Rehabilitation training method and device

Abstract

The invention discloses a rehabilitation training method and device, and relates to the technical field of medical treatment. Different training types are determined for patients with different illness states through the same rehabilitation training system, virtual-real combined rehabilitation training of training scenes is carried out, and limb training scenes and training interestingness of the patients are enriched. And meanwhile, video guidance and a mirror image posture correction process can be carried out through reference posture video data, so that the standard of rehabilitation training actions of the patient is improved, the illness recovery condition of the patient can be accurately evaluated according to the posture data, and the rehabilitation training efficiency and the rehabilitation training effect of the patient are greatly improved.

Description

Technical Field

[0001] The present invention relates to the field of medical technology, and particularly to a rehabilitation training method and device. Background Art

[0002] Some patients will temporarily lose or partially lose their limb motor ability due to the development of the disease. As the condition improves, they need to use some rehabilitation training equipment for training, aiming to help patients recover their limb functions. However, the training scenarios corresponding to the existing limb rehabilitation training equipment are relatively single. For example, patients can only simulate basic actions such as simple walking, flexion and extension, and grip stretching, and usually perform repetitive training in a single rehabilitation training environment such as a hospital. This can easily reduce the rehabilitation training efficiency and training effect of patients. Summary of the Invention

[0003] In view of the technical problem that the limb training scenarios of the current rehabilitation training equipment are relatively single and easily reduce the rehabilitation training efficiency and training effect of patients, the present invention is proposed to provide a rehabilitation training method and device that can overcome or at least partially solve the above problems.

[0004] Based on the first aspect of the present invention, a rehabilitation training method is provided, which is applied to a rehabilitation training system. The rehabilitation training system includes a server and a wearable terminal. The wearable terminal includes: a head-mounted display terminal, a hand wearable terminal, and a lower limb wearable terminal. The method includes:

[0005] Obtain patient information and determine the training type of the patient according to the patient information;

[0006] Determine at least one training scenario corresponding to the training type and obtain the reference pose video data associated with the training scenario;

[0007] Send the reference pose video data to the head-mounted display terminal so that the head-mounted display terminal displays the reference pose video data, enabling the target patient to perform rehabilitation training;

[0008] Receive rehabilitation training data, which is determined based on the wearable terminal;

[0009] Determine the mirror pose data of the target patient according to the rehabilitation training data, and send the mirror pose data to the head-mounted display terminal so that the head-mounted display terminal displays the mirror pose data;

[0010] Update the rehabilitation training data and evaluate the rehabilitation training score of the target patient according to the updated rehabilitation training data;

[0011] Generate training suggestions according to the rehabilitation training score, training type, and patient information, and send them to the head-mounted display terminal for display.

[0012] An optional invention content, the rehabilitation training data includes upper limb pose data and patient coordinate data, and determining the mirror pose data of the target patient according to the rehabilitation training data includes:

[0013] Perform a first coordinate transformation on the upper limb pose data to obtain mirror upper limb pose data;

[0014] According to a preset mirror distance, perform a second coordinate transformation on the patient coordinate data to obtain mirror patient coordinate data;

[0015] Combine the mirror upper limb pose data and the mirror patient coordinate data to obtain the mirror pose data of the target patient.

[0016] An optional invention content, the rehabilitation training data includes lower limb pose data and patient coordinate data, and determining the mirror pose data of the target patient according to the rehabilitation training data includes:

[0017] Perform a first coordinate transformation on the lower limb pose data to obtain mirror lower limb pose data;

[0018] According to a preset mirror distance, perform a second coordinate transformation on the patient coordinate data to obtain mirror patient coordinate data;

[0019] Combine the mirror lower limb pose data and the mirror patient coordinate data to obtain the mirror pose data of the target patient.

[0020] An optional invention content, evaluating the rehabilitation training score of the target patient according to the updated rehabilitation training data includes:

[0021] According to the updated rehabilitation training data, determine the pose completion scores of the target patient in each training scenario of the current training type;

[0022] According to the pose completion scores in all training scenarios and the training weight coefficients corresponding to each training scenario, determine the rehabilitation training score of the target patient.

[0023] An optional invention content, determining the pose completion scores of the target patient in each training scenario of the current training type according to the updated rehabilitation training data includes:

[0024] Intermittently separate the training pose data of the target patient from the updated rehabilitation training data, and determine the training pose images corresponding to each training pose data;

[0025] Calculate the image similarity values between multiple training pose images and the reference pose images corresponding to the reference pose video data respectively;

[0026] Arrange all the image similarity values in time sequence, and determine the image weight coefficients of the images associated with each image similarity value according to a preset weighting rule;

[0027] Determine the pose completion score of the target patient in the current training scenario based on the image similarity values and the image weight coefficients.

[0028] An optional invention content, the preset weighting rule at least includes:

[0029] Determine the corresponding default weight coefficients according to the image similarity values corresponding to each training pose image;

[0030] When the image similarity value at the previous position is greater than the image similarity value at the current position, reduce the default weight coefficient corresponding to the image similarity value at the current position by a first preset ratio to obtain the initial weight coefficient of the image associated with the image similarity value at the current position;

[0031] When the image similarity value at the previous position is less than the image similarity value at the current position, increase the default weight coefficient corresponding to the image similarity value at the current position by a second preset ratio to obtain the initial weight coefficient of the image associated with the image similarity value at the current position;

[0032] Perform statistical processing on the initial weight coefficients of all the image similarity values to obtain the image weight coefficients of the images associated with the image similarity values.

[0033] An optional invention content, the determining the rehabilitation training score of the target patient based on the pose completion scores in all training scenarios and the training weight coefficients corresponding to each training scenario includes:

[0034] The rehabilitation training score of the target patient can be calculated by the following formula:

[0035]

[0036] X ji =IF(T j1 +T ji +...+T jn =1,"T ji ","C ji );

[0037] C ji =(T ji -T jmin ) / (T jmax -T jmin );

[0038] Among them, F refers to the rehabilitation training score of the target patient, and G j refers to the training weight coefficient corresponding to the j-th training scenario among the K training scenarios corresponding to the current training type; S ji refers to the image similarity value of the image at the i-th position in the j-th training scenario; X ji refers to the image weight coefficient corresponding to the image similarity value of the image at the i-th position in the j-th training scenario; T ji refers to the initial weight coefficient corresponding to the image similarity value of the image at the i-th position in the j-th training scenario; C ji refers to the weighted weight coefficient of the image similarity value of the image at the i-th position in the j-th training scenario; T jmin refers to the minimum value among the initial weight coefficients corresponding to all image similarity values in the j-th training scenario; T jmax refers to the maximum value among the initial weight coefficients corresponding to all image similarity values in the j-th training scenario; n refers to the set number of training pose images included in each training scenario; The IF function is to execute the first item after the condition when the condition is satisfied, and execute the second item after the condition when the condition is not satisfied.

