Intelligent gait analysis and posture correction optimization method and system

Abstract

The present invention relates to the technical field of gait and posture correction, and discloses an intelligent gait analysis and posture correction optimization method and system, which collects user gait and posture data through sensors, ensures the accuracy of the data and realizes diverse gait and posture recognition; processes and analyzes the collected data, identifies the user's gait pattern and gait abnormality information, and alarms the abnormal gait to adapt to the performance improvement of the deep learning model; formulates a posture correction optimization plan based on the analysis results to improve posture and gait problems; implements the posture correction optimization plan, monitors the user's gait and posture changes in real time, and adjusts according to the real-time data, so as to facilitate continuous updating and optimization of the posture correction plan; and continuously optimizes the posture correction plan based on the monitoring results and feedback information.

Description

Technical Field

[0001] The present invention relates to the technical field of gait posture correction, and in particular to an intelligent gait analysis and posture correction optimization method and system. Background Art

[0002] With the advancement of sensor technology, the accuracy and reliability of gait and posture data collection have been improved, providing a non-invasive posture correction method that can help users reduce the risk of sports injuries, improve exercise efficiency and comfort, and can be applied to rehabilitation medicine, sports training and other fields. However, most of them have not considered the issues of diverse gait posture recognition and the real-time and accuracy of data.

[0003] For example, the patent with publication number CN105250066A discloses a method for correcting the plantar of the human body based on the change of the center of gravity of gait, a corrective shoe and a corrective insole, the method comprising the following steps: measuring the time period from the heel touching the ground to the big toe leaving the ground when the human body is moving and the center of gravity data of the plantar during this period; dividing the period into multiple sub-periods as the landing time of different parts of the plantar, and calculating the difference integral of the center of gravity data of the plantar and the plantar midline in each sub-period; when it is judged that the difference integral exceeds the preset threshold range, increasing the pressure on the corresponding part of the plantar during human movement, so that the corresponding part of the plantar is evenly stressed. By adjusting the force on the corresponding part of the plantar, the correction of excessive force is achieved to prevent the deterioration of the excessive force part, and at the same time changing the distribution range of the force on the entire plantar, so that the force on the entire plantar is restored to the normal range, so as to achieve the purpose of protecting the plantar and lower limbs.

[0004] For example, a Chinese patent with authorization announcement number CN110338951B discloses a gait correction pad for teenagers and a correction method, including: a correction pad, a plurality of pressure sensors arranged in the interlayer of the correction pad, and a data collector electrically connected to the pressure sensors; the pressure sensor can detect the pressure at each point of the correction pad, and the detected pressure is collected by the data collector, and a display light is electrically connected to the top of the pressure sensor; the correction pad is provided with at least one light strip along the center line direction; when the pressure sensor is subjected to pressure, the display light lights up, the sole of the foot leaves the correction pad, and the brightness of the display light is temporarily retained after lighting up.

[0005] The above patents have the problem raised by the background technology: they do not consider the problem of diverse gait posture recognition and the real-time and accuracy of data. To solve this problem, the present invention proposes an intelligent gait analysis and posture correction optimization method and system. Summary of the invention

[0006] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0007] In view of the above-mentioned problems existing in the existing intelligent gait analysis and posture correction optimization method and system, the present invention is proposed.

[0008] Therefore, the object of the present invention is to provide an intelligent gait analysis and posture correction optimization method and system.

[0009] In order to solve the above technical problems, the present invention provides an intelligent gait analysis and posture correction optimization method: collecting user gait and posture data through sensors;

[0010] Process and analyze the collected data to identify the user's gait pattern and gait abnormality information;

[0011] Develop an optimization plan for posture correction based on the analysis results;

[0012] Implement posture correction optimization solutions, monitor the user's gait and posture changes in real time, and make adjustments based on real-time data;

[0013] Based on the monitoring results and feedback information, the posture correction plan is continuously optimized.

[0014] As a preferred solution of the intelligent gait analysis and posture correction optimization method described in the present invention, the sensor includes an inertial sensor, a visual sensor, a pressure sensor and a sound sensor;

[0015] Inertial sensors are used to measure the user’s acceleration;

[0016] Visual sensors are used to extract user posture information;

[0017] The pressure sensor is used to detect the user's footsteps landing;

[0018] Sound sensors are used to capture the user's footsteps and breathing sounds.

