A gait correction method and related device based on biomechanical characteristics

Abstract

The present invention provides a gait correction method and related devices based on biomechanical characteristics, which are applied to the field of data processing technology. In this application, the server obtains the real-time body state information of the subject and obtains dynamic three-dimensional motion data and ground reaction force data corresponding to the dynamic three-dimensional motion data based on the real-time body state information, processes the ground reaction force data to generate the support phase within the gait cycle of the subject, processes the dynamic three-dimensional motion data to generate gait three-dimensional kinematic characteristic parameters, generates support phase ankle dorsiflexion peak angle data based on the gait three-dimensional kinematic characteristic parameters and the ground reaction force data, processes the support phase ankle dorsiflexion peak angle data to generate the monitoring result of the subject and the identification information corresponding to the monitoring result; if the monitoring result is in an abnormal state, obtain the correction plan corresponding to the identification information, process the subject to generate a posture correction result.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly relates to a gait correction method based on biomechanical characteristics and related devices. Background Art

[0002] The range of motion of ankle dorsiflexion is defined as the maximum angle at which the foot actively or passively bends towards the tibia. Sufficient ankle dorsiflexion range of motion is necessary to meet daily functional activities, such as walking, landing, going up and down stairs, etc. Limited ankle dorsiflexion during exercise is one of the risk factors for lower limb injuries. Limited ankle dorsiflexion during walking will cause compensatory movements in other joints, change the lower limb movement pattern, generate excessive pressure, and have an adverse impact on the lower limb biomechanical movement, thus leading to lower limb injuries, such as plantar fasciitis, Achilles tendinitis, and knee injuries caused by changes in the knee joint alignment. At the same time, a decrease in the ankle dorsiflexion angle will lead to an increase in the foot progression angle, an earlier heel-off time, and a shorter step length during the gait cycle. From the perspective of the motion chain coupling mode, the movement of the ankle joint may affect the spatio-temporal and kinematic parameters of the knee, hip, and pelvis. It can be seen that limited ankle dorsiflexion may cause a series of functional disorders. Effectively and accurately determining whether a patient's ankle dorsiflexion is limited and analyzing the lower limb biomechanical characteristics of the limited individuals are necessary for precise treatment of patients and correction of the abnormal biomechanical movements of the lower limbs during the patient's exercise.

[0003] Currently, the conventional methods for measuring the range of motion of the ankle joint include measuring by passively flexing the ankle joint with a goniometer or inclinometer in the non-weight-bearing position (supine or prone position) or measuring in the weight-bearing position in the lunge posture. However, limited ankle dorsiflexion mainly affects people's daily functional activities, changes the lower limb biomechanics, and affects people's motor ability. The non-weight-bearing measurement method cannot well evaluate the ankle joint function because it is evaluated in an open-chain posture, and the reliability of the non-weight-bearing measurement is also questioned because it highly depends on the experience of clinical measurers. The weight-bearing measurement can better represent the function of the lower limbs during activities than the non-weight-bearing measurement, but it still cannot accurately confirm whether an individual has a proper range of motion of the ankle joint during walking or other functional movements. Moreover, regardless of whether it is non-weight-bearing measurement or weight-bearing measurement, due to different testers and different testing methods, the measurement results will also deviate, thus affecting clinical diagnosis. Limited ankle dorsiflexion will lead to limited daily activities, decreased motor ability, and functional disorders in people. Accurately evaluating whether ankle dorsiflexion is limited and further correcting the abnormal biomechanics of the lower limbs during exercise accordingly has very important clinical value.

[0004] It should be noted that the information disclosed in the above background art section is only used to strengthen the understanding of the background of the present disclosure, and thus may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0005] The purpose of this application is to provide a gait correction method and related equipment based on biomechanical characteristics, which can at least overcome the problems existing in the prior art to a certain extent. By obtaining the kinematic characteristic parameters of the lower limb joints and the ground reaction force parameters of the subject, and then generating the change of the ankle dorsiflexion angle during the gait support phase in the walking test of the subject, according to the peak angle of ankle dorsiflexion during the support phase, the subjects are divided into an ankle dorsiflexion limitation group and an ankle dorsiflexion non-limitation group, so as to judge whether the patient's ankle dorsiflexion is limited, and achieve the purpose of correcting the abnormal biomechanical movement of the lower limbs during the patient's movement.

[0006] Other features and advantages of this application will become apparent through the following detailed description, or be learned in part through the practice of the present invention.

[0007] According to one aspect of this application, a gait correction method based on biomechanical characteristics is provided, including: obtaining the real-time body state information of the subject; obtaining dynamic three-dimensional motion data and ground reaction force data corresponding to the dynamic three-dimensional motion data based on the real-time body state information, wherein the dynamic three-dimensional motion data includes the data generated when the subject is in a static state or walking; processing the ground reaction force data based on a first preset rule to generate the support phase within the gait cycle of the subject; processing the dynamic three-dimensional motion data based on a second preset rule to generate gait three-dimensional kinematic characteristic parameters; generating peak ankle dorsiflexion angle data during the support phase based on the gait three-dimensional kinematic characteristic parameters and the ground reaction force data; processing the peak ankle dorsiflexion angle data during the support phase based on a third preset rule to generate the monitoring result of the subject and the identification information corresponding to the monitoring result, wherein the identification information is used to characterize the abnormal type of the monitoring result; if the monitoring result is in an abnormal state, obtaining a correction plan corresponding to the identification information; processing the subject based on the correction plan to generate a posture correction result.

