Head-mounted intelligent rehabilitation training device and method for patient with frozen gait

Abstract

The invention relates to a head-mounted intelligent rehabilitation training device and method for patients with frozen gaits. Comprising a head-mounted rehabilitation training device which is provided with a motion sensing module, a sound prompt generation module and a vibration prompt generation module; a gait cycle calculation step: calculating a left and right footstep cycle of the user in a non-frozen state based on the gait data; a frozen gait detection step: constructing a frozen gait detection model based on an SVM (Support Vector Machine); and a multi-mode prompt generation step: when the frozen gait is detected, generating a vibration and sound dual-mode fusion prompt on the basis of the left and right step state periods of the user in the normal state, and continuously updating the gait period of the user in the non-frozen state in the process so as to match the real-time state of the user. According to the method, corresponding sound and vibration fused multi-mode feedback information can be adaptively generated according to the actual condition of a patient with frozen gaits, and the patient can be helped to improve the gait freezing condition after long-time use.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a head-mounted intelligent rehabilitation training device and method for patients with freezing gait. Background Art

[0002] Parkinson's disease (PD), as a neurodegenerative disease, has an increasing incidence in China and around the world. It is estimated that the number of PD cases in China will reach 5 million in 2030, accounting for half of the world's total. The main symptoms of PD are movement disorders, among which freezing of gait is particularly common. When patients start walking or try to move, they suddenly feel that their legs are "frozen" on the ground, and they are unable to start gait smoothly or maintain a normal walking rhythm, which seriously affects their daily life and mobility. Due to the incurability of Parkinson's disease, clinical treatment strategies mainly focus on relieving symptoms and improving quality of life. Treatment methods mainly include drug therapy, rehabilitation training and surgical intervention. Although drug therapy can quickly relieve symptoms, long-term use may cause side effects and drug resistance; surgical intervention is suitable for specific patient groups and has certain risks; in contrast, rehabilitation training has gradually become an important part of Parkinson's disease treatment with its advantages of non-invasiveness, few side effects and easy implementation. More and more research and clinical evidence show that rehabilitation training can not only effectively improve the movement disorders of Parkinson's patients, such as improving gait stability and reducing the occurrence of freezing gait, but also delay the progression of the disease to a certain extent. However, the heterogeneity of Parkinson's disease makes the symptoms and disease progression of each patient different, which puts higher demands on home rehabilitation training. Home rehabilitation training without personalized guidance and professional supervision is often difficult to effectively adjust to the patient's specific symptoms and condition, thus affecting the rehabilitation effect. Therefore, how to overcome this challenge and maximize the advantages of rehabilitation training has become an urgent problem to be solved in the current treatment and research of Parkinson's disease.

[0003] At present, the United States has developed medrhythm in the field of post-stroke motor rehabilitation training. The software uses auditory stimulation for rehabilitation training prompts. Related patents include: CN116096289A, CN115120835A. The Swiss Federal Institute of Technology has developed the GaitAssist auditory prompt system, which can assist in sports training in a home environment. The system uses frequency analysis and machine learning techniques to detect freezing gait and produces rhythmic ticking sounds when freezing gait is identified or expected. The University of Pennsylvania in the United States has developed a laser shoe that combines two laser transmitters and two heel switches, which are placed under the sole of each foot of the user. During walking, each laser shoe attachment projects a static horizontal red laser line vertically forward when the contralateral heel touches the ground. The Daegu Gyeongbuk Institute of Science and Technology in South Korea has developed an auxiliary training system based on AR devices, which can realize real-time freezing gait detection and generate visual prompts that adapt to the user's walking speed and head direction. The visual prompts are adjusted according to the user's walking speed and their current head direction.

[0004] Most existing rehabilitation training methods require wearing multiple devices or using additional walking aids, which are complicated to operate and may even cause walking discomfort. Furthermore, most existing rehabilitation training methods focus on the detection of freezing gait, but lack research on personalized prompts for rehabilitation training for PD patients. PD is highly heterogeneous and patients have different symptoms, so unified visual or auditory prompts may not match the actual situation of the patient. For the freezing gait of PD, the time and duration of freezing are different for each patient, and even for the same patient, there will be differences due to the influence of status, environmental factors, etc. Therefore, in addition to timely detection of the occurrence of freezing gait, rehabilitation training for PD patients also requires external stimulation for training prompts based on the specific situation of the patient.

