Method and system for adjusting lower limb hip, knee and ankle rehabilitation equipment based on directional health recognition

Abstract

The invention discloses a method and a system for adjusting lower limb hip, knee and ankle rehabilitation equipment based on directional health recognition. In a rehabilitation period, synchronously acquiring equipment signals and video data, and respectively analyzing to generate first and second motion feature data; the method comprises the following steps: constructing a self-encoder, carrying out dimension reduction reconstruction on feature data, dividing according to a motion period, periodically analyzing a difference degree, marking an abnormal period, positioning an abnormal joint limb, and formulating a modular rehabilitation regulation scheme through the abnormal limb joint and an occurrence frequency so as to be suitable for different rehabilitation users. Rehabilitation data are analyzed by fusing two dimensions of equipment signals and videos, the abnormal motion state and motion characteristics in the rehabilitation process are accurately recognized, directional rehabilitation anomaly recognition is achieved, a basis is provided for personalized rehabilitation adjustment, and the rehabilitation effect is improved.

Description

Technical Field

[0001] The present invention relates to the field of rehabilitation equipment, and more specifically, to a method and system for adjusting lower limb hip, knee and ankle rehabilitation equipment based on directional health identification. Background Art

[0002] At present, people are paying more and more attention to the health of the lower limbs, especially the rehabilitation of the lower limbs. Traditional lower limb rehabilitation methods use manual techniques to achieve limb rehabilitation of patients, but traditional techniques are inefficient and ineffective. At present, there is no robot with strong pertinence and less burden to achieve more efficient and comfortable rehabilitation training for walking and other sports rehabilitation. At the same time, the convenience of the equipment used cannot meet expectations, and there are certain requirements for the environment. The overall rehabilitation equipment is large in size and does not have the function of optimizing the equipment combination for users. In addition, the existing technology lacks reasonable and efficient motion characteristics analysis of user rehabilitation data collected in different dimensions, making it difficult to formulate feasible personalized rehabilitation plans, resulting in difficulty in improving the rehabilitation level.

[0003] Therefore, there is an urgent need for a lower limb hip, knee and ankle rehabilitation equipment adjustment method based on directional health identification to solve the above problems. Summary of the invention

[0004] The present invention overcomes the defects of the prior art and proposes a lower limb hip, knee and ankle rehabilitation equipment adjustment method and system based on directional health identification.

[0005] The first aspect of the present invention provides a method for adjusting lower limb hip, knee and ankle rehabilitation equipment based on directional health recognition, comprising: During a rehabilitation period, device signal data and video acquisition data are collected when the user is using the lower limb hip, knee and ankle rehabilitation equipment; The device signal data is analyzed based on the motion state to generate first motion feature data, and the device key point recognition and motion state analysis are performed based on the video acquisition data to generate second motion feature data; Constructing an autoencoder, and constructing a low-dimensional vector space based on a preset motion feature vector, and performing data dimension reduction and reconstruction on the first and second motion feature data respectively through the autoencoder to generate a first reconstructed feature and a second reconstructed feature; The rehabilitation time period is divided into multiple movement cycles, and the difference between the first reconstructed feature and the second reconstructed feature is periodically analyzed based on the Mahalanobis distance, and the abnormal movement cycle is marked by the difference; Through targeted identification and analysis of abnormal movement cycles, abnormal limb joint locations and abnormal frequency of occurrence are identified, and a modular rehabilitation and adjustment plan is formulated.

[0006] In this solution, during a rehabilitation period, the device signal data and video acquisition data of the user during the use of the lower limb hip, knee and ankle rehabilitation device are collected, specifically: The lower limb hip, knee and ankle rehabilitation equipment includes left and right hip joint modules, left and right knee joint modules, and electric stimulation modules; The device signal data is collected through various modules in the lower limb hip, knee and ankle rehabilitation equipment, and the video acquisition data is collected through the visual device.

[0007] In this solution, the first motion characteristic data is specifically: Perform data analysis on the device signal data based on the motion state, and convert the device signal data into device motion data; According to the device motion data, the device motion parameter characteristics are calculated in three dimensions: motion angle, motion amplitude, and motion speed, and first motion characteristic data is generated.

[0008] In this solution, the second motion characteristic data is specifically: Extract key frames from video acquisition data to generate key image sets; The limb joint images of the lower limb hip, knee and ankle rehabilitation equipment are used as target detection objects, and a target detection model based on image recognition is trained; Through the target detection model, the limb joints are identified and located in the key image set. Combined with the image frame information, the device motion parameter characteristics are calculated in three dimensions: motion angle, motion amplitude, and motion speed to generate the second motion feature data.

[0009] In this solution, the autoencoder is constructed, and a low-dimensional vector space is constructed based on a preset motion feature vector. The autoencoder is used to perform data dimension reduction and reconstruction on the first and second motion feature data to generate the first reconstructed feature and the second reconstructed feature, specifically: Based on the rehabilitation exercise plan, corresponding preset motion characteristic data and data value limit range information are set for each module of the lower limb hip, knee and ankle rehabilitation equipment; The preset motion characteristic data includes motion characteristic data corresponding to each rehabilitation stage; Vectorize the preset motion feature data, and set a low-dimensional vector space in combination with the value limit range information; Based on the autoencoder, the first and second motion feature data are respectively mapped into a low-dimensional vector space to generate corresponding low-dimensional representation data; The low-dimensional representation data is reconstructed, and a first reconstructed feature and a second reconstructed feature are generated accordingly.

[0010] In this solution, the rehabilitation time period is divided into multiple movement cycles, and the difference between the first reconstructed feature and the second reconstructed feature is periodically analyzed based on the Mahalanobis distance, and the abnormal movement cycle is marked by the difference, specifically: Based on preset intervals, the rehabilitation time period is divided into multiple exercise cycles; In a motion cycle, the difference between the first reconstructed feature and the second reconstructed feature is calculated based on the Mahalanobis distance, and if the difference is within a preset abnormal value range, the motion cycle is marked as an abnormal motion cycle; Analyze all motion cycles and perform abnormal cycle analysis and marking.

