79 results about "Muscle force" patented technology

The invention provides an intelligent wearable rehabilitation monitoring and evaluation device after anterior cruciate ligament injury, and relates to the technical field of exercise rehabilitation and intelligent medical monitoring, the device comprises a sensor acquisition module, a signal processing module, a compensation determination module, a difference determination module and an evaluation analysis module, a force-electricity coupling flexible sensor, an IMU and a pressure sensor, the method comprises the following steps: synchronously collecting a muscle force signal, a surface electromyogram signal, an attitude signal and a plantar pressure signal at the same position, performing dynamic filtering, confidence enhancement and personalized compensation processing, extracting a difference feature vector, inputting the difference feature vector into a muscle force prediction model, and outputting a quantitative evaluation result. The portable wearable long-term dynamic monitoring is realized, the core indexes of muscles, joints and gaits are covered in multiple dimensions, the assessment is accurate and real-time, the rehabilitation scheme can be optimized, the risk of re-injury is reduced, and the rehabilitation effect and compliance of a patient are improved.

The invention relates to the technical field of rehabilitation medical treatment, and discloses a muscle group stress analysis method and device, a terminal and a storage medium, and the method comprises the steps: respectively obtaining motion data collected by inertial measurement units arranged on the body of a user, and recognizing gait events based on the motion data corresponding to the inertial measurement units of the lower limbs, dividing the continuous motion data into a plurality of gait cycles according to the gait event; fusing the motion data acquired by each inertial measurement unit to obtain a three-dimensional posture of each preset segment of the body, and constructing a three-dimensional motion track of the spine area of the user in combination with a human kinematics chain model; processing the three-dimensional motion track and the known muscle group stress data by adopting a singular value decomposition embedding regression method to obtain a preliminary target muscle group stress curve of each gait cycle; and correcting the initial target muscle group stress curve based on a human body multi-rigid-body dynamic model in combination with a control cost function to obtain a final target muscle group stress curve.

The invention provides a patient rehabilitation tracking system, a rehabilitation training regulation and control method based on active perception and environment self-adaption, equipment and a medium, and the method comprises the steps: determining a cooperative motion state of a nerve-muscle-bone system according to a multi-modal physiological data flow of rehabilitation training tracking of a target patient; performing intention-muscle force cooperative identification based on the cooperative motion state to obtain motion intention and muscle force contribution distribution of the target patient; determining a dynamic risk map of the target patient during rehabilitation training; variable universe fuzzy reasoning is carried out on the motion intention, the muscle force contribution distribution and the dynamic risk map, and then a rehabilitation adjustment instruction matched with the rehabilitation state of the target patient is obtained; the rehabilitation progress of the target patient is continuously tracked, and the rehabilitation training robot is controlled to execute self-adaptive power-assisted compensation according to the rehabilitation adjustment instruction. By means of the scheme, motion intention decoding and muscle force contribution analysis can be conducted on rehabilitation training of the patient, and rehabilitation training regulation and control are conducted in combination with the dynamic environment risk.

The invention provides a muscular-bone rehabilitation posture correction method and system based on visual identification, and the method comprises the steps: firstly collecting the posture video data of the muscular-bone rehabilitation training of a rehabilitation object, and covering the joint movement, muscle contour change and body balance state change processes; analyzing the posture video data to generate joint movement tracks, muscle force application association and body balance state features, corresponding the joint movement tracks, the muscle force application association and the body balance state features to a preset muscle-bone rehabilitation stage target to establish a multi-dimensional adaptation relationship, and generating layered and staged correction guide information according to the multi-dimensional adaptation relationship, joint, muscle and balance adjustment layers are divided according to priorities, a specific adjustment mode is provided, new posture video data after adjustment is obtained, repeated operation is conducted, correction guide information is updated according to deviation changes, accurate and dynamic muscle-bone rehabilitation posture correction is achieved, and the rehabilitation effect and efficiency are improved.