[0008] In an embodiment of this application, the obtaining of the real-time body state information of the subject includes: obtaining the limb data and real-time environment data of the subject; processing the limb data and the real-time environment data based on an early warning model to generate early warning information; generating the real-time body state information of the subject based on the early warning information.

[0009] In an embodiment of this application, the obtaining of the real-time body state information of the subject further includes: obtaining a body state prediction model; processing the real-time heart rate information or body posture information of the subject based on the body state prediction model to generate the health state of the subject; comparing the health state of the subject with the preset human body state information to generate the corresponding health level information of the subject.

[0010] In one embodiment of the present application, obtaining the dynamic three-dimensional motion data and the ground reaction force data corresponding to the dynamic three-dimensional motion data based on the real-time body state information includes: annotating the dynamic three-dimensional motion data based on the health level information corresponding to the subject to generate annotation information, where the annotation information is used to characterize whether the dynamic three-dimensional motion data is currently in an abnormal state.

[0011] In one embodiment of the present application, if the monitoring result is in an abnormal state, obtaining the correction plan corresponding to the identification information includes: processing the identification information, and if the identification information characterizes that the dynamic three-dimensional motion data is currently in an abnormal state, obtaining the correction plan corresponding to the identification information from a preset correction model.

[0012] In one embodiment of the present application, processing the ground reaction force data based on a first preset rule to generate the support phase within the gait cycle of the subject includes: obtaining the division criteria for the gait cycle; obtaining the ground forces in different directions received by the subject's foot during the walking test, where the ground forces include the vertical reaction force, the anteroposterior reaction force, and the mediolateral reaction force; using the vertical reaction force, the anteroposterior reaction force, and the mediolateral reaction force as the ground reaction force data; and processing the reaction force data based on the division criteria to generate the joint torques of each lower limb joint.

[0013] In one embodiment of the present application, if the monitoring result is in an abnormal state, obtaining the correction plan corresponding to the identification information further includes: obtaining the digital human image of the subject; obtaining the abnormal state information of the subject according to the identification information; obtaining the normal state information corresponding to the abnormal state information, where the normal state information includes preset gait posture data; obtaining the image difference between the digital human image in the normal state information and the digital human image in the abnormal state information; and generating a corresponding posture adjustment plan based on the image difference, where the posture adjustment plan is used as the correction plan.

[0014] Another aspect of the present application is a gait correction device based on biomechanical characteristics, which is characterized by including: an acquisition module for acquiring real-time body state information of a subject; a processing module for acquiring dynamic three-dimensional motion data and ground reaction force data corresponding to the dynamic three-dimensional motion data based on the real-time body state information; processing the ground reaction force data based on a first preset rule to generate a support phase within the gait cycle of the subject; processing the dynamic three-dimensional motion data based on a second preset rule to generate gait three-dimensional kinematic characteristic parameters; generating support phase ankle dorsiflexion peak angle data based on the gait three-dimensional kinematic characteristic parameters and the ground reaction force data; processing the support phase ankle dorsiflexion peak angle data based on a third preset rule to generate a monitoring result of the subject and identification information corresponding to the monitoring result; if the monitoring result is in an abnormal state, acquiring a correction plan corresponding to the identification information; and processing the subject based on the correction plan to generate a posture correction result.

[0015] According to still another aspect of the present application, an electronic device is provided, which is characterized by including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the above-mentioned gait correction method based on biomechanical characteristics by executing the executable instructions.

[0016] According to yet another aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored, and the computer program realizes the above-mentioned gait correction method based on biomechanical characteristics when being executed by a processor.

[0017] According to yet another aspect of the present application, a computer program product is provided, including a computer program, which is characterized in that the computer program realizes the above-mentioned gait correction method based on biomechanical characteristics when being executed by a processor.

[0018] A gait correction method based on biomechanical characteristics provided by this application obtains the real-time body state information of the subject by the server; obtains dynamic three-dimensional motion data and ground reaction force data corresponding to the dynamic three-dimensional motion data based on the real-time body state information, wherein the dynamic three-dimensional motion data includes data generated when the subject is in a static state or walking; processes the ground reaction force data based on a first preset rule to generate the support phase within the gait cycle of the subject; processes the dynamic three-dimensional motion data based on a second preset rule to generate gait three-dimensional kinematic characteristic parameters; generates support phase ankle dorsiflexion peak angle data based on the gait three-dimensional kinematic characteristic parameters and the ground reaction force data; processes the support phase ankle dorsiflexion peak angle data based on a third preset rule to generate the monitoring result of the subject and the identification information corresponding to the monitoring result, wherein the identification information is used to characterize the abnormal type of the monitoring result; if the monitoring result is in an abnormal state, obtains the correction plan corresponding to the identification information; processes the subject based on the correction plan to generate a posture correction result. By obtaining the kinematic characteristic parameters of the lower limb joints and the ground reaction force parameters of the subject, and then generating the change of the ankle dorsiflexion angle during the gait support phase in the walking test of the subject, according to the peak angle of ankle dorsiflexion in the support phase, the subject is divided into an ankle dorsiflexion restricted group and an ankle dorsiflexion non-restricted group, so as to judge whether the ankle dorsiflexion of the patient is restricted, and achieve the purpose of correcting the abnormal biomechanical movement of the lower limb during the patient's movement.