[0011] In this scheme, the abnormal limb joint positions and abnormal frequencies are identified and analyzed through abnormal movement cycles, and a modular rehabilitation adjustment scheme is formulated, specifically: According to the abnormal movement cycle, the operation status of each module of the lower limb hip, knee and ankle rehabilitation equipment is analyzed from the equipment signal data, and the abnormal limb joint parts are marked; Analyze all abnormal movement cycles, calculate the frequency of abnormal movement of abnormal limb joints, and obtain the frequency of abnormal occurrence; Combine abnormal limb joints with abnormal frequencies within the same preset frequency range to obtain a lower limb rehabilitation combination, and formulate a modular rehabilitation plan based on the lower limb rehabilitation combination; The modular rehabilitation program includes a combination of one or more sub-modules and rehabilitation plan data.

[0012] The second aspect of the present invention also provides a lower limb hip, knee and ankle rehabilitation equipment adjustment system based on directional health recognition, the system comprising: a memory, a processor, the memory comprising a lower limb hip, knee and ankle rehabilitation equipment adjustment program based on directional health recognition, the lower limb hip, knee and ankle rehabilitation equipment adjustment program based on directional health recognition being executed by the processor to implement the following steps: During a rehabilitation period, device signal data and video acquisition data are collected when the user is using the lower limb hip, knee and ankle rehabilitation equipment; The device signal data is analyzed based on the motion state to generate first motion feature data, and the device key point recognition and motion state analysis are performed based on the video acquisition data to generate second motion feature data; Constructing an autoencoder, and constructing a low-dimensional vector space based on a preset motion feature vector, and performing data dimension reduction and reconstruction on the first and second motion feature data respectively through the autoencoder to generate a first reconstructed feature and a second reconstructed feature; The rehabilitation time period is divided into multiple movement cycles, and the difference between the first reconstructed feature and the second reconstructed feature is periodically analyzed based on the Mahalanobis distance, and the abnormal movement cycle is marked by the difference; Through targeted identification and analysis of abnormal movement cycles, abnormal limb joint locations and abnormal frequency of occurrence are identified, and a modular rehabilitation and adjustment plan is formulated.

[0013] The third aspect of the present invention also provides a computer-readable storage medium, which includes a lower limb hip, knee and ankle rehabilitation equipment adjustment program based on directional health identification. When the lower limb hip, knee and ankle rehabilitation equipment adjustment program based on directional health identification is executed by a processor, the steps of the lower limb hip, knee and ankle rehabilitation equipment adjustment method based on directional health identification as described in any one of the above items are implemented.

[0014] The present invention discloses a method and system for adjusting lower limb hip, knee and ankle rehabilitation equipment based on directional health identification. During the rehabilitation period, the device signal and video data are synchronously collected, and the first and second motion feature data are respectively analyzed and generated. An autoencoder is constructed, and after the feature data is reconstructed by dimensionality reduction, it is divided according to the motion cycle and the difference is periodically analyzed. The abnormal cycle is marked and the abnormal joints and limbs are located. According to the abnormal limb joints and the frequency of occurrence, a modular rehabilitation adjustment plan is formulated to suit different rehabilitation users. The present invention analyzes rehabilitation data by fusing the two dimensions of device signals and videos, accurately identifies abnormal motion states and motion characteristics during the rehabilitation process, realizes directional rehabilitation abnormality identification, provides a basis for personalized rehabilitation adjustment, and improves the rehabilitation effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A flow chart of a method for adjusting lower limb hip, knee and ankle rehabilitation equipment based on directional health recognition according to the present invention is shown; Figure 2 Shows a schematic diagram of different module combinations of the present invention; Figure 3 A schematic diagram of wearing the lower limb hip, knee and ankle rehabilitation device of the present invention is shown; Figure 4 A schematic diagram of the assisting process of the lower limb hip, knee and ankle rehabilitation device of the present invention is shown; Figure 5 A block diagram of a lower limb hip, knee and ankle rehabilitation equipment adjustment system based on directional health identification according to the present invention is shown. DETAILED DESCRIPTION

[0016] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0017] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0018] Figure 1 A flow chart of a method for adjusting lower limb hip, knee and ankle rehabilitation equipment based on directional health identification according to the present invention is shown.

[0019] like Figure 1 As shown, the first aspect of the present invention provides a method for adjusting lower limb hip, knee and ankle rehabilitation equipment based on directional health identification, comprising: S102, collecting device signal data and video acquisition data of a user using a lower limb hip, knee and ankle rehabilitation device during a rehabilitation period; S104, performing data analysis based on the motion state of the device signal data to generate first motion feature data, and performing device key point recognition and motion state analysis based on the video acquisition data to generate second motion feature data; S106, constructing an autoencoder, and constructing a low-dimensional vector space based on a preset motion feature vector, and performing data dimension reduction and reconstruction on the first and second motion feature data respectively through the autoencoder to generate a first reconstructed feature and a second reconstructed feature; S108, dividing the rehabilitation time period into a plurality of movement cycles, periodically analyzing the difference between the first reconstructed feature and the second reconstructed feature based on the Mahalanobis distance, and marking abnormal movement cycles according to the difference; S110, through the directional identification and analysis of abnormal movement cycles, abnormal limb joint locations and abnormal frequency of occurrence are identified, and a modular rehabilitation adjustment plan is formulated.

[0020] It is worth mentioning here that traditional rehabilitation technology generally analyzes rehabilitation and exercise conditions based on manual experience, and requires rehabilitation physicians to collect data from the equipment and make manual judgments. The degree of informatization and intelligence is not high, and it is difficult to improve rehabilitation efficiency. In addition, the degree of modularization of traditional technology is not high, and there is a lack of modular-based program formulation, which makes it difficult to improve the level of rehabilitation. The present invention can effectively solve the above problems.

[0021] The rehabilitation formulation method proposed in the present invention has extremely strong portability and reconfigurable reorganization characteristics. The minimum combination unit that solves the rehabilitation needs can be freely matched according to needs, so as to achieve the effect of solving the problem without adding extra burden. The equipment has a simple structure, light weight, strong portability, and comfortable use. Both hip joints, knee joints, and ankle joints can be rehabilitated, and various modes such as passive training and active training can be realized. It can be used on both sides.