[0039] An optional aspect of the invention content, the method further includes a coefficient determination step for the training weight coefficient:

[0040] Send the coefficient-related data to the head-mounted display terminal so that the head-mounted display terminal displays the coefficient-related data;

[0041] Receive the coefficient operation data of the hand-worn terminal based on the coefficient-related data;

[0042] Based on the coefficient operation data, determine the training weight coefficients set by the target user for each training scenario corresponding to the current training type.

[0043] Based on the second aspect of the present invention, there is also provided a limb rehabilitation training device, which is applied to a rehabilitation training system. The rehabilitation training system includes a server and a wearable terminal. The wearable terminal includes: a head-mounted display terminal, a hand-worn terminal, and a lower limb wearable terminal. The device includes:

[0044] A patient information receiving module, configured to obtain patient information and determine the training type of the patient according to the patient information;

[0045] A reference data acquisition module, configured to determine at least one training scenario corresponding to the training type and acquire reference pose video data associated with the training scenario;

[0046] A reference data sending module, configured to send the reference pose video data to the head-mounted display terminal, so that the head-mounted display terminal displays the reference pose video data, enabling the target patient to perform rehabilitation training;

[0047] A training data receiving module, configured to receive rehabilitation training data, where the rehabilitation training data is determined based on the wearable terminal;

[0048] A mirror image data determining module, configured to determine the mirror pose data of the target patient according to the rehabilitation training data, and send the mirror pose data to the head-mounted display terminal, so that the head-mounted display terminal displays the mirror pose data;

[0049] A training evaluation module, configured to update the rehabilitation training data, and evaluate the rehabilitation training score of the target patient according to the updated rehabilitation training data;

[0050] A suggestion generating module, configured to generate training suggestions according to the rehabilitation training score, training type, and patient information, and send them to the head-mounted display terminal for display.

[0051] An optional invention content, where the rehabilitation training data includes upper limb pose data and patient coordinate data, and the mirror image data determining module includes:

[0052] A first mirror image sub-module, configured to perform a first coordinate transformation on the upper limb pose data to obtain mirror image upper limb pose data;

[0053] A second mirror image sub-module, configured to perform a second coordinate transformation on the patient coordinate data according to a preset mirror image distance to obtain mirror image patient coordinate data;

[0054] A mirror image data determining sub-module, configured to combine the mirror image upper limb pose data and the mirror image patient coordinate data to obtain the mirror pose data of the target patient.

[0055] Compared with the prior art, the present invention includes determining different training types for patients with different conditions through the same rehabilitation training system, and performing virtual-real combined rehabilitation training in different training scenarios, enriching the limb training scenarios and training interest of patients. At the same time, video guidance can be carried out through the reference pose video data, and the deviation correction process of the mirror image pose can improve the standardization of the rehabilitation training actions of patients, and the condition recovery of patients can be accurately evaluated according to the pose data, greatly improving the rehabilitation training efficiency and rehabilitation training effect of patients.

[0056] The above description is only an overview of the technical solution of the present invention. In order to understand the technical means of the present invention more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present invention more obvious and understandable, the specific embodiments of the present invention are specifically exemplified below. Brief Description of the Drawings

[0057] By reading the detailed description of the preferred embodiments below, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention. Moreover, throughout the drawings, the same reference numerals are used to represent the same components.

[0058] In the drawings:

[0059] Figure 1 is a schematic diagram of the system architecture of a rehabilitation training system provided by an embodiment of the present invention;

[0060] Figure 2 is a schematic diagram of the step flow of a rehabilitation training method provided by an embodiment of the present invention;

[0061] Figure 3 is a schematic diagram of the step flow of another rehabilitation training method provided by an embodiment of the present invention;

[0062] Figure 4 is a schematic diagram of the structure of a rehabilitation training device provided by an embodiment of the present invention. Detailed Embodiments

[0063] Hereinafter, exemplary embodiments of the present invention will be described in more detail with reference to the drawings. Although the exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided so that the present invention can be more thoroughly understood and the scope of the present invention can be completely conveyed to those skilled in the art.

[0064] All method embodiments in the embodiments of the present invention are applied to a rehabilitation training system. Refer to Figure 1As shown in the figure, the rehabilitation training system includes a server 101 and a wearable terminal 102. The wearable terminal includes: a head-mounted display terminal 1021, a hand wearable terminal 1022, and a lower limb wearable terminal 1023. Among them, the head-mounted display terminal device may include, but is not limited to, head-mounted devices such as head-mounted displays and mixed reality glasses. The hand wearable terminal device may include, but is not limited to, glove controllers, sensor bracelets, motion trackers, and hand training wearable devices, etc. The lower limb wearable terminal device may include, but is not limited to, sensor ankle rings, lower limb motion trackers, and lower limb training wearable devices, etc. Thus, through the wearable terminal device, the position information and posture information of the wearing user can be obtained.

[0065] Referring to Figure 2 , a rehabilitation training method provided by an embodiment of the present invention is shown. The method includes:

[0066] S201. Obtain patient information and determine the training type of the patient according to the patient information.

[0067] In the embodiment of the present invention, the patient information refers to personal relevant information of the patient, such as the patient's name, age, and condition, etc. The training type refers to the classification of rehabilitation training that the patient needs to do. In some embodiments, the training type may include, but is not limited to: joint range of motion training, muscle strength training, balance training, upper limb coordination training, lower limb coordination training, and gait training, etc.

