Hearing aid system for monitoring real-time gait characteristics by artificially simulating vestibular function

Abstract

The embodiment of the invention discloses an artificial simulation vestibular function real-time gait characteristic monitoring hearing aid system which comprises a hearing aid and an artificial simulation vestibular function system integrated in the hearing aid, and the artificial simulation vestibular function system comprises a three-axis gyroscope, a three-axis accelerometer and a three-axis magnetometer; wherein the artificial simulation vestibular function system is used for detecting motion state data of a user, and the hearing aid is used for extracting gait characteristic parameters of the user according to the motion state data and performing in-ear early warning when the gait characteristic parameters are abnormal. According to the embodiment of the invention, accurate gait detection, disease risk early warning and prognosis recovery evaluation can be realized.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of hearing aids, and in particular, to a hearing aid system for real-time gait feature monitoring by artificially simulating vestibular function. Background Art

[0002] Multiple diseases such as Parkinson's disease, arthritis, stroke, and vestibular neuronitis can cause changes in gait features. Doctors can analyze gait feature data for disease risk early warning and prognosis recovery evaluation.

[0003] However, devices such as bracelets and watches have obvious deficiencies in gait feature monitoring. The movement amplitude of the hand is large, and the consistency with body movement is poor, resulting in large errors in the collected data and being unable to play an accurate role in gait detection, disease risk early warning, and prognosis recovery evaluation. Summary of the Invention

[0004] The embodiments of the present invention provide a hearing aid system for real-time gait feature monitoring by artificially simulating vestibular function to solve the above technical problems.

[0005] The hearing aid system for real-time gait feature monitoring by artificially simulating vestibular function includes:

[0006] A hearing aid, and

[0007] An artificially simulated vestibular function system integrated in the hearing aid, including: a three-axis gyroscope, a three-axis accelerometer, and a three-axis magnetometer;

[0008] Wherein, the artificially simulated vestibular function system is used to detect the motion state data of the user, and the hearing aid is used to extract the gait feature parameters of the user according to the motion state data and give an in-ear warning when the gait feature parameters are abnormal.

[0009] The embodiments of the present invention can achieve the following beneficial effects:

[0010] (1) In this embodiment, an artificially simulated vestibular system is used to accurately measure the acceleration and angular momentum of human motion, and gait features are extracted through algorithms for evaluating the user's health status and rehabilitation progress, providing data support for medical treatment;

[0011] (2) It has the hearing aid function with warning: The hearing aid system uses advanced audio technology to provide clear hearing compensation. At the same time, it can monitor data in real time. Once abnormal, it will immediately give an in-ear warning, enabling users and guardians to know the risk in time;

[0012] (3) Improve the test accuracy: Aiming at the problem of inaccurate testing of conventional wearable devices, this system combines an artificial vestibular system and a hearing aid system, and reduces interference by relying on the head movement characteristics, improving the accuracy of gait data and realizing the accurate evaluation of individual motion and health status, breaking through the limitations of traditional technologies. Brief Description of the Drawings

[0013] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0014] Figure 1 is a schematic diagram of a hearing aid system for real-time gait feature monitoring with artificial simulation of vestibular function provided by an embodiment of the present invention;

[0015] Figure 2 is a block diagram of a hearing aid system for real-time gait feature monitoring with artificial simulation of vestibular function provided by an embodiment of the present invention. Detailed Description of the Embodiments

[0016] To make the objectives, technical solutions and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope protected by the present invention.

[0017] In the description of the present invention, it should be noted that the orientation or positional relationships indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are based on the orientation or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus cannot be construed as a limitation of the present invention. In addition, the terms "first", "second", and "third" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance.

[0018] In the description of the present invention, it should also be noted that unless otherwise clearly specified and defined, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the internal communication of two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0019] Figure 1 is a schematic diagram of a hearing aid system for real-time gait feature monitoring with artificial simulation of vestibular function provided by an embodiment of the present invention. AsFigure 1 As shown in Figure 1 , the hearing aid system includes a hearing aid and an artificial vestibular function simulation system integrated within the hearing aid. Among them, the artificial vestibular function simulation system includes: a three-axis gyroscope, a three-axis accelerometer, and a three-axis magnetometer. The artificial vestibular function simulation system is used to detect the motion state data of the user's head, and the hearing aid is used to extract the gait characteristic parameters of the user based on the motion state data and give an in-ear warning when the gait characteristic parameters are abnormal. In this embodiment, the hearing aid is combined with the artificial vestibular system, and by utilizing the characteristics of small head movement amplitude, strong consistency with body movement, and bilateral symmetry, the human gait characteristics can be accurately detected.

