in detail below.

The wearing detection unit 300 is used for judging whether the user has worn the wireless earphone. Only when the wireless earphone is in the wearing state, the posture tracking unit 301 will be enabled and the provided data will be valid. At the same time, when the wireless headset is not worn, it is in a deep sleep state to reduce the power consumption of the entire system. The wearing detection unit 300 includes a distance detector and an acceleration sensor, wherein the distance detector can be any one of a proximity infrared sensor and a capacitive sensor. Meanwhile, a distance detector may be provided around each speaker. In practical applications, the wearing detection unit 300 is used to regularly read the acceleration value of the acceleration sensor. When the acceleration value changes within a preset time, it is determined that the wireless earphone is in a moving state; the distance detector is started for timing detection. When the distance detector When the detected distance value is less than or equal to the preset distance threshold, it is determined that the wireless headset is in the wearing state.

The posture tracking unit 301 is configured to monitor the movement data of the user's head. The attitude tracking unit 301 may include an acceleration sensor and/or an angular velocity sensor (also called a gyroscope). The acceleration value of the wireless headset can be obtained through the acceleration sensor, and the angle of the wireless headset can be obtained through the gyroscope.

The audio vibration unit 302 is used to provide electro-acoustic conversion, audio collection, vibration reminder and other functions. The audio vibration unit 302 includes but not limited to a microphone (Microphone, MIC for short), a bone conduction speaker and a motor. Among them, the microphone is used to collect audio data; the bone conduction speaker is used to convert electrical signals into audio data; the motor is used to generate vibration. In practical applications, when a user makes a call with a bone conduction wireless headset, the audio vibration unit 302 is used to transmit audio data to the user through bone conduction, and also sends the collected audio data to the management control unit 306 for management The control unit 306 sends the audio data to the mobile terminal. In addition, the audio vibration unit 302 is also used to receive prompt information sent by the management control unit 306, and provide timely auditory and tactile reminders to the user according to the prompt information, so as to remind the user to pay attention to rest or adjust bad sitting posture.

The wireless connection unit 303 is configured to provide a mobile network to connect the wireless headset with external devices such as mobile terminals, for example, by using Bluetooth or WIFI connection. The management control unit 306 communicates audio data with external devices such as mobile terminals through the wireless connection unit 303 to realize voice communication. When the wireless earphone can be connected to the cloud, the motion data of the user's head can also be transmitted to the mobile terminal through the wireless connection unit 303, and then transmitted to the cloud by the mobile terminal. In this way, the artificial intelligence algorithm in the cloud (such as the K nearest neighbor algorithm) can construct the motion curve of the user's head according to the motion data of the user's head; and then feed back the motion curve of the user's head to the wireless earphone through the mobile terminal. It should be understood that the motion curve of the user's head estimated by the cloud is the motion curve when the user's head is in a normal posture, which can be used as a reference motion curve for judging the current posture of the user's head. called the standard motion curve.

The power management unit 304 is used to supply power to other units in the attitude detection device and to charge the battery in this unit. Since the wireless headset does not need to be equipped with an audio cable to improve portability, each unit inside the wireless headset needs to be powered by a battery. In addition, the power management unit 304 can also include a power switch, which can be used to control the power supply circuits of other units in the posture detection device, so as to further reduce power consumption.

The storage unit 305 is configured to store the motion data of the user's head and the motion curve (that is, the standard motion curve) when the user's head is in a normal posture. In a practical application scenario, when the wireless connection unit 303 in the wireless headset is offline, or the wireless headset cannot be successfully connected to the cloud due to unstable network, or the wireless headset does not have the cloud service function, the management control unit 306 can access the The standard motion curve is obtained in unit 305. In this manner, the standard motion curve is estimated by a local algorithm. Meanwhile, the storage unit 305 includes but is not limited to a TF card (Trans-flash Card, TF card for short), and a flash memory (Flash EEPROM, Flash for short) storage chip.

