Rehabilitation system and method based on virtual reality

Abstract

The invention provides a rehabilitation system and method based on virtual reality, and the method comprises the steps: carrying out the posture node recognition of a simulation posture and an actual posture of a patient based on a bidirectional association rule, and determining an interaction identifier of the patient in a virtual reality interaction behavior; extracting behavior characteristics of stress behaviors of the target patient and other patients in virtual reality interaction from the electromyographic signals of rehabilitation training, and performing confidence association on all the behavior characteristics to obtain association state quantities of the stress behaviors; determining the difference degree of interaction responses of virtual reality interaction in rehabilitation training of the target patient and other patients through the interaction identifier and the associated state quantity; according to the difference degree of the interaction response and the current rehabilitation index of the target patient, an execution instruction of the virtual reality equipment is predicted and generated, and then the virtual reality equipment executes the execution instruction to guide rehabilitation actions. By adopting the scheme of the invention, dynamic adaptive adjustment of individualized guide requirements in rehabilitation training can be realized, so that the adaptability of rehabilitation training intensity is improved.

Description

Technical Field

[0001] The present application relates to the field of virtual reality technology, and more specifically, to a rehabilitation system and method based on virtual reality. Background Art

[0002] Virtual Reality (VR) helps patients perform rehabilitation exercises in a safe and controllable virtual scene by providing an immersive and interactive environment in rehabilitation training, thereby improving motor function and rehabilitation effects. VR can simulate various scenes and tasks to help patients complete repeated action exercises in a virtual environment, which helps to restore coordination, balance and muscle strength. In addition, the real-time feedback function of VR technology can enhance patients' sense of participation and enthusiasm, bringing new improvements to the boredom and monotony of traditional rehabilitation training.

[0003] Patients' rehabilitation needs vary significantly due to their condition, physical function and rehabilitation progress, and VR rehabilitation systems find it difficult to adjust training intensity in real time to adapt to individualized guidance needs. In existing technologies, traditional rehabilitation VR systems are usually based on preset training modules and lack the ability to adjust to patients' real-time status. They are unable to dynamically optimize training plans based on patients' rehabilitation feedback at any time. Furthermore, traditional rehabilitation VR systems lack real-time adaptation to efficient data processing and dynamic feedback mechanisms, making it difficult to ensure the smoothness of patients' rehabilitation training process, resulting in poor patient rehabilitation training experience and even affecting rehabilitation effects. Therefore, how to achieve dynamic adaptive adjustment of individualized guidance needs in rehabilitation training, thereby improving the adaptability of rehabilitation training intensity, has become a difficult problem faced by the industry. Summary of the invention

[0004] The present application provides a rehabilitation system and method based on virtual reality, which can realize dynamic adaptive adjustment of individualized guidance needs in rehabilitation training, thereby improving the adaptability of rehabilitation training intensity.

[0005] In a first aspect, the present application provides a rehabilitation training method based on virtual reality, comprising the following steps: Collect the simulated posture and actual posture of all patients in rehabilitation training from the virtual reality device; Performing posture node recognition on the simulated posture and the actual posture of each patient based on a bidirectional association rule, thereby determining an interaction identifier of each patient in the virtual reality interaction behavior; Detect the electromyographic signals of the target patient and other patients in rehabilitation training, and then extract the behavioral characteristics of the stress behaviors of the target patient and other patients in virtual reality interaction, perform confidence association on the behavioral characteristics of all stress behaviors, and obtain the associated state quantity of the stress behaviors of the target patient and other patients in rehabilitation training; Matching the rehabilitation training behaviors of the target patient with those of other patients through all the interaction identifiers and the associated state quantities, and obtaining the difference degree of interaction response of the target patient with other patients in the virtual reality interaction during rehabilitation training; When the target patient uses the virtual reality device for rehabilitation training, an execution instruction of the virtual reality device is generated based on the target patient's current rehabilitation index and the difference degree of the interactive response, and then the virtual reality device executes the execution instruction to guide the rehabilitation action.

[0006] Preferably, performing posture node recognition on the simulated posture and the actual posture of each patient based on the bidirectional association rule, and then determining the interaction identifier of each patient in the virtual reality interaction behavior specifically includes: For each patient, feature recognition is performed on key posture nodes in the patient's simulated posture and actual posture to obtain simulated node features and actual node features; Using a bidirectional association rule algorithm to match the simulated node features with the actual node features, and identifying the deviation position and deviation degree between the node features; The interaction mark of the patient in the virtual reality interaction behavior is determined by the deviation position and the deviation degree.

