Walking posture detection method and device based on walking posture correction wearable equipment

Abstract

The invention belongs to the technical field of walking posture detection, and provides a walking posture detection method and device based on walking posture correction wearable equipment, and the method comprises the steps: S1, collecting body posture data in a walking process through a sensor on the wearable equipment; s2, analyzing and processing the collected body posture data so as to identify abnormal walking posture features; s3, generating a walking posture correction instruction according to the recognized abnormal walking posture features, and outputting the walking posture correction instruction to the user through the wearable device to guide the user to carry out walking posture correction; according to the invention, the walking data is comprehensively acquired by integrating various sensors, the abnormal walking posture characteristics are accurately analyzed and processed and identified by applying denoising, weighted average and machine learning algorithms, and the personalized correction instruction is generated and fed back to the user in real time, so that the accuracy of walking posture detection and the pertinence and effectiveness of correction are effectively improved, and the user experience is improved. Compared with a traditional method, the method is more convenient and efficient, the walking posture of the user can be improved, and physical diseases caused by bad walking postures are prevented.

Description

Technical Field

[0001] The present invention belongs to the technical field of gait detection, and specifically relates to a gait detection method and device based on a wearable device for gait correction. Background Art

[0002] With the increasing attention of people to a healthy life, gait correction has gradually become the focus of attention. In recent years, with the rapid development of wearable devices and sensor technologies, new solutions have been provided for gait correction. A correct gait can not only improve walking efficiency and reduce energy consumption, but also help prevent various physical diseases caused by incorrect gaits, such as scoliosis, arthritis, etc.

[0003] However, most traditional gait correction methods rely on manual observation and professional guidance. This method is not only time-consuming and laborious, but also difficult to achieve real-time and personalized correction.

[0004] Therefore, those skilled in the art have proposed a gait detection method and device based on a wearable device for gait correction to solve the problems raised in the background art. Summary of the Invention

[0005] In order to solve the above technical problems, the present invention provides a gait detection method and device based on a wearable device for gait correction to solve the problems that most existing gait correction methods rely on manual observation and professional guidance, which is not only time-consuming and laborious, but also difficult to achieve real-time and personalized correction, etc.

[0006] A gait detection method based on a wearable device for gait correction includes:

[0007] S1. Using sensors on the wearable device to collect body posture data during walking;

[0008] S2. Analyzing and processing the collected body posture data to identify abnormal gait features;

[0009] S3. Generating a gait correction instruction according to the identified abnormal gait features and outputting it to the user through the wearable device to guide the user to correct the gait.

[0010] Preferably, the sensors include an acceleration sensor, a gyroscope, and an electromyogram sensor.

[0011] Preferably, in step S1, using sensors on the wearable device to collect body posture data during walking, and using a denoising algorithm to reduce the influence of environmental noise on the sensor data;

[0012] At the same time, in order to fuse data from different sensors, a weighted average algorithm is introduced to improve the accuracy and reliability of gait detection.

[0013] Preferably, the body posture data includes step length, step frequency, joint angles, and muscle activity information during walking.

[0014] Preferably, in step S2, when analyzing and processing the collected body posture data, for the identified abnormal walking posture features, a machine learning classification algorithm is introduced.

[0015] Preferably, the walking posture correction instruction is output to the user through a vibration motor, a display screen, or an audio module on the wearable device.

[0016] Preferably, in step S3, a genetic algorithm is introduced to optimize the generation strategy of the correction instruction to find the best or approximate best correction solution;

[0017] Meanwhile, an adaptive control algorithm is introduced to dynamically adjust the parameters of the correction instruction (including vibration intensity, frequency, etc.) according to the user's real-time feedback and walking state to achieve personalized walking posture correction.

[0018] A walking posture detection device based on a walking posture correction wearable device, using the above-mentioned walking posture detection method based on a walking posture correction wearable device, includes:

[0019] A data acquisition module, a sensor worn on a specific part of the user's body, for collecting motion data of various parts of the user's body during walking;

[0020] A data processing module, for receiving the motion data collected by the sensor and performing preprocessing on it, including denoising, filtering, and standardization;

[0021] A walking posture analysis module, for extracting the walking posture features of the user based on the preprocessed motion data, including step length, step frequency, joint angles, and swing amplitude, etc.;

[0022] A correction suggestion generation module, for comparing the walking posture features with a preset standard walking posture model to generate personalized walking posture correction suggestions;

[0023] An output module, for presenting the correction suggestions to the user in a visual form, or reminding the user to adjust the walking posture in the form of feedback such as vibration, sound, etc.