The invention relates to the field of upper limb joint rehabilitation training, in particular to an upper limb joint rehabilitation training method and system based on an exoskeleton mechanical arm, and the method comprises the steps: collecting sEMG signals of a target muscle group of a user in real time in a training process; calculating the root mean square of the amplitude of the sEMG signal in the current time window; if the root mean square is smaller than a muscle force insufficient threshold value, a training mode is switched to a full-assistance mode; if the root mean square is not smaller than the muscle force insufficient threshold value and smaller than the normal muscle force threshold value, the training mode is switched to a semi-assistance mode; if the root mean square is larger than or equal to the normal muscle force threshold value, the training mode is switched to an anti-resistance training mode. The rehabilitation training effect of the upper limb joints can be effectively improved.

The invention relates to a gait monitoring algorithm which is used for a traditional four-foot walking aid, a six-axis gyroscope is installed in the middle of four feet of the walking aid, pressure sensor data is installed at the bottom of a handle and the bottoms of the four feet, and the gait monitoring algorithm comprises a sensor data acquisition module used for acquiring original sensor data related to gaits of a user, acquiring three-axis acceleration information; acquiring triaxial angular velocity information according to gyroscope sensor data; acquiring handle pressure and ground contact pressure information according to data of a pressure sensor; the gait feature extraction system is used for extracting gait features from original sensor data and comprises a gait feature extraction module used for extracting gait feature values from the original sensor data, the gait feature values comprise stride frequency, and the number of steps per second is calculated by analyzing periodic fluctuation of pressure or acceleration; and calculating the distance between the two steps through acceleration integration or the ground contact interval between the left foot and the right foot.

The invention provides a rehabilitation training feedback system and method. The method comprises the following steps: acquiring a surface electromyogram signal; a plurality of activation trend indexes are determined through the surface electromyogram signals, and then muscle force activation points of different muscle areas are extracted from the surface electromyogram signals according to all the activation trend indexes; performing collaborative analysis on the basis of a function collaborative relationship in combination with all muscle force activation points to obtain time sequence response tensors between all motion joints and corresponding muscle areas when motion responses are inconsistent; according to the joint angle information and the time sequence response tensor, constructing a functional coupling graph, and further performing kinematic chain simulation on a rehabilitation training process through the functional coupling graph to obtain a response consistency index; and performing feedback control on the rehabilitation training process of the patient according to the response consistency index in combination with a preset consistency threshold. By means of the scheme, feedback control can be conducted on rehabilitation training of the patient based on the space-time coupling relation between muscle group microstructure changes and mechanical conduction characteristics.

The invention relates to the technical field of health assessment, in particular to an orthopedic rehabilitation process real-time monitoring and assessment method, which comprises the following steps of: based on gait biomechanical parameters, identifying feature points, optimizing nodes in combination with body weight, stride frequency and stride change, extracting node correction parameter groups, analyzing muscle force change of knee joints and ankle joints, and evaluating the rehabilitation process of the orthopedics department. And combining the gait stability and the joint movement to obtain a correlation index proportion sequence. Parameters such as stride frequency, stride and body weight are combined with automatic recognition of feature points in a gait cycle, the time sequence sensitivity and individual adaptability of data are enhanced by dynamically correcting a feature point judgment standard, muscle force recovery and gait stability indexes are synchronously integrated and quantified in different stages, and the accuracy and the accuracy of gait recognition are improved. The linkage relation between the indexes can be adjusted according to real-time data, accurate tracking of a function recovery path is further supported, and the rehabilitation progress can be reflected by a dynamic structure of multi-dimensional parameters.