[0019] As a preferred solution of the intelligent gait analysis and posture correction optimization method described in the present invention, the data collected by the sensor is calibrated, and the function expression of the data calibration is as follows:

[0020] y=merge(y i ,y v ,y p ,y s );

[0021] In the formula, y represents the data after overall calibration, merge(·) means merging the data in brackets, and y i Represents the data after inertial sensor calibration, y v Represents the data after visual sensor calibration, y p Represents the data after the pressure sensor is calibrated, y s Indicates the data after the sound sensor is calibrated;

[0022] The function expression of each sensor data calibration is as follows:

[0023] y i =branch i (x i );

[0024] y v =branch v (x v );

[0025] y p =branch p (x p );

[0026] y s =branch s (x s );

[0027] In the formula, y i Represents the data after inertial sensor calibration, y v Represents the data after visual sensor calibration, y p Represents the data after the pressure sensor is calibrated, y s Represents the data after the sound sensor is calibrated, branch i (·) represents the branch network for calibrating and processing inertial sensor data. v (·) represents the branch network that calibrates and processes the visual sensor data. p (·) represents the branch network for calibrating and processing pressure sensor data. s (·) represents the branch network for calibrating and processing sound sensor data, x i Represents inertial sensor data, x v Represents visual sensor data, x p Represents the pressure sensor data, x s Represents sound sensor data.

[0028] As a preferred solution of the intelligent gait analysis and posture correction optimization method described in the present invention, the collected data is processed and analyzed, and the function expression for identifying gait abnormality is as follows:

[0029] S=sig(w o ×MaxPool(F(y))+b o );

[0030] Where S represents the score of gait abnormality, sig(·) represents the activation function, which is used to map the score of gait abnormality to the range of (0, 1), and w o represents the weight matrix of the fully connected layer, MaxPool(·) represents the maximum pooling operation, F(·) represents the feature representation of the collected data after the convolution layer, y represents the overall calibrated data, and b o Represents the bias term of the fully connected layer.

[0031] As a preferred solution of the intelligent gait analysis and posture correction optimization method described in the present invention, the process of formulating the posture correction optimization solution is as follows:

[0032] S31, analyzing the extracted key footstep positions and gait rhythm, including the user's joint angles, muscle activity, step frequency, and stride length;

[0033] S32, evaluating the user's posture based on the analysis result;

[0034] S33. Develop a plan to adjust gait and improve posture based on the results of the posture assessment;

[0035] S34. Develop a corresponding training plan based on the plan to adjust gait and improve posture;

[0036] S35. Use virtual technology to guide users to implement training plans and provide real-time feedback;

[0037] S36. Regularly assess the user's posture and gait to monitor improvements and adjust the training plan in a timely manner.

[0038] As a preferred solution of the intelligent gait analysis and posture correction optimization method described in the present invention, the function expression for real-time monitoring of the user's gait and posture changes and feedback is as follows:

[0039] t = f(y, F(y), e);

[0040] Where t represents the feedback information generated by real-time monitoring, f(·) represents the calculation and learning of the multi-layer neurons in the brackets, y represents the overall calibrated data, F(y) represents the feature representation of the overall calibrated data after the convolution layer, and e represents the environmental factors.

[0041] As a preferred solution of the intelligent gait analysis and posture correction optimization method described in the present invention, the rules for optimizing the posture correction solution are as follows:

[0042] Evaluate the feedback information generated by real-time monitoring and update the posture correction plan based on the feedback evaluation results;

[0043] If the feedback information is valid, that is, the user responds positively to it and posture and gait improve, then the postural correction program is effective;

[0044] If the feedback information is invalid, that is, the user fails to improve posture and gait, the posture correction program needs to be updated.

[0045] An intelligent gait analysis and posture correction optimization system, comprising: a data acquisition module, a data processing module, a correction optimization module, a real-time monitoring module and a feedback optimization module;

[0046] The data acquisition module is used to collect the user's gait and posture data through sensors;

[0047] The data processing module is used to process and analyze the collected data and identify the user's gait pattern and gait abnormality information;

[0048] The correction optimization module is used to formulate posture correction optimization plans based on the analysis results;

[0049] The real-time monitoring module is used to implement posture correction optimization solutions, monitor the user's gait and posture changes in real time, and make adjustments based on real-time data;

[0050] The feedback optimization module is used to continuously optimize the posture correction plan based on the monitoring results and feedback information.