[0019] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit this disclosure. Brief Description of the Drawings

[0020] Figure 1 The flowchart showing a gait correction method based on biomechanical characteristics provided by an embodiment of this application;

[0021] Figure 2 The structural schematic diagram showing a gait correction device based on biomechanical characteristics provided by an embodiment of this application;

[0022] Figure 3 The structural schematic diagram showing an electronic device provided by an embodiment of this application;

[0023] Figure 4 The schematic diagram showing a storage medium provided by an embodiment of this application;

[0024] Figure 5 The schematic diagram showing five characteristic moments of the support phase provided by an embodiment of this application;

[0025] Figure 6Shows the schematic diagram of the changes in the movement angles of each joint of the lower limb, the coronal plane, sagittal plane and horizontal plane of the pelvis of the subjects with normal ankle dorsiflexion and the subjects with limited ankle dorsiflexion provided by an embodiment of the present application during the gait support phase;

[0026] Figure 7 Shows the schematic diagram of the changes in the moments of each joint of the lower limb, the coronal plane, sagittal plane and horizontal plane of the subjects with normal ankle dorsiflexion and the subjects with limited ankle dorsiflexion provided by an embodiment of the present application during the gait support phase. Detailed implementation manners

[0027] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0028] The following is combined with Figure 1 to describe the gait correction method based on biomechanical characteristics according to the exemplary embodiments of the present application. It should be noted that the following application scenarios are only shown for the convenience of understanding the spirit and principle of the present application, and the embodiments of the present application are not limited in this regard. On the contrary, the embodiments of the present application can be applied to any applicable scenario.

[0029] In one embodiment, the present application also proposes a gait correction method based on biomechanical characteristics. Figure 1 Schematically shows the flow schematic diagram of a gait correction method based on biomechanical characteristics according to an embodiment of the present application. As Figure 1 shown, this method is applied to a server and includes:

[0030] S101, obtaining the real-time body state information of the subject.

[0031] In one embodiment, the limb data and real-time environment data of the subject are obtained, and the limb data and real-time environment data are processed based on the early warning model to generate early warning information, and the real-time body state information of the subject is generated based on the early warning information. By identifying the limb data of the subject, it is judged whether the subject has trauma or physical discomfort, etc. In addition, the weather condition or road implementation condition of the current location of the subject will also be judged. If the current body posture of the subject is abnormal due to any of the above factors, the factors causing the abnormality will be screened out. For example, if there is rain in the current scenario and the subject has trauma, in order to prevent wound infection, the posture may be problematic at this time.

[0032] S102, obtaining dynamic three-dimensional motion data and ground reaction force data corresponding to the dynamic three-dimensional motion data based on the real-time body state information.

[0033] In one implementation, the dynamic three-dimensional motion data includes the data generated when the subject is static or walking. Among them, the data generated when the subject is static refers to the static data collected through three static tests where the subject stands at the center of the laboratory, with feet shoulder-width apart, both upper limbs naturally placed on both sides of the body, and maintaining the neutral position of the subtalar joint, which is used to define the coordinate system of the bone segments. The data generated during walking refers to the reflective marker points being pasted on the bony landmark points of the lower limbs of each subject, and then the subject performs a walking test at the speed that feels most comfortable to obtain the original three-dimensional coordinate data. In this embodiment, the reflective marker points are respectively pasted on the left and right lateral malleoli, medial malleoli, heels, second metatarsophalangeal joints, first metatarsophalangeal joints, fifth metatarsophalangeal joints, tibial tuberosities, medial femoral condyles, lateral femoral condyles, anterior thigh, anterior superior iliac spines, and posterior superior iliac spines. In addition, the ground reaction force data refers to the synchronous acquisition of kinetic parameters using two three-dimensional force platforms (AMTI, BP400600) at a sampling frequency of 1000 Hz to obtain the ground forces in different directions received by the subject's feet during the walking test, including the vertical reaction force, anteroposterior reaction force, and mediolateral reaction force.

[0034] In another implementation, the dynamic three-dimensional motion data is labeled based on the corresponding health level information of the subject to generate labeled information, where the labeled information is used to characterize whether the dynamic three-dimensional motion data is currently in an abnormal state. By judging whether the subject's current physical state is normal, if the body is abnormal, it is judged whether the abnormality of the dynamic three-dimensional motion data is caused by the physical state.

[0035] S103. Process the ground reaction force data based on the first preset rule to generate the support phase within the gait cycle of the subject.

[0036] In one implementation, processing the ground reaction force data means filtering the ground reaction force obtained by the three-dimensional force platform (AMTI, BP400600) through a 100HZ Butterworth filter, and determining the occurrence of heel strike and toe-off to determine the support phase of the entire gait process. In addition, the support phase is further divided into five moments, namely: first foot contact (FFC), first metatarsal contact (FMC), forefoot flat (FFF), heel off (HO), and last foot contact (LFC). The joint torques of each lower limb joint are calculated using the ground reaction force through inverse dynamics.

[0037] By obtaining the ground reaction force received by each foot of the subject during the walking test, it means filtering the ground reaction force through a 100HZ Butterworth filter to determine the occurrence of heel strike and toe-off, thereby determining the stance phase of the entire gait process. According to the division criteria of the gait cycle, the normal gait stance phase is divided into 5 moments, and the 5 divided moments are: heel contact, forefoot contact, fore-and-aft foot support, heel lift-off, and toe-off. For details, see Figure 5 . During gait, the peak ankle dorsiflexion occurs before heel lift-off. According to the division of the stance phase, the moment when the peak ankle dorsiflexion occurs can be determined. At the same time, the joint moments of each lower limb joint are calculated through inverse dynamics using the ground reaction force.

[0038] S104, Process the dynamic three-dimensional motion data based on the second preset rule to generate gait three-dimensional kinematic characteristic parameters.