[0005] To address the above problems, no effective solution has been proposed yet. Summary of the invention

[0006] Based on this, it is necessary to provide a head-mounted intelligent rehabilitation training device and method for patients with freezing gait in response to the above technical problems. For PD rehabilitation training, a head-mounted rehabilitation training device for patients with freezing gait is proposed; for the freezing gait of PD patients, a multimodal personalized intervention training method is proposed, which constructs a vibration and sound dual-modal fusion prompt, and can formulate personalized prompts according to the patient's own situation to improve the occurrence of freezing gait, reduce the risk of falls in PD patients, and delay the progression of motor symptoms.

[0007] According to a first aspect of the present invention, a head-mounted rehabilitation training device for patients with freezing gait is provided, comprising: a motion perception module, a sound prompt generation module, and a vibration prompt generation module;

[0008] The motion sensing module uses an ESP32 microprocessor as the core control unit, including an accelerometer, a gyroscope, and a magnetometer, which can obtain user motion data and send it to the host computer;

[0009] The sound prompt generation module plays sound prompts through bone conduction headphones for user rehabilitation training;

[0010] The vibration prompt generation module includes two parts: a voice coil vibration motor and a driving circuit. The driving circuit uses L9110S to realize the conversion of microprocessor pulse signals into AC vibration signals. The signal is then smoothed by an RC filter circuit and used to drive the vibration motor, making the vibration feel softer. Vibration prompts can be generated for patient rehabilitation training.

[0011] According to a second aspect of the present invention, a head-mounted intelligent rehabilitation training method for patients with freezing gait is provided, comprising:

[0012] a gait cycle calculation step, calculating the gait cycles of the left and right feet of the user in a non-frozen state based on the gait data;

[0013] In the freezing gait detection step, a freezing gait detection model is constructed based on SVM;

[0014] The multimodal prompt generation step, when a frozen gait is detected, generates a vibration and sound dual-modal fusion prompt based on the user's normal left and right foot gait cycle. In this process, the user's non-frozen gait cycle is continuously updated in the hope of matching the user's real-time state.

[0015] In some embodiments, the types of multimodal prompts include: vibration prompts and sound prompts.

[0016] In some embodiments, the step of calculating the gait cycle of the left and right feet of the user in a non-frozen state based on the gait data includes:

[0017] Step S1: performing endpoint detection, using a dynamic threshold filtering method to exclude the atypical cycle effects of static state and turning period;

[0018] Step S2: The gait cycle range is defined as between 1 and 2 seconds, and the corresponding gait frequency is between 0.5 and 1 Hz. After the original data is converted into frequency domain data, the frequency with the largest energy in the range of 0.5 to 1 Hz represents the main periodic component of the gait signal, that is, the preliminary gait cycle;

[0019] Step S3: Combined with the motion mutation situation, the gait timing data is comprehensively analyzed using the data of the acceleration sensor and the angle sensor to determine the specific gait cycle.

[0020] In some embodiments, generating a multimodal prompt based on the user's gait performance includes:

[0021] The sound prompt is generated based on the gait cycle of the left and right feet of the user in a non-frozen state, and the target number of gait cycles per minute, that is, the target number of beats per minute, is calculated. Then, the beat number of the selected music is adjusted to the target beat number through rhythm modulation technology, thereby ensuring that the music rhythm is synchronized with the user's ideal gait cycle.

[0022] Vibration prompt generation, based on the user's average gait cycle in a non-freezing state, generates a vibration with a duration of 1s that matches the current cycle. The initial frequency of the vibration prompt is 20HZ. If the user continues to freeze after the prompt is generated, the frequency is increased by 10HZ per minute until the vibration frequency reaches 60HZ.