The invention relates to the technical field of medical instruments, in particular to a magnetic control pulse type pelvic floor nerve muscle stimulator and a parameter optimization system thereof. Comprising a host, a dynamic layered pulse waveform generation technology module, a multi-target reinforcement learning parameter optimization module, a multi-modal biofeedback fusion and VR enhancement module, and a flexible wearable stimulation array and ultrasonic targeting module. The system has the advantages that real-time data and deep learning are achieved, and personalized precise treatment is achieved, in the actual use process, the dynamic layered pulse waveform generation technology module predicts the requirements of muscles in the next stage through a deep learning model on the basis of pelvic floor electromyographic signals, pressure data and infrared thermal imaging which are collected in real time, and the treatment accuracy is improved. Dynamically generating a composite pulse waveform; the multi-objective reinforcement learning parameter optimization module constructs a'state-action-reward 'reinforcement learning framework, and takes patient treatment feedback, muscle force improvement, pain score and treatment compliance as reward signals.

The LNTPI is a surgical instrument used to cut through fibrotic and edematous tissue to define the natural tissue plane of dissection. After defining the natural tissue plane, it is designed to move or carefully insinuate tissues along these natural planes without cutting the tissue, so that targeted organs or parts thereof could be viewed and reached during laparoscopic procedures. The following features make the LNTPI unique compared to standard blunt dissectors used in laparoscopy: 1. The tip of the LNTPI is coarse and not smooth. The tip has diagonal, spiral ridges from the sides which are carried onto the tip converging as a single spiral at the center of the tip, creating a pattern resembling that of a screw; 2. The ridges of the LNTPI are comprised of asymmetrical triangular ridges with an acute angle at the apex that may be leaning along with or against the rotation of the spiral; 3. The tip of the LNTPI is made of tungsten carbide metal instead of stainless steel; 4. Dissection can be done in the usual up, down, left, and right motions as standard dissectors; 5. The side of the LNTPI can be used to "peel" tissue by using the ridges on its side combined with a twisting movement. This maneuver cannot be performed using standard dissectors; and 6. The tip of the LNTPI can perform circumferential dissection when used with a twisting movement causing it to engage tissue like a "drill" along the natural tissue plane. The ridges that converge into a single spiral at the tip of the invention appear like a screw and with the proper twisting movement have a similar effect on tissue. Because of the texture, design, and material used for the tip of the LNTPI, it has the following advantages over standard dissectors: The LNTPI can engage tissues more easily even if the tissues are slippery due to the presence of blood or fluids. The LNTPI can be used to engage tissues through a twisting motion which motion allows the tissues to be engaged in a specific manner that defines natural tissue dissection planes. The LNTPI can insinuate / "peel" tissue by using the side spiral ridges in combination with a twisting movement. The LNTPI can perform circumferential dissection by using the tip and the convergence of the spiral ridges at the center of the tip in combination with a twisting movement. The transfer of lateral shear force to the tissue at various angles (45, 90, and 180 degrees) when using the LNTPI is significantly higher whether the motion is by a sweeping motion or twisting of the instrument, allowing it to insinuate better than standard instruments, especially in a wet field. Hand movements needed in insinuating tissue using the LNTPI are different from the usual hand movements when using standard dissection instruments. The hand movements in using LNTPI require less muscular effort and repetitiveness, thus preventing muscle fatigue and repetitive use injury among surgeons. The instrument is reusable, as compared to dissectors that have fabric at the tip, which must be disposed of and replaced once the fabric tip fully absorbs the blood or other fluid in the wet tissue surface.

This invention relates to the interdisciplinary field of image recognition and intelligent medical technology, specifically disclosing a method for orthopedic rehabilitation movement recognition and assessment based on image recognition. This method acquires patient motion images using a non-invasive multi-view visual sensor, extracts the three-dimensional coordinates of key skeletal points, and constructs a parametric biomechanical digital twin model integrating joint range of motion, muscle force lines, and ligament tension mechanisms. The key point data is input into a graph neural network for posture recognition, and the digital twin model is simultaneously invoked for physical feasibility verification and posture correction. Finally, the spatiotemporal trajectory similarity is calculated using a standard rehabilitation movement template, generating a comprehensive assessment result including movement completion, safety level, and injury risk. This invention, through the above technical solution, improves the robustness, physiological rationality, and clinical safety of movement recognition.