[0022] like Figure 2201 is a schematic diagram of the combination of different submodules, including: 201 bilateral hip joints use left and right hip joint modules, 202 bilateral knee joints use left and right knee joint modules, 203 left lower limb uses left knee joint module and electrical stimulation module, 204 bilateral auxiliary uses left knee joint module + bilateral electrical stimulation module + right hip joint, 205 bilateral auxiliary uses left knee joint module + bilateral hip joint.

[0023] In the present invention, a lower limb hip, knee and ankle rehabilitation device is proposed as a bilateral 6-joint exoskeleton configuration device. The device is equipped with a waist belt, hip power joints, knee power joints, ankle joints, electrical stimulation modules and other parts. Each module is independent and does not need to be physically connected to each other. The hip joint needs to be connected to the waist belt to make each joint independent, and only has a power output part and a binding part, which can reduce the weight of each module to the greatest extent. The interconnection and power supply between the modules are achieved through cables, so as to realize the movement of the whole machine and complete the assistance to the hip joint, knee joint and ankle joint.

[0024] Different robot combinations can be matched according to different joint rehabilitation needs. For example, if a patient has problems with both knee joints, only the left knee joint module and the right knee joint module can be used. If a patient only has problems with the left hip joint, only the left hip joint module can be used. The combination can be freely matched. The present invention also performs modular analysis and formulates a rehabilitation plan by analyzing multi-dimensional rehabilitation data.

[0025] In the combination of multiple sub-modules, the rehabilitation algorithm will be automatically adjusted according to the specific plug-in modules and the rehabilitation plan, and the current state and output of each joint will be calculated to achieve algorithm adaptation and control adaptation in different matching situations.

[0026] The hip joint module is mainly based on the binding of the waist belt and the thigh, so that when the hip joint outputs power, it can drive the human thigh to move, and then realize the rotation of the hip joint, so as to achieve the effect of hip joint rehabilitation. The knee joint module is mainly based on the binding of the thigh and the calf, so that when the knee joint outputs power, it can drive the human calf to move, and then realize the rotation of the knee joint, so as to achieve the effect of knee joint rehabilitation. At the same time, the ankle joint electrical stimulation module of the exoskeleton needs to attach the stimulation electrodes of the electrical stimulation module to the tibialis anterior muscle and the common peroneal nerve. There are two electrodes in total. When the electrical stimulation module stimulates, it will stimulate the human calf muscle to contract, drive the ankle dorsiflexion, generate ankle movement, stimulate muscle contraction, and achieve the effect of rehabilitation training. So as to achieve the effect of ankle joint rehabilitation.

[0027] The ankle joint module can be realized by electrical stimulation instead of the motor structure, which can greatly reduce the weight of the exoskeleton. At the same time, without the support of the foot, the patient can keep his feet on the ground, and the proprioception rehabilitation effect will be better. In addition, the modular design can reduce the power joint output requirements of the hip and knee joints, thereby reducing the weight of the hip and knee joints, making the overall weight further reduced, and can achieve the effect of lightweight and convenience, so as to reduce the limb burden of the already weak people who need rehabilitation. The free matching feature also greatly reduces the burden on patients.

[0028] like Figure 3 The diagram shows the various angles of wearing the lower limb hip, knee and ankle rehabilitation equipment. Specifically, it includes the front, side and back diagrams. The front diagram includes the positions of the corresponding 7 power supply signal lines and 6 electrical stimulation modules. The side diagram includes the position of 1 energy and control system. The back diagram includes the positions of 2 right side of hip joint module, 3 left side of hip joint module, 4 right side of knee joint module and 5 left side of knee joint module.

[0029] Figure 4 This is a schematic diagram of auxiliary rehabilitation exercises for the hip, knee and ankle rehabilitation of the lower limbs during user exercise. The assistance can be applied to running, walking, moving joints, etc.

[0030] According to an embodiment of the present invention, during a rehabilitation period, the device signal data and video acquisition data of the user during the process of using the lower limb hip, knee and ankle rehabilitation device are collected, specifically: The lower limb hip, knee and ankle rehabilitation equipment includes left and right hip joint modules, left and right knee joint modules, and electric stimulation modules; The device signal data is collected through various modules in the lower limb hip, knee and ankle rehabilitation equipment, and the video acquisition data is collected through the visual device.

[0031] It should be noted that the device signal data can be used to obtain the user's motion characteristics corresponding to different limb joints through data analysis. Lower limb hip, knee and ankle rehabilitation is a rehabilitation device, which includes multiple subdivided modules (i.e. submodules). In addition. Based on directional health analysis and directional limb movement analysis, different modules can be combined to form modular rehabilitation equipment, which is suitable for users in different situations. The visual device includes a multi-angle high-definition camera device.

[0032] According to an embodiment of the present invention, the first motion feature data is specifically: Perform data analysis on the device signal data based on the motion state, and convert the device signal data into device motion data; According to the device motion data, the device motion parameter characteristics are calculated in three dimensions: motion angle, motion amplitude, and motion speed, and first motion characteristic data is generated.

[0033] It should be noted that the device motion data includes the device's operating status data, specific parameter values ​​of the motion, etc. The user's rehabilitation motion status can be reflected through the device's motion analysis.

[0034] According to an embodiment of the present invention, the second motion characteristic data is specifically: Extract key frames from video acquisition data to generate key image sets; The limb joint images of the lower limb hip, knee and ankle rehabilitation equipment are used as target detection objects, and a target detection model based on image recognition is trained; Through the target detection model, the limb joints are identified and located in the key image set. Combined with the image frame information, the device motion parameter characteristics are calculated in three dimensions: motion angle, motion amplitude, and motion speed to generate the second motion feature data.

[0035] It should be noted that the target detection model can be specifically trained with a CNN image recognition model, and the target detection training is performed on the images of relevant limb joint parts through the recognition model, and a recognition model that can perform target detection analysis on the relevant parts of the device is obtained. The limb joint parts are specifically the joint parts corresponding to the device, which can be set by the user to analyze the movement state of the joints and limbs. Key point recognition is limb joint part recognition. The motion feature data is specifically parameter data based on the motion characteristics of the limb joints, including numerical parameters such as motion angle, motion amplitude, and motion speed.