[0020] In a specific embodiment, the artificial vestibular system is mainly composed of a 9-axis IMU. This sensor is assembled by a variety of motion sensors and is an inertial measurement unit that can measure the motion state and posture of an object in three-dimensional space. It mainly includes the following parts:

[0021] Three-axis gyroscope: It can measure the angular velocity of the carrier, and the angle change information can be obtained through integration;

[0022] Three-axis accelerometer: It can measure the acceleration of the carrier and is used to judge the motion state of the carrier; and

[0023] Three-axis magnetometer: It is used to assist in judging the direction.

[0024] The three work together and use a data fusion algorithm (such as the extended Kalman filter algorithm) to comprehensively process the data of these sensors, enabling more accurate calculation of data and correction of direction.

[0025] Specifically, the three-axis accelerometer mainly measures the linear acceleration of an object and can detect the acceleration changes of the object in three axes (X / Y / Z axes), including gravitational acceleration and motion acceleration. Its specific functions are as follows:

[0026] (1) Detect basic motion information: Accurately capture the acceleration changes of the body in three axes (X / Y / Z axes) during movement. Sense the acceleration changes generated by the body swing, foot landing, and lifting during walking. The frequency and amplitude of these changes can be used to judge information such as step length, step frequency, and step width.

[0027] (2) Analyze the conversion of motion states: Detect the conversion of different motion states in gait, such as the changes from standing to walking, from slow walking to fast walking, from walking to running, etc. Since the acceleration change characteristics are different in different motion states, analyzing these characteristics can accurately identify the conversion moment and frequency of motion states.

[0028] (3)Evaluate exercise intensity: The greater the peak value and the range of variation of the acceleration, the higher the exercise intensity. Based on this, analyze the exercise intensity of the user when walking or running to provide data support for exercise health management, such as determining whether the user meets the intensity standard of aerobic exercise.

[0029] The triaxial gyroscope is mainly used to measure the angular velocity of an object, which measures the rotational speed of the object around the (X / Y / Z axis). Its specific functions are as follows:

[0030] (1)Precisely measure posture changes: Real-time measure the angular velocity and rotation angle of the body or limbs during exercise, and use it to precisely analyze the posture changes of the feet, legs, etc. when walking. For example, it can monitor the rotation angle and speed of the feet during landing and swinging, and understand the internal rotation and external rotation of the feet, which is very important for evaluating the motor function of the ankle joint and the biomechanical characteristics of gait.

[0031] (2)Assist in judging the movement direction: Accurately sense changes in the movement direction. For example, during walking, when turning, going up and down stairs, etc., the gyroscope can provide information about direction changes. Combining the data of the acceleration sensor can more comprehensively analyze the gait pattern and improve the accuracy of gait monitoring.

[0032] (3)Detect balance ability: By monitoring the posture stability and angle changes of the body when walking, the gyroscope can evaluate the balance ability of the user. In gait analysis, balance ability is an important indicator, especially for the elderly and rehabilitation patients. The evaluation of balance ability is of great significance for preventing falls and formulating rehabilitation training plans.

[0033] The triaxial magnetometer fuses the magnetometer with other sensors (gyroscope, accelerometer) to improve the accuracy of heading angle correction. Specifically, the gyroscope has a drift problem, that is, pure integral angular velocity will cause the heading angle to accumulate errors over time (typical error is about 1° / s); while the accelerometer has a direction limitation and can only accurately sense the direction of gravity when static, and is easily interfered by linear acceleration during dynamic movement; the magnetometer can provide an absolute heading reference by measuring the earth's magnetic field (accuracy can reach 0.5° - 1°).

[0034] Based on the motion state data measured by the above sensors, this embodiment proposes an adaptive calculation method to extract various gait feature parameters of the user, and assist in realizing the prevention and recovery of various diseases. Generally speaking, the gait feature parameters extracted in this embodiment include two categories. One category is basic gait feature parameters, including step length, step frequency, step width, gait cycle symmetry and variability; the other category is auxiliary gait feature parameters, including stance phase / swing phase ratio, knee flexion, ankle dorsiflexion and freezing gait. The following will introduce the adaptive calculation methods of various gait parameters respectively.