[0039] In one implementation, filter the three-dimensional kinematic coordinate data through a 12HZ Butterworth filter and calculate using Visual 3D software (Cmotion, Germantown, MD) to obtain the coronal plane, sagittal plane, and horizontal plane angle data of each joint of the lower limbs of each subject. Filter and calculate the three-dimensional kinematic coordinate data to obtain the motion angle data of different motion planes of the lower limb joints of each subject.

[0040] S105, Generate peak ankle dorsiflexion angle data during the stance phase based on the gait three-dimensional kinematic characteristic parameters and the ground reaction force data.

[0041] In one implementation, through the analysis and processing of the gait three-dimensional kinematic characteristic parameters and the ground reaction force parameters, the change in the ankle dorsiflexion angle during the gait stance phase of the subject during the walking test can be determined, and the three-dimensional angle data of the lower limb bones of the subject during the gait stance phase can be obtained, including the three-dimensional angle data and time series data of the pelvis, hip joint, knee joint, and ankle joint in the sagittal plane, coronal plane, and horizontal plane.

[0042] In another implementation, three-dimensional kinematic data, ground reaction force data, and joint moments of each lower limb calculated based on the ground reaction force of 51 subjects (ankle dorsiflexion limitation group (<10°, n = 30) and non-ankle dorsiflexion limitation group (>10°, n = 21)) were collected, and the data was statistically analyzed. All statistical analyses were completed using SPSS26.0 (IBM, New York, USA). Quantitative data was first subjected to a normality test. If it conformed to a normal distribution, it was expressed as mean ± standard deviation, and a two-sample t-test was performed. If it did not conform to a normal distribution, it was expressed as median and quartiles, and a two-sample rank sum test was performed. The significance level was set at a type I error probability not greater than 0.05. For details, see Table 1.

[0043]

[0044] Table 1 shows the pelvic and lower limb biomechanical parameters corresponding to the peak moment of ankle dorsiflexion angle during the stance phase while walking.

[0045] S106. Process the stance-phase ankle dorsiflexion peak angle data based on the third preset rule to generate the monitoring result of the subject and the identification information corresponding to the monitoring result.

[0046] In one implementation, refer to Figure 6 、 7 As shown, according to the peak angle of ankle dorsiflexion during the stance phase, the subjects are divided into an ankle dorsiflexion limitation group and an ankle dorsiflexion non-limitation group. If the peak angle of ankle dorsiflexion on either side of the subject during the walking test is less than 10°, the subject is divided into the ankle dorsiflexion limitation group, and other subjects are included in the non-limitation group. In addition, corresponding identification information is set for the subjects belonging to the ankle dorsiflexion limitation group, where the identification information is used to characterize the abnormal type of the monitoring result.

[0047] S107. If the monitoring result is in an abnormal state, obtain the correction plan corresponding to the identification information.

[0048] In one implementation, process the identification information. If the identification information indicates that the current dynamic three-dimensional motion data is in an abnormal state, obtain the correction plan corresponding to the identification information from the preset correction model. By comparing the subject's dynamic three-dimensional motion data with the standard gait database, the problems existing in the current patient are obtained after the comparison. Combining the inverse kinematics principle, the recovery status of each muscle group of the subject is deduced, and some relevant analyses and rehabilitation training plans are carried out for these recovery statuses, thereby improving the subject's gait. In addition, the correction plan suitable for the subject can be customized individually by comprehensively considering the subject's occupation, age, family situation, etc.

[0049] S108. Process the subject based on the correction plan to generate a posture correction result.

[0050] In one implementation, by collecting the gait of the subject after rehabilitation and comparing it with the standard gait database, and combining the inverse kinematics principle to deduce the recovery status of each muscle group of the patient, and carrying out some relevant analyses and rehabilitation training plans for these recovery statuses, the problem of gait recovery of the subject after rehabilitation can be effectively improved, and the reduction or elimination of the sequelae of limb rehabilitation of the patient can be achieved.

[0051] In this application, the server obtains the real-time body status information of the subject, and based on the real-time body status information, obtains the dynamic three-dimensional motion data and the ground reaction force data corresponding to the dynamic three-dimensional motion data. Among them, the dynamic three-dimensional motion data includes the data generated when the subject is in a static state or walking. The ground reaction force data is processed based on the first preset rule to generate the support phase within the gait cycle of the subject. The dynamic three-dimensional motion data is processed based on the second preset rule to generate the gait three-dimensional kinematic characteristic parameters. The support phase ankle dorsiflexion peak angle data is generated based on the gait three-dimensional kinematic characteristic parameters and the ground reaction force data. The support phase ankle dorsiflexion peak angle data is processed based on the third preset rule to generate the monitoring result of the subject and the identification information corresponding to the monitoring result. Among them, the identification information is used to characterize the abnormal type of the monitoring result. If the monitoring result is in an abnormal state, the correction plan corresponding to the identification information is obtained, and the subject is processed based on the correction plan to generate the posture correction result. By obtaining the lower limb joint kinematic characteristic parameters and the ground reaction force parameters of the subject, the change of the ankle dorsiflexion angle during the gait support phase in the subject's walking test is generated. According to the support phase ankle dorsiflexion peak angle, the subject is divided into an ankle dorsiflexion restricted group and an ankle dorsiflexion non-restricted group, so as to judge whether the subject's ankle dorsiflexion is restricted, and achieve the purpose of correcting the abnormal biomechanical movement of the lower limb during the subject's movement.