[0051] A computer device includes a memory for storing instructions and a processor for executing the instructions, so that the device implements an intelligent gait analysis and posture correction optimization method.

[0052] A computer-readable storage medium stores a computer program, which, when executed, implements an intelligent gait analysis and posture correction optimization method.

[0053] The beneficial effects of the present invention are as follows: the present invention collects the data of the user's gait and posture through sensors, thereby ensuring the accuracy of the data and realizing the recognition of diverse gait postures; processes and analyzes the collected data, identifies the user's gait pattern and gait abnormality information, and issues an alarm for abnormal gait to adapt to the performance improvement of the deep learning model; formulates a posture correction optimization plan based on the analysis results to improve posture and gait problems; implements the posture correction optimization plan to monitor the user's gait and posture changes in real time, and adjusts according to the real-time data to facilitate continuous updating and optimization of the posture correction plan; continuously optimizes the posture correction plan based on the monitoring results and feedback information. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0055] Figure 1 A method flow chart of an intelligent gait analysis and posture correction optimization method of the present invention;

[0056] Figure 2 This is a system structure diagram of an intelligent gait analysis and posture correction optimization system of the present invention. DETAILED DESCRIPTION

[0057] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0058] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention can also be implemented in other ways different from those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0059] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0060] Example 1

[0061] In this embodiment, a method flow chart of an intelligent gait analysis and posture correction optimization method is provided. Figure 1 As shown, an intelligent gait analysis and posture correction optimization method includes:

[0062] S1. Collect user gait and posture data through sensors.

[0063] Sensors include inertial sensors, visual sensors, pressure sensors, and sound sensors;

[0064] Inertial sensors are used to measure the user’s acceleration;

[0065] Visual sensors are used to extract user posture information;

[0066] The pressure sensor is used to detect the user's footsteps landing;

[0067] Sound sensors are used to capture the user's footsteps and breathing sounds.

[0068] The data collected by the sensor is calibrated. The function expression of data calibration is as follows:

[0069] y=merge(y i ,y v ,y p ,y s );

[0070] In the formula, y represents the data after overall calibration, merge(·) means merging the data in brackets, and y i Represents the data after inertial sensor calibration, y v Represents the data after visual sensor calibration, y p Represents the data after the pressure sensor is calibrated, y s Indicates the data after the sound sensor is calibrated.

[0071] The function expression of each sensor data calibration is as follows:

[0072] y i =branch i (x i );

[0073] y v =branch v (x v );

[0074] y p =branch p (x p );

[0075] y s =branch s (x s );

[0076] In the formula, y i Represents the data after inertial sensor calibration, y v Represents the data after visual sensor calibration, y p Represents the data after the pressure sensor is calibrated, y s Represents the data after the sound sensor is calibrated, branch i (·) represents the branch network for calibrating and processing inertial sensor data. v (·) represents the branch network that calibrates and processes the visual sensor data. p (·) represents the branch network for calibrating and processing pressure sensor data.s (·) represents the branch network for calibrating and processing sound sensor data, x i Represents inertial sensor data, x v Represents visual sensor data, x p Represents pressure sensor data, x s Represents sound sensor data.

[0077] It should be explained that a multi-branch neural network is used to process sensor data. Each branch is responsible for processing the data of one sensor. Each branch includes multiple hidden layers and activation functions, and an output layer is used to generate calibrated data. merge(·) means connecting the calibrated data of four sensors into an overall calibrated data.

[0078] In specific applications, the inertial sensor here is an accelerometer, which can capture the acceleration changes in the user's gait movement and help identify the gait characteristics and gait cycle; the visual sensor here is a camera, which can extract posture information, such as joint angles and body postures, to identify the user's gait and movements; the pressure sensor here is a ground pressure sensor, which is placed on the ground to detect the user's footsteps and foot pressure distribution, and help identify gait characteristics, such as step frequency and stride; the sound sensor can capture the sound signals generated in the gait movement, such as footsteps and breathing sounds, which can be used as auxiliary information for gait recognition; through the combination of the above multiple sensors, the user's gait data and posture information can be fully perceived, thereby achieving accurate gait recognition and posture monitoring;

[0079] The data collected by the four sensors are calibrated and a multi-branch neural network is used to process the sensor data. Each branch includes multiple hidden layers, activation functions and output layers to convert the sensor data into a calibrated output. The calibrated data of the four sensors are then merged into an overall calibrated data.