[0007] Preferably, extracting the behavioral characteristics of stress behaviors of the target patient and other patients in virtual reality interaction specifically includes: For each patient, the electromyographic signal of the patient during rehabilitation training is obtained; The electromyographic signal is smoothed by using a bandpass filter to obtain an electromyographic signal after removing motion artifacts; Performing time domain feature extraction and frequency domain feature extraction on the electromyographic signal after removing the motion artifacts to obtain behavioral time domain features and behavioral frequency domain features; The behavioral characteristics of the patient's stress behavior in virtual reality interaction are determined through the behavioral time domain characteristics and the behavioral frequency domain characteristics.

[0008] Preferably, confidence association is performed on the behavioral characteristics of all stress behaviors to obtain the associated state quantity of the stress behaviors of the target patient and other patients during rehabilitation training, which specifically includes: Correlate and match the behavioral characteristics of the target patient with the behavioral characteristics of all other patients to obtain a correlation matching degree; The correlation matching degree is confidence modified by the average score of the current rehabilitation action to obtain the correlation state quantity of the stress behavior of the target patient and other patients in rehabilitation training.

[0009] Preferably, generating an execution instruction of the virtual reality device based on the target patient's current rehabilitation index and the difference between the interactive responses specifically includes: Determining feedback parameters of a virtual reality device in rehabilitation training according to the difference in the interactive response; Determining initialization parameters of a virtual reality device in rehabilitation training according to the rehabilitation index; The rehabilitation training parameters of the target patient are predicted by the feedback parameters and the initialization parameters, and then the execution instructions of the virtual reality device are generated according to the rehabilitation training parameters.

[0010] Preferably, a surface electromyography sensor is used to detect electromyographic signals of the target patient and other patients during rehabilitation training.

[0011] Preferably, the virtual reality device is a VR head mounted device.

[0012] In a second aspect, the present application provides a rehabilitation system based on virtual reality, comprising: A collection module, used to collect the simulated postures and actual postures of all patients in rehabilitation training from the virtual reality device; A processing module, used for performing posture node recognition on the simulated posture and the actual posture of each patient based on a bidirectional association rule, and then determining an interaction identifier of each patient in the virtual reality interaction behavior; The processing module is also used to detect the electromyographic signals of the target patient and other patients in rehabilitation training, and then extract the behavioral characteristics of the stress behaviors of the target patient and other patients in virtual reality interaction, perform confidence association on the behavioral characteristics of all stress behaviors, and obtain the association state quantity of the stress behaviors of the target patient and other patients in rehabilitation training; The processing module is further used to match the target patient's rehabilitation training behaviors with other patients' behavior patterns through all the interaction identifiers and the associated state quantities, and obtain the difference degree of interaction response of the target patient with other patients in virtual reality interaction during rehabilitation training; The execution module is used to generate execution instructions for the virtual reality device based on the target patient's current rehabilitation index and the difference degree of the interactive response when the target patient uses the virtual reality device for rehabilitation training, and then the virtual reality device executes the execution instructions to guide the rehabilitation movements.

[0013] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory stores codes, and the processor is configured to obtain the codes and execute the above-mentioned virtual reality-based rehabilitation training method.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned virtual reality-based rehabilitation training method is implemented.

[0015] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects: In an embodiment of the present application, first, the simulated postures and actual postures of all patients in rehabilitation training are collected from a virtual reality device; posture node recognition is performed on the simulated posture and actual posture of each patient based on a bidirectional association rule, and then the interaction identifier of each patient in the virtual reality interaction behavior is determined; the electromyographic signals of the target patient and other patients in rehabilitation training are detected, and then the behavioral characteristics of the stress behaviors of the target patient and other patients in the virtual reality interaction are extracted, and the behavioral characteristics of all stress behaviors are confidence-associated to obtain the associated state quantity of the stress behaviors of the target patient and other patients in rehabilitation training; the rehabilitation training behaviors of the target patient and other patients are matched with behavioral patterns through all interaction identifiers and the associated state quantities to obtain the difference degree of interaction response of the target patient and other patients in the virtual reality interaction in rehabilitation training; when the target patient uses the virtual reality device for rehabilitation training, an execution instruction of the virtual reality device is generated based on the current rehabilitation index of the target patient and the difference degree of the interaction response, and then the virtual reality device executes the execution instruction to guide the rehabilitation action.