The invention discloses novel rehabilitation medical knee assisting equipment, and relates to the technical field of medical rehabilitation equipment and disability assisting medicines.The novel rehabilitation medical knee assisting equipment comprises two knee fixing base plates, knee rotating connecting pieces are arranged on one sides of the two knee fixing base plates, and extension spring guide plates are arranged on one sides of the two knee rotating connecting pieces; one side of each extension spring guide disc is provided with a deep groove ball bearing, one end of each deep groove ball bearing is provided with an end face bearing, one side of each deep groove ball bearing is provided with a plurality of locknuts, and the other side of each deep groove ball bearing is provided with a plurality of first fastening screws. Extension spring positioning pin columns are arranged at the bottoms of the two knee fixing base plates and used for fixing the lower limbs, the user can adapt according to the actual muscle strength of the legs of the user according to the magnitude of knee bending force determined by the user, meanwhile, the used muscle strength can be reversely trained, and the training effect is good. And a certain rehabilitation training effect can be achieved on damaged muscular tissues.

The present invention relates to an orthodontic appliance and system for aligning the patient's teeth. It consists of a specially designed bracket with rounded edges and several guides or perforations around the wing, to which a special fastening system is applied. This method allows for treatment under a straight-wire orthodontic system with light forces and minimal friction between the archwires and the bracket. It promotes the physiological movement of the teeth on the alveolar bone and supporting tissues, maintaining a perfect balance between muscular forces and producing a more stable position in the alveolar bone.

The invention discloses a bone trabecular bionic implant, and relates to the field of bone trabecular bionic planting, the bone trabecular bionic implant comprises a bone trabecular bionic body, the lower end of the bone trabecular bionic body is fixedly connected with a fixed threaded part, and a reserved filling cavity is formed in the bone trabecular bionic body; an external threaded piece is arranged at the lower end of the bone trabecula bionic body. According to the bone trabecular bionic implant, the whole bone trabecular bionic body is made of a tantalum metal material, the tantalum metal has bone healing force and supporting strength, and the surface of the bone trabecular bionic body is of a porous structure, so that attachment and ingrowth of muscle fulcrums are facilitated, fulcrums are provided for long-term stability of nodules and muscles, exertion of muscle force is facilitated, and the bone trabecular bionic implant has a good application prospect. The bone trabecula bionic body is filled with gel biological factor substances through a reserved filling cavity, the bone trabecula bionic body is mainly applied to implant operation after femoral head necrosis in early and middle stages and drilling decompression, and other drugs can be plugged into micropores in the surface of the bone trabecula bionic body and are slowly released.

The application provides a muscle force prediction method under functional electrical stimulation, which can be applied to the field of electrical stimulation technology. The muscle force prediction method comprises the following steps: obtaining muscle fiber length information and muscle fiber velocity information of a target object; processing electrical stimulation parameters by using a neural activation model to obtain a neural activation value; the neural activation model represents the correlation between the predetermined electrical stimulation parameters and the predetermined neural activation value; the neural activation value represents the neural activation degree of the electrical stimulation parameters on the nerve; processing the neural activation value by using a muscle activation model to obtain a muscle activation value; the muscle activation model represents the correlation between the predetermined neural activation value and the predetermined muscle activation value; the muscle activation value represents the activation degree of the target muscle under the condition that the nerve of the target muscle is in the neural activation degree; processing the muscle fiber length information, the muscle fiber velocity information and the muscle activation value by using a muscle force prediction model to predict muscle force information of the target muscle.