[0080] S2. Process and analyze the collected data to identify the user's gait pattern and gait abnormality information.

[0081] The collected data is processed and analyzed, and the function expression for identifying gait abnormalities is as follows:

[0082] S=sig(w o ×MaxPool(F(y))+b o );

[0083] Where S represents the score of gait abnormality, sig(·) represents the activation function, which is used to map the score of gait abnormality to the range of (0, 1), and w orepresents the weight matrix of the fully connected layer, MaxPool(·) represents the maximum pooling operation, F(·) represents the feature representation of the collected data after the convolution layer, y represents the overall calibrated data, and b o Represents the bias term of the fully connected layer.

[0084] It should be explained that MaxPool(·) represents the maximum pooling operation, which is used to downsample in the spatial dimension to capture the global characteristics of the collected data; o and b o It is the weight matrix and bias term of the fully connected layer used to calculate the final gait abnormality score.

[0085] In specific applications, feature extraction is performed on the calibrated data, and the gait cycle is extracted from the inertial sensor data, the key point position of the footstep is extracted from the visual sensor data, the gait rhythm is extracted from the pressure sensor data, and the gait rhythm is extracted from the sound sensor data. The features are input into the deep learning model for training, and the gait pattern and gait abnormality are output. Here, the user's current gait pattern is judged based on the output of the deep learning model, such as walking, running, and standing still;

[0086] For gait abnormality information, the features of the collected data are effectively extracted by combining convolution operations with global pooling operations, and the gait abnormality score is calculated through the fully connected layer, and an abnormality score threshold is set. The abnormality score threshold needs to be adjusted according to the actual scenario and needs, including but not limited to the data distribution of normal gait and abnormal gait, the sensitivity and tolerance to gait abnormalities, and real-time environmental interference factors. When the abnormality score threshold is exceeded, an alarm is triggered and corresponding measures are taken. The abnormality score threshold needs to be updated regularly to adapt to changes in data distribution and performance improvements of deep learning models.

[0087] S3. Develop a posture correction optimization plan based on the analysis results.

[0088] The process of developing a posture correction optimization plan is as follows:

[0089] S31, analyzing the extracted key footstep positions and gait rhythm, including the user's joint angles, muscle activity, step frequency, and stride length;

[0090] S32, evaluating the user's posture based on the analysis result;

[0091] S33. Develop a plan to adjust gait and improve posture based on the results of the posture assessment;

[0092] S34. Develop a corresponding training plan based on the plan to adjust gait and improve posture;

[0093] S35. Use virtual technology to guide users to implement training plans and provide real-time feedback;

[0094] S36. Regularly assess the user's posture and gait to monitor improvements and adjust the training plan in a timely manner.

[0095] In specific applications, the extracted key footstep positions and gait rhythm are first analyzed, including the user's joint angles, muscle activity, step frequency and stride. By analyzing the features, existing problems and room for improvement can be found. Secondly, based on the analysis results, the user's posture is evaluated, focusing on whether there are bad gait or posture habits, as well as risk factors that may lead to injuries. Then, according to the posture evaluation results, a plan for adjusting gait and improving posture is formulated. If the user has the problem of inward collapse of the knees, the gait can be improved by increasing hip stability and strengthening leg muscles. At the same time, the entire posture can be made more effective by adjusting the body's inclination angle, the amplitude of arm swing and the change of foot landing position. Then, according to the plan for adjusting gait and improving posture, a corresponding training plan is formulated, including strength training and flexibility training for specific muscle groups. Then, virtual technology is used to guide users to implement the training plan and provide real-time feedback. Users need to gradually adjust their gait and posture in practice. Finally, the user's posture and gait are evaluated regularly to monitor the improvement and adjust the training plan in time. This can be achieved by collecting data again and analyzing it.

[0096] S4. Implement posture correction optimization program, monitor the user's gait and posture changes in real time, and make adjustments based on real-time data.