[0023] In some embodiments, the multimodal prompt generation is characterized by setting an update cycle, recalculating the average gait cycle of the left and right feet of the user in a non-frozen state every cycle. When it is detected that the cycle change exceeds a threshold, the prompt is updated based on the new cycle data.

[0024] In some embodiments, the threshold is 10% and the period is 1 minute.

[0025] According to a third aspect of the present invention, there is provided a computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any of the above-mentioned method embodiments when executing the computer program.

[0026] According to a fourth aspect of the present invention, there is provided a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method of any of the above embodiments are implemented.

[0027] Most existing rehabilitation training systems require the use of additional walking aids or multiple sensor devices, which are relatively complicated to use. The present invention only requires wearing one headset and is relatively simple to use. In addition, most existing rehabilitation training systems focus on the detection of frozen gait, but lack research on personalized stimulation for rehabilitation training of PD patients. The present invention obtains the user's gait data, and then calculates the left and right foot gait cycles in the non-freezing state, and generates vibration prompts and sound prompts that match the patient's normal state based on the gait cycle, and enhances the prompt effect through personalized dual-modal fusion stimulation, thereby improving motor symptoms. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 is a schematic diagram of a head-mounted rehabilitation training device for patients with freezing gait according to the present invention;

[0029] Figure 2 It is a structural schematic diagram of an embodiment of a head-mounted rehabilitation training device for patients with freezing gait of the present invention;

[0030] Figure 3 is a schematic diagram of a system for implementing a head-mounted rehabilitation training method for patients with freezing gait according to the present invention;

[0031] Figure 4 is a flow chart of some embodiments of the head-mounted rehabilitation training method for patients with frozen gait of the present invention;

[0032] Figure 5 is a schematic diagram of the gait event detection process of the present invention;

[0033] Figure 6 It is a diagram of the internal structure of a computer device used to implement some embodiments of the present invention. DETAILED DESCRIPTION

[0034] Embodiments of the present invention will be described more fully below with reference to the accompanying drawings, in which embodiments of the present invention are shown. However, the present invention can be embodied in many different forms and should not be construed as limited to the embodiments set forth herein.

[0035] The terms used herein are used only for the purpose of describing specific embodiments and are not intended to limit the present disclosure. As used herein, the singular forms "a", "an", "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that when used herein, the term "comprising" specifies the presence of the claimed features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof.

[0036] Unless otherwise defined, the terms (including technical and scientific terms) used herein have the same meanings as commonly understood by those of ordinary skill in the art to which the present disclosure belongs. The terms used herein should be interpreted as having the meanings consistent with their meanings in the context of this specification and in the relevant field, and should not be interpreted in an idealized or overly formal sense, unless specifically defined as such herein.

[0037] Gait cycle: The process from when the same foot leaves the ground to when it touches the ground again when walking.

[0038] Auditory cues: Refers to regular, repetitive rhythmic signals, usually generated by music, used to activate the auditory center and motor area of ​​the brain, thereby controlling the lower limb muscles to cooperate with rhythmic training and adjust the gait pattern. It relies on the repetitive nature of rhythm to promote rhythmic motor function rehabilitation.

[0039] Vibration prompt: refers to a vibration signal with a specific frequency and amplitude, which is used to activate the sensory center and the motor area of ​​the brain, thereby controlling the lower limb muscles to cooperate with rhythmic training and adjust the gait pattern. It relies on the setting of the vibration frequency to promote rhythmic motor function rehabilitation.

[0040] The invention provides a head-mounted rehabilitation training device for patients with freezing gait. The device comprises a motion perception module, a sound prompt generation module, and a vibration prompt generation module. Figure 1 FIG. 1 shows a schematic diagram of a head-mounted rehabilitation training device for patients with freezing gait. Figure 1 As shown, the device only needs to be worn like a normal headset. The added motion sensor module is used to obtain the patient's gait data, the vibration module is used to generate vibration prompts, and the bone conduction headset ensures that the patient can hear the sound prompts and external sounds.

[0041] Figure 2 The schematic structural diagrams of some embodiments of the head-mounted rehabilitation training device for patients with freezing gait of the present invention are shown.