The invention discloses a gait muscle force and activation real-time prediction method based on a physical constraint model, and belongs to the technical field of sports biomechanics and artificial intelligence. The method comprises the following steps: 1, inputting only hip, knee and ankle joint angles as input data; 2, a model backbone is a Transform; 3, multi-task loss constraint model training; 4, adjusting model parameters; and 5, calculating muscle activation. According to the invention, force and activation of multiple muscles can be output in real time only by inputting a joint angle sequence; the joint moment constraint is added in the loss, so that the prediction meets the biomechanical law, the precision, robustness and interpretability are considered, the traditional static optimization or dynamic optimization method can be replaced, and the process can be carried out in multiple scenes.

The postoperative muscle force rehabilitation detection system comprises a muscle sound sensing module, a wireless receiving module and an upper computer, the muscle sound sensing module comprises a vibration sensing module and a communication module, the communication module comprises a wireless transmitting module, and the wireless transmitting module is in signal connection with the wireless receiving module. And the wireless receiving module is electrically connected with the upper computer. According to the postoperative muscle strength rehabilitation detection system and method, through cooperative arrangement of the muscle sound sensing module, the wireless receiving module and the upper computer, noninvasive detection of human muscle strength is achieved, the influence of skin surface binding on muscle vibration is greatly reduced, and the postoperative muscle strength rehabilitation detection system and method have the advantages of being high in sensitivity and large in frequency response range.

The utility model belongs to the field of rehabilitation instruments, and particularly relates to a knee joint training device which comprises a supporting part, a plurality of roll shafts rotationally arranged on the supporting part, a transmission belt arranged on the roll shafts in a transmission mode and a foot fixing part arranged on the transmission belt. When a patient is in a supine position or a sitting position, during use, the bottoms of feet are placed on the transmission belts or the feet penetrate through the foot fixing parts to fix the feet, the patient bends and stretches the knees to enable the transmission belts to do annular movement, the muscle force and the joint movement range of the patient are increased, the patient can do active movement training, and the knee joint training device is simple in structure, convenient to use and high in practicability. The device is easy to carry, small in occupied area and convenient to use, and joints can move in a full range.

A method implemented on an electronic computing device for estimating a force potential of a muscle or muscle group is described. The method comprising: receiving an image of a patient, the image depicting at least a portion of a muscle or muscle group; segmenting the image of the patient to produce a segmented patient image, the segmented patient image comprising at least one segmented muscle or segmented muscle group; and estimating a muscle force potential for the segmented muscle or segmented muscle group, wherein the estimated muscle force potential is based at least partially on the segmented patient image.

The invention discloses a forearm motion posture recognition method based on flexible pressure and inertial sensing. The forearm motion posture recognition method comprises a recognition device used for obtaining inertial sensing data and muscle acting force signals of a forearm in a motion posture. Three-axis inertial motion data and muscle force signal data of the forearm of a human body are collected, after data preprocessing, kinematics features and muscle activation features are extracted from a time domain, a frequency domain and a space domain respectively, then the features are subjected to multi-level matching with a pre-constructed standard motion feature library, and a motion feature library is obtained. And finally, high-precision action recognition is realized through a decision-level fusion algorithm.

The invention provides a folding support frame for clinical seat balance training, and relates to the technical field of clinical medical treatment. Four adjusting legs are arranged at the bottom of the seat frame, and a mounting seat is fixedly mounted in the middle of the rear end of the top of the seat frame. The angle of the backrest frame can be flexibly adjusted according to the recovery condition of a patient and can be adjusted to 90 degrees to provide complete support during primary training, the inclination amplitude can be gradually adjusted along with muscle force increase of the patient, the patient is guided to actively exert force to maintain balance, transition from passive support to active training is achieved, and the training requirements of different recovery stages are met. The problems that although folding backrest chairs sold in the market at present can meet the supporting function, but the folding backrest chairs lack effective protection measures, and when patients in the early stage after operation and bedridden for a long time are subjected to sitting training, the patients slip off and even fall down from the bedside due to insufficient muscle force of the lower back are solved.