[0068] In some embodiments, the patient information may be obtained by the wearable terminal device. For example, a code scanning device is integrated on the wearable terminal device. The code scanning device may be set on the head-mounted wearable terminal device or the hand wearable terminal device, so that the patient information can be obtained by scanning the medical barcode printed wristband through the code scanning device.

[0069] In other embodiments, the rehabilitation training system further includes an interaction terminal communicatively connected to the server. The interaction terminal device may also be integrated with a code scanning device and / or a card reading device, so that the patient information can be obtained by scanning the medical barcode printed wristband or the medical insurance electronic voucher through the code scanning device. Or, the patient information can be obtained by reading the card information of the electronic medical insurance card and the electronic medical record card through the card reading device.

[0070] When it is determined that the patient is a periarthritis of shoulder patient according to the patient information, the associated rehabilitation training type should be joint range of motion training. Thus, the training mapping relationship between different conditions and training types can be preset, so that after obtaining the patient information, the corresponding training type can be matched according to the training mapping relationship.

[0071] 202. Determine at least one training scenario corresponding to the training type, and obtain the reference pose video data associated with the training scenario.

[0072] In the embodiments of the present invention, for different training types, multiple training scenarios are usually set. For example, when the training type of the patient is range of motion training of joints, the corresponding rehabilitation training exercises may include: arm abduction training, arm adduction training, and arm rotation training, etc. Thus, each rehabilitation training exercise can be separately divided into a training scenario. By analogy, the reference pose video data of each training scenario can be obtained. Among them, the reference pose can be understood as the standard pose when a person without any diseases makes the rehabilitation training movement in this training scenario.

[0073] S203. Send the reference pose video data to the head-mounted display terminal, so that the head-mounted display terminal displays the reference pose video data, enabling the target patient to perform rehabilitation training.

[0074] S204. Receive the rehabilitation training data, where the rehabilitation training data is determined based on the wearable terminal.

[0075] In the embodiments of the present invention, the server sends the reference pose video data to the head-mounted display terminal. The head-mounted display terminal displays the reference pose video data associated with the training scenario, so that the target patient can perform rehabilitation training according to the reference pose in the reference pose video data. Among them, the target patient refers to the patient currently wearing the wearable terminal device.

[0076] During the rehabilitation training process, the rehabilitation training data is the relevant training data executed by the patient based on the head-mounted display terminal, the hand wearable terminal, and the lower limb wearable terminal. The rehabilitation training data at least includes the position information and pose information of the target patient. Thus, after the server receives the rehabilitation training data, it can determine whether the current rehabilitation training movement of the patient meets the standard based on the analysis of the rehabilitation training data, or evaluate the current condition recovery of the patient.

[0077] S205. Determine the mirror pose data of the target patient according to the rehabilitation training data, and send the mirror pose data to the head-mounted display terminal, so that the head-mounted display terminal displays the mirror pose data.

[0078] In the embodiments of the present invention, considering that when a patient performs rehabilitation training following a reference posture by himself / herself without being corrected by other personnel, the mirror pose data of the target patient can be determined through the rehabilitation training data. The mirror pose data refers to the data that is mirror-symmetrical to the current pose of the target patient. For example, the mirror pose data of the target patient can be obtained by converting the pose data in the rehabilitation training data.

[0079] After determining the mirror pose data, the server can also send it to the head-mounted display terminal. The mirror pose data is displayed on the head-mounted display terminal so that the user can correct their own rehabilitation training actions based on the reference pose and the mirror pose during the rehabilitation training process.

[0080] S206. Update the rehabilitation training data, and evaluate the rehabilitation training score of the target patient based on the updated rehabilitation training data.

[0081] S207. Generate a training suggestion based on the rehabilitation training score, training type, and patient information, and send it to the head-mounted display terminal for display.

[0082] In the embodiments of the present invention, since the rehabilitation training takes a long time, the rehabilitation training data can be updated regularly, and the rehabilitation training score of the target patient can be evaluated based on the updated rehabilitation training data. The rehabilitation training score can be determined based on the difference between the reference pose and the patient's pose during the rehabilitation training process. The rehabilitation training score can be used to represent the patient's condition recovery. Thus, after determining the rehabilitation training score, the server can generate corresponding training suggestions for the target patient in combination with the rehabilitation training score, training type, and patient information. For example, the training suggestion can include suggestions for the target patient's next rehabilitation training, such as the training type of the next rehabilitation training.

[0083] Therefore, different patients with different conditions can be subjected to virtual-real combined rehabilitation training in different scenarios through the same rehabilitation training system, thereby enriching the patient's limb training scenarios. Moreover, through video guidance and the correction process of the mirror pose, the standardization of the patient's rehabilitation training actions can be improved, and the patient's condition recovery can be accurately evaluated based on the pose data, greatly improving the efficiency and effect of the patient's rehabilitation training.

[0084] Referring to Figure 3 , another rehabilitation training method provided by the embodiments of the present invention is shown, and the method may include:

[0085] S301. Obtain patient information, and determine the training type of the patient based on the patient information.

[0086] S302. Determine at least one training scenario corresponding to the training type, and obtain reference pose video data associated with the training scenario.

[0087] S303. Send the reference pose video data to the head-mounted display terminal, so that the head-mounted display terminal displays the reference pose video data, enabling the target patient to perform rehabilitation training.

[0088] S304. Receive rehabilitation training data, where the rehabilitation training data is determined based on the wearable terminal.

[0089] In the embodiments of the present invention, for the description content of steps S301 - S304, refer to the description content of steps S201 - S204 above.

[0090] S305. Determine the mirror pose data of the target patient based on the rehabilitation training data, and send the mirror pose data to the head-mounted display terminal, so that the head-mounted display terminal displays the mirror pose data.

[0091] In the embodiments of the present invention, considering the situation where there is no other person to correct the patient during the rehabilitation training by following the reference pose by himself / herself, the mirror pose data of the target patient can be determined through the rehabilitation training data. Among them, the mirror pose data refers to the data that is mirror-symmetrical to the current pose of the target patient. For example, the mirror pose data of the target patient can be obtained by converting the pose data in the rehabilitation training data.

[0092] After the server determines the mirror pose data, it can also be sent to the head-mounted display terminal. The head-mounted display terminal displays the mirror pose data, so that the user can correct his / her own rehabilitation training actions based on the reference pose and the mirror pose during the rehabilitation training process.