[0016] It can be seen that the present application determines the difference in interactive response between the target patient and other patients in virtual reality interaction during rehabilitation training through all interactive identifiers and associated state quantities, and generates an execution instruction of the virtual reality device based on the target patient's current rehabilitation index and the difference in interactive response prediction, and then the virtual reality device executes the execution instruction to guide rehabilitation movements; wherein, firstly, the posture node recognition of the patient's simulated posture and actual posture is performed based on the bidirectional association rule to obtain the patient's interactive behavior in virtual reality. The patient's actual behavioral performance in virtual reality interactive training can be identified through the interactive identifier, which can provide accurate data support for personalized guidance; then, by detecting the patient's electromyographic signal and extracting the stress behavior characteristics, the associated state quantities of different patients in stress behavior are further calculated by using the association analysis, and the stress response of different patients in training can be analyzed through the associated state quantities, and then the training intensity can be adaptively adjusted according to the same physiological feedback between patients; The difference in interactive responses between the target patient and other patients in virtual reality interaction during rehabilitation training is determined through all interactive identifiers and associated state quantities. The difference in interactive responses can be used to measure the degree of difference between the target patient's behavioral responses during rehabilitation training and other patients, and the degree of difference is used as a feedback correction parameter of the rehabilitation system. The dynamic adjustment capability based on the feedback correction parameter can make up for the deficiency that the training content and intensity in the traditional rehabilitation VR system are difficult to flexibly change. Finally, individualized rehabilitation training parameters are predicted based on the individual's rehabilitation index and the difference in interactive responses. The rehabilitation training parameters ensure the synchronous adjustment of the training content and the patient's rehabilitation process, avoiding the limitation of the rehabilitation effect due to excessive or insufficient training. Finally, the execution instructions of the virtual reality device are generated based on the rehabilitation training parameters, and the execution instructions are executed to guide the rehabilitation movements. In summary, the present application scheme can realize dynamic adaptive adjustment of individualized guidance needs in rehabilitation training, thereby improving the adaptability of rehabilitation training intensity. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is an exemplary flow chart of a rehabilitation training method based on virtual reality according to some embodiments of the present application; Figure 2 is a virtual reality logic diagram according to some embodiments of the present application; Figure 3 is a schematic diagram of a process for extracting behavioral features according to some embodiments of the present application; Figure 4 is a structural schematic diagram of a rehabilitation system based on virtual reality according to some embodiments of the present application; Figure 5 It is a structural schematic diagram of a computer device for implementing a rehabilitation training method based on virtual reality according to some embodiments of the present application. DETAILED DESCRIPTION

[0018] In order to better understand the technical solution of the present application, the technical solution of the present application will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0019] refer to Figure 1 , which is an exemplary flow chart of a rehabilitation training method based on virtual reality according to some embodiments of the present application. The rehabilitation training method 100 based on virtual reality mainly includes the following steps: In step 101, simulated postures and actual postures of all patients in rehabilitation training are collected from a virtual reality device.

[0020] In specific implementation, the simulated posture and actual posture of the patient in rehabilitation training can be collected through the sensors in the virtual reality device, the simulated posture refers to the action information data in the virtual environment, and the actual posture refers to the patient's limb movement data captured by the sensor device; it should be noted that the virtual reality device in this application is a VR head-mounted device, and in other embodiments, the virtual reality device can also be other devices, such as a somatosensory tracker, which is not limited here; it should also be noted that all patients in this application refer to all patients who use virtual reality devices for rehabilitation training within a period of time, and a period of time here refers to the time period corresponding to the current moment to the past 3.

[0021] In some embodiments, reference Figure 2 , which is a virtual reality logic diagram in some embodiments of the present application, and which shows the application logic flow of a virtual reality (VR) system, which aims to improve the effect of rehabilitation training through VR technology. The process starts with rehabilitation capacity analysis to determine whether the patient needs to use the VR system for rehabilitation training. If it is decided not to use VR, other strategies will be selected. If it is decided to use VR, the process will enter the preliminary analysis stage, including a detailed analysis of the patient's needs, content and environment to ensure that the design and implementation of the VR system can meet specific training goals. Then, the process enters the design and implementation stage, which is divided into two main parts: scenario development and effective implementation. In scenario development, content design, interaction design, experience design and reflective design are required. Effective implementation includes scenario analysis, introduction strategy, simulation exercises and retrospective reflection. These steps can ensure that the VR system can be correctly introduced and effectively used in the rehabilitation training process. Finally, the effect of the VR system is evaluated through qualitative analysis, quasi-experimental research and multimodal analysis. The whole process is a cycle, which means that after the result diagnosis, it may return to the preliminary analysis or design and implementation stage based on feedback to make necessary adjustments and improvements.

[0022] In step 102, posture nodes are identified for the simulated posture and actual posture of each patient based on a bidirectional association rule, thereby determining an interaction identifier of each patient in the virtual reality interaction behavior.

[0023] In some embodiments, performing posture node recognition on the simulated posture and actual posture of each patient based on the bidirectional association rule, and then determining the interaction identifier of each patient in the virtual reality interaction behavior can be implemented by the following steps: For each patient, feature recognition is performed on key posture nodes in the patient's simulated posture and actual posture to obtain simulated node features and actual node features; Using a bidirectional association rule algorithm to match the simulated node features with the actual node features, and identifying the deviation position and deviation degree between the node features; The interaction mark of the patient in the virtual reality interaction behavior is determined by the deviation position and the deviation degree.