The management control unit 306 is configured to judge the current posture of the user's head. In practical applications, when the wireless headset is worn, it is necessary to judge the current posture of the user's head. At this time, the management control unit 306 obtains the standard motion curve from the storage unit 305, or obtains the standard motion curve from the cloud through the wireless connection unit 303 and the mobile terminal; and obtains the motion data of the user's head from the posture tracking unit 301, and The motion data of the user's head is used to construct the motion curve of the user's head; the current posture of the user's head is judged according to the motion curve and the standard motion curve, and finally a prompt message is generated according to the comparison result and sent to the audio vibration unit 302.

In order to better understand the present disclosure, the present disclosure will elaborate on the pose detection method and device in combination with application scenario 1 and application scenario 2.

Application Scenario 1

The posture detection device and method provided in the present disclosure can be applied to monitor the driver's fatigue state, so that the driver can enjoy the convenience of travel brought by the car and have an additional security monitoring. At this time, the wireless earphone is a bone conduction type wireless earphone. Since the wireless headset adopts the bone conduction method, there is no need to insert earplugs into the ear canal, and it will not reduce the driver's perception of external sounds.

Please refer to Fig. 6, the posture detection device applied to wireless earphones includes the following units: posture tracking unit 301, audio vibration unit 302, wearing detection unit 300, wireless connection unit 303, power management unit 304, storage unit 305 and management control Unit 306. Wherein, the wearing detection unit 300 includes an acceleration sensor and an infrared proximity sensor; the attitude tracking unit 301 includes a gyroscope and an acceleration sensor; the audio vibration unit 302 includes: an audio codec unit, MIC, a bone conduction speaker, and a motor; the wireless connection unit 303 uses Bluetooth The power management unit 304 includes a charging and power conversion unit and a battery; the storage unit 305 includes a Flash storage chip; the management control unit 306 includes a micro control unit (Micro Control Unit, referred to as MCU).

Please refer to FIG. 7 , the posture detection method applied to wireless earphones includes the following steps S501 to S518.

S501: The wireless earphone is in a dormant state, regularly acquires the acceleration value detected by the acceleration sensor, and judges whether the acceleration value has changed within the preset time, and if so, determines that the wireless earphone is in a moving state, and then executes S502; otherwise, does not do any processing.

S502: Start the infrared proximity sensor for detection.

S503: Obtain the distance value detected by the infrared proximity sensor regularly, and determine whether the distance values are less than or equal to the preset distance value within the preset time; if so, determine that the wireless earphone is in the wearing state; otherwise, determine that the wireless earphone is only in the moving state.

S504: Determine that the wireless headset is in the wearing state, and then execute S506;

S505: Determine that the wireless headset is only in a moving state, and do not perform any processing.

S506: Calibrate the acceleration sensor and the gyroscope, and establish a Bluetooth connection with the mobile terminal.

S507: Determine whether the wireless headset can be connected to the cloud; if not, execute S508; otherwise, execute S509.

S508: Obtain a pre-stored standard motion curve locally.

S509: Obtain the acceleration value of the acceleration sensor regularly.

S510: Determine whether the acceleration value within the preset time is smaller than the preset acceleration threshold; if yes, execute S511; otherwise, return to execute S509.

S511: Upload the motion data of the user's head to the cloud through the mobile terminal, and estimate the motion curve (that is, the standard motion curve) of the user's head in a normal posture by the artificial intelligence algorithm of the cloud.

S512: Receive the standard motion curve sent by the cloud through the mobile terminal.

S513: Obtain the acceleration value of the acceleration sensor and the parameters of the gyroscope at regular intervals.

S514: Determine the motion curve of the user's head according to the parameters of the gyroscope.

S515: Determine whether the acceleration value is greater than the preset acceleration threshold within the preset time; if yes, execute S516; otherwise, execute S517.

S516: When the acceleration value shows an increasing trend within the preset time, it is determined that the driver's fatigue level is high, and the driver is reminded to take a rest in time.

S517: Further judge whether the current posture of the user's head is in an abnormal posture according to the motion curve and the standard motion curve; if so, execute S518; otherwise, return to execute S513.