[0052] Optionally, in another embodiment based on the above method of this application, the obtaining of the real-time body status information of the subject further includes:

[0053] Obtain a body status prediction model;

[0054] Process the real-time heart rate information or body posture information of the subject based on the body status prediction model to generate the health status of the subject;

[0055] Compare the health status of the subject with the preset human body status information to generate the health level information corresponding to the subject.

[0056] In one implementation, the current body status of the subject is judged based on the real-time heart rate information of the subject. For example, if the current real-time heart rate of the subject is greater than 120 beats per minute, it means that the current user is walking or in a more excited mood. If the duration of this real-time heart rate is relatively long, the degree of fatigue of the current user is judged. If the degree of fatigue is higher, the health level information of the subject will be in a dangerous state. In addition, if the subject has problems with body shape due to sitting posture, sleeping posture or bad habits, such as crossing legs for a long time, it will cause the body posture of the subject to be abnormal. Under the same walking or exercise intensity, the exercise risk of this subject will be greater than that of a subject with a normal body posture.

[0057] Optionally, in another embodiment of the method based on the present application, the processing of the ground reaction force data according to the first preset rule to generate the support phase within the gait cycle of the subject includes:

[0058] Obtain the division criteria for the gait cycle;

[0059] Obtain the ground forces in different directions received by the subject's foot during the walking test, where the ground forces include the vertical reaction force, the anteroposterior reaction force, and the mediolateral reaction force;

[0060] Use the vertical reaction force, the anteroposterior reaction force, and the mediolateral reaction force as the ground reaction force data;

[0061] Process the reaction force data based on the division criteria to generate the joint torques of each joint of the lower limb.

[0062] In one implementation, the ground reaction force obtained by a three-dimensional force platform (AMTI, BP400600) is filtered by a 100HZ Butterworth filter, and the occurrence of heel strike and toe-off is determined, thereby determining the support phase of the entire gait process. In addition, the support phase is divided into 5 moments, namely: first foot contact (FFC), first metatarsal contact (FMC), forefoot flat (FFF), heel off (HO), and last foot contact (LFC).

[0063] Optionally, in another embodiment of the method based on the present application, if the monitoring result is in an abnormal state, obtaining a correction plan corresponding to the identification information further includes:

[0064] Obtain the digital human image of the subject;

[0065] Obtain the abnormal state information of the subject according to the identification information;

[0066] Obtain the normal state information corresponding to the abnormal state information, where the normal state information includes preset gait posture data;

[0067] Obtain the image difference between the digital human image in the normal state information and the digital human image in the abnormal state information;

[0068] Generate a corresponding posture adjustment plan based on the image difference, and use the posture adjustment plan as the correction plan.

[0069] In one implementation, the posture adjustment plan includes, but is not limited to, pelvic anterior and posterior rotation training, ankle eversion training, ankle dorsiflexion training, hip abduction training, quadriceps femoris eccentric and concentric training, balance training (standing position secondary balance training / single-leg weight-bearing training), hip flexion and extension training, walking training, etc. That is, in this embodiment, targeted training of a single link or multiple links can be carried out as needed according to the actual gait abnormality of the patient. The present invention judges whether the ankle dorsiflexion of the subject is limited according to the peak value of the ankle dorsiflexion angle during the gait support phase, and can judge whether the subject has a suitable ankle dorsiflexion angle to complete daily functional activities such as walking. At the same time, the extracted three-dimensional kinematic data of the subject is also helpful for formulating a targeted training plan for the patient to improve the abnormal movement pattern of the ankle dorsiflexion patient.

[0070] By applying the above technical solutions, the server obtains the limb data and real-time environment data of the subject, processes the limb data and real-time environment data based on the warning model to generate a warning message, and generates the real-time body state information of the subject based on the warning message. Obtain a body state prediction model, process the real-time heart rate information or body posture information of the subject based on the body state prediction model to generate the health state of the subject, compare the health state of the subject with the preset human body state information to generate the health level information corresponding to the subject, and label the dynamic three-dimensional motion data based on the health level information corresponding to the subject to generate label information, where the label information is used to characterize whether the dynamic three-dimensional motion data is currently in an abnormal state, and the dynamic three-dimensional motion data includes the data generated when the subject is in a static state or walking.

[0071] In addition, obtain the division standard of the gait cycle, obtain the ground forces in different directions received by the foot of the subject during the walking test, where the ground forces include the vertical reaction force, the anteroposterior reaction force, and the mediolateral reaction force, use the vertical reaction force, the anteroposterior reaction force, and the mediolateral reaction force as the ground reaction force data, process the reaction force data based on the division standard to generate the joint torques of each joint of the lower limb, process the dynamic three-dimensional motion data based on the second preset rule to generate gait three-dimensional kinematic characteristic parameters, generate the peak ankle dorsiflexion angle data during the support phase based on the gait three-dimensional kinematic characteristic parameters and the ground reaction force data, process the peak ankle dorsiflexion angle data during the support phase based on the third preset rule to generate the monitoring result of the subject and the identification information corresponding to the monitoring result, where the identification information is used to characterize the abnormal type of the monitoring result, process the identification information, and if the identification information characterizes that the dynamic three-dimensional motion data is currently in an abnormal state, obtain the correction plan corresponding to the identification information from the preset correction model.