[0024] In specific implementation, for each patient, first, the simulated posture and actual posture collected from the patient can be pre-smoothed, and then the smoothed simulated posture and actual posture can be converted into standard feature representations, such as joint angles, position coordinates, etc., and then the key posture nodes of the body (such as shoulders, elbows, knees, ankles, etc.) can be identified through the recognition model, and the node features at these key posture nodes can be extracted from the standard feature representation through the recognition model, and the set of node features extracted from the simulated posture is used as the simulated node features, and the set of node features extracted from the actual posture is used as the actual node features; then, the extracted simulated node features and actual node features are input into the bidirectional association rule algorithm for matching, so as to identify the deviation positions (such as shoulders, knee joints) and deviations between key nodes. The difference (such as angle difference, distance difference) can be detected through the bidirectional association rule algorithm, and the change trend of key nodes under different states (simulated state and actual state) can be identified, and the specific location and deviation amplitude of posture deviation can be identified. In the bidirectional association rule algorithm, the rule setting includes the angle, distance and other threshold settings between key nodes. For example, when the angle deviation of a joint exceeds a certain threshold, it is considered that the node has a deviation; finally, the position label of the location where the deviation occurs (such as shoulder, elbow, knee, etc.) can be given according to the identified deviation position, and then the degree of deviation (such as angle deviation exceeding 15 degrees) is given according to the preset rules. Grade labels, such as "slight deviation", "moderate deviation" and "severe deviation", are assigned, and then the set of position labels and grade labels is used as the patient's interaction identifier in virtual reality interactive behavior.

[0025] It should be noted that the interaction identifier in the present application is a performance identifier used to describe the deviation of the patient's interactive behavior during virtual interaction in rehabilitation training, which can provide a basis for subsequent personalized training adjustments and effect monitoring; in addition, the present application uses a bidirectional association rule algorithm to identify the behavioral deviations between simulated postures and actual postures, so that the rehabilitation system can specifically analyze the location and degree of deviations in the patient's rehabilitation movements. The generated interaction identifier provides a specific identifier for the patient's movement characteristics, which is helpful for the formulation of personalized rehabilitation training plans. In addition, through the accumulation of interaction identifiers, the rehabilitation system can gradually record and track the patient's rehabilitation progress, and adjust the training plan to gradually correct the deviation.

[0026] In step 103, the electromyographic signals of the target patient and other patients in rehabilitation training are detected, and then the behavioral characteristics of the stress behaviors of the target patient and other patients in virtual reality interaction are extracted, and the behavioral characteristics of all stress behaviors are confidence-associated to obtain the associated state quantity of the stress behaviors of the target patient and other patients in rehabilitation training.

[0027] It should be noted that electromyographic signal refers to the electrical signal generated during muscle contraction. It is a weak potential fluctuation detected by electrodes, which reflects the activity state of muscle fibers under nerve stimulation. In specific implementation, the detection of electromyographic signals of target patients and other patients in rehabilitation training can be achieved in the following way, namely: surface electromyographic sensors can be used to detect electromyographic signals of target patients and other patients in rehabilitation training. When using surface electromyographic sensors, they can be fixed on the surface of the patient's target muscle group (such as upper arms, legs, etc.). The specific muscle part of the target muscle group surface can be selected according to the rehabilitation training goal. Further, the surface electromyographic sensor can be used to detect the electromyographic signals of the target patient and other patients in rehabilitation training in real time according to a preset sampling frequency.

[0028] In some embodiments, reference Figure 3 As shown, this figure is a schematic diagram of the process of extracting behavioral features in some embodiments of the present application. In this embodiment, the behavioral features of the stress behaviors of the target patient and other patients in the virtual reality interaction can be extracted by the following steps: In step 1031, for each patient, the electromyographic signal of the patient during rehabilitation training is obtained; In step 1032, the electromyographic signal is smoothed by using a bandpass filter to obtain an electromyographic signal after removing motion artifacts; In step 1033, time domain feature extraction and frequency domain feature extraction are performed on the electromyographic signal after the motion artifacts are removed to obtain behavioral time domain features and behavioral frequency domain features; In step 1034, the behavioral characteristics of the patient's stress behavior in the virtual reality interaction are determined by using the behavioral time domain characteristics and the behavioral frequency domain characteristics.