[0093] During the rehabilitation training process of the patient's limbs, generally, the rehabilitation training is performed on the upper limbs alone, or on the lower limbs alone, or on both the upper and lower limbs simultaneously. Thus, in some embodiments, the rehabilitation training data may include upper limb pose data and patient coordinate data. Determining the mirror pose data of the target patient based on the rehabilitation training data includes:

[0094] Perform a first coordinate transformation on the upper limb pose data to obtain mirror upper limb pose data.

[0095] Perform a second coordinate transformation on the patient coordinate data according to a preset mirror distance to obtain mirror patient coordinate data.

[0096] Combining the mirror upper limb pose data and the mirror patient coordinate data, the mirror pose data of the target patient is obtained.

[0097] In the embodiments of the present invention, the first coordinate transformation can be understood as performing a first coordinate transformation on the upper limb pose data according to a preset mirror transformation matrix to obtain the mirror upper limb pose data. For example, the upper limb pose data may include key coordinates such as the coordinates of each finger of the hand and the coordinates of the arm joints that can characterize the upper limb pose distribution. For example, in a three-dimensional space coordinate, when the rehabilitation training pose of the target patient is symmetric with the mirror pose about the XZ plane (the plane formed by the X axis and the Z axis), the corresponding mirror transformation matrix can be

[0098] The preset mirror distance refers to the spatial distance between the preset observation pose and the patient himself. Thus, according to the preset mirror distance, a second coordinate transformation can be performed on the patient coordinate data to obtain the mirror patient coordinate data. Finally, by combining the mirror upper limb pose data and the mirror patient coordinate data, the mirror pose data of the target patient is obtained. For example, the preset mirror distance can be kept consistent with the reference mirror distance corresponding to the reference pose. Thus, the reference pose and the mirror pose can coincide, which can facilitate the patient to more clearly correct his own rehabilitation training actions and improve the training effect of the rehabilitation training movement.

[0099] In some other embodiments, the rehabilitation training data includes lower limb pose data and patient coordinate data. Determining the mirror pose data of the target patient according to the rehabilitation training data includes:

[0100] Performing a first coordinate transformation on the lower limb pose data to obtain the mirror lower limb pose data.

[0101] According to the preset mirror distance, performing a second coordinate transformation on the patient coordinate data to obtain the mirror patient coordinate data.

[0102] Combining the mirror lower limb pose data and the mirror patient coordinate data, the mirror pose data of the target patient is obtained.

[0103] In the embodiments of the present invention, for the description content of the method steps of determining the mirror pose data according to the lower limb pose data and the patient coordinate data, refer to the description content of determining the mirror pose data according to the upper limb pose data and the patient coordinate data above.

[0104] In a training scenario where the coordination between the upper limbs and the lower limbs needs to be involved, the rehabilitation training data may include upper limb pose data, lower limb pose data, and mirror pose data. Thus, the first coordinate transformation is respectively performed on the upper limb pose data and the lower limb pose data to obtain the corresponding mirror upper limb pose data and mirror lower limb pose data. Then, the mirror pose data of the target patient is determined according to the above steps.

[0105] S306. Determine the pose completion scores of the target patient in each training scenario of the current training type according to the updated rehabilitation training data.

[0106] In the embodiments of the present invention, since the rehabilitation training takes a long time and the patient needs to maintain a certain pose for a certain period of time during the rehabilitation training. Therefore, the rehabilitation training data can be updated regularly (or at a fixed time), and the pose completion scores of the target patient in each training scenario of the current training type can be determined according to the updated rehabilitation training data. Wherein, the pose completion score is used to characterize the degree of completion of the patient's current rehabilitation training action.

[0107] In some embodiments, the determining the pose completion scores of the target patient in each training scenario of the current training type according to the updated rehabilitation training data includes:

[0108] Separate the training pose data of the target patient from the updated rehabilitation training data at intervals, and determine the training pose images corresponding to the respective training pose data.

[0109] Calculate the image similarity values between multiple training pose images and the reference pose images corresponding to the reference pose video data respectively.

[0110] Arrange all the image similarity values in time sequence, and determine the image weight coefficients of the images associated with the respective image similarity values according to a preset weighting rule.

[0111] Determine the pose completion score of the target patient in the current training scenario according to the image similarity values and the image weight coefficients.

[0112] In an embodiment of the present invention, training pose data of a target patient is separated at intervals from the updated rehabilitation training data. Thus, a set of training poses for the patient to perform rehabilitation training according to the reference poses in the reference pose video data can be determined from multiple pieces of training pose data collected continuously in time sequence. And an image similarity value between each training pose image and the reference pose image corresponding to the reference pose video data at the corresponding moment can be determined according to time. In some embodiments, the image similarity value may be determined based on the proportion of the pixel points where the pose in the training pose image coincides with the pose area in the reference pose image when the training pose image and the reference pose image are superimposed (the ratio of the number of coincident pixel points to the number of pixel points occupied by the pose in the reference pose image). For example, if the proportion of the pixel points where the pose areas coincide is 85%, the corresponding image similarity value is 0.85, or 85.

[0113] The higher the image similarity value, the closer the training pose made by the patient is to the reference pose. For example, when the corresponding image similarity value reaches 0.95 or 95 during the patient's arm rotation training, it indicates that the patient's arm rotation function has recovered well and is close to the fully recovered state. By arranging the image similarity values in time sequence, the limb recovery situation of the target patient can be determined through the set of image similarity values.

[0114] The preset weighting rule can be understood as a relevant rule that stipulates the image weight coefficients corresponding to different training pose images arranged in time sequence. Thus, the image weight coefficients corresponding to each image similarity value are determined according to the preset weighting rule. The image weight coefficient is used to represent the probability that the target patient is close to the reference pose in the subsequent rehabilitation training process after this training pose.

[0115] Thus, the pose completion score of the target patient in the current training scenario can be determined by combining the image similarity value and the image weight coefficient. For example, multiplying the image similarity value and the image weight coefficient corresponding to the same training pose image can obtain the pose completion score associated with this training pose image. And so on, by accumulating and then averaging the pose completion scores associated with all training pose images, the pose completion score of the target patient in the current training scenario is obtained. Among them, the pose completion score in the current training scenario can be used to evaluate the completion situation of the user's rehabilitation training actions in this training scenario.