[0036] According to an embodiment of the present invention, the autoencoder is constructed, and a low-dimensional vector space is constructed based on a preset motion feature vector, and the first and second motion feature data are respectively reduced in dimension and reconstructed by the autoencoder to generate a first reconstructed feature and a second reconstructed feature, specifically: Based on the rehabilitation exercise plan, corresponding preset motion characteristic data and data value limit range information are set for each module of the lower limb hip, knee and ankle rehabilitation equipment; The preset motion characteristic data includes motion characteristic data corresponding to each rehabilitation stage; Vectorize the preset motion feature data, and set a low-dimensional vector space in combination with the value limit range information; Based on the autoencoder, the first and second motion feature data are respectively mapped into a low-dimensional vector space to generate corresponding low-dimensional representation data; The low-dimensional representation data is reconstructed, and a first reconstructed feature and a second reconstructed feature are generated accordingly.

[0037] It should be noted that the rehabilitation exercise plan includes multiple rehabilitation stages and the user's limb and joint movement requirements corresponding to each stage, which are set in the corresponding motion feature data by analyzing the movement requirements, such as the movement amplitude and angle of a joint or the movement speed and amplitude of a limb at different stages. The value limit range information is set based on the movement requirements and includes the value range of motion feature data of multiple rehabilitation stages. In the low-dimensional vector space, all preset motion feature data can be represented, and multi-dimensional data representation can be realized, which is used for subsequent data dimensionality reduction and data unification. The low-dimensional representation data includes the low-dimensional representation corresponding to the first and second motion feature data.

[0038] In addition, during the motion state analysis process, the present invention utilizes the encoded vector space to perform data dimensionality reduction and reconstruction on the collected motion features, which can reduce the dimensionality of the motion features collected over a long period to a unified vector space, and perform effective comparisons in the subsequent process, thereby realizing the correlation analysis of the two-dimensional motion features and the mining of abnormal motion features, screening out key limb parts for rehabilitation, and setting up modular rehabilitation plans for target users based on the corresponding time nodes.

[0039] According to an embodiment of the present invention, the rehabilitation time period is divided into a plurality of movement cycles, and the difference between the first reconstructed feature and the second reconstructed feature is periodically analyzed based on the Mahalanobis distance, and the abnormal movement cycle is marked by the difference, specifically: Based on preset intervals, the rehabilitation time period is divided into multiple exercise cycles; In a motion cycle, the difference between the first reconstructed feature and the second reconstructed feature is calculated based on the Mahalanobis distance, and if the difference is within a preset abnormal value range, the motion cycle is marked as an abnormal motion cycle; Analyze all motion cycles and perform abnormal cycle analysis and marking.

[0040] It should be noted that the first reconstruction feature and the second reconstruction feature are obtained based on the analysis of the first motion feature data and the second motion feature data, respectively, and include data within the entire rehabilitation time period. When analyzing based on the motion cycle, the data of the corresponding motion cycle are divided out from the overall first reconstruction feature and the second reconstruction feature for difference analysis, thereby realizing periodic analysis of motion feature differences.

[0041] According to an embodiment of the present invention, the abnormal limb joint positions and abnormal occurrence frequencies are identified and analyzed through abnormal movement cycles, and a modular rehabilitation adjustment plan is formulated, specifically: According to the abnormal movement cycle, the operation status of each module of the lower limb hip, knee and ankle rehabilitation equipment is analyzed from the equipment signal data, and the abnormal limb joint parts are marked; Analyze all abnormal movement cycles, calculate the frequency of abnormal movement of abnormal limb joints, and obtain the frequency of abnormal occurrence; Combine abnormal limb joints with abnormal frequencies within the same preset frequency range to obtain a lower limb rehabilitation combination, and formulate a modular rehabilitation plan based on the lower limb rehabilitation combination; The modular rehabilitation program includes a combination of one or more sub-modules and rehabilitation plan data.

[0042] It should be noted that in the modules corresponding to the lower limb hip, knee and ankle rehabilitation equipment, different modules correspond to different parts of sports rehabilitation and also correspond to different parts of the limbs for sports rehabilitation. Therefore, based on the directional analysis of abnormal movement cycles and the corresponding abnormal parts of rehabilitation, they can be combined to form a modular rehabilitation plan. For example, if there is abnormal recognition of the left hip joint and the right hip joint, and the frequency is within a consistent numerical range, and there is also a certain abnormal recognition of the left knee joint, then the left and right hip joint modules can be combined based on the combination of the left hip joint and the right hip joint, and the left knee joint module and the electrical stimulation module can be added. Based on the abnormal judgment situation, a certain modular combination is performed, so that it can be intelligently applied to the rehabilitation needs of different types of users, and assist rehabilitation physicians in rehabilitation analysis and plan judgment.

[0043] According to a preferred embodiment of the present invention, it also includes: The rehabilitation time period is divided into N movement cycles, and within the N movement cycles, the first reconstruction feature and the second reconstruction feature are respectively divided into corresponding data to obtain N first data items and N second data items; The Mean-shift clustering algorithm is introduced to perform cluster analysis after data standardization on the N first data items, and the bandwidth parameter value is set for cluster fitting. After the cluster fitting is completed, the number of cluster centers K1 is recorded; Based on the same Mean-shift clustering algorithm and consistent bandwidth parameter value, cluster fitting is performed on the N second data items, and the number of cluster centers K2 is recorded; Calculate the absolute distance D between K1 and K2; Integrate all the first data items and the second data items into a data item set, perform correlation analysis on the data item set based on the Apriori association algorithm, and set a minimum support threshold and a minimum confidence threshold; The minimum support threshold is adjusted based on the size of D, and D is inversely proportional to the minimum support threshold; Through the minimum support threshold, the candidate item set and frequent item set are screened out from the data item set, and the association rules of the data items are set based on the minimum confidence threshold; Filter out strongly associated data and weakly associated data from the data item set by using association rules, and filter out the weakly associated first data item and the second data item from the weakly associated data, and mark them as weakly associated data items; Through weakly associated data items, the corresponding abnormal movement cycle is located, and the abnormal limb joint part information corresponding to the positioning data is located.