S518: When the frequency of the motion curve is less than the frequency of the standard motion curve, and the angle of the motion curve is smaller than the angle of the standard motion curve, determine that the driver's fatigue is high, and promptly remind the driver to take a rest. If the control unit of the car has the driver status data access function, the fatigue degree is transmitted to the control unit of the car at the same time, and the driving speed is limited or reduced according to the degree of fatigue.

With the attitude detection method and device provided in the present disclosure, after the driver wears the wireless earphone, since the wireless earphone has an attitude detection function, the fatigue state of the driver can be monitored. At the same time, during the process of monitoring the driver's fatigue state, the wireless earphone can give the driver an auditory and/or tactile warning according to the degree of fatigue state, so that the driver can enjoy the convenience of travel brought by the car while having an additional safety monitoring.

Application Scenario 2

The posture detection device and method provided by the present disclosure can be applied to monitor the fatigue state of primary school students, so that the primary school students can keep their attention focused. At this time, the wireless earphone may be an in-ear wireless earphone or a bone conduction wireless earphone.

Please refer to Fig. 8, the posture detection device applied to wireless earphones includes the following units: posture tracking unit 301, audio vibration unit 302, wearing detection unit 300, wireless connection unit 303, power management unit 304, storage unit 305 and management control Unit 306. Wherein, the wearing detection unit 300 includes an acceleration sensor and a capacitive sensor (that is, the capacitive touch button in the figure); the posture tracking unit 301 includes a gyroscope and an acceleration sensor; the audio vibration unit 302 includes: an audio codec unit, MIC, bone conduction Loudspeaker and motor; Wireless connection unit 303 adopts the mode of bluetooth to be connected with mobile terminal; Power management unit 304 comprises charging and power conversion unit and battery; Storage unit 305 comprises Flash storage chip; Management control unit 306 comprises micro control unit (Micro Control Unit, referred to as MCU).

Please refer to FIG. 9 , the posture detection method applied to wireless earphones includes the following steps: S701 to S718.

S701: The wireless earphone is in a dormant state, regularly acquires the acceleration value detected by the acceleration sensor, and judges whether the acceleration value has changed within the preset time, and if so, determines that the wireless earphone is in a moving state, and then executes S702; otherwise, does not perform any processing.

S702: Start the capacitive sensor for detection.

S703: Obtain the distance value detected by the capacitive sensor regularly, and determine whether the distance value is less than or equal to the preset distance value within the preset time; if so, determine that the wireless earphone is in the wearing state; otherwise, determine that the wireless earphone is only in the moving state.

S704: Determine that the wireless earphone is in the wearing state, and then execute S706.

S705: Determine that the wireless headset is only in a moving state, without any processing.

S706: Calibrate the acceleration sensor and the gyroscope, and establish a Bluetooth connection with the mobile terminal.

S707: Determine whether the wireless headset can be connected to the cloud; if not, execute S708; otherwise, execute S709.

S708: Obtain a pre-stored standard motion curve locally.

S709: Obtain the acceleration value of the acceleration sensor regularly.

S710: Determine whether the acceleration value within the preset time is smaller than the preset acceleration threshold; if yes, execute S711; otherwise, return to execute S709.

S711: Upload the motion data of the user's head to the cloud through the mobile terminal, and estimate the motion curve (that is, the standard motion curve) when the user's head is in a normal posture by the artificial intelligence algorithm in the cloud.

S712: Receive the standard motion curve sent by the cloud through the mobile terminal.

S713: Obtain the parameters of the gyroscope at regular intervals.

S714: Determine the motion curve of the user's head according to the parameters of the gyroscope.

S715: Judging whether the first preset condition is satisfied between the motion curve and the standard motion curve, the first preset condition is that the frequency of the motion curve is less than the frequency of the standard motion curve, and the angle of the motion curve is smaller than the angle of the standard motion curve; if If no, execute S716; otherwise, return to execute S717.

S716: Determine that the primary school students have a high degree of fatigue, and promptly remind the primary school students to rest or move their heads a little.

S717: Continue to judge whether the second preset condition is satisfied between the motion curve and the standard motion curve, the second preset condition is that the frequency of the motion curve is greater than the frequency of the standard motion curve, and the angle of the motion curve is greater than the angle of the standard motion curve; If yes, execute S718; otherwise, return to execute S713.