[0035] (1) Calculation method of step length. The step length (SL) is the horizontal distance of a single-foot step. For normal adults, it is about 60 - 80 cm, and for patients, it may be shortened to less than 40 cm. Optionally, based on the double integration of the accelerometer and the zero velocity update (ZUPT) method, the start and end times of a single step can be determined through the zero velocity interval first, and then the step length of the user can be calculated by integrating the accelerations on the X-axis and Y-axis within the start and end times of the single step. Specifically,

[0036]

[0037] where a x and a y are the accelerations in the horizontal direction (the gravity component needs to be removed), and t1 and t2 are the start and end times of a single step (detected through the zero velocity interval).

[0038] Specially, the algorithm needs to be adaptively corrected during operation, and the method is as follows:

[0039] ① Reset the velocity accumulation error during the foot stationary stage (stance phase), and improve the accuracy to ±5%;

[0040] ② After the user walks a known distance (10 meters), adjust the step length coefficient through linear regression to eliminate the cumulative error.

[0041] (2) Calculation method of step frequency. The step frequency (SC) is the number of steps per minute. For healthy adults, it is about 100 - 120 steps / minute, and for fatigued or sarcopenia patients, it may drop to 80 steps / minute. Optionally, the unilateral gait cycle can be determined based on the acceleration on the Z-axis, and the step frequency of the user can be determined based on the average gait cycle within the detection window. Specifically,

[0042]

[0043] where T is the average gait cycle, in seconds, representing the time interval between two consecutive contacts of the same foot with the ground.

[0044] The step frequency can be determined through peak detection of the accelerometer, and the method is as follows:

[0045] ① Perform low-pass filtering (cutoff frequency is 5 Hz) on the acceleration signal of the vertical axis (Z-axis);

[0046] ② Detect the peaks (corresponding to heel strike events), and the peak-to-peak interval is the unilateral gait cycle;

[0047] ③ Calculate the average cycle T within a 30-second window and convert it to the step frequency value according to the above formula.

[0048] (3) Calculation method of step width. The step width (SW) is the distance between the midlines of the two feet, with a normal value of 4 - 10 cm. The step width of stroke patients may exceed 15 cm. Optionally, the head attitude angle of the user can be calculated based on the detection data of the three-axis gyroscope; then, according to the head attitude angle, the lateral acceleration of the user's head can be determined; finally, according to the integral energy of the lateral acceleration within a gait cycle and the integral energy reference value corresponding to the user's straight walking, the step width of the user can be determined. Specifically,

[0049]

[0050] where a lat represents the head lateral acceleration (the influence of attitude rotation needs to be removed), N1 represents a total of N1 single steps, i represents the i-th single step, t i represents the start time of the i-th single step, Δt represents the single-step time window, and K represents the single-step calibration coefficient, which is calibrated by the calibration step width when initially worn.

[0051] In a specific embodiment, the step width can be calculated in the following manner:

[0052] ① Use the gyroscope data to calculate the head attitude angle and convert the acceleration to the global coordinate system;

[0053] ② Extract the lateral acceleration component a lat , and calculate its integral energy within a gait cycle;

[0054] ③ Determine the coefficient K through a calibration experiment (for example, when the user walks in a straight line, set the step width = 8 cm corresponding to the integral energy reference value, and the specific value needs to be calibrated when first worn);

[0055] ④ Multi-step moving average (window = 5 steps) to reduce random fluctuations, with an accuracy of ±2 cm;

[0056] ⑤ Exclude turning gaits by detecting the gyroscope angular velocity (pause calculation when > 30° / s).

[0057] (4) Calculation method of gait cycle symmetry and variability.

[0058] ① Gait symmetry index GSI:

[0059]

[0060] where L and R are the left step length and the right step length respectively.

[0061] The normal gait symmetry index > 95%, and the GSI of stroke patients is often lower than 85%.

[0062] ② Standard deviation δ T :

[0063]

[0064] Among them, N represents the number of samples of the gait cycle, and \(T_i\) i is the \(i\)th gait cycle, and T is the average value of all gait cycles. The larger the standard deviation, the greater the fluctuation of the gait cycle and the higher the variability.