[0044] It should be noted that the reconstructed data contains important user motion characteristics, and the two reconstructed data represent motion characteristics analyzed in different dimensions. Therefore, in the reconstructed feature analysis based on a long period of time, in addition to the difference analysis, an embodiment of abnormal judgment based on data correlation can also be performed. Through the above correlation judgment, the user's long-term motion characteristics can be correlated and judged, so as to screen out abnormal limb joints in different motion cycles. In the present invention, for the two-dimensional motion feature data (the first and second reconstructed features), the feature vector space is uniformly represented, and on this basis, the correlation analysis of the feature data and the directional health abnormality judgment can be realized, so as to improve the efficient and directional analysis capabilities of the user's motion rehabilitation characteristics and rehabilitation needs. Absolute distance D = |K1-K2|, the larger the D, the smaller the minimum support threshold. The association rule can screen out strongly correlated data, and mark the non-strongly correlated data as weakly correlated data.

[0045] Through weakly associated data items, the corresponding abnormal motion cycle and the abnormal limb joint part information corresponding to the data are located. Specifically, based on the weakly associated data items, the data segment of the corresponding first reconstruction feature or the second reconstruction feature can be located, and the motion feature data is further located based on the located data segment. Finally, the data source information of the module where the weakly associated data item is located is located through the device signal data or video acquisition data, that is, including the corresponding motion cycle (time information) and the applied submodule and limb joint. By screening out the weakly associated data, the corresponding abnormal motion cycle and abnormal limb joint part are further located. It can be understood here that the device signal data and the video acquisition data, the first and second motion feature data, the first reconstruction feature and the second reconstruction feature are one-to-one corresponding data, and the data of different stages are obtained based on the corresponding analysis method, and the data has the corresponding acquisition time information, which is used to determine the limb joint or submodule involved in the corresponding motion cycle and the corresponding rehabilitation process.

[0046] In the correlation analysis, the present invention performs overall data item similarity analysis on the motion feature data of two dimensions (the first and the second reconstructed features), uses the Mean-shift clustering method for analysis, and represents the overall similarity based on the difference between the number of clusters K1 and K2, and uses K1K2 to set the minimum support threshold in the association analysis process. The smaller the overall similarity, the larger D is, and the smaller the set minimum support threshold is, so that data with strong or weak correlation in the data items can be accurately mined, and the corresponding motion cycle data and motion modules can be located based on the weakly correlated data, and data with abnormal correlation can be marked. The abnormally correlated data can be directed to the corresponding rehabilitation modules and limb joints, and corresponding modular rehabilitation plans can be formulated.

[0047] It is worth mentioning that in traditional rehabilitation analysis, there is often a lack of multi-dimensional motion state analysis and motion characteristic analysis of the collected data, and a lack of correlation analysis of motion characteristics in different dimensions, making it difficult to conduct precise and modular analysis of rehabilitation programs. The embodiments of the present invention can effectively solve the above problems.

[0048] The first data item and the second data item are both used as data items for correlation analysis, and the mark here is used to distinguish whether the data item belongs to the first reconstructed data or the second reconstructed data. Data normalization is an optional operation.

[0049] Figure 5 A block diagram of a lower limb hip, knee and ankle rehabilitation equipment adjustment system based on directional health identification according to the present invention is shown.

[0050] The second aspect of the present invention further provides a lower limb hip, knee and ankle rehabilitation equipment adjustment system 5 based on directional health recognition, the system comprising: a memory 51, a processor 52, the memory 51 comprising a lower limb hip, knee and ankle rehabilitation equipment adjustment program based on directional health recognition, the lower limb hip, knee and ankle rehabilitation equipment adjustment program based on directional health recognition being executed by the processor 52 to implement the following steps: During a rehabilitation period, device signal data and video acquisition data are collected when the user is using the lower limb hip, knee and ankle rehabilitation equipment; The device signal data is analyzed based on the motion state to generate first motion feature data, and the device key point recognition and motion state analysis are performed based on the video acquisition data to generate second motion feature data; Constructing an autoencoder, and constructing a low-dimensional vector space based on a preset motion feature vector, and performing data dimension reduction and reconstruction on the first and second motion feature data respectively through the autoencoder to generate a first reconstructed feature and a second reconstructed feature; The rehabilitation time period is divided into multiple movement cycles, and the difference between the first reconstructed feature and the second reconstructed feature is periodically analyzed based on the Mahalanobis distance, and the abnormal movement cycle is marked by the difference; Through targeted identification and analysis of abnormal movement cycles, abnormal limb joint locations and abnormal frequency of occurrence are identified, and a modular rehabilitation and adjustment plan is formulated.

[0051] It is worth mentioning here that traditional rehabilitation technology generally analyzes rehabilitation and exercise conditions based on manual experience, and requires rehabilitation physicians to collect data from the equipment and make manual judgments. The degree of informatization and intelligence is not high, and it is difficult to improve rehabilitation efficiency. In addition, the degree of modularization of traditional technology is not high, and there is a lack of modular-based program formulation, which makes it difficult to improve the level of rehabilitation. The present invention can effectively solve the above problems.

[0052] The rehabilitation formulation method proposed in the present invention has extremely strong portability and reconfigurable reorganization characteristics. The minimum combination unit that solves the rehabilitation needs can be freely matched according to needs, so as to achieve the effect of solving the problem without adding extra burden. The equipment has a simple structure, light weight, strong portability, and comfortable use. Both hip joints, knee joints, and ankle joints can be rehabilitated, and various modes such as passive training and active training can be realized. It can be used on both sides.