S718: Determine the pupil's lack of concentration, and promptly remind the pupil to concentrate or adjust the sitting posture for writing.

With the attitude detection method and device provided in the present disclosure, after the pupil wears the wireless earphone, since the wireless earphone has an attitude detection function, the fatigue state of the pupil can be monitored. At the same time, the wireless earphone can send out auditory and/or tactile warnings to primary school students according to the fatigue state during the process of monitoring the fatigue state of primary school students, so that primary school students can concentrate and maintain correct sitting posture when writing homework or listening to classes.

Embodiment Four

This embodiment provides a wireless earphone, as shown in FIG. 10, which includes a processor 801, a memory 802, and a communication bus 803, wherein: the communication bus 803 is used to realize connection and communication between the processor 801 and the memory 802; The device 801 is configured to execute one or more computer programs stored in the memory 802, so as to realize at least one step in the posture detection method in the above-mentioned embodiments.

The present embodiment also provides a computer-readable storage medium, which includes information implemented in any method or technology for storing information, such as computer-readable instructions, data structures, computer program modules, or other data. volatile or nonvolatile, removable or non-removable media. Computer-readable storage media include, but are not limited to, RAM (Random Access Memory, random access memory), ROM (Read-Only Memory, read-only memory), EEPROM (Electrically Erasable Programmable read-only memory, electrically erasable programmable read-only memory), flash memory or other memory technologies, CD-ROM (CompactDiscRead-OnlyMemory, compact disk read-only memory), digital versatile disk (DVD) or other optical disk storage, magnetic box, magnetic tape, magnetic disk storage or other magnetic storage devices, or can be used to store desired information and can be Any other media accessed by a computer.

The computer-readable storage medium in this embodiment can be used to store one or more computer programs, and the one or more computer programs stored in it can be executed by a processor to implement at least one step in the posture detection method in the above-mentioned embodiments .

This embodiment also provides a computer program (or computer software), which can be distributed on a computer-readable medium and executed by a computing device to implement at least one of the pose detection methods in the above-mentioned embodiments steps; and in some cases, at least one step shown or described may be performed in a sequence different from that described in the above embodiments.

This embodiment also provides a computer program product, including a computer-readable device, on which the above-mentioned computer program is stored. The computer-readable device in this embodiment may include the computer-readable storage medium as described above.

According to the posture detection method, device, wireless earphone and storage medium provided in the present disclosure, by collecting the first motion data of the user's head; generating the motion curve of the user's head according to the collected first motion data; obtaining the motion curve and the standard motion The comparison results of the curves, and send an alarm to the user according to the comparison results; it is possible to obtain the posture data of the user's head with the help of wireless headphones, and when the user's head is in an abnormal posture (such as a fatigue state), send an alarm to the user's head Send an alarm prompt to timely remind the user to pay attention to rest or adjust bad posture.

It can be seen that those skilled in the art should understand that all or some of the steps in the methods disclosed above, the functional modules/units in the system and the device can be implemented as software (the computer program code executable by the computing device can be used to realize ), firmware, hardware, and appropriate combinations thereof. In a hardware implementation, the division between functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be composed of several physical components. Components cooperate to execute. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit .

In addition, as is well known to those of ordinary skill in the art, communication media typically embodies computer readable instructions, data structures, computer program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery medium. Therefore, the present disclosure is not limited to any specific combination of hardware and software.

The above content is a further detailed description of the present disclosure in conjunction with specific implementation modes, and it cannot be deemed that the implementation of the present disclosure is limited to these descriptions. Those of ordinary skill in the technical field to which the present disclosure belongs can make some simple deduction or substitution without departing from the concept of the present disclosure, which should be deemed to belong to the protection scope of the present disclosure.