The invention discloses a real-time self-adaptive human musculoskeletal modeling and muscle force simulation system, and belongs to the field of computer vision. The system comprises a multi-sensor data acquisition module, a space-time calibration module, a three-dimensional force prediction module, a real-time modeling and parameter adjustment module, a muscle force simulation module and a data visualization module, and realizes space-time calibration fusion by acquiring and summarizing positions and pressure distribution data of human body joint points; a joint diagram structure and a body segment diagram structure are established, spatiotemporal features are obtained through feature extraction and fusion, three-dimensional foot hip bottom pressure is predicted, a human body musculoskeletal model containing a muscle geometric path is constructed, model parameters are optimized in real time, a joint objective function is established to calculate the muscle activation degree, and muscle force simulation is completed. According to the system provided by the invention, the connection between the muscle and the skeleton can be directly established, the individual adaptability is improved, the physiological rationality of muscle activation distribution is improved, and high-precision real-time muscle force simulation analysis is realized.

Methods and apparatus disclosed treat pain and mobility impairments by applying controlled subatmospheric pressure to skin over muscle tissue or joints during volitional muscle contractions against adaptive therapist resistance. Domes with basal openings sealing against skin perimeters, are evacuated to 13-90% of atmospheric pressure. Some embodiments have 3-10 second contraction intervals repeated at least three times per subatmospheric treatment cycle, before pressure is ramped to ambient pressure over at least 2 seconds. Results are improved range of motion, muscle strength, and pain reduction. Apparatus embodiments include vacuum manifolds, sensors for pressure and tissue distension, and optional integrated electrodes for performing TENS / STIM.

The utility model discloses a spine muscle force measuring device which comprises a support and a multi-gear height adjusting frame body arranged on the support. The measuring part is arranged on the front side of the multi-gear height adjusting frame body and is used for measuring the muscle force of the waist and neck of a measured person; the measuring part is composed of a sensing assembly and a contact module. According to the spine muscle measuring device, a tested person does neck and waist flexion and extension actions, the contact module is used as a contact point, the sensing assembly is used as a display unit and a counting unit of a standard value, and the standard times are used as a standard for judging muscle strength, so that the spine muscle measuring process of the tested person is realized, the operation is simple, and meanwhile, the multi-gear height adjusting frame body is convenient to use. The position of the contact module is further adjusted, and muscle force measurement of different postures is met.

The application belongs to the technical field of robots, and discloses a rehabilitation robot force perception network method and system based on dynamic weight fusion, which acquires original electromyography signals and original force signals, and respectively performs feature enhancement on the original electromyography signals and the original force signals by using a generative adversarial network; based on a muscle force grading adaptive mechanism, the original electromyography signals and the original force signals after feature enhancement are respectively fused to obtain a fused force perception value; by using an adaptive calibration mechanism and an adaptive compensation mechanism, the acquired temperature and humidity data and the calibration signals are processed to extract a baseline drift correction value and a temperature compensation coefficient, and the baseline drift correction value is input into the muscle force grading adaptive mechanism for optimization; by using a multi-scale feature fusion mechanism, the extracted fused force perception value and the temperature compensation coefficient are fused and processed to obtain fused multi-scale features. The application significantly improves the perception effect of patients with extremely weak muscle strength and spasm.

A muscle force assistance device and method are described. The disclosed device comprises: a first device worn on a portion of a user's body; a second device worn on another portion of the user's body; and a constant load generating part including a constant load spring device that is provided on the first device and applies a constant load to the second device, the method comprises the steps that the first device worn on a part of the body of the user applies a constant load to the second device worn on another part of the body of the user, a constant load generating portion provided on the first device applies a constant load to the user in response to a change in a relative distance between the first device and the second device or a change in a body shape according to a body movement of the user.