[0029] In the specific implementation, first, for each patient, the electromyographic signal of the patient in rehabilitation training is obtained by the method of the aforementioned embodiment, and then a suitable bandpass filter is selected according to the frequency range of the electromyographic signal. Usually, the effective frequency range of the electromyographic signal is 10Hz to 500Hz, so the bandpass range of the filter can be set to 10Hz to 500Hz, and then the bandpass filter is used to process the electromyographic signal to remove low-frequency noise (such as motion artifacts) in the signal to obtain the electromyographic signal after the motion artifacts are removed; then, time domain feature extraction is performed on the electromyographic signal after the motion artifacts are removed, and the changes of the electromyographic signal in the time dimension are analyzed. The behavioral time domain features are mainly used to describe the intensity and waveform characteristics of muscle activity, and can reflect the intensity of stress. In the embodiment of the present application, the behavioral time domain features include root mean square value and average absolute value. Through these time domain features, the contraction intensity and activity frequency of the muscle can be described, providing basic data for the identification of stress behavior, and then the power spectrum density of the electromyographic signal is used as the behavioral frequency domain feature; finally, the behavioral time domain features (such as root mean square value and average absolute value) and the behavioral frequency domain features (such as power spectrum density) are combined to form a multidimensional feature vector, which is used as the behavioral feature of the patient's stress behavior in virtual reality interaction. The behavioral features can comprehensively reflect the stress state of the muscle. Through the above method, the behavioral characteristics of the stress behavior of the target patient and other patients in virtual reality interaction can be obtained.

[0030] In some embodiments, confidence association is performed on the behavioral features of all stress behaviors to obtain the associated state quantity of the stress behaviors of the target patient and other patients during rehabilitation training, which can be achieved by the following steps: Correlate and match the behavioral characteristics of the target patient with the behavioral characteristics of all other patients to obtain a correlation matching degree; The correlation matching degree is confidence modified by the average score of the current rehabilitation action to obtain the correlation state quantity of the stress behavior of the target patient and other patients in rehabilitation training.

[0031] In specific implementation, first, the behavioral characteristics of the target patient are matched with the behavioral characteristics of each other patient to evaluate the similarity between the target patient's stress behavior in the rehabilitation action and that of others, and the quantified value of the similarity (such as the Euclidean distance) is used as the matching degree of the target patient and each other patient. The matching degree of the target patient and all other patients can be obtained by the above method, and then the average degree value of all matching degrees is used as the associated matching degree; then, the average score of each rehabilitation action is obtained from the system, and the average score represents the average completion quality of the rehabilitation action. Further, a confidence correction model is initialized, and the associated matching degree is combined with the average score of the current rehabilitation action through the confidence correction model to adjust the confidence of the matching result. For example, if the average score is greater than a preset first threshold, it means that most patients have a low stress level in the action, so the confidence of the associated matching degree is reduced. If the average score is less than a preset second threshold, the confidence of the associated matching degree is increased to reflect that the action is more challenging. Finally, the product of the associated matching degree and the confidence degree is used as the associated state quantity of the stress behavior of the target patient and other patients in rehabilitation training.

[0032] It should be noted that the association state quantity of stress behavior in the present application is an indicator to measure the degree of difference in the association between the target patient and other patients' stress behaviors; in addition, the present application adopts a dynamic matching update mechanism. During the rehabilitation training process, as the patient's stress behavior changes in real time, the rehabilitation system needs to recalculate the association matching degree to ensure that its matching degree is timely.

[0033] It should also be noted that in the present application, by analyzing the patient's stress behavior characteristics through electromyographic signals, the patient's physiological stress and muscle load during training can be evaluated, thereby avoiding potential risks caused by overtraining or stress response. At the same time, the calculation of the associated state quantity enables the patient's stress behavior characteristics to be compared with others, which can help identify and correct abnormalities in the patient's movements and stress responses.

[0034] In step 104, the target patient and other patients' rehabilitation training behaviors are matched with each other through all the interaction identifiers and the associated state quantities to obtain the difference in the interaction response of the target patient and other patients in the virtual reality interaction during rehabilitation training.

[0035] In some embodiments, the following steps may be used to match the behavior patterns of the rehabilitation training behaviors of the target patient and other patients through all the interaction identifiers and the associated state quantities to obtain the difference in the interaction responses of the target patient and other patients in the virtual reality interaction during rehabilitation training: Extract the target patient's interaction identifiers in the virtual reality interaction behavior; Cluster all interaction identifiers to obtain behavior clusters at different levels; The best matching behavior cluster is selected based on the similarity between the target patient's interaction identifier and each behavior cluster; Performing coupling compensation on the credibility of the optimal matching behavior cluster according to the associated state quantity to obtain the behavior credibility of the optimal matching behavior cluster; The difference in the interactive response of the target patient and other patients in virtual reality interaction during rehabilitation training is determined by the behavioral credibility of the optimal matching behavior cluster and the interactive identification of the target patient.