[0072] In addition, the server will also obtain the digital human image of the subject, obtain the abnormal state information of the subject according to the identification information, obtain the normal state information corresponding to the abnormal state information, where the normal state information includes preset gait posture data, obtain the image difference between the digital human image in the normal state information and the digital human image in the abnormal state information, generate a corresponding posture adjustment plan based on the image difference, where the posture adjustment plan is used as the correction plan, and process the subject based on the correction plan to generate a posture correction result. By obtaining the lower limb joint kinematic characteristic parameters and ground reaction force parameters of the subject, the change of the ankle dorsiflexion angle during the gait support phase in the subject's walking test is generated, and according to the peak ankle dorsiflexion angle during the support phase, the subject is divided into an ankle dorsiflexion restricted group and an ankle dorsiflexion non-restricted group, so as to judge whether the patient's ankle dorsiflexion is restricted, and achieve the purpose of correcting the abnormal biomechanical movement of the lower limbs during the patient's movement.

[0073] In one implementation, as Figure 2 shown, the present application also provides a gait correction device based on biomechanical characteristics, including:

[0074] A generation module 201, configured to obtain the real-time body state information of the subject;

[0075] A processing module 202, configured to obtain dynamic three-dimensional motion data and ground reaction force data corresponding to the dynamic three-dimensional motion data based on the real-time body state information; process the ground reaction force data based on a first preset rule to generate the support phase within the gait cycle of the subject; process the dynamic three-dimensional motion data based on a second preset rule to generate gait three-dimensional kinematic characteristic parameters; generate peak ankle dorsiflexion angle data during the support phase based on the gait three-dimensional kinematic characteristic parameters and the ground reaction force data; process the peak ankle dorsiflexion angle data during the support phase based on a third preset rule to generate the monitoring result of the subject and identification information corresponding to the monitoring result; if the monitoring result is in an abnormal state, obtain a correction plan corresponding to the identification information; process the subject based on the correction plan to generate a posture correction result.

[0076] In this application, the server obtains the real-time physical state information of the subject, and based on the real-time physical state information, obtains dynamic three-dimensional motion data and ground reaction force data corresponding to the dynamic three-dimensional motion data. Among them, the dynamic three-dimensional motion data includes the data generated when the subject is in a static state or walking. The ground reaction force data is processed based on the first preset rule to generate the support phase within the gait cycle of the subject. The dynamic three-dimensional motion data is processed based on the second preset rule to generate gait three-dimensional kinematic characteristic parameters. The support phase ankle dorsiflexion peak angle data is generated based on the gait three-dimensional kinematic characteristic parameters and the ground reaction force data. The support phase ankle dorsiflexion peak angle data is processed based on the third preset rule to generate the monitoring result of the subject and the identification information corresponding to the monitoring result. Among them, the identification information is used to characterize the abnormal type of the monitoring result. If the monitoring result is in an abnormal state, the correction plan corresponding to the identification information is obtained, and the subject is processed based on the correction plan to generate a posture correction result. By obtaining the kinematic characteristic parameters of the lower limb joints and the ground reaction force parameters of the subject, the change of the ankle dorsiflexion angle during the gait support phase in the walking test of the subject is generated. According to the peak angle of ankle dorsiflexion during the support phase, the subject is divided into an ankle dorsiflexion restricted group and an ankle dorsiflexion non-restricted group, so as to judge whether the ankle dorsiflexion of the patient is restricted, and achieve the purpose of correcting the abnormal biomechanical movement of the lower limbs during the movement of the patient.

[0077] In another embodiment of the present application, the processing module 202 is configured to obtain the real-time physical state information of the subject, including: obtaining the limb data and real-time environment data of the subject; processing the limb data and the real-time environment data based on the warning model to generate warning information; generating the real-time physical state information of the subject based on the warning information.

[0078] In another embodiment of the present application, the processing module 202 is configured to obtain the real-time physical state information of the subject, further including: obtaining a physical state prediction model; processing the real-time heart rate information or body posture information of the subject based on the physical state prediction model to generate the health state of the subject; comparing the health state of the subject with the preset human state information to generate the health level information corresponding to the subject.

[0079] In another embodiment of the present application, the processing module 202 is configured to obtain the dynamic three-dimensional motion data and the ground reaction force data corresponding to the dynamic three-dimensional motion data based on the real-time physical state information, including: annotating the dynamic three-dimensional motion data based on the health level information corresponding to the subject to generate annotation information, where the annotation information is used to characterize whether the dynamic three-dimensional motion data is currently in an abnormal state.

[0080] In another embodiment of the present application, the processing module 202 is configured to, if the monitoring result is in an abnormal state, obtain a correction plan corresponding to the identification information, including: processing the identification information, and if the identification information indicates that the dynamic three-dimensional motion data is currently in an abnormal state, obtaining a correction plan corresponding to the identification information from a preset correction model.

[0081] In another embodiment of the present application, the processing module 202 is configured to process the ground reaction force data based on a first preset rule to generate a support phase within the gait cycle of the subject, including: obtaining a division criterion for the gait cycle; obtaining the ground reaction forces in different directions received by the subject's foot during the walking test, where the ground reaction forces include vertical reaction forces, anterior-posterior reaction forces, and medial-lateral reaction forces; taking the vertical reaction forces, the anterior-posterior reaction forces, and the medial-lateral reaction forces as the ground reaction force data; and processing the reaction force data based on the division criterion to generate joint torques of each lower limb joint.

[0082] In another embodiment of the present application, the processing module 202 is configured to, if the monitoring result is in an abnormal state, obtain a correction plan corresponding to the identification information, and further include: obtaining a digital human image of the subject; obtaining abnormal state information of the subject according to the identification information; obtaining normal state information corresponding to the abnormal state information, where the normal state information includes preset gait posture data; obtaining an image difference between the digital human image in the normal state information and the digital human image in the abnormal state information; and generating a corresponding posture adjustment plan based on the image difference, where the posture adjustment plan is used as the correction plan.