[0042] like Figure 2 As shown, the head-mounted rehabilitation training device for patients with freezing gait in the embodiment includes:

[0043] The motion sensing module uses the ESP32 microprocessor as the core control unit, including an accelerometer, a gyroscope, and a magnetometer, which are used to obtain user motion data and send it to the host computer;

[0044] The sound prompt generation module plays sound prompts through bone conduction headphones for user rehabilitation training;

[0045] The vibration prompt generation module consists of two parts: a voice coil vibration motor and a drive circuit. The drive circuit uses L9110S to realize the conversion of microprocessor pulse signals into AC vibration signals. The signal is then smoothed by an RC filter circuit and used to drive the vibration motor, making the vibration softer. Vibration prompts can be generated for patient rehabilitation training.

[0046] The present invention also provides a head-mounted rehabilitation training method for patients with freezing gait. The method is implemented through a system, which includes: a head-mounted rehabilitation training device (the device only needs to be worn like a normal headset) and a personalized auxiliary training system (used to process gait data and generate sound prompts and vibration prompts based on the patient's gait performance). Figure 3 FIG. 1 is a schematic diagram showing a system for implementing a head-mounted rehabilitation training method for patients with frozen gait according to the present invention. Figure 3 As shown, firstly, the user's gait data is obtained based on a head-mounted rehabilitation training device for patients with frozen gait. Then, based on the gait data, the left and right foot gait cycles of the user in a non-frozen state are calculated. In summary, a frozen gait detection model is constructed based on SVM. When a frozen gait is detected, a rhythmic stimulation prompt can be generated based on the left and right foot gait cycles of the user in a normal state. The stimulation is based on the patient's normal gait performance and can better prompt the user to restore a normal walking rhythm. At the same time, the present invention will use 1 minute as an iteration cycle to continuously update the left and right foot gait cycles of the user in a non-frozen state and then update the sound prompts and vibration prompts, in order to match the user's real-time state.

[0047] Figure 4 is a flow chart of some embodiments of the head-mounted rehabilitation training method for patients with frozen gait of the present invention;

[0048] like Figure 4 As shown, the method includes:

[0049] a gait cycle calculation step, calculating the gait cycles of the left and right feet of the user in a non-frozen state based on the gait data;

[0050] The present invention adopts a spatial stepwise estimation method to obtain comprehensive gait information including special gaits. This method uses the frequency domain information of gait data to accurately determine the basic gait cycle of PD patients. This cycle is an important basis for delineating the threshold of intervals between posture events. Specifically, the present invention performs the following steps on the collected gait data: First, endpoint detection is performed, and a dynamic threshold filtering method is used to exclude the atypical cycle effects of static states and turning periods to ensure that the analyzed data reflects a normal walking cycle. Next, the frequency domain periodic relationship of the gait data is analyzed, and a preliminary judgment is made on the gait cycle. This step helps to identify and locate key gait event points. In general, the gait cycle of an adult is usually between 1 and 1.32 seconds. Compared with healthy adults of the same age, early PD patients have a slower gait and a shorter step length. Therefore, this article defines the gait cycle range as between 1 and 2 seconds, and the corresponding gait frequency is between 0.5 and 1 Hz. According to the formula After converting the raw data into frequency domain data, the frequency with the largest energy in the range of 0.5 to 1 Hz represents the main periodic component of the gait signal, that is, the preliminary gait cycle. In addition, based on the preliminary cycle, the influence of abnormal cycles is eliminated to improve the accuracy and reliability of gait cycle detection. In order to more accurately identify gait events, the present invention combines the motion mutation situation, uses the data of the acceleration sensor and the angle sensor, and conducts a comprehensive analysis of the gait time series data to determine the specific gait event. Then the cycle is calculated as follows:

[0051]

[0052] Among them, SP is the sampling starting point; is the basic gait cycle, k is the index of the corresponding point in the frequency domain, and f k is the frequency; angle z is the angle z-axis data; acc z It is the acceleration z-axis data.

[0053] Figure 5 A schematic diagram of the gait cycle calculation process of the present invention is shown.

[0054] In the freezing gait detection step, a freezing gait detection model is constructed based on SVM.