[0116] In an optional embodiment of the invention, the preset weighting rule at least includes:

[0117] Determining the corresponding default weight coefficient according to the image similarity value corresponding to each training pose image;

[0118] When the image similarity value at the previous position is greater than the image similarity value at the current position, the default weight coefficient corresponding to the image similarity value at the current position is decreased by a first preset ratio to obtain the initial weight coefficient of the image associated with the image similarity value at the current position.

[0119] When the image similarity value at the previous position is less than the image similarity value at the current position, the default weight coefficient corresponding to the image similarity value at the current position is increased by a second preset ratio to obtain the initial weight coefficient of the image associated with the image similarity value at the current position.

[0120] Statistical processing is performed on the initial weight coefficients of all image similarity values to obtain the image weight coefficient of the image associated with the image similarity value.

[0121] In the embodiments of the present invention, considering that due to the patient's condition, the patient cannot reach the reference posture or cannot maintain the reference posture for a long time, it can be analyzed from the sequence of image similarity values arranged in time series. For example, the default weight coefficient corresponding to each training posture image can be determined in advance according to the image similarity value. For example, when the image similarity value is equal to or greater than the first threshold, the corresponding default weight coefficient is 0.9. For another example, when the image similarity value is less than the first threshold and greater than or equal to the second threshold, the corresponding default weight coefficient is 0.5, etc.

[0122] When the image similarity value at the previous position is greater than the image similarity value at the current position, it means that when the patient corrects his own rehabilitation training actions according to the mirror posture, due to the development of the condition, he still cannot approach the reference posture and cannot maintain the training posture at the previous position in a short time. Then, the default weight coefficient of the image at the current position is decreased according to the first preset ratio, and thus, the initial weight coefficient of the image associated with the image similarity at the current position can be obtained. For example, the first preset ratio can be 5%, 7%, 10%, etc.

[0123] When the image similarity value at the previous position is less than the image similarity value at the current position, it means that when the patient corrects his own rehabilitation training actions according to the mirror posture, the rehabilitation training actions he performs tend to approach the reference posture, indicating that the patient's previous rehabilitation training actions are not standard and the patient's condition has a tendency to improve. Then, the default weight coefficient of the image at the current position is increased according to the second preset ratio, and thus, the initial weight coefficient of the image associated with the image similarity at the current position can be obtained. For example, the second preset ratio can be 5%, 7%, 10%, etc.

[0124] Statistical processing is performed on the initial weight coefficients of all image similarity values to obtain the image weight coefficients of the images associated with the image similarity values. Among them, the statistical processing may include, but is not limited to, data screening, data normalization and other processing methods.

[0125] S307. Determine the rehabilitation training score of the target patient according to the pose completion scores in all training scenarios and the training weight coefficients corresponding to each training scenario.

[0126] In the embodiment of the present invention, the rehabilitation training score of the target patient can be calculated according to the following formula (1), formula (2) and formula (3):

[0127]

[0128] X ji =IF(T j1 +T ji +...+T jn =1,"T ji ","C ji ") formula (2)

[0130] Cj i =(Tj i -Tj min ) / (Tj max -Tj min ) formula (3)

[0132] Among them, F refers to the rehabilitation training score of the target patient, and G j refers to the training weight coefficient corresponding to the jth training scenario among the K training scenarios corresponding to the current training type. S ji refers to the image similarity value of the image at the ith position in the jth training scenario; X ji refers to the image weight coefficient corresponding to the image similarity value at the ith position in the jth training scenario; T ji refers to the initial weight coefficient corresponding to the image similarity value at the ith position in the jth training scenario; C ji refers to the weighted weight coefficient of the image similarity value at the ith position in the jth training scenario; T jmin refers to the minimum value among the initial weight coefficients corresponding to all image similarity values in the jth training scenario; T jmax refers to the maximum value among the initial weight coefficients corresponding to all image similarity values in the jth training scenario; n refers to the set number of training pose images included in each training scenario.

[0133] Moreover, according to formulas (2) and (3), it can be known that the IF function executes the first item after the condition when the condition is satisfied, and executes the second item after the condition when the condition is not satisfied. That is to say, if the cumulative sum of the initial weight coefficients corresponding to all training pose images in the j-th training scenario is 1, then the initial weight coefficient corresponding to the training pose image at each position is directly used as the image weight coefficient of the training pose image associated with the image similarity value at each position. If the cumulative sum of the initial weight coefficients corresponding to all training pose images in the j-th training scenario is not 1, then the initial weight coefficient corresponding to the training pose image at each position is normalized respectively, and the normalized weight coefficients are respectively used as the image weight coefficients of the training pose images associated with the image similarity values at each position.

[0134] Multiply the image similarity value and the image weight coefficient associated with each training pose image to obtain the pose completion score corresponding to each training pose image, and then accumulate and average the pose completion scores corresponding to each training pose image to determine the pose completion score of the target patient in the j-th training scenario. By analogy, after multiplying the pose completion scores in the K training scenarios by the training weight coefficients corresponding to each training scenario and then performing cumulative summation, taking the average value after the accumulation gives the rehabilitation training score of the target patient. The rehabilitation training score is obtained through the comprehensive evaluation of all training scenarios of the patient under the same training type, and it can accurately represent the current rehabilitation training effect of the patient and the rehabilitation status of the patient's condition.

[0135] In some embodiments, the method further includes a coefficient determination step for the training weight coefficient:

[0136] Send the coefficient-related data to the head-mounted display terminal so that the head-mounted display terminal displays the coefficient-related data.

[0137] Receive the coefficient operation data of the hand-worn terminal based on the coefficient-related data.

[0138] Based on the coefficient operation data, determine the training weight coefficients set by the target user for each training scenario corresponding to the current training type.