[0024] A processor, configured to execute the walking posture detection method based on a walking posture correction wearable device as described above.

[0025] A computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the walking posture detection method based on a walking posture correction wearable device as described above.

[0026] Compared with the prior art, the present invention has the following beneficial effects:

[0027] 1. The present invention can comprehensively and accurately collect body posture data during walking, including step length, step frequency, joint angles, muscle activity information, etc., by integrating multiple sensors such as acceleration sensors, gyroscopes, and electromyogram sensors, providing a rich and reliable data basis for subsequent analysis and processing.

[0028] 2. The present invention introduces a denoising algorithm and a weighted average algorithm to preprocess the collected original sensor data, effectively reducing the interference of environmental noise and improving the accuracy and reliability of the data; at the same time, through machine learning classification algorithms, the preprocessed data is analyzed and processed, and abnormal walking posture features can be accurately identified, providing strong support for generating personalized correction suggestions.

[0029] 3. The present invention generates personalized walking posture correction instructions according to the identified abnormal walking posture features, and outputs them to the user through various means such as vibration motors, display screens, or audio modules on the wearable device to guide the user to perform real-time walking posture correction; in addition, the present invention also introduces genetic algorithms and adaptive control algorithms to optimize and adjust the generation strategy of the correction instructions to achieve the best or approximate best correction effect, improving the pertinence and effectiveness of the correction. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 is a flowchart of the walking posture detection method for the wearable device for walking posture correction according to the present invention;

[0031] Figure 2 is a framework diagram of the walking posture detection device for the wearable device for walking posture correction according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0032] The following further describes in detail the embodiments of the present invention in conjunction with the drawings and embodiments. The following embodiments are used to illustrate the present invention, but cannot be used to limit the scope of the present invention.

[0033] Embodiment: The present invention provides a walking posture detection method for a wearable device for walking posture correction, as Figure 1 shown, including:

[0034] S1. Use the sensors on the wearable device to collect body posture data during walking;

[0035] S2. Analyze and process the collected body posture data to identify abnormal walking posture features;

[0036] S3. Generate walking posture correction instructions according to the identified abnormal walking posture features, and output them to the user through the wearable device to guide the user to perform walking posture correction.

[0037] As can be seen from the above, this method comprehensively collects walking data by integrating multiple sensors, accurately analyzes and processes the data using denoising, weighted average, and machine learning algorithms, identifies abnormal gait features, and generates personalized correction instructions in real time to feedback to the user. This effectively improves the accuracy of gait detection and the pertinence and effectiveness of correction. Compared with traditional methods, it is more convenient and efficient, which helps users improve their gait and prevent physical diseases caused by poor gait.

[0038] Further, the sensors include an acceleration sensor, a gyroscope, and an electromyogram sensor.

[0039] Furthermore, in step S1, the sensors on the wearable device are used to collect body posture data during walking, and a denoising algorithm is used to reduce the influence of environmental noise on the sensor data. The formula of the denoising algorithm includes:

[0040]

[0041] where x(i) is the original sensor data, y(t) is the denoised data, and N is the filter window size;

[0042] At the same time, in order to fuse data from different sensors, a weighted average algorithm is introduced to improve the accuracy and reliability of gait detection. The formula of the weighted average algorithm includes:

[0043]

[0044] where x i is the data of the i-th sensor, and w i is the corresponding weight.

[0045] As can be seen from the above, by using the denoising algorithm to reduce the interference of environmental noise on sensor data and combining the weighted average algorithm to fuse data from different sensors, the present invention significantly improves the accuracy and reliability of the collected body posture data. This data processing method provides a solid foundation for subsequent analysis and processing, making gait detection more accurate, and thus enabling the generation of gait correction instructions that better meet the actual needs of users, improving the scientific nature and effectiveness of the entire gait correction process.

[0046] Further, the body posture data includes step length, step frequency, joint angle, and muscle activity information during walking.