[0036] It should be noted that the aforementioned embodiment method can be used to extract the interaction identifier of the target patient in the virtual reality interaction behavior, which will not be described in detail here.

[0037] In specific implementation, clustering all interaction identifiers to obtain behavior clusters of different levels can be implemented in the following manner, namely: a K-means clustering algorithm can be used to cluster all interaction identifiers, and all similar interaction identifiers can be divided into one cluster, and all obtained clusters are used as behavior clusters, each behavior cluster represents a specific type of rehabilitation deviation state (i.e., the degree of deviation between virtual and reality is different); selecting the best matching behavior cluster according to the similarity between the target patient's interaction identifier and each behavior cluster can be implemented in the following manner, namely: firstly calculating the average similarity between the target patient's interaction identifier and all interaction identifiers in each behavior cluster, and then taking the behavior cluster corresponding to the maximum average similarity as the best matching behavior cluster; coupling compensation is performed on the credibility of the best matching behavior cluster according to the associated state quantity, and the behavior credibility of the best matching behavior cluster can be obtained in the following manner, namely: the average deviation degree of the virtual reality interaction behavior corresponding to the best matching behavior cluster is obtained through the interaction identifier in the best matching behavior cluster, the inverse of the average deviation degree can be used as the credibility of the best matching behavior cluster, and then the product between the associated state quantity and the credibility of the best matching behavior cluster is used as the behavior credibility of the best matching behavior cluster.

[0038] Preferably, in the above embodiment, determining the difference between the target patient and other patients in the virtual reality interaction during rehabilitation training through the behavior credibility of the optimal matching behavior cluster and the interaction identifier of the target patient can be achieved by the following steps: Get all interaction identifiers in the best matching behavior cluster; Determine the average distance between the target patient's interaction identifier and all interaction identifiers in the best matching behavior cluster; The behavioral difference between the target patient and other patients is evaluated by the average distance and the behavioral credibility of the optimal matching behavior cluster, and the difference degree of interactive response of the target patient and other patients in virtual reality interaction during rehabilitation training is obtained.

[0039] In specific implementation, first, the aforementioned method can be used to obtain all the interaction identifiers in the optimal matching behavior cluster, then the Euclidean distance between the target patient's interaction identifier and each interaction identifier in the optimal matching behavior cluster can be calculated, and then the average of all Euclidean distances can be used as the average distance between the target patient's interaction identifier and all interaction identifiers in the optimal matching behavior cluster; finally, the product of the average distance and the behavior credibility of the optimal matching behavior cluster can be used as the difference in interaction response between the target patient and other patients in virtual reality interaction during rehabilitation training.

[0040] It should be noted that the difference in interactive response in this application is to measure the degree of difference between the target patient's interactive behavior response during rehabilitation training and that of other patients. It can provide a key feedback mechanism for the rehabilitation system, helping the rehabilitation system to adapt to the patient's ability level in real time and continuously optimize the training plan to make rehabilitation training more accurate and effective.

[0041] In step 105, when the target patient uses the virtual reality device for rehabilitation training, an execution instruction of the virtual reality device is generated based on the target patient's current rehabilitation index and the difference degree of the interactive response, and then the virtual reality device executes the execution instruction to guide the rehabilitation movement.

[0042] It should be noted that the rehabilitation index is a comprehensive indicator that reflects the patient's current physical rehabilitation status. The current rehabilitation index of the target patient can be obtained in the following way, namely: a pre-trained rehabilitation assessment model can be used to output the current rehabilitation index of the target patient. It should be noted that the rehabilitation assessment model in this application can be based on a convolutional neural network trained according to historical patients' motor performance data, stress behavior characteristics, and physiological signal data.

[0043] In some embodiments, the following steps may be used to generate an execution instruction of a virtual reality device based on the target patient's current rehabilitation index and the difference between the interactive responses: Determining feedback parameters of a virtual reality device in rehabilitation training according to the difference in the interactive response; Determining initialization parameters of a virtual reality device in rehabilitation training according to the rehabilitation index; The rehabilitation training parameters of the target patient are predicted by the feedback parameters and the initialization parameters, and then the execution instructions of the virtual reality device are generated according to the rehabilitation training parameters.

[0044] In the specific implementation, first, a rehabilitation training model is initialized, and the rehabilitation training model is a regression model based on a decision tree. The current rehabilitation index of the target patient can be used as the initialization parameter of the rehabilitation training model in the virtual reality device, and the difference in interactive response can be used as the feedback parameter of the rehabilitation training model in the virtual reality device. The rehabilitation training model corrects the predicted rehabilitation training movements in real time through the feedback parameters, which can improve the adaptability of the patient's rehabilitation training. The corrected rehabilitation training movements are then used as rehabilitation training parameters for the target patient, and the rehabilitation training parameters are converted into a data stream that can be understood by the VR device, and the data stream is used as the execution instruction of the virtual reality device.