[0097] The function expression for real-time monitoring of the user's gait and posture changes and feedback is as follows:

[0098] t = f(y, F(y), e);

[0099] Where t represents the feedback information generated by real-time monitoring, f(·) represents the calculation and learning of the multi-layer neurons in the brackets, y represents the overall calibrated data, F(y) represents the feature representation of the overall calibrated data after the convolution layer, and e represents the environmental factors.

[0100] In specific applications, the data collected by the sensor is calibrated and the corresponding features are extracted as the unique features of the user, including the key positions of the user's footsteps and the gait rhythm. At the same time, the impact of environmental factors on the sensor is considered. Such comprehensive consideration can make the feedback information generated by real-time monitoring more personalized and targeted. The function f(·) is a deep neural network that accepts calibration data, features and environmental factors as input, and outputs feedback information generated by real-time monitoring, which can be various forms of feedback, including sound prompts and vibration feedback.

[0101] S5. Based on the monitoring results and feedback information, continuously optimize the posture correction plan to achieve better correction results.

[0102] The rules for optimizing posture correction solutions are as follows:

[0103] Evaluate the feedback information generated by real-time monitoring and update the posture correction plan based on the feedback evaluation results;

[0104] If the feedback information is valid, that is, the user responds positively to it and posture and gait improve, then the postural correction program is effective;

[0105] If the feedback information is invalid, that is, the user fails to improve posture and gait, the posture correction program needs to be updated.

[0106] In specific applications, feedback information is generated based on real-time monitoring, and user feedback is collected. The generated feedback information is monitored in real time for evaluation. The effectiveness of the feedback information and the user's feedback can be evaluated by monitoring the user's posture adjustment and the degree of improvement in posture and gait after feedback. The posture correction plan is updated based on the feedback evaluation results. If the feedback information is valid, that is, the user responds positively to it and the posture and gait are improved, then the posture correction plan is effective. If the feedback information is invalid, that is, the user fails to improve his posture and gait, the posture correction plan needs to be updated. Continuous monitoring and feedback are carried out to dynamically adjust the posture correction plan. According to the user's feedback, the posture correction plan is continuously updated and optimized, and the iterative cycle is continuously carried out to continuously optimize the posture correction plan until the expected correction effect is achieved.

[0107] Example 2

[0108] In this embodiment, a system structure diagram of an intelligent gait analysis and posture correction optimization system is provided, such as Figure 2 As shown, an intelligent gait analysis and posture correction optimization system includes a data acquisition module, a data processing module, a correction optimization module, a real-time monitoring module and a feedback optimization module.

[0109] The data acquisition module is used to collect the user's gait and posture data through sensors;

[0110] The data processing module is used to process and analyze the collected data and identify the user's gait pattern and gait abnormality information;

[0111] The correction optimization module is used to formulate posture correction optimization plans based on the analysis results;

[0112] The real-time monitoring module is used to implement posture correction optimization solutions, monitor the user's gait and posture changes in real time, and make adjustments based on real-time data;

[0113] The feedback optimization module is used to continuously optimize the posture correction scheme based on the monitoring results and feedback information to achieve better correction effects;

[0114] The specific implementation methods of the above modules are the same as the aforementioned intelligent gait analysis and posture correction optimization method, which will not be repeated here.

[0115] Example 3

[0116] In this embodiment, a computer device is provided, including a memory and a processor, the memory is used to store instructions, and the processor is used to execute the instructions, so that the computer device executes the steps of implementing the above-mentioned intelligent gait analysis and posture correction optimization method.

[0117] Example 4

[0118] In this embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed, the steps of the above-mentioned intelligent gait analysis and posture correction optimization method are implemented.

[0119] The computer-readable storage medium includes: a U disk, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk or an optical disk, and other media for storing program codes.

[0120] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should be included in the scope of the claims of the present invention.