[0047] Furthermore, in step S2, when analyzing and processing the collected body posture data, for the identified abnormal gait features, a machine learning classification algorithm is introduced. The formula of the machine learning classification algorithm includes:

[0048]

[0049] where α i is the Lagrange multiplier, y i is the sample label, K(x i , x) is the kernel function, and b is the bias term.

[0050] As can be seen from the above, by introducing a machine learning classification algorithm to analyze and process the collected body posture data, the present invention can accurately identify abnormal walking posture features; this algorithm utilizes parameters such as the Lagrange multiplier, sample label, kernel function, and bias term, effectively improving the accuracy and efficiency of walking posture feature recognition; this not only enhances the intelligent level of walking posture detection, but also provides strong support for generating personalized walking posture correction suggestions subsequently, making the correction plan more scientific and targeted, and helping users to more effectively improve their bad walking postures.

[0051] Furthermore, the walking posture correction instruction is output to the user through a vibration motor, a display screen, or an audio module on the wearable device.

[0052] Even further, in step S3, a genetic algorithm is introduced to optimize the generation strategy of the correction instruction to find the best or approximately best correction plan. The formula of the genetic algorithm includes:

[0053]

[0054] where f(x i ) is the fitness value of the individual x i .

[0055] Meanwhile, an adaptive control algorithm is introduced to dynamically adjust the parameters of the correction instruction (including vibration intensity, frequency, etc.) according to the user's real-time feedback and walking state to achieve personalized walking posture correction. The formula of the adaptive control algorithm includes:

[0056]

[0057] where e(t) is the error signal, and K p , K i , K d are the proportional, integral, and differential gains respectively.

[0058] As described above, by introducing a genetic algorithm to optimize the generation strategy of correction instructions, the present invention can find the best or approximate best correction plan, thereby ensuring the accuracy and effectiveness of gait correction; at the same time, combined with an adaptive control algorithm, the parameters of the correction instructions, such as vibration intensity, frequency, etc., are dynamically adjusted according to the user's real-time feedback and walking state, realizing personalized gait correction; the above combination of the two algorithms not only improves the pertinence and flexibility of correction, but also significantly enhances the user experience, making the gait correction process more comfortable and natural, and helping users to adhere to it for a long time and form good gait habits.

[0059] Furthermore, a comparison of the effects of a gait detection method based on a wearable device for gait correction in an embodiment with a current traditional gait correction method (comparative example) is made to obtain the following table:

[0060]

[0061]

[0062] As can be seen from the above table, a gait detection method based on a wearable device for gait correction in this embodiment is superior to the traditional gait correction method in terms of data collection, data processing, anomaly recognition, correction instruction generation, user feedback, and correction effect; this method can comprehensively and accurately collect walking data, analyze and process it through advanced algorithms, accurately identify abnormal gait characteristics, and generate personalized correction instructions to be fed back to the user in real time, thereby significantly improving the pertinence and effectiveness of gait correction, and helping users to improve their gait and prevent physical diseases caused by bad gait.

[0063] Working principle: The body posture data during walking is collected by sensors on the wearable device, and the original data is preprocessed using a denoising algorithm and a weighted average algorithm to improve the accuracy and reliability of the data; then, a machine learning classification algorithm is used to analyze the processed data to identify abnormal gait characteristics; then, a genetic algorithm is introduced to optimize the generation strategy of correction instructions, and combined with an adaptive control algorithm, the correction parameters are dynamically adjusted according to the user's real-time feedback; finally, the correction instructions are output to the user through the vibration motor, display screen or audio module of the wearable device to guide the user to perform real-time gait correction, thereby improving bad gait and preventing physical diseases caused by bad gait.

[0064] A gait detection device based on a wearable device for gait correction, as Figure 2 shown, uses the above-mentioned gait detection method based on a wearable device for gait correction, including:

[0065] A data collection module, sensors worn on specific parts of the user's body, for collecting the motion data of each part of the user's body during walking;

[0066] A data processing module, configured to receive the motion data collected by the sensor and perform preprocessing on it, including denoising, filtering, and standardization;

[0067] A gait analysis module, configured to extract the gait features of the user based on the preprocessed motion data, including step length, step frequency, joint angle, swing amplitude, etc.;

[0068] A correction suggestion generation module, configured to compare with a preset standard gait model according to the gait features and generate personalized gait correction suggestions;

[0069] An output module, configured to display the correction suggestions to the user in a visual form, or remind the user to adjust the gait in the form of feedback such as vibration and sound.