[0045] It should be noted that the rehabilitation training parameters in this application refer to the training parameters set for patients during the rehabilitation training process, including specific movement types, training intensity, number of times, frequency, amplitude and speed.

[0046] It should also be noted that in the present application, the execution of the rehabilitation training parameters by the virtual reality device for rehabilitation movement guidance means that the virtual reality device executes the rehabilitation training parameters and uses a virtual character (NPC, Non-Player Character) in a virtual reality environment to demonstrate and guide rehabilitation movements, so as to help patients understand and imitate the correct training movements more intuitively.

[0047] On the other hand, in some embodiments, the present application provides a rehabilitation system based on virtual reality, referring to Figure 4 , which is a structural schematic diagram of a rehabilitation system based on virtual reality according to some embodiments of the present application. The rehabilitation system based on virtual reality 400 includes: an acquisition module 401, a processing module 402 and an execution module 403, which are described as follows: The acquisition module 401 in this application is mainly used to collect the simulated posture and actual posture of all patients in rehabilitation training from the virtual reality device; Processing module 402, in the present application, is used to perform posture node recognition on the simulated posture and actual posture of each patient based on a bidirectional association rule, and then determine the interaction identifier of each patient in the virtual reality interaction behavior; The processing module 402 in the present application is also used to detect the electromyographic signals of the target patient and other patients in rehabilitation training, and then extract the behavioral characteristics of the stress behaviors of the target patient and other patients in virtual reality interaction, perform confidence association on the behavioral characteristics of all stress behaviors, and obtain the association state quantity of the stress behaviors of the target patient and other patients in rehabilitation training; The processing module 402 in the present application is also used to match the target patient's rehabilitation training behaviors with other patients' behavior patterns through all the interaction identifiers and the associated state quantities, and obtain the difference degree of the interaction response of the target patient and other patients in the virtual reality interaction during rehabilitation training; Execution module 403. In the present application, execution module 403 is mainly used to generate execution instructions for the virtual reality device based on the target patient's current rehabilitation index and the difference prediction of the interactive response when the target patient uses the virtual reality device for rehabilitation training, and then the virtual reality device executes the execution instructions to guide the rehabilitation movements.

[0048] In addition, the present application also provides a computer device, which includes a memory and a processor, wherein the memory stores codes, and the processor is configured to obtain the codes and execute the above-mentioned virtual reality-based rehabilitation training method.

[0049] In some embodiments, reference Figure 5 , which is a schematic diagram of the structure of a computer device for implementing a rehabilitation training method based on virtual reality according to some embodiments of the present application. The rehabilitation training method based on virtual reality in the above embodiments can be Figure 5 The computer device 500 shown in the figure is implemented, and the computer device 500 includes at least one processor 501, a communication bus 502, a memory 503 and at least one communication interface 504.

[0050] The processor 501 may be a general-purpose central processing unit (CPU) or an application specific integrated circuit (ASIC).

[0051] The communication bus 502 may be used to transmit information between the above-mentioned components.

[0052] The memory 503 may be a read only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read only memory (EEPROM), a compact disc read only memory (CD ROM) or other optical disc storage, an optical disc storage (including a compressed optical disc, a laser disc, an optical disc, a digital versatile disc, a Blu-ray disc, etc.), a magnetic disk or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory 503 may exist independently and be connected to the processor 501 via the communication bus 502. The memory 503 may also be integrated with the processor 501.

[0053] The memory 503 is used to store the program code for executing the solution of the present application, and the execution is controlled by the processor 501. The processor 501 is used to execute the program code stored in the memory 503. The program code may include one or more software modules. The virtual reality-based rehabilitation training method in the above embodiment can be implemented by the processor 501 and one or more software modules in the program code in the memory 503.

[0054] The communication interface 504 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0055] In a specific implementation, as an embodiment, a computer device may include multiple processors, each of which may be a single-core (single CPU) processor or a multi-core (multi CPU) processor. The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0056] The above-mentioned computer device may be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device may be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device or an embedded device. The embodiment of the present application does not limit the type of computer device.

[0057] In addition, the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned virtual reality-based rehabilitation training method is implemented.