[0053] In the present invention, a lower limb hip, knee and ankle rehabilitation device is proposed as a bilateral 6-joint exoskeleton configuration device. The device is equipped with a waist belt, hip power joints, knee power joints, ankle joints, electrical stimulation modules and other parts. Each module is independent and does not need to be physically connected to each other. The hip joint needs to be connected to the waist belt to make each joint independent, and only has a power output part and a binding part, which can reduce the weight of each module to the greatest extent. The interconnection and power supply between the modules are achieved through cables, so as to realize the movement of the whole machine and complete the assistance to the hip joint, knee joint and ankle joint.

[0054] Different robot combinations can be matched according to different joint rehabilitation needs. For example, if a patient has problems with both knee joints, only the left knee joint module and the right knee joint module can be used. If a patient only has problems with the left hip joint, only the left hip joint module can be used. The combination can be freely matched. The present invention also performs modular analysis and formulates a rehabilitation plan by analyzing multi-dimensional rehabilitation data.

[0055] In the combination of multiple sub-modules, the rehabilitation algorithm will be automatically adjusted according to the specific plug-in modules and the rehabilitation plan, and the current state and output of each joint will be calculated to achieve algorithm adaptation and control adaptation in different matching situations.

[0056] The hip joint module is mainly based on the binding of the waist belt and the thigh, so that when the hip joint outputs power, it can drive the human thigh to move, and then realize the rotation of the hip joint, so as to achieve the effect of hip joint rehabilitation. The knee joint module is mainly based on the binding of the thigh and the calf, so that when the knee joint outputs power, it can drive the human calf to move, and then realize the rotation of the knee joint, so as to achieve the effect of knee joint rehabilitation. At the same time, the ankle joint electrical stimulation module of the exoskeleton needs to attach the stimulation electrodes of the electrical stimulation module to the tibialis anterior muscle and the common peroneal nerve. There are two electrodes in total. When the electrical stimulation module stimulates, it will stimulate the human calf muscle to contract, drive the ankle dorsiflexion, generate ankle movement, stimulate muscle contraction, and achieve the effect of rehabilitation training. So as to achieve the effect of ankle joint rehabilitation.

[0057] The ankle joint module can be realized by electrical stimulation instead of the motor structure, which can greatly reduce the weight of the exoskeleton. At the same time, without the support of the foot, the patient can keep his feet on the ground, and the proprioception rehabilitation effect will be better. In addition, the modular design can reduce the power joint output requirements of the hip and knee joints, thereby reducing the weight of the hip and knee joints, making the overall weight further reduced, and can achieve the effect of lightweight and convenience, so as to reduce the limb burden of the already weak people who need rehabilitation. The free matching feature also greatly reduces the burden on patients.

[0058] According to an embodiment of the present invention, during a rehabilitation period, the device signal data and video acquisition data of the user during the process of using the lower limb hip, knee and ankle rehabilitation device are collected, specifically: The lower limb hip, knee and ankle rehabilitation equipment includes left and right hip joint modules, left and right knee joint modules, and electric stimulation modules; The device signal data is collected through various modules in the lower limb hip, knee and ankle rehabilitation equipment, and the video acquisition data is collected through the visual device.

[0059] It should be noted that the device signal data can be used to obtain the user's motion characteristics corresponding to different limb joints through data analysis. Lower limb hip, knee and ankle rehabilitation is a rehabilitation device, which includes multiple subdivided modules (i.e. submodules). In addition. Based on directional health analysis and directional limb movement analysis, different modules can be combined to form modular rehabilitation equipment, which is suitable for users in different situations. The visual device includes a multi-angle high-definition camera device.

[0060] According to an embodiment of the present invention, the first motion feature data is specifically: Perform data analysis on the device signal data based on the motion state, and convert the device signal data into device motion data; According to the device motion data, the device motion parameter characteristics are calculated in three dimensions: motion angle, motion amplitude, and motion speed, and first motion characteristic data is generated.

[0061] It should be noted that the device motion data includes the device's operating status data, specific parameter values ​​of the motion, etc. The user's rehabilitation motion status can be reflected through the device's motion analysis.

[0062] According to an embodiment of the present invention, the second motion characteristic data is specifically: Extract key frames from video acquisition data to generate key image sets; The limb joint images of the lower limb hip, knee and ankle rehabilitation equipment are used as target detection objects, and a target detection model based on image recognition is trained; Through the target detection model, the limb joints are identified and located in the key image set. Combined with the image frame information, the device motion parameter characteristics are calculated in three dimensions: motion angle, motion amplitude, and motion speed to generate the second motion feature data.

[0063] It should be noted that the target detection model can be specifically trained with a CNN image recognition model, and the target detection training is performed on the images of relevant limb joint parts through the recognition model, and a recognition model that can perform target detection analysis on the relevant parts of the device is obtained. The limb joint parts are specifically the joint parts corresponding to the device, which can be set by the user to analyze the movement state of the joints and limbs. Key point recognition is limb joint part recognition. The motion feature data is specifically parameter data based on the motion characteristics of the limb joints, including numerical parameters such as motion angle, motion amplitude, and motion speed.

[0064] According to an embodiment of the present invention, the autoencoder is constructed, and a low-dimensional vector space is constructed based on a preset motion feature vector, and the first and second motion feature data are respectively reduced in dimension and reconstructed by the autoencoder to generate a first reconstructed feature and a second reconstructed feature, specifically: Based on the rehabilitation exercise plan, corresponding preset motion characteristic data and data value limit range information are set for each module of the lower limb hip, knee and ankle rehabilitation equipment; The preset motion characteristic data includes motion characteristic data corresponding to each rehabilitation stage; Vectorize the preset motion feature data, and set a low-dimensional vector space in combination with the value limit range information; Based on the autoencoder, the first and second motion feature data are respectively mapped into a low-dimensional vector space to generate corresponding low-dimensional representation data; The low-dimensional representation data is reconstructed, and a first reconstructed feature and a second reconstructed feature are generated accordingly.

[0065] It should be noted that the rehabilitation exercise plan includes multiple rehabilitation stages and the user's limb and joint movement requirements corresponding to each stage, which are set in the corresponding motion feature data by analyzing the movement requirements, such as the movement amplitude and angle of a joint or the movement speed and amplitude of a limb at different stages. The value limit range information is set based on the movement requirements and includes the value range of motion feature data of multiple rehabilitation stages. In the low-dimensional vector space, all preset motion feature data can be represented, and multi-dimensional data representation can be realized, which is used for subsequent data dimensionality reduction and data unification. The low-dimensional representation data includes the low-dimensional representation corresponding to the first and second motion feature data.