[0070] An embodiment of the present application provides an electronic device, applicable to the above-mentioned gait detection method of a wearable device based on gait correction, including:

[0071] A memory, configured to store computer programs and data;

[0072] A processor, configured to run the system program.

[0073] An embodiment of the present application provides a computer storage medium, applicable to the above-mentioned gait detection method of a wearable device based on gait correction, and performs hierarchical confidentiality management on the above system and data according to the confidentiality management requirements.

[0074] Those skilled in the art should understand that the embodiments of the present application can be provided as a system or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0075] The present application is described with reference to the flowcharts and / or block diagrams of the devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, and the combination of processes and / or blocks in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate for implementing in the process Figure 1 one process or multiple processes and / or blocks Figure 1means for the functions specified in one or more blocks.

[0076] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction means that implements the functions specified in one Figure 1 one or more processes and / or blocks Figure 1 means for the functions specified in one or more blocks.

[0077] These computer program instructions may also be loaded onto a computer or other programmable data processing device, such that a series of operational steps are performed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one Figure 1 one or more processes and / or blocks Figure 1 means for the functions specified in one or more blocks.

[0078] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0079] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

[0080] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology for information storage. The information may be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transitory media that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media such as modulated data signals and carrier waves.

[0081] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, commodity or device including the elements.

[0082] The embodiments of the present invention are provided for the purpose of illustration and description. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations of the present invention. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A walking posture detection method based on a walking posture correction wearable device, characterized in that: include: S1. Collect body posture data during walking using sensors on wearable devices; S2, analyzing and processing the collected body posture data; S3. Generate walking posture correction instructions based on the identified abnormal walking posture features and output them to the user through the wearable device.

2. A walking posture detection method and device based on a walking posture correction wearable device as claimed in claim 1, characterized in that: The sensors include an acceleration sensor, a gyroscope and an electromyography sensor.

3. A walking posture detection method and device based on a walking posture correction wearable device as claimed in claim 2, characterized in that: In step S1, the body posture data during walking is collected using sensors on the wearable device, and a denoising algorithm is used to reduce the impact of environmental noise on the sensor data; At the same time, in order to fuse data from different sensors, a weighted average algorithm is introduced.

4. A walking posture detection method and device based on a walking posture correction wearable device as claimed in claim 1, characterized in that: The body posture data includes step length, step frequency, joint angles and muscle activity information during walking.

5. A walking posture detection method and device based on a walking posture correction wearable device as claimed in claim 4, characterized in that: In step S2, the collected body posture data is analyzed and processed, and a machine learning classification algorithm is introduced to identify abnormal walking posture features.

6. A walking posture detection method and device based on a walking posture correction wearable device as claimed in claim 1, characterized in that: The walking posture correction instruction is output to the user through a vibration motor, display screen or audio module on the wearable device.

7. A walking posture detection method and device based on a walking posture correction wearable device as claimed in claim 6, characterized in that: In step S3, a genetic algorithm is introduced to optimize the generation strategy of correction instructions; At the same time, an adaptive control algorithm is introduced to dynamically adjust the parameters of the correction instructions according to the user's real-time feedback and walking status.

8. A walking posture detection device based on a walking posture correction wearable device, characterized in that: A walking posture detection method based on a walking posture correction wearable device according to any one of claims 1 to 7 comprises: The data acquisition module is a sensor worn on a specific part of the user's body, which is used to collect movement data of various parts of the user's body during walking; A data processing module is used to receive the motion data collected by the sensor and pre-process it, including denoising, filtering and standardization; The walking posture analysis module is used to extract the user's walking posture characteristics based on the preprocessed motion data, including step length, step frequency, joint angle and swing amplitude; A correction suggestion generation module is used to generate personalized walking posture correction suggestions based on walking posture characteristics and compare them with a preset standard walking posture model; The output module is used to display the correction suggestions to the user in a visual form, or to remind the user to adjust his walking posture in the form of feedback such as vibration and sound.

9. A processor, characterized in that: The device is configured to execute a walking posture detection method based on a walking posture correction wearable device according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, a walking posture detection method based on a walking posture correction wearable device according to any one of claims 1 to 7 is implemented.

Images