[0065] ③Coefficient of variation CV T :

[0066]

[0067] Among them, CV T eliminates the influence of the average value of the gait cycle on variability and more intuitively reflects the relative change degree of the gait cycle. The higher the coefficient of variation, the worse the stability of the gait cycle. The evaluation criteria of CV T are as follows: for normal people, it is 5 - 10%, for Parkinson's patients, it is 15 - 30%, and for stroke rehabilitation patients, it is 20 - 30%, and it gradually recovers with training. When this coefficient is greater than 20%, the risk of falling increases significantly, and an in-ear warning will be given.

[0068] In addition to the above basic gait characteristic parameters, multiple auxiliary parameters can also be calculated to determine the gait:

[0069] (1) Stance phase / swing phase ratio. In a healthy gait, the stance phase accounts for 60% of the gait cycle (for example, abnormal single-leg support phase indicates knee joint lesions). Optionally, the Z-axis signal of the accelerometer is processed using high-pass filtering (>10 Hz) to remove low-frequency walking noise and retain high-frequency components of the ground contact impact, which correspond to ground contact (peak) and lift-off (valley) events; the ratio is calculated by comparing the peak-valley time, that is, calculating the ratio of the duration span of the peak to the total duration, and the ratio of the duration span of the peak and valley to the total duration, so as to obtain the stance phase / swing phase ratio.

[0070] (2) Knee flexion. The normal flexion angle in the swing phase is 60 - 70°, for patients with osteoarthritis, it is reduced to 45 - 50°, and a flexion angle <45° in the swing phase results in gait drag.

[0071] Optionally, the knee flexion angle

[0072] Among them, ω is the angular velocity of the knee joint, which is calculated from the Y-axis data of the gyroscope; \(\theta_0\) is the initial angular velocity (initial calibration and calibration); \(T_1\) and \(T_2\) respectively represent the start time and end time of the test period.

[0073] (3) Dorsiflexion of the ankle joint: In the gait of children with cerebral palsy, there is insufficient dorsiflexion (<5° vs normal 10 - 15°). The calculation method of ankle dorsiflexion is similar to that of knee flexion. Just replace the test cycle (T1 - T2) and the initial angular velocity θ0 with the corresponding values of ankle dorsiflexion.

[0074] (4) Detection of freezing gait: Freezing gait can be detected based on the characteristics of the acceleration signal. Specifically, freezing gait exhibits the following characteristics in the time domain and frequency domain:

[0075] ① In the time domain: The amplitude of the vertical acceleration (Z - axis) drops suddenly, and the variance decreases significantly.

[0076] ② In the frequency domain: The high - frequency tremor component (4 - 8 Hz) may increase (some patients are accompanied by tremors).

[0077] Therefore, this embodiment provides the following standard division:

[0078]

[0079] Optionally, the freezing gait detection algorithm is implemented using the window variance method, specifically as follows:

[0080] ① Sensor data acquisition:

[0081] Acquisition: Acquire the vertical acceleration (Z - axis), with a sampling rate ≥50 Hz;

[0082] Filtering: Band - pass filtering at 4 - 8 Hz (retaining the freezing tremor characteristics and suppressing noise);

[0083] Detrending: Remove the baseline drift (high - pass filtering);

[0084] ② Sliding window segmentation: The length of the sliding window is 2 seconds (100 data points @50 Hz), with an overlap of 1 second;

[0085] ③ Calculate the variance of the acceleration within the sliding window, and judge normal gait and freezing gait according to the division criteria shown in the above table.

[0086] ④ Optionally, in addition to the above parameters, additional parameters such as age, height, gender, and fatigue can be introduced to assist in correcting the algorithm.

[0087] Based on the above parameters, the hearing aid judges whether the gait characteristic parameters are within the normal range in at least one of the following ways and gives an early warning in special abnormal situations:

[0088]

[0089]

[0090] Optionally, when the step length is less than 50 cm, abnormal Parkinson's disease gait is judged and a warning is issued; when the step frequency drops by 15% of the normal range, abnormal step frequency during fatigue is judged; when the step width is greater than 15 cm, abnormal step width of stroke patients is judged; according to the symmetry and variability of the gait cycle, the ratio of the stance phase / swing phase, the knee joint flexion degree, the ankle joint dorsiflexion, and the gait freezing parameter, the gait abnormalities caused by various diseases are comprehensively judged and a warning is issued.