[0066] In addition, during the motion state analysis process, the present invention utilizes the encoded vector space to perform data dimensionality reduction and reconstruction on the collected motion features, which can reduce the dimensionality of the motion features collected over a long period to a unified vector space, and perform effective comparisons in the subsequent process, thereby realizing the correlation analysis of the two-dimensional motion features and the mining of abnormal motion features, screening out key limb parts for rehabilitation, and setting up modular rehabilitation plans for target users based on the corresponding time nodes.

[0067] According to an embodiment of the present invention, the rehabilitation time period is divided into a plurality of movement cycles, and the difference between the first reconstructed feature and the second reconstructed feature is periodically analyzed based on the Mahalanobis distance, and the abnormal movement cycle is marked by the difference, specifically: Based on preset intervals, the rehabilitation time period is divided into multiple exercise cycles; In a motion cycle, the difference between the first reconstructed feature and the second reconstructed feature is calculated based on the Mahalanobis distance, and if the difference is within a preset abnormal value range, the motion cycle is marked as an abnormal motion cycle; Analyze all motion cycles and perform abnormal cycle analysis and marking.

[0068] It should be noted that the first reconstruction feature and the second reconstruction feature are obtained based on the analysis of the first motion feature data and the second motion feature data, respectively, and include data within the entire rehabilitation time period. When analyzing based on the motion cycle, the data of the corresponding motion cycle are divided out from the overall first reconstruction feature and the second reconstruction feature for difference analysis, thereby realizing periodic analysis of motion feature differences.

[0069] According to an embodiment of the present invention, the abnormal limb joint positions and abnormal occurrence frequencies are identified and analyzed through abnormal movement cycles, and a modular rehabilitation adjustment plan is formulated, specifically: According to the abnormal movement cycle, the operation status of each module of the lower limb hip, knee and ankle rehabilitation equipment is analyzed from the equipment signal data, and the abnormal limb joint parts are marked; Analyze all abnormal movement cycles, calculate the frequency of abnormal movement of abnormal limb joints, and obtain the frequency of abnormal occurrence; Combine abnormal limb joints with abnormal frequencies within the same preset frequency range to obtain a lower limb rehabilitation combination, and formulate a modular rehabilitation plan based on the lower limb rehabilitation combination; The modular rehabilitation program includes a combination of one or more sub-modules and rehabilitation plan data.

[0070] It should be noted that in the modules corresponding to the lower limb hip, knee and ankle rehabilitation equipment, different modules correspond to different parts of sports rehabilitation and also correspond to different parts of the limbs for sports rehabilitation. Therefore, based on the directional analysis of abnormal movement cycles and the corresponding abnormal parts of rehabilitation, they can be combined to form a modular rehabilitation plan. For example, if there is abnormal recognition of the left hip joint and the right hip joint, and the frequency is within a consistent numerical range, and there is also a certain abnormal recognition of the left knee joint, then the left and right hip joint modules can be combined based on the combination of the left hip joint and the right hip joint, and the left knee joint module and the electrical stimulation module can be added. Based on the abnormal judgment situation, a certain modular combination is performed, so that it can be intelligently applied to the rehabilitation needs of different types of users, and assist rehabilitation physicians in rehabilitation analysis and plan judgment.

[0071] The third aspect of the present invention also provides a computer-readable storage medium, which includes a lower limb hip, knee and ankle rehabilitation equipment adjustment program based on directional health identification. When the lower limb hip, knee and ankle rehabilitation equipment adjustment program based on directional health identification is executed by a processor, the steps of the lower limb hip, knee and ankle rehabilitation equipment adjustment method based on directional health identification as described in any one of the above items are implemented.

[0072] The present invention discloses a method and system for adjusting lower limb hip, knee and ankle rehabilitation equipment based on directional health identification. During the rehabilitation period, the device signal and video data are synchronously collected, and the first and second motion feature data are respectively analyzed and generated. An autoencoder is constructed, and after the feature data is reconstructed by dimensionality reduction, it is divided according to the motion cycle and the difference is periodically analyzed. The abnormal cycle is marked and the abnormal joints and limbs are located. According to the abnormal limb joints and the frequency of occurrence, a modular rehabilitation adjustment plan is formulated to suit different rehabilitation users. The present invention analyzes rehabilitation data by fusing the two dimensions of device signals and videos, accurately identifies abnormal motion states and motion characteristics during the rehabilitation process, realizes directional rehabilitation abnormality identification, provides a basis for personalized rehabilitation adjustment, and improves the rehabilitation effect.

[0073] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0074] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0075] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0076] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0077] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0078] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A method for adjusting lower limb hip, knee and ankle rehabilitation equipment based on directional health recognition, characterized in that: include: During a rehabilitation period, device signal data and video acquisition data are collected when the user is using the lower limb hip, knee and ankle rehabilitation equipment; The device signal data is analyzed based on the motion state to generate first motion feature data, and the device key point recognition and motion state analysis are performed based on the video acquisition data to generate second motion feature data; Constructing an autoencoder, and constructing a low-dimensional vector space based on a preset motion feature vector, and performing data dimension reduction and reconstruction on the first and second motion feature data respectively through the autoencoder to generate a first reconstructed feature and a second reconstructed feature; The rehabilitation time period is divided into multiple movement cycles, and the difference between the first reconstructed feature and the second reconstructed feature is periodically analyzed based on the Mahalanobis distance, and the abnormal movement cycle is marked by the difference; Through targeted identification and analysis of abnormal movement cycles, abnormal limb joint locations and abnormal frequency of occurrence are identified, and a modular rehabilitation and adjustment plan is formulated.