[0139] In the embodiments of the present invention, considering that the key rehabilitation contents to which different patients' work or life focuses may tend to vary. For example, some patients may need to undergo vocational rehabilitation training. When their key concern is the finger flexibility in the upper limb rehabilitation training in a training scenario, the server may send the coefficient-related data to the head-mounted display terminal for display before the patient starts the training. The user generates coefficient operation data for updating the coefficient-related data through a hand-worn terminal device and uploads it to the server. After receiving the coefficient operation data, the server updates the pre-set coefficient-related data according to the coefficient operation data, that is, updates the training weight coefficients set for each training scenario in the current training scenario.

[0140] For example, when the patient focuses on increasing the training weight coefficient of one or two training scenarios and the finally evaluated rehabilitation training score is relatively high, it indicates that when the patient's condition has not fully recovered, they can start to return to work without affecting the work progress. If the finally evaluated rehabilitation training score is relatively low, it means that when the patient's condition has not fully recovered, they are not yet suitable to return to work and need to continue to rest and do rehabilitation training.

[0141] S308. Generate a training suggestion according to the rehabilitation training score, training type, and patient information, and send it to the head-mounted display terminal for display.

[0142] In the embodiments of the present invention, the rehabilitation training score can be used to represent the patient's condition recovery. For example, the higher the rehabilitation training score, the closer the patient's all limb movement conditions are to the fully recovered state, and the better the rehabilitation training effect. The lower the rehabilitation training score, the more the patient's limbs need further rehabilitation training. The server can generate corresponding training suggestions for the target patient by combining the rehabilitation training score, training type, and patient information. For example, the training suggestion may include the suggestion for the target patient's next rehabilitation training, such as the training type of the next rehabilitation training.

[0143] Thus, through the same rehabilitation training system, patients with different conditions can be subjected to virtual-real combined rehabilitation training in different scenarios, thereby enriching the patient's limb training scenarios. Moreover, through video guidance and the process of correcting mirror postures, the standardization of the patient's rehabilitation training actions can be improved, and the patient's condition recovery can be accurately evaluated based on the posture data, greatly improving the efficiency and effect of the patient's rehabilitation training.

[0144] In summary, the embodiments of the present invention provide a rehabilitation training method. The training method may include determining different training types for patients with different conditions through the same rehabilitation training system, and performing virtual-real combined rehabilitation training in different training scenarios, which enriches the limb training scenarios and training interest of patients. At the same time, video guidance can be carried out by referring to the pose video data, and the deviation correction process of the mirror pose can improve the standardization of the rehabilitation training actions of patients, and the recovery of the patient's condition can be accurately evaluated according to the pose data, greatly improving the rehabilitation training efficiency and rehabilitation training effect of patients.

[0145] It should be noted that for the method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the embodiments of the present application are not limited by the described action sequences, because according to the embodiments of the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present application.

[0146] Referring to Figure 4 , there is shown a rehabilitation training device provided by an embodiment of the present invention. The device may include:

[0147] A patient information receiving module 401, configured to obtain patient information and determine the training type of the patient according to the patient information.

[0148] A reference data obtaining module 402, configured to determine at least one training scenario corresponding to the training type and obtain reference pose video data associated with the training scenario.

[0149] A reference data sending module 403, configured to send the reference pose video data to the head-mounted display terminal, so that the head-mounted display terminal displays the reference pose video data, enabling the target patient to perform rehabilitation training.

[0150] A training data receiving module 404, configured to receive rehabilitation training data, where the rehabilitation training data is determined based on the wearable terminal.

[0151] A mirror image data determining module 405, configured to determine the mirror pose data of the target patient according to the rehabilitation training data, and send the mirror pose data to the head-mounted display terminal, so that the head-mounted display terminal displays the mirror pose data.

[0152] A training evaluation module 406, configured to update the rehabilitation training data and evaluate the rehabilitation training score of the target patient according to the updated rehabilitation training data.

[0153] A suggestion generation module 407, configured to generate training suggestions according to the rehabilitation training score, training type, and patient information, and send the training suggestions to the head-mounted display terminal for display.

[0154] In an alternative embodiment of the invention, the rehabilitation training data includes upper limb posture data and patient coordinate data, and the mirror image data determination module includes:

[0155] A first mirror image sub-module, configured to perform a first coordinate transformation on the upper limb posture data to obtain mirror image upper limb posture data.

[0156] A second mirror image sub-module, configured to perform a second coordinate transformation on the patient coordinate data according to a preset mirror image distance to obtain mirror image patient coordinate data.

[0157] A mirror image data determination sub-module, configured to combine the mirror image upper limb posture data and the mirror image patient coordinate data to obtain the mirror image pose data of the target patient.

[0158] In an alternative embodiment of the invention, the rehabilitation training data includes lower limb posture data and patient coordinate data, and the mirror image data determination module includes:

[0159] A first mirror image sub-module, configured to perform a first coordinate transformation on the lower limb posture data to obtain mirror image lower limb posture data.

[0160] A second mirror image sub-module, configured to perform a second coordinate transformation on the patient coordinate data according to a preset mirror image distance to obtain mirror image patient coordinate data.

[0161] A mirror image data determination sub-module, configured to combine the mirror image lower limb posture data and the mirror image patient coordinate data to obtain the mirror image pose data of the target patient.

[0162] In an alternative embodiment of the invention, the training evaluation module 406 includes:

[0163] A posture score determination sub-module, configured to determine the posture completion scores of the target patient in each training scenario of the current training type according to the updated rehabilitation training data.

[0164] A training evaluation sub-module, configured to determine the rehabilitation training score of the target patient according to the posture completion scores in all training scenarios and the training weight coefficients corresponding to each training scenario.

[0165] In an alternative embodiment of the invention, the posture score determination sub-module includes:

[0166] A posture image determination unit, configured to separately extract the training posture data of the target patient from the updated rehabilitation training data at intervals, and determine the training posture images corresponding to the respective training posture data.

[0167] A similarity value calculation unit for calculating the image similarity values between multiple training pose images and the reference pose images corresponding to the reference pose video data respectively.

[0168] An image coefficient determination unit for arranging all the image similarity values in time sequence and determining the image weight coefficients of the images associated with the respective image similarity values according to a preset weighting rule.

[0169] A pose score determination unit for determining the pose completion score of the target patient in the current training scenario based on the image similarity values and the image weight coefficients.