[0083] In the present application, the server obtains the limb data and real-time environment data of the subject, processes the limb data and real-time environment data based on an early warning model to generate early warning information, and generates real-time body state information of the subject based on the early warning information. Obtain a body state prediction model, process the real-time heart rate information or body posture information of the subject based on the body state prediction model to generate the health state of the subject, compare the health state of the subject with preset human state information to generate health level information corresponding to the subject, and label the dynamic three-dimensional motion data based on the health level information corresponding to the subject to generate labeling information, where the labeling information is used to indicate whether the dynamic three-dimensional motion data is currently in an abnormal state, where the dynamic three-dimensional motion data includes data generated when the subject is static or walking.

[0084] In addition, obtain the division criteria for the gait cycle, and obtain the ground forces acting on the subject's feet in different directions during the walking test. Among them, the ground forces include the vertical reaction force, the anteroposterior reaction force, and the mediolateral reaction force. Take the vertical reaction force, the anteroposterior reaction force, and the mediolateral reaction force as the ground reaction force data, process the reaction force data based on the division criteria to generate the joint torques of each lower limb joint, process the dynamic three-dimensional motion data based on the second preset rule to generate the gait three-dimensional kinematic characteristic parameters, generate the peak ankle dorsiflexion angle data during the stance phase based on the gait three-dimensional kinematic characteristic parameters and the ground reaction force data, process the peak ankle dorsiflexion angle data during the stance phase based on the third preset rule to generate the monitoring results of the subject and the identification information corresponding to the monitoring results. Among them, the identification information is used to characterize the abnormal type of the monitoring results. Process the identification information. If the identification information characterizes that the dynamic three-dimensional motion data is currently in an abnormal state, obtain the correction plan corresponding to the identification information from the preset correction model.

[0085] In addition, the server will also obtain the digital human image of the subject, obtain the abnormal state information of the subject according to the identification information, and obtain the normal state information corresponding to the abnormal state information. Among them, the normal state information includes the preset gait posture data. Obtain the image difference between the digital human image in the normal state information and the digital human image in the abnormal state information, and generate the corresponding posture adjustment plan based on the image difference. Among them, take the posture adjustment plan as the correction plan and process the subject based on the correction plan to generate the posture correction result. By obtaining the kinematic characteristic parameters of the subject's lower limb joints and the ground reaction force parameters, the change in the ankle dorsiflexion angle during the gait stance phase of the subject's walking test is generated. According to the peak ankle dorsiflexion angle during the stance phase, the subject is divided into an ankle dorsiflexion restricted group and an ankle dorsiflexion non-restricted group, so as to judge whether the patient's ankle dorsiflexion is restricted, and achieve the purpose of correcting the abnormal biomechanical movement of the lower limb during the patient's movement.

[0086] An embodiment of the present application provides an electronic device, such as Figure 3 shown, which includes a processor 300, a memory 301, a bus 302, and a communication interface 303. The processor 300, the communication interface 303, and the memory 301 are connected through the bus 302; a computer program that can run on the processor 300 is stored in the memory 301, and when the processor 300 runs the computer program, it executes the gait correction method based on biomechanical characteristics provided by any one of the foregoing embodiments of the present application.

[0087] Among them, the memory 301 may include high-speed random access memory (RAM), and may also include non-volatile memory, such as at least one disk memory. The communication connection between this system network element and at least one other network element is realized through at least one communication interface 303 (which can be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. can be used.

[0088] The bus 302 can be an ISA bus, a PCI bus, an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. Among them, the memory 301 is used to store a program. After receiving an execution instruction, the processor 300 executes the program. Any implementation manner of the gait correction method based on biomechanical characteristics disclosed in any implementation manner of the foregoing embodiments of the present application can be applied to the processor 300 or implemented by the processor 300.

[0089] The processor 300 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit in the hardware of the processor 300 or by instructions in software form. The above-mentioned processor 300 may be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application can be embodied as being completed by a hardware decoding processor or by a combination of hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers, etc. This storage medium is located in the memory 301, and the processor 300 reads the information in the memory 301 and combines its hardware to complete the steps of the above method.

[0090] The electronic device provided in the above embodiment of the present application and the gait correction method based on biomechanical characteristics provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0091] The embodiment of the present application provides a computer-readable storage medium, such asFigure 4 As shown, the computer-readable storage medium stores a computer program. When the computer program is read and run by a processor 402, the gait correction method based on biomechanical characteristics as described above is implemented.

[0092] Essentially, or in terms of the part that contributes to the prior art, or all or part of the technical solution of the embodiments of the present application can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing an electronic device (which can be an air conditioner, a refrigeration device, a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the method described in the embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, external hard drives, ROM, RAM, magnetic disks, or optical discs that can store program codes.

[0093] The computer-readable storage medium provided in the above embodiments of the present application and the gait correction method based on biomechanical characteristics provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the method adopted, run, or implemented by the application program stored therein.

[0094] The embodiments of the present application provide a computer program product, including a computer program, and the computer program is executed by a processor to implement the method as described above.

[0095] The computer program product provided in the above embodiments of the present application and the gait correction method based on biomechanical characteristics provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the method adopted, run, or implemented by the application program stored therein.

[0096] It should be noted that in the present application, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variation thereof is intended to cover a non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including the element.