[0091] Further, in a specific embodiment, the architecture diagram of the entire gait monitoring hearing aid system is as Figure 2 shown. Among them, the hardware layer includes:

[0092] Artificial simulated vestibule: 9-axis IMU, integrating a three-axis gyroscope, a three-axis accelerometer, and a three-axis magnetometer to accurately collect motion data;

[0093] Hearing aid module: An in-ear hearing aid unit, consisting of a high-precision microphone, a high-precision REC, and a hearing aid chip, etc., to provide clear hearing compensation for users;

[0094] Low-power Bluetooth module: Realize wireless data transmission between the front-end device and the mobile phone;

[0095] Power supply system: Consisting of a rechargeable micro lithium battery and a power supply support circuit to provide power support for the device; and

[0096] Customized shell: Customize the shell according to the user's ear canal environment to improve the wearing comfort.

[0097] The data sources include:

[0098] Real-time motion data stream: Real-time collected by the sensor module (gyroscope, accelerometer, magnetometer) to provide the original data of human motion;

[0099] User health record: Containing information such as the user's past medical history and health status, providing background data for system analysis; and

[0100] Clinical gait database: Store a large amount of clinical gait data for data comparison.

[0101] The main operations of the data processing layer include:

[0102] Signal preprocessing: Convert, filter, denoise, and calibrate the collected signals to improve the data quality;

[0103] Spatio-temporal feature calculation: Calculate spatio-temporal features such as step frequency, step length, step width, and symmetry to provide a basis for gait analysis;

[0104] Motion mode recognition: Realize functions such as fall detection and gait cycle division to identify different motion modes;

[0105] Data compression and storage: Compress and store the processed data to save storage space.

[0106] The algorithm layer includes:

[0107] Multi-sensor data fusion: Extended Kalman filter algorithm;

[0108] Gait feature extraction engine: Extract key gait features to provide a basis for subsequent analysis; and

[0109] Anomaly detection model: Adopt a gait monitoring algorithm to detect gait features.

[0110] The application layer includes:

[0111] Disease warning system: Based on disease models such as Parkinson's, stroke, arthritis, hypertension, sudden cerebral infarction, stroke, and vestibular neuronitis, realize disease warning;

[0112] Real-time gait correction feedback: Provide real-time feedback and correction of gait through in-ear voice prompts; and

[0113] Rehabilitation training plan management: Develop and manage rehabilitation training plans according to the user's situation;

[0114] And health data report generation: Generate detailed health data reports to provide reference for users and medical staff.

[0115] The user layer includes:

[0116] Patients / rehabilitants: Use the device for gait monitoring and receive feedback and training plans;

[0117] [[ID=3,6]]Doctors / rehabilitation therapists: Obtain patient data through the mobile / Web visualization interface (mobile APP) and develop treatment plans;

[0118] Mobile / Web visualization interface (mobile APP): Provide an intuitive data display and interaction interface.

[0119] [[ID=4,2]]It should be noted that the user data involved in this application are all information and data authorized by the user or fully authorized by all parties. And the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0120] In summary, this embodiment provides a hearing aid system for real-time gait feature monitoring with artificial vestibular function simulation. It uses motion sensors to simulate the artificial vestibule, collects human motion state data, combines the artificial vestibular function simulation and the hearing aid, integrates an adaptive algorithm in the hearing aid, extracts gait feature parameters, and realizes real-time monitoring and real-time warning functions, which has a positive effect on the prevention, diagnosis, and recovery of various diseases. Specifically, the hearing aid system of this embodiment has the following advantages:

[0121] (1) Functional integration innovation: Integrate the hearing aid and artificial vestibular technology, realize real-time gait monitoring while assisting hearing, integrate multiple functions into one, improve the practicality and convenience of the device, reduce the wearing burden of users, and improve the compliance of use;

[0122] (2) Disease monitoring and rehabilitation assistance: It can monitor and warn in real time about neurological diseases such as Parkinson's disease and stroke, orthopedic diseases such as arthritis, and vestibular lesions such as vestibular neuronitis. Provide data support for diagnosis and treatment through gait analysis, assist in treatment and rehabilitation training, and help patients' health recovery;

[0123] (3) Precise data collection: The in-ear test environment is good, the two ears are symmetrical, there is less motion artifact and noise, and the accuracy of gait monitoring data is high, providing a reliable basis for disease diagnosis and health assessment;

[0124] (4) Visual health management: Create a visual hearing and gait health record system, which is convenient for users to view the changes in health data, is conducive to doctors' long-term tracking and analysis, realizes personalized health intervention, and improves the effect of health management.