2. A method for adjusting lower limb hip, knee and ankle rehabilitation equipment based on directional health recognition according to claim 1, characterized in that: In a rehabilitation period, the device signal data and video acquisition data of the user in the process of using the lower limb hip, knee and ankle rehabilitation device are collected, specifically: The lower limb hip, knee and ankle rehabilitation equipment includes left and right hip joint modules, left and right knee joint modules, and electric stimulation modules; The device signal data is collected through various modules in the lower limb hip, knee and ankle rehabilitation equipment, and the video acquisition data is collected through the visual device.

3. The method for adjusting lower limb hip, knee and ankle rehabilitation equipment based on directional health recognition according to claim 1, characterized in that: The first motion characteristic data is specifically: Perform data analysis on the device signal data based on the motion state, and convert the device signal data into device motion data; According to the device motion data, the device motion parameter characteristics are calculated in three dimensions: motion angle, motion amplitude, and motion speed, and first motion characteristic data is generated.

4. The method for adjusting lower limb hip, knee and ankle rehabilitation equipment based on directional health recognition according to claim 1, characterized in that: The second motion characteristic data is specifically: Extract key frames from video acquisition data to generate key image sets; The limb joint images of the lower limb hip, knee and ankle rehabilitation equipment are used as target detection objects, and a target detection model based on image recognition is trained; Through the target detection model, the limb joints are identified and located in the key image set. Combined with the image frame information, the device motion parameter characteristics are calculated in three dimensions: motion angle, motion amplitude, and motion speed to generate the second motion feature data.

5. The method for adjusting lower limb hip, knee and ankle rehabilitation equipment based on directional health recognition according to claim 1, characterized in that: The autoencoder is constructed, and a low-dimensional vector space is constructed based on a preset motion feature vector, and the first and second motion feature data are respectively reduced in dimension and reconstructed by the autoencoder to generate a first reconstructed feature and a second reconstructed feature, specifically: Based on the rehabilitation exercise plan, corresponding preset motion characteristic data and data value limit range information are set for each module of the lower limb hip, knee and ankle rehabilitation equipment; The preset motion characteristic data includes motion characteristic data corresponding to each rehabilitation stage; Vectorize the preset motion feature data, and set a low-dimensional vector space in combination with the value limit range information; Based on the autoencoder, the first and second motion feature data are respectively mapped into a low-dimensional vector space to generate corresponding low-dimensional representation data; The low-dimensional representation data is reconstructed, and a first reconstructed feature and a second reconstructed feature are generated accordingly.

6. The method for adjusting lower limb hip, knee and ankle rehabilitation equipment based on directional health recognition according to claim 1, characterized in that: The rehabilitation time period is divided into a plurality of movement cycles, and the difference between the first reconstructed feature and the second reconstructed feature is periodically analyzed based on the Mahalanobis distance, and the abnormal movement cycle is marked by the difference, specifically: Based on preset intervals, the rehabilitation time period is divided into multiple exercise cycles; In a motion cycle, the difference between the first reconstructed feature and the second reconstructed feature is calculated based on the Mahalanobis distance, and if the difference is within a preset abnormal value range, the motion cycle is marked as an abnormal motion cycle; Analyze all motion cycles and perform abnormal cycle analysis and marking.

7. The method for adjusting lower limb hip, knee and ankle rehabilitation equipment based on directional health recognition according to claim 1, characterized in that: The abnormal limb joint locations and abnormal frequencies are identified and analyzed through abnormal movement cycles, and a modular rehabilitation adjustment plan is formulated, specifically: According to the abnormal movement cycle, the operation status of each module of the lower limb hip, knee and ankle rehabilitation equipment is analyzed from the equipment signal data, and the abnormal limb joint parts are marked; Analyze all abnormal movement cycles, calculate the frequency of abnormal movement of abnormal limb joints, and obtain the frequency of abnormal occurrence; Combine abnormal limb joints with abnormal frequencies within the same preset frequency range to obtain a lower limb rehabilitation combination, and formulate a modular rehabilitation plan based on the lower limb rehabilitation combination; The modular rehabilitation program includes a combination of one or more sub-modules and rehabilitation plan data.

8. A lower limb hip, knee and ankle rehabilitation equipment adjustment system based on directional health recognition, characterized in that: The system includes: a memory and a processor, wherein the memory includes a lower limb hip, knee and ankle rehabilitation equipment adjustment program based on directional health recognition, and the lower limb hip, knee and ankle rehabilitation equipment adjustment program based on directional health recognition is executed by the processor to implement the following steps: During a rehabilitation period, device signal data and video acquisition data are collected when the user is using the lower limb hip, knee and ankle rehabilitation equipment; The device signal data is analyzed based on the motion state to generate first motion feature data, and the device key point recognition and motion state analysis are performed based on the video acquisition data to generate second motion feature data; Constructing an autoencoder, and constructing a low-dimensional vector space based on a preset motion feature vector, and performing data dimension reduction and reconstruction on the first and second motion feature data respectively through the autoencoder to generate a first reconstructed feature and a second reconstructed feature; The rehabilitation time period is divided into multiple movement cycles, and the difference between the first reconstructed feature and the second reconstructed feature is periodically analyzed based on the Mahalanobis distance, and the abnormal movement cycle is marked by the difference; Through targeted identification and analysis of abnormal movement cycles, abnormal limb joint locations and abnormal frequency of occurrence are identified, and a modular rehabilitation and adjustment plan is formulated.

9. A lower limb hip, knee and ankle rehabilitation equipment adjustment system based on directional health recognition according to claim 8, characterized in that: In a rehabilitation period, the device signal data and video acquisition data of the user in the process of using the lower limb hip, knee and ankle rehabilitation device are collected, specifically: The lower limb hip, knee and ankle rehabilitation equipment includes left and right hip joint modules, left and right knee joint modules, and electric stimulation modules; The device signal data is collected through various modules in the lower limb hip, knee and ankle rehabilitation equipment, and the video acquisition data is collected through the visual device.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a lower limb hip, knee and ankle rehabilitation equipment adjustment program based on directional health identification. When the lower limb hip, knee and ankle rehabilitation equipment adjustment program based on directional health identification is executed by a processor, the steps of the lower limb hip, knee and ankle rehabilitation equipment adjustment method based on directional health identification as described in any one of claims 1 to 7 are implemented.

Images