The invention discloses limb rehabilitation equipment, and belongs to the technical field of limb rehabilitation, a leg stretching assembly comprises two symmetrically arranged leg limiting cylinders, the top of a lifting plate is connected with two symmetrically arranged vertical fixing plates, one side of each vertical fixing plate is provided with a stroke groove, and the stroke groove is connected with the lifting plate. The side, close to the vertical fixing plate, of the leg limiting cylinder is connected with a stroke block, the stroke block is connected into the stroke groove in a sliding mode, and one end of the leg limiting cylinder is provided with a foot bottom bearing box used for bearing and attaching to the foot bottom of the patient. According to the invention, a patient with autonomous movement ability is allowed to actively bend knees to overcome the resistance of the adjustable spring for strength exercise; the acting force of the spring can be accurately adjusted according to the rehabilitation progress through the adjusting bolt, so that the muscle force requirements in different rehabilitation stages are met, on one hand, auxiliary rehabilitation training of the lower limbs of paralyzed patients is achieved, blood circulation of the lower limbs of the patients is promoted, and on the other hand, progressive muscle force improvement of active training patients is met.

The invention relates to the field of medical health monitoring, in particular to a chronic respiratory disease patient muscle health intelligent monitoring and intervention system which comprises a multi-dimensional time-frequency impedance analysis monitoring module, a respiration-movement cooperative training device module and a nutrition management platform. Performing time-frequency domain analysis on the signals by using multi-scale wavelet decomposition, and extracting muscle function characteristic parameters; quantitative evaluation of a respiratory muscle and intestinal muscle collaborative function is realized through phase synchronization analysis, a personalized baseline and a multi-stage early warning threshold are constructed, and early recognition of muscle dysfunction is realized; the training load and the training mode are dynamically adjusted according to the breathing muscle force percentage, and breathing training and swallowing muscle group training are combined; a personalized nutrition scheme is formulated based on muscle function parameters and metabolic states, the system achieves multi-dimensional evaluation of respiratory muscle and intestinal muscle functions, the function degradation trend is found 2-4 weeks ahead of time, and the training effect is improved by about 35%.

The invention relates to the cross technical field of artificial intelligence, digital twinning, biomechanics and the like, in particular to an AI Agent construction method based on motion digital twinning and deep motion data analysis, and the method comprises the following steps: collecting motion data of a user, calculating joint angles and displacements at each moment, calculating moments borne by joints, and obtaining motion data of the user; then, the activation degree and muscle force of each muscle in the model at each moment are solved by taking the minimum muscle activation quadratic sum as a target, then heel landing and tiptoe off-ground events are recognized, a feature time sequence is obtained, distance features with training set samples are calculated and embedded into a target low-dimensional space, and embedded features are obtained; and generating personalized feedback information according to the embedded features. Therefore, the problems that in the prior art, only a displacement-time sequence can be observed in a real scene, external force information is lost, and fine labeling of a muscle layer is scarce, so that driving mechanical quantity is difficult to recover, evaluation cannot be explained, and engineering landing is difficult are solved.

The application provides an exoskeleton robot control method, system, controller and storage medium, and relates to the technical field of exoskeleton robots. The method comprises the following steps: obtaining a deformation variable of a human muscle group; inputting the deformation variable into an intention recognition model to obtain an action intention of the human body output by the intention recognition model; inputting the deformation variable into a muscle force mapping model to obtain muscle force of the muscle group output by the muscle force mapping model; determining a control instruction of each joint of the exoskeleton robot based on the action intention and the muscle force of the muscle group; wherein the intention recognition model is obtained by training based on sample data of the deformation variable of the human muscle group and sample data of the action intention of the human body; and the muscle force mapping model is obtained by training based on sample data of the deformation variable of the human muscle group and sample data of the muscle force of the muscle group. In the control process, both the active force provided by the muscle force of the human muscle group and the action intention of the human body are considered, so that the exoskeleton robot adjusts the provided auxiliary force according to the high and low active force of the human body to automatically adapt to the change of the muscle force of the user.