[0055] Use SVM to detect the gait freezing state and divide the sample space into two categories: freezing and non-freezing. The goal of SVM is to find a partitioning hyperplane that separates the two types of samples and maximizes the interval from the hyperplane to the nearest data point, so that the model has the strongest generalization ability.

[0056] Assume that given a linearly separable training dataset T and a hyperplane w in the feature space T x+b=0, then define the hyperplane about the sample point (x i ,y i ) is the geometric interval The minimum value is That is, the distance from the support vector to the hyperplane. Therefore, the objective of SVM can be expressed in mathematical form.

[0057]

[0058] Maximizing γ is equivalent to maximizing This is equivalent to minimizing Therefore, the problem of solving the maximum segmentation hyperplane of the SVM model can be expressed as the following constrained optimization problem:

[0059]

[0060] st yi (w·x i +b)≥1,i=1,2,…,N

[0061] This is a convex quadratic programming problem with inequality constraints, and the Lagrange multiplier method can be used to obtain its dual problem.

[0062]

[0063] For non-support vectors in the data set, the corresponding α i is 0. Therefore, we only need to calculate the α corresponding to the support vector i , then the relevant parameters of SVM can be calculated.

[0064]

[0065]

[0066] The final classification decision function is The result f(x) is a binary classification result of 1 or -1. When it is +1, it is frozen; when it is -1, it is not frozen. However, for the freezing problem, the data is linearly inseparable. Here, the kernel function is introduced to map the gait data to a high-dimensional space and transform the nonlinear problem into a linear problem. Specifically, the Gaussian kernel function is used. The corresponding SVM is a Gaussian radial basis function classifier. In this case, the classification decision function is

[0067] The multimodal prompt generation step, when a frozen gait is detected, generates a vibration and sound dual-modal fusion prompt based on the left and right foot gait cycles of the user in the normal state. In this process, the left and right foot gait cycles of the user in the non-frozen state are continuously updated in order to match the user's real-time state.

[0068] In order to effectively assist users in restoring a stable walking rhythm, the present invention adopts a personalized dual-modal fusion prompt of hearing and touch. The present invention first generates sound prompts and vibration prompts that match the user's own gait based on the user's normal walking left and right foot gait cycle. At the same time, the system will collect and analyze the user's motion data in real time, iteratively calculate the user's gait cycle in a non-frozen state with a cycle of 1 minute, and then update the vibration prompts and sound prompts.

[0069] Specifically, the sound prompt generation process is as follows: the system calculates the target number of gait cycles per minute, that is, the target number of beats per minute, based on the gait cycles of the left and right feet of the user in a non-frozen state. Then, the system searches for the music clip closest to the target number of beats in the preset music database, and adjusts the number of beats of the selected music to the target number of beats through rhythm modulation technology, thereby ensuring that the music rhythm is synchronized with the user's ideal gait cycle.

[0070] The vibration prompt generation process is as follows: the system generates a vibration with a duration of 1s that matches the current cycle based on the user's average gait cycle in a non-freezing state. The initial frequency of the vibration prompt is 20HZ. If the user continues to freeze after the prompt is generated, the frequency is increased by 10HZ per minute until the vibration frequency reaches 60HZ.

[0071] In order to adapt to the possible dynamic changes in the user's gait, the system will continuously monitor the user's gait data. With an update cycle of 1 minute, the system will recalculate the user's average gait cycle in a non-frozen state. When the cycle change is detected to exceed 10%, the system will update the auditory prompts and vibration prompts based on the new cycle data to ensure that the stimulation is always consistent with the user's actual gait needs, thereby helping the user to overcome the freezing gait more stably and restore the ability to walk smoothly.

[0072] The present invention also provides a computer device, which may be a terminal, and its internal structure diagram may be as follows: Figure 6 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the above-mentioned head-mounted rehabilitation training method for patients with frozen gait is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc. Those skilled in the art can understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0073] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned gait intervention method for patients with early Parkinson's disease is implemented.