Claims

A posture detection method applied to a wireless headset, comprising:

Collecting the first motion data of the user's head;

generating a motion curve of the user's head according to the collected first motion data;

A comparison result between the motion curve and the standard motion curve is obtained, and an alarm prompt is sent to the user according to the comparison result.
The posture detection method according to claim 1, wherein, before collecting the first movement data of the user's head, it further comprises detecting the wearing state of the wireless earphone;

The detection of the wearing state of the wireless headset includes:

Collecting the acceleration value of the wireless earphone, and determining that the wireless earphone is in the wearing state when the acceleration value changes within a preset time;

or,

Collecting a distance value between the wireless headset and the user's head, and determining that the wireless headset is in a wearing state when the distance value is less than or equal to a preset distance threshold within a preset time;

or,

Collecting the acceleration value of the wireless earphone and the distance value between the wireless earphone and the user's head respectively, when the acceleration value changes within a preset time and the distance value is less than or equal to a preset distance threshold, It is determined that the wireless headset is in a wearing state.
The gesture detection method according to claim 1, wherein said method further comprises:

Generate a motion curve of the user's head through the wireless earphone according to the collected first motion data; obtain the pre-stored standard motion curve from the wireless earphone, and use the wireless earphone to generate the motion curve of the user's head; comparing the motion curve with the standard motion curve to obtain the comparison result;

or,

generating a motion curve of the user's head through the wireless earphone according to the collected first motion data;

receiving the standard motion curve sent by a third-party device, and comparing the motion curve with the standard motion curve through the wireless earphone to obtain the comparison result;

or,

Sending the first motion data to a third-party device; and receiving the comparison result sent by the third-party device.
The posture detection method according to claim 3, wherein, before receiving the standard motion curve sent by the third-party device, the method further comprises:

Collecting second motion data of the user's head, where the second motion data includes the acceleration value of the wireless earphone;

When the acceleration value is less than or equal to a preset acceleration threshold within a preset time, the second motion data is sent to the third-party device, so that the third-party device can generate the standard motion curve according to the second motion data .
The posture detection method according to claim 1, wherein said obtaining the comparison result of said motion curve and standard motion curve comprises:

Obtaining the first frequency and first angle of the motion curve and the second frequency and second angle of the standard motion curve;

When the first frequency is less than the second frequency and the first angle is less than the second angle, generating a comparison result that the user's head is in an abnormal posture;

and / or,

When the first frequency is greater than the second frequency and the first angle is greater than the second angle, a comparison result that the user's head is in an abnormal posture is generated.
The posture detection method according to claim 1, wherein, when the first motion data includes the acceleration value of the wireless earphone; the method further comprises:

When the acceleration value is greater than the preset acceleration threshold within the preset time and the acceleration value shows an increasing trend, an abnormal result that the user's head is in an abnormal posture is generated, and an alarm prompt is sent to the user according to the abnormal result;

When the acceleration value is less than a preset acceleration threshold within a preset time, the motion curve is compared with the standard motion curve to obtain the comparison result.
An attitude detection device, applied to a wireless earphone, comprising:

a gesture acquiring unit, configured to acquire the first motion data of the user's head;

A posture judging unit, configured to generate a motion curve of the user's head according to the collected first motion data, and obtain a comparison result between the motion curve and a standard motion curve;

A posture reminder unit, configured to send an alarm prompt to the user according to the comparison result.
The posture detection device according to claim 7, further comprising: a wearing detection unit;

The attitude acquisition unit is also used to acquire the acceleration value of the wireless earphone and/or acquire the distance value between the wireless earphone and the user's head;

The wearing detection unit is configured to determine that the wireless earphone is in the wearing state when the acceleration value changes within a preset time;

or,

The wearing detection unit is configured to determine that the wireless earphone is in a wearing state when the distance value is less than or equal to a preset distance threshold within a preset time;

or,

The wearing detection unit is configured to determine that the wireless earphone is in a wearing state when the acceleration value changes within a preset time and the distance value is less than or equal to a preset distance threshold.
A wireless earphone, comprising: a processor, a memory and a communication bus;

The communication bus is used to realize connection and communication between the processor and the memory;

The processor is used to execute one or more computer programs stored in the memory, so as to realize the steps of the posture detection method according to any one of claims 1-6.
A computer-readable storage medium, the computer-readable storage medium stores one or more computer programs, and the one or more computer programs can be executed by one or more processors to implement claims 1 to 6 The step of the attitude detection method described in any one.