[0170] In an optional embodiment of the invention, the preset weighting rule at least includes:

[0171] Determining the corresponding default weight coefficients according to the image similarity values corresponding to the respective training pose images;

[0172] When the image similarity value at the previous position is greater than the image similarity value at the current position, decreasing the default weight coefficient corresponding to the image similarity value at the current position by a first preset ratio to obtain the initial weight coefficient of the image associated with the image similarity value at the current position.

[0173] When the image similarity value at the previous position is less than the image similarity value at the current position, increasing the default weight coefficient corresponding to the image similarity value at the current position by a second preset ratio to obtain the initial weight coefficient of the image associated with the image similarity value at the current position.

[0174] Performing statistical processing on the initial weight coefficients of all the image similarity values to obtain the image weight coefficients of the images associated with the image similarity values.

[0175] In an optional embodiment of the invention, the training evaluation module 406 includes:

[0176] The rehabilitation training score of the target patient can be calculated by the following formula:

[0177]

[0178] X ji =IF(T j1 +T ji +...+T jn =1,"T ji ","C ji );

[0179] C ji =(T ji -T jmin ) / (T jmax -T jmin );

[0180] Among them, F refers to the rehabilitation training score of the target patient, and the G j refers to the training weight coefficient corresponding to the j-th training scenario among the K training scenarios corresponding to the current training type; S ji refers to the image similarity value of the image at the i-th position in the j-th training scenario; X ji refers to the image weight coefficient corresponding to the image similarity value at the i-th position in the j-th training scenario; T ji refers to the initial weight coefficient corresponding to the image similarity value at the i-th position in the j-th training scenario; C ji refers to the weighted weight coefficient of the image similarity value at the i-th position in the j-th training scenario; T jmin refers to the minimum value among the initial weight coefficients corresponding to all image similarity values in the j-th training scenario; T jmax refers to the maximum value among the initial weight coefficients corresponding to all image similarity values in the j-th training scenario; n refers to the set number of training pose images included in each training scenario.

[0181] In an alternative embodiment of the invention, the device may further include a coefficient determination module for the training weight coefficient, and the coefficient determination module is further configured to:

[0182] Send the coefficient-related data to the head-mounted display terminal so that the head-mounted display terminal displays the coefficient-related data.

[0183] Receive the coefficient operation data of the hand-worn terminal based on the coefficient-related data.

[0184] Based on the coefficient operation data, determine the training weight coefficients set by the target user for each training scenario corresponding to the current training type.

[0185] Each embodiment in this specification is described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The same or similar parts among the embodiments can be referred to each other.

[0186] It is easy for those skilled in the art to think that any combination application of the above embodiments is feasible. Therefore, any combination among the above embodiments is an implementation scheme of the present invention. However, due to space limitations, this specification does not elaborate on them one by one here.

[0187] In the specification provided here, a large number of specific details are described. However, it can be understood that the embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures, and technologies are not shown in detail so as not to obscure the understanding of this specification.

[0188] Similarly, it should be understood that, in order to streamline the present invention and assist in understanding one or more of the various inventive aspects, in the above description of the exemplary embodiments of the present invention, the various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, the disclosed method should not be construed as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected by the claims, the inventive aspects lie in less than all the features of the single embodiments disclosed previously. Thus, the claims following the detailed description hereby expressly incorporate the detailed description, where each claim itself serves as a separate embodiment of the present invention.

[0189] Those skilled in the art can understand that the modules in the devices in the embodiments can be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments can be combined into one module or unit or component, and in addition, they can be divided into multiple sub-modules or sub-units or sub-components. Except that at least some of such features and / or processes or units are mutually exclusive, any combination can be adopted to combine all the features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all the processes or units of any method or device so disclosed. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) can be replaced by an alternative feature that provides the same, equivalent, or similar purpose.

[0190] An electronic device, comprising:

[0191] One or more processors;

[0192] A memory;

[0193] One or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to execute the method described in the above embodiments.

[0194] A computer-readable storage medium storing a computer program for use in conjunction with an electronic device, the computer program being executable by a processor to complete the method described in the above embodiments.

[0195] A computer program product, comprising a computer program / computer-executable instructions, which, when executed by a processor in an electronic device, implement the method described in any one of the above invention embodiments.

[0196] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, apparatus, or computer program product. Therefore, the embodiments of the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0197] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing terminal devices generate a device for implementing the functions specified in Figure 1 one or more of the flows Figure 1 or a plurality of flows and / or blocks

[0198] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device that implements the functions specified in Figure 1 one or more of the flows Figure 1 or a plurality of flows and / or blocks

[0199] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device, such that a series of operation steps are executed on the computer or other programmable terminal device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable terminal device provide steps for implementing the functions specified in Figure 1 one or more of the flows Figure 1 or a plurality of flows and / or blocks

[0200] Although the preferred embodiments of the embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they know the basic creative concepts. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0201] Finally, it should also be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or terminal device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or terminal device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the existence of additional identical elements in the process, method, article or terminal device comprising the said element.

[0202] The above has introduced in detail a rehabilitation training method and a rehabilitation training device provided by the present invention. Specific examples are used in this text to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A rehabilitation training method, characterized in that, Applied to a rehabilitation training system, the rehabilitation training system includes a server and a wearable terminal, and the wearable terminal includes: a head-mounted display terminal, a hand wearable terminal, and a lower limb wearable terminal. The method includes: Obtain patient information and determine the training type of the patient according to the patient information; Determine at least one training scenario corresponding to the training type and obtain the reference pose video data associated with the training scenario; Send the reference pose video data to the head-mounted display terminal so that the head-mounted display terminal displays the reference pose video data, enabling the target patient to perform rehabilitation training; Receive rehabilitation training data, which is determined based on the wearable terminal; Determine the mirror pose data of the target patient according to the rehabilitation training data, and send the mirror pose data to the head-mounted display terminal so that the head-mounted display terminal displays the mirror pose data; Update the rehabilitation training data, and evaluate the rehabilitation training score of the target patient according to the updated rehabilitation training data; Generate training suggestions according to the rehabilitation training score, training type, and patient information, and send them to the head-mounted display terminal for display.