Claims

1. An intelligent gait analysis and posture correction optimization method, characterized in that: include, Collect data about the user’s gait and posture through sensors; The data collected by the sensor is calibrated. The function expression of data calibration is as follows: and merge(and i ,and v ,and p ,and s ); In the formula, y represents the data after overall calibration, merge(·) means merging the data in brackets, and y i Represents the data after inertial sensor calibration, y v Represents the data after visual sensor calibration, y p Represents the data after the pressure sensor is calibrated, y s Indicates the data after the sound sensor is calibrated; The function expression of each sensor data calibration is as follows: y i =branch i (x i ); y v =branch v (x v ); y p =branch p (x p ); y s =branch s (x s ); In the formula, y i Represents the data after inertial sensor calibration, y v Represents the data after visual sensor calibration, y p Represents the data after the pressure sensor is calibrated, y s Represents the data after the sound sensor is calibrated, branch i (·) represents the branch network for calibrating and processing inertial sensor data. v (·) represents the branch network that calibrates and processes the visual sensor data. p (·) represents the branch network for calibrating and processing pressure sensor data. s (·) represents the branch network for calibrating and processing sound sensor data, x i Represents inertial sensor data, x v Represents visual sensor data, x p Represents pressure sensor data, x s Represents sound sensor data; Process and analyze the collected data to identify the user's gait pattern and gait abnormality information; The collected data is processed and analyzed, and the function expression for identifying gait abnormalities is as follows: S=sig(w o ×MaxPool(F(y))+b o ); Where S represents the score of gait abnormality, sig(·) represents the activation function, which is used to map the score of gait abnormality to the range of (0,1), and w o represents the weight matrix of the fully connected layer, MaxPool(·) represents the maximum pooling operation, F(·) represents the feature representation of the collected data after the convolution layer, y represents the overall calibrated data, and b o represents the bias term of the fully connected layer; Develop an optimal posture correction plan based on the analysis results; Implement posture correction optimization solutions, monitor the user's gait and posture changes in real time, and make adjustments based on real-time data; The function expression for real-time monitoring of the user's gait and posture changes and feedback is as follows: t=f(y,F(y),e); Where t represents the feedback information generated by real-time monitoring, f(·) represents the calculation and learning of the multi-layer neurons in the brackets, y represents the overall calibrated data, F(y) represents the feature representation of the overall calibrated data after the convolution layer, and e represents the environmental factors; Based on the monitoring results and feedback information, the posture correction plan is continuously optimized.

2. The intelligent gait analysis and posture correction optimization method according to claim 1, characterized in that: Sensors include inertial sensors, visual sensors, pressure sensors, and sound sensors; Inertial sensors are used to measure the user’s acceleration; Visual sensors are used to extract user posture information; The pressure sensor is used to detect the user's footsteps landing; Sound sensors are used to capture the user's footsteps and breathing sounds.

3. The intelligent gait analysis and posture correction optimization method according to claim 2, characterized in that: The process of developing a posture correction optimization plan is as follows: S31, analyzing the extracted key footstep positions and gait rhythm, including the user's joint angles, muscle activity, step frequency, and stride length; S32, evaluating the user's posture based on the analysis result; S33. Develop a plan to adjust gait and improve posture based on the results of the posture assessment; S34. Develop a corresponding training plan based on the plan to adjust gait and improve posture; S35. Use virtual technology to guide users to implement training plans and provide real-time feedback; S36. Regularly assess the user's posture and gait to monitor improvements and adjust the training plan in a timely manner.

4. The intelligent gait analysis and posture correction optimization method according to claim 3, characterized in that: The rules for optimizing posture correction solutions are as follows: Evaluate the feedback information generated by real-time monitoring and update the posture correction plan based on the feedback evaluation results; If the feedback information is valid, that is, the user responds positively to it and posture and gait improve, then the postural correction program is effective; If the feedback information is invalid, that is, the user fails to improve posture and gait, the posture correction program needs to be updated.

5. An intelligent gait analysis and posture correction optimization system, used to implement an intelligent gait analysis and posture correction optimization method according to any one of claims 1 to 4, characterized in that: include, Data acquisition module, data processing module, correction optimization module, real-time monitoring module and feedback optimization module; The data acquisition module is used to collect the user's gait and posture data through sensors; The data processing module is used to process and analyze the collected data and identify the user's gait pattern and gait abnormality information; The correction optimization module is used to formulate posture correction optimization plans based on the analysis results; The real-time monitoring module is used to implement posture correction optimization solutions, monitor the user's gait and posture changes in real time, and make adjustments based on real-time data; The feedback optimization module is used to continuously optimize the posture correction plan based on the monitoring results and feedback information.

6. A computer device, characterized in that: include, A memory for storing instructions; The processor is used to execute the instruction so that the device implements an intelligent gait analysis and posture correction optimization method as described in any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed, an intelligent gait analysis and posture correction optimization method as described in any one of claims 1 to 4 is implemented.

Images