[0125] Finally, it should be noted that: The above embodiments are only used to illustrate the technical solutions of the present invention, not to limit them; Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: They can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; And these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the technical solutions of the embodiments of the present invention.

Claims

1. A hearing aid system for real-time gait feature monitoring by artificially simulating vestibular function, characterized in that, Comprising: A hearing aid, and An artificial vestibular function simulation system integrated in the hearing aid, including: a three-axis gyroscope, a three-axis accelerometer, and a three-axis magnetometer; Wherein, the artificial vestibular function simulation system is used to detect the motion state data of the user, and the hearing aid is used to extract the gait characteristic parameters of the user according to the motion state data, and give an in-ear warning when the gait characteristic parameters are abnormal.

2. The system according to claim 1, wherein The gait characteristic parameters include step length, and the hearing aid extracts the step length of the user in the following way: Determine the start and end time of a single step through the zero-velocity interval; Calculate the step length of the user through the integration of the accelerations on the X-axis and Y-axis within the start and end time.

3. The system according to claim 1, characterized in that, The gait characteristic parameters include step frequency, and the hearing aid extracts the step frequency of the user in the following way: Determine the unilateral gait cycle according to the Z-axis acceleration; Determine the step frequency of the user according to the average gait cycle within the detection window.

4. The system according to claim 1, characterized in that, The gait characteristic parameters include step width, and the hearing aid extracts the step width of the user in the following way: Solve the head attitude angle of the user according to the detection data of the three-axis gyroscope; Determine the lateral acceleration of the user's head according to the head attitude angle; Determine the step width of the user according to the integrated energy of the lateral acceleration within a gait cycle and the integrated energy reference value corresponding to the user's straight walking.

5. The system according to claim 1, wherein The gait characteristic parameters include gait cycle symmetry and variability, and the hearing aid extracts the gait cycle symmetry and variability of the user in the following way: Determine the gait symmetry of the user according to the left and right step lengths of the user; Determine the gait variability of the user according to the standard deviation of the user's gait cycle and the average gait cycle.

6. The system according to claim 1, wherein the gait characteristic parameters include the stance phase / swing phase ratio, and the hearing aid extracts the stance phase / swing phase ratio of the user in the following way: Perform high-pass filtering on the Z-axis acceleration to retain the high-frequency components of the ground contact impact; Calculate the peak-valley duration ratio according to the high-frequency components, so as to obtain the stance phase / swing phase ratio of the user.

7. The system according to claim 1, wherein the gait characteristic parameters include the knee flexion angle, and the hearing aid extracts the knee flexion angle of the user in the following way: Calculate the knee angular velocity of the user according to the data of the Y-axis gyroscope; Calculate the knee flexion angle of the user according to the knee angular velocity.

8. The system according to claim 1, wherein the gait characteristic parameters include freezing gait, and the hearing aid extracts the freezing gait of the user in the following way: When the variance of the Z-axis acceleration is within the normal range and the Z-axis acceleration shows periodic fluctuations, determine that the user's gait is a normal gait; When the variance of the Z-axis acceleration is less than the set threshold and the Z-axis acceleration shows low-frequency stagnation and / or high-frequency tremor, determine that the user's gait is a freezing gait.

9. The system according to claim 1, wherein the gait characteristic parameters include at least one of step length, step frequency, step width, gait cycle symmetry and variability; The hearing aid judges the abnormality of the gait characteristic parameters by at least one of the following methods: When the step length is less than 50 cm, judge that the Parkinson's disease gait is abnormal; When the step frequency drops by 15% within the normal range, it is judged that the step frequency is abnormal during fatigue; When the step width is greater than 15 cm, it is judged that the step width of stroke patients is abnormal; Based on the symmetry and variability of the gait cycle, the stance phase / swing phase ratio, knee joint flexion, ankle dorsiflexion, and gait freezing parameters, the gait abnormalities caused by various diseases are comprehensively judged.

10. The system according to claim 1, wherein It also includes an APP side for visual display of the user's gait parameters and warning status.

Images