[0058] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0059] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A rehabilitation training method based on virtual reality, characterized in that: The steps include: Collect the simulated posture and actual posture of all patients in rehabilitation training from the virtual reality device; Performing posture node recognition on the simulated posture and the actual posture of each patient based on a bidirectional association rule, thereby determining an interaction identifier of each patient in the virtual reality interaction behavior; Detect the electromyographic signals of the target patient and other patients in rehabilitation training, and then extract the behavioral characteristics of the stress behaviors of the target patient and other patients in virtual reality interaction, perform confidence association on the behavioral characteristics of all stress behaviors, and obtain the associated state quantity of the stress behaviors of the target patient and other patients in rehabilitation training; Matching the rehabilitation training behaviors of the target patient with those of other patients through all the interaction identifiers and the associated state quantities, and obtaining the difference degree of interaction response of the target patient with other patients in the virtual reality interaction during rehabilitation training; When the target patient uses the virtual reality device for rehabilitation training, an execution instruction of the virtual reality device is generated based on the target patient's current rehabilitation index and the difference degree of the interactive response, and then the virtual reality device executes the execution instruction to guide the rehabilitation action.

2. The method according to claim 1, characterized in that Performing posture node recognition on the simulated posture and actual posture of each patient based on the bidirectional association rule, and then determining the interaction identifier of each patient in the virtual reality interaction behavior specifically includes: For each patient, feature recognition is performed on key posture nodes in the patient's simulated posture and actual posture to obtain simulated node features and actual node features; Using a bidirectional association rule algorithm to match the simulated node features with the actual node features, and identifying the deviation position and deviation degree between the node features; The interaction mark of the patient in the virtual reality interaction behavior is determined by the deviation position and the deviation degree.

3. The method according to claim 1, characterized in that The behavioral characteristics of the target patient and other patients' stress behaviors in virtual reality interaction are extracted specifically including: For each patient, the electromyographic signal of the patient during rehabilitation training is obtained; The electromyographic signal is smoothed by using a bandpass filter to obtain an electromyographic signal after removing motion artifacts; Performing time domain feature extraction and frequency domain feature extraction on the electromyographic signal after removing the motion artifacts to obtain behavioral time domain features and behavioral frequency domain features; The behavioral characteristics of the patient's stress behavior in virtual reality interaction are determined through the behavioral time domain characteristics and the behavioral frequency domain characteristics.

4. The method according to claim 1, characterized in that The behavioral characteristics of all stress behaviors are associated with confidence, and the associated state quantities of the stress behaviors of the target patient and other patients during rehabilitation training are obtained, including: Correlate and match the behavioral characteristics of the target patient with the behavioral characteristics of all other patients to obtain a correlation matching degree; The correlation matching degree is confidence modified by the average score of the current rehabilitation action to obtain the correlation state quantity of the stress behavior of the target patient and other patients in rehabilitation training.

5. The method according to claim 1, characterized in that Predicting and generating execution instructions for the virtual reality device based on the current rehabilitation index of the target patient and the difference between the interactive responses specifically includes: Determining feedback parameters of a virtual reality device in rehabilitation training according to the difference in the interactive response; Determining initialization parameters of a virtual reality device in rehabilitation training according to the rehabilitation index; The rehabilitation training parameters of the target patient are predicted by the feedback parameters and the initialization parameters, and then the execution instructions of the virtual reality device are generated according to the rehabilitation training parameters.

6. The method according to claim 1, characterized in that Surface electromyography sensors were used to detect the electromyographic signals of the target patient and other patients during rehabilitation training.

7. The method according to claim 1, characterized in that The virtual reality device is a virtual reality head mounted device.

8. A rehabilitation system based on virtual reality, characterized in that: include: A collection module, used to collect the simulated postures and actual postures of all patients in rehabilitation training from the virtual reality device; A processing module, used for performing posture node recognition on the simulated posture and the actual posture of each patient based on a bidirectional association rule, and then determining an interaction identifier of each patient in the virtual reality interaction behavior; The processing module is also used to detect the electromyographic signals of the target patient and other patients in rehabilitation training, and then extract the behavioral characteristics of the stress behaviors of the target patient and other patients in virtual reality interaction, perform confidence association on the behavioral characteristics of all stress behaviors, and obtain the association state quantity of the stress behaviors of the target patient and other patients in rehabilitation training; The processing module is further used to match the target patient's rehabilitation training behaviors with other patients' behavior patterns through all the interaction identifiers and the associated state quantities, and obtain the difference degree of interaction response of the target patient with other patients in virtual reality interaction during rehabilitation training; The execution module is used to generate execution instructions for the virtual reality device based on the target patient's current rehabilitation index and the difference degree of the interactive response when the target patient uses the virtual reality device for rehabilitation training, and then the virtual reality device executes the execution instructions to guide the rehabilitation movements.

9. A computer device, comprising a memory and a processor, wherein the memory stores a code, characterized in that: The processor is configured to obtain the code and execute the virtual reality-based rehabilitation training method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the virtual reality-based rehabilitation training method according to any one of claims 1 to 7 is implemented.

Images