[0074] Those skilled in the art can understand that all or part of the processes in the above method embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus), direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0075] So far, the embodiments of the present invention have been described in detail. In order to avoid obscuring the concept of the present invention, some details known in the art are not described. Based on the above description, those skilled in the art can fully understand how to implement the technical solutions disclosed herein.

[0076] Although some specific embodiments of the present invention have been described in detail by way of examples, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present invention. It should be understood by those skilled in the art that the above embodiments may be modified or some technical features may be replaced by equivalents without departing from the scope and spirit of the present invention. The scope of the present invention is defined by the appended claims.

Claims

1. A head-mounted rehabilitation training device for patients with freezing gait, characterized in that: The functional modules of the head-mounted rehabilitation training device include: a motion perception module, a sound prompt generation module, and a vibration prompt generation module.

2. The head-mounted rehabilitation training device according to claim 1, characterized in that: The motion sensing module uses an ESP32 microprocessor as the core control unit, including an accelerometer, a gyroscope, and a magnetometer, which are used to obtain user motion data and send it to the host computer; The sound prompt generation module plays sound prompts through bone conduction headphones for user rehabilitation training; The vibration prompt generation module includes two parts: a voice coil vibration motor and a driving circuit. The driving circuit uses L9110S to realize the conversion of microprocessor pulse signals into AC vibration signals. The signal is then smoothed by an RC filter circuit and used to drive the vibration motor, making the vibration softer. Vibration prompts can be generated for patient rehabilitation training.

3. A head-mounted intelligent rehabilitation training method for patients with freezing gait, characterized in that: include: a gait cycle calculation step, calculating the gait cycles of the left and right feet of the user in a non-frozen state based on the gait data; In the freezing gait detection step, a freezing gait detection model is constructed based on SVM; The multimodal prompt generation step, when a frozen gait is detected, generates a vibration and sound dual-modal fusion prompt based on the left and right foot gait cycles of the user in the normal state. In this process, the left and right foot gait cycles of the user in the non-frozen state are continuously updated in order to match the user's real-time state.

4. The head-mounted intelligent rehabilitation training method for patients with gait freezing as claimed in claim 3, characterized in that: The types of multimodal prompts include: vibration prompts and sound prompts.

5. The gait cycle calculation as claimed in claim 3, characterized in that: The step of calculating the gait cycles of the left and right feet of the user in a non-frozen state based on the gait data includes: Step S1: performing endpoint detection, using a dynamic threshold filtering method to exclude the atypical cycle effects of static state and turning period; Step S2: The gait cycle range is defined as between 1 and 2 seconds, and the corresponding gait frequency is between 0.5 and 1 Hz. After the original data is converted into frequency domain data, the frequency with the largest energy in the range of 0.5 to 1 Hz represents the main periodic component of the gait signal, that is, the preliminary gait cycle; Step S3: Combined with the motion mutation situation, the gait timing data is comprehensively analyzed using the data of the acceleration sensor and the angle sensor to determine the specific gait cycle.

6. The multimodal prompt generation as claimed in claim 3, characterized in that: Generating the hearing and touch dual-modal prompts according to the user's gait performance includes: The sound prompt is generated based on the gait cycle of the left and right feet of the user in a non-frozen state, and the target number of gait cycles per minute, that is, the target number of beats per minute, is calculated. Then, the beat number of the selected music is adjusted to the target beat number through rhythm modulation technology, thereby ensuring that the music rhythm is synchronized with the user's ideal gait cycle. Vibration prompt generation, based on the user's average gait cycle in a non-freezing state, generates a vibration with a duration of 1s that matches the current cycle. The initial frequency of the vibration prompt is 20HZ. If the user continues to freeze after the prompt is generated, the frequency is increased by 10HZ per minute until the vibration frequency reaches 60HZ.

7. The multimodal prompt generation as claimed in claim 5, characterized in that: Set the update cycle to recalculate the average gait cycle of the left and right feet of the user in the non-freezing state every cycle. When the cycle change exceeds the threshold, the prompt will be updated based on the new cycle data.

8. The multimodal prompt generation according to any one of claims 5-6, characterized in that: The threshold is 10%, and the period is 1 minute.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 3 to 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 3 to 8 are implemented.

Images