[0097] Each embodiment in this application is described in a related manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the embodiments of the gait correction method, electronic device, electronic equipment, and readable storage medium based on biomechanical characteristics, since they are basically similar to the embodiments of the gait correction method based on biomechanical characteristics described above, the description is relatively simple. For the relevant parts, reference can be made to the partial description of the embodiments of the gait correction method based on biomechanical characteristics described above.

[0098] Although the present application is disclosed as above, the present application is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present application. Therefore, the protection scope of the present application should be subject to the scope defined by the claims.

Claims

1. A gait correction method based on biomechanical characteristics, characterized in that Including: Obtaining real-time physical state information of a subject; Obtaining dynamic three-dimensional motion data and ground reaction force data corresponding to the dynamic three-dimensional motion data based on the real-time physical state information, wherein the dynamic three-dimensional motion data includes data generated when the subject is in a static state or walking; Processing the ground reaction force data based on a first preset rule to generate a support period within the gait cycle of the subject; Processing the dynamic three-dimensional motion data based on a second preset rule to generate gait three-dimensional kinematic characteristic parameters; Generating support period ankle dorsiflexion peak angle data based on the gait three-dimensional kinematic characteristic parameters and the ground reaction force data, wherein the gait three-dimensional kinematic characteristic parameters are knee external rotation angle, hip extension angle, and pelvic ipsilateral tilt angle, and the ground reaction force data is ankle plantar flexion moment, ground reaction force in the X-axis direction, and ground reaction force in the Y-axis direction; Processing the support period ankle dorsiflexion peak angle data based on a third preset rule to generate a monitoring result of the subject and identification information corresponding to the monitoring result, wherein the identification information is used to characterize the abnormal type of the monitoring result; If the monitoring result is in an abnormal state, obtaining a correction plan corresponding to the identification information; Processing the subject based on the correction plan to generate a posture correction result.

2. The method according to claim 1, wherein The obtaining of the real-time physical state information of the subject includes: Obtaining limb data and real-time environment data of the subject; Processing the limb data and the real-time environment data based on an early warning model to generate early warning information; Generating the real-time physical state information of the subject based on the early warning information.

3. The method according to claim 1, characterized in that, The obtaining of the real-time physical state information of the subject further includes: Obtaining a physical state prediction model; Processing the real-time heart rate information or body posture information of the subject based on the physical state prediction model to generate the health state of the subject; Comparing the health state of the subject with preset human state information to generate health level information corresponding to the subject.

4. The method according to claim 3, wherein The obtaining of the dynamic three-dimensional motion data and the ground reaction force data corresponding to the dynamic three-dimensional motion data based on the real-time physical state information includes: Annotating the dynamic three-dimensional motion data based on the health level information corresponding to the subject to generate annotation information, wherein the annotation information is used to characterize whether the dynamic three-dimensional motion data is currently in an abnormal state.

5. The method according to claim 4, wherein The if the monitoring result is in an abnormal state, obtaining a correction plan corresponding to the identification information includes: Processing the identification information, and if the identification information characterizes that the monitoring result is currently in an abnormal state, obtaining a correction plan corresponding to the identification information from a preset correction model.

6. The method according to claim 1, characterized in that, The processing of the ground reaction force data based on a first preset rule to generate a support period within the gait cycle of the subject includes: Obtaining a division standard for the gait cycle; Obtain the ground reaction forces in different directions on the subject's foot during the walking test, where the ground reaction forces include vertical reaction force, anteroposterior reaction force, and mediolateral reaction force; Use the vertical reaction force, the anteroposterior reaction force, and the mediolateral reaction force as ground reaction force data; Process the reaction force data based on the division criteria to generate joint torques of each joint of the lower limb.

7. The method according to claim 1, wherein If the monitoring result is in an abnormal state, obtain a correction plan corresponding to the identification information, and further include: Obtain the digital human image of the subject; Obtain the abnormal state information of the subject according to the identification information; Obtain the normal state information corresponding to the abnormal state information, where the normal state information includes preset gait posture data; Obtain the image difference between the digital human image in the normal state information and the digital human image in the abnormal state information; Generate a corresponding posture adjustment plan based on the image difference, and use the posture adjustment plan as the correction plan.

8. A gait correction device based on biomechanical characteristics, characterized in that, The device includes: An acquisition module, configured to acquire real-time body state information of a subject; A processing module, configured to obtain dynamic three-dimensional motion data and ground reaction force data corresponding to the dynamic three-dimensional motion data based on the real-time body state information; process the ground reaction force data based on a first preset rule to generate a support phase within the gait cycle of the subject; process the dynamic three-dimensional motion data based on a second preset rule to generate gait three-dimensional kinematic characteristic parameters; generate support phase ankle dorsiflexion peak angle data based on the gait three-dimensional kinematic characteristic parameters and the ground reaction force data, where the gait three-dimensional kinematic characteristic parameters are knee external rotation angle, hip extension angle, and pelvic ipsilateral tilt angle, and the ground reaction force data is ankle plantar flexion torque, ground reaction force in the X-axis direction, and ground reaction force in the Y-axis direction; process the support phase ankle dorsiflexion peak angle data based on a third preset rule to generate a monitoring result of the subject and identification information corresponding to the monitoring result; if the monitoring result is in an abnormal state, obtain a correction plan corresponding to the identification information; process the subject based on the correction plan to generate a posture correction result.

9. An electronic device, characterized in that, Include: A processor; And A memory, configured to store executable instructions of the processor; Wherein, the processor is configured to execute the biomechanics feature-based gait correction method according to any one of claims 1 to 7 by executing the executable instructions.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the biomechanics feature-based gait correction method according to any one of claims 1 to 7.

Images