2. The rehabilitation training method according to claim 1, wherein The rehabilitation training data includes upper limb pose data and patient coordinate data. Determining the mirror pose data of the target patient according to the rehabilitation training data includes: Perform a first coordinate transformation on the upper limb pose data to obtain mirror upper limb pose data; Perform a second coordinate transformation on the patient coordinate data according to a preset mirror distance to obtain mirror patient coordinate data; Combine the mirror upper limb pose data and the mirror patient coordinate data to obtain the mirror pose data of the target patient.

3. The rehabilitation training method according to claim 1, characterized in that, The rehabilitation training data includes lower limb pose data and patient coordinate data. Determining the mirror pose data of the target patient according to the rehabilitation training data includes: Perform a first coordinate transformation on the lower limb pose data to obtain mirror lower limb pose data; Perform a second coordinate transformation on the patient coordinate data according to a preset mirror distance to obtain mirror patient coordinate data; Combine the mirror lower limb pose data and the mirror patient coordinate data to obtain the mirror pose data of the target patient.

4. The rehabilitation training method according to claim 2 or 3, characterized in that, Evaluating the rehabilitation training score of the target patient according to the updated rehabilitation training data includes: Determine the pose completion scores of the target patient in each training scenario of the current training type according to the updated rehabilitation training data; Determine the rehabilitation training score of the target patient according to the pose completion scores in all training scenarios and the training weight coefficients corresponding to each training scenario.

5. The rehabilitation training method according to claim 4, wherein Determining the pose completion scores of the target patient in each training scenario of the current training type according to the updated rehabilitation training data includes: Intermittently separate the training pose data of the target patient from the updated rehabilitation training data and determine the training pose images corresponding to each training pose data; Calculate the image similarity values between multiple training pose images and the reference pose images corresponding to the reference pose video data respectively; Arrange all image similarity values in time sequence and determine the image weight coefficients of the images associated with each image similarity value according to a preset weighting rule; Determine the pose completion score of the target patient in the current training scenario based on the image similarity value and the image weight coefficient.

6. The rehabilitation training method according to claim 5, wherein The preset weighting rule at least includes: Determine the corresponding default weight coefficient according to the image similarity value corresponding to each training pose image; If the image similarity value at the previous position is greater than the image similarity value at the current position, decrease the default weight coefficient corresponding to the image similarity value at the current position by a first preset ratio to obtain the initial weight coefficient of the image associated with the image similarity value at the current position; If the image similarity value at the previous position is less than the image similarity value at the current position, increase the default weight coefficient corresponding to the image similarity value at the current position by a second preset ratio to obtain the initial weight coefficient of the image associated with the image similarity value at the current position; Perform statistical processing on the initial weight coefficients of all image similarity values to obtain the image weight coefficient of the image associated with the image similarity value.

7. The rehabilitation training method according to claim 6, wherein The determining of the rehabilitation training score of the target patient based on the pose completion scores in all training scenarios and the training weight coefficients corresponding to each training scenario includes: The rehabilitation training score of the target patient can be calculated using the following formula: X ji =IF(T j1 +T ji +...+T jn =1,"T ji ","C ji "); C ji = (T ji - T jmin ) / (T jmax - T jmin ); Among them, F refers to the rehabilitation training score of the target patient, and G j refers to the training weight coefficient corresponding to the j-th training scenario among the K training scenarios corresponding to the current training type; S ji refers to the image similarity value of the image at the i-th position in the j-th training scenario; X ji refers to the image weight coefficient corresponding to the image similarity value of the image at the i-th position in the j-th training scenario; T ji refers to the initial weight coefficient corresponding to the image similarity value of the image at the i-th position in the j-th training scenario; C ji refers to the weighted weight coefficient of the image similarity value of the image at the i-th position in the j-th training scenario; T jmin refers to the minimum value among the initial weight coefficients corresponding to all image similarity values in the j-th training scenario; T jmax refers to the maximum value among the initial weight coefficients corresponding to all image similarity values in the j-th training scenario; n refers to the set number of training pose images included in each training scenario; The IF function is to execute the first item after the condition when the condition is met, and execute the second item after the condition when the condition is not met.

8. The rehabilitation training method according to claim 4, characterized in that The method further includes a coefficient determination step for the training weight coefficient: Send the coefficient-related data to the head-mounted display terminal so that the head-mounted display terminal displays the coefficient-related data; Receive the coefficient operation data of the hand-worn terminal based on the coefficient-related data; Based on the coefficient operation data, determine the training weight coefficients set by the target user for each training scenario corresponding to the current training type.

9. A rehabilitation training device, characterized in that, Applied to a rehabilitation training system, the rehabilitation training system includes a server and wearable terminals. The wearable terminals include: a head-mounted display terminal, a hand-worn terminal, and a lower limb wearable terminal. The device includes: A patient information receiving module, configured to obtain patient information and determine the training type of the patient according to the patient information; A reference data obtaining module, configured to determine at least one training scenario corresponding to the training type and obtain reference pose video data associated with the training scenario; A reference data sending module, configured to send the reference pose video data to the head-mounted display terminal so that the head-mounted display terminal displays the reference pose video data, enabling the target patient to perform rehabilitation training; A training data receiving module, configured to receive rehabilitation training data, where the rehabilitation training data is determined based on the wearable terminal; A mirror image data determining module, configured to determine the mirror pose data of the target patient according to the rehabilitation training data, and send the mirror pose data to the head-mounted display terminal so that the head-mounted display terminal displays the mirror pose data; A training evaluation module, configured to update the rehabilitation training data and evaluate the rehabilitation training score of the target patient according to the updated rehabilitation training data; A suggestion generating module, configured to generate training suggestions according to the rehabilitation training score, training type, and patient information, and send them to the head-mounted display terminal for display.

10. The rehabilitation training device according to claim 9, wherein The rehabilitation training data includes upper limb pose data and patient coordinate data. The mirror image data determining module includes: The first mirror sub-module is used to perform a first coordinate transformation on the upper limb pose data to obtain mirrored upper limb pose data; The second mirror sub-module is used to perform a second coordinate transformation on the patient coordinate data according to a preset mirror distance to obtain mirrored patient coordinate data; The mirror data determination sub-module is used to combine the mirrored upper limb pose data and the mirrored patient coordinate data to obtain the mirrored pose data of the target patient.

Images