Rehabilitation training video guidance method, system and device and storage medium

Abstract

The invention discloses a rehabilitation training video guidance method, system and device and a storage medium. The method comprises the steps that first patient information and second patient information of a patient are collected; inputting the first patient information into a pre-trained first random forest classification model to obtain a first rehabilitation training video tag; inputting the second patient information into a pre-trained second random forest classification model to obtain a second rehabilitation training video tag; querying first rehabilitation training video data corresponding to each first rehabilitation training video tag from a first video library, and querying second rehabilitation training video data corresponding to each second rehabilitation training video tag from a second video library; and playing each piece of first rehabilitation training video data and each piece of second rehabilitation training video data in sequence, so that the patient can perform rehabilitation guidance training based on each piece of first rehabilitation training video data and each piece of second rehabilitation training video data.

Description

Technical Field

[0001] The present invention relates to the field of medical health technology, and in particular to a rehabilitation training video guidance method, system, device and storage medium. Background Art

[0002] Falls in the elderly during hospitalization can not only cause physical injuries, but also cause psychological fear, seriously affecting the quality of life and rehabilitation process of the elderly. Although there are some fall prevention measures in hospitals, most of them lack targeted personalized training programs and cannot provide continuous and effective guidance and support. Therefore, the development of a fall prevention system that can provide personalized rehabilitation training video guidance has important practical significance and social value. Summary of the invention

[0003] The present invention provides a rehabilitation training video guidance method, system, device and storage medium, so as to solve the technical problem that the information of hot-swappable NVME hard disk cannot be reflected in time in the BMC management interface.

[0004] The embodiment of the present invention provides a rehabilitation training video guidance method, comprising:

[0005] Collecting first patient information including basic information and health status information of the patient and second patient information including action video information of various activities;

[0006] Obtaining one or more first rehabilitation training video labels by inputting the first patient information into a pre-trained first random forest classification model;

[0007] Obtaining one or more second rehabilitation training video labels by inputting the second patient information into a pre-trained second random forest classification model;

[0008] According to the one or more first rehabilitation training video tags, query the first rehabilitation training video data corresponding to each first rehabilitation training video tag from the first video library, and according to the one or more second rehabilitation training video tags, query the second rehabilitation training video data corresponding to each second rehabilitation training video tag from the second video library;

[0009] Each of the first rehabilitation training video data and each of the second rehabilitation training video data are played in sequence, so that the patient can perform rehabilitation guidance training based on each of the first rehabilitation training video data and each of the second rehabilitation training video data.

[0010] Preferably, the basic information includes at least: age, gender, height, weight and body mass index (BMI); the health status information includes at least: vision status, hearing status, perception status, depression status, cognitive history, falls within the year and high-fall risk medications taken; the action video information of the multiple activities includes at least: action videos of balance activities and action videos of gait activities.

[0011] Preferably, the pre-trained first random forest classification model includes:

[0012] Collecting first patient information including basic information and health status information of a plurality of different patients;

[0013] By performing feature analysis on the basic information and health status information in the first patient information of each patient, one or more types of feature information contained in the first patient information of each patient is determined, and a corresponding first rehabilitation training video tag is configured for each type of feature information;

[0014] A first random forest classification model is constructed, and the first patient information of each patient and the corresponding one or more first rehabilitation training video labels are used as a set of training data sets to train the first random forest classification model to obtain a trained first random forest classification model.

[0015] Preferably, the pre-trained second random forest classification model includes:

[0016] collecting second patient information including motion video information of a plurality of different patients including a plurality of activities;

[0017] By performing feature analysis on the action video information of multiple activities in the second patient information of each patient, one or more types of feature information contained in the second patient information of each patient is extracted, and a corresponding second rehabilitation training video tag is configured for each type of feature information;

[0018] A second random forest classification model is constructed, and the second patient information of each patient and the corresponding one or more second rehabilitation training video labels are used as a set of training data sets to train the second random forest classification model to obtain a trained second random forest classification model.

[0019] Preferably, the first video library contains a first rehabilitation training video tag and its corresponding first rehabilitation training video data; the second video library contains a second rehabilitation training video tag and its corresponding second rehabilitation training video data.

[0020] Preferably, it also includes:

[0021] Calculating the patient's fall risk level using the one or more first rehabilitation training video tags and the one or more second rehabilitation training video tags, and determining an exercise standard range for rehabilitation guidance training based on the fall risk level;

[0022] During the playing of each of the first rehabilitation training video data or each of the second rehabilitation training video data, collecting the physiological detection data and the activity video data of the patient during each rehabilitation training in real time;

[0023] Based on the patient's physiological detection data and activity movement video data during each rehabilitation training process and the exercise standard range of the rehabilitation guidance training, the patient's rehabilitation training video guidance is evaluated for training effect to obtain an evaluation result.

[0024] Preferably, the physiological detection data at least includes: heart rate data, blood pressure data, movement data of each key part and pressure data of each part of the sole of the foot.

[0025] The embodiment of the present invention further provides a rehabilitation training video guidance system, including:

[0026] A collection module, used for collecting first patient information including basic information and health status information of the patient and second patient information including action video information of various activities;

[0027] An acquisition module, configured to obtain one or more first rehabilitation training video labels by inputting the first patient information into a pre-trained first random forest classification model; and obtain one or more second rehabilitation training video labels by inputting the second patient information into a pre-trained second random forest classification model;

[0028] A query module, configured to query the first rehabilitation training video data corresponding to each first rehabilitation training video tag from the first video library according to the one or more first rehabilitation training video tags, and query the second rehabilitation training video data corresponding to each second rehabilitation training video tag from the second video library according to the one or more second rehabilitation training video tags;

[0029] The rehabilitation guidance training module is used to play each of the first rehabilitation training video data and each of the second rehabilitation training video data so that the patient can perform rehabilitation guidance training based on each of the first rehabilitation training video data and each of the second rehabilitation training video data.

[0030] An embodiment of the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the rehabilitation training video guidance method when executing the computer program.

[0031] An embodiment of the present invention further 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 steps of the rehabilitation training video guidance method are implemented.

[0032] The beneficial effect of the present invention is that it provides personalized rehabilitation training video guidance by intelligently analyzing the physical condition and personal preferences of hospitalized elderly patients, helping patients improve their body balance and muscle strength and effectively reducing the risk of falling. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 It is a flow chart of a rehabilitation training video guidance method provided by the present invention;

[0034] Figure 2 is a schematic diagram of a rehabilitation training video guidance system provided by the present invention;

[0035] Figure 3 is a schematic diagram of a balance assessment table provided by the present invention;

[0036] Figure 4 Schematic diagram of the gait assessment table provided by the present invention. DETAILED DESCRIPTION

[0037] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. In the subsequent description, the use of suffixes such as "module", "component" or "unit" used to represent elements is only to facilitate the description of the present invention and has no specific meaning in itself. Therefore, "module", "component" or "unit" can be used in a mixed manner.

[0038] Figure 1 is a flow chart of a rehabilitation training video guidance method provided by the present invention, such as Figure 1 As shown, including:

[0039] Step S101: collecting first patient information including basic information and health status information of the patient and second patient information including action video information of various activities;

[0040] In one embodiment of the present invention, the basic information includes at least: age, gender, height, weight and body mass index (BMI); the health status information includes at least: vision status, hearing status, perception status, depression status, cognitive history, falls within the year and high-fall risk medications taken; the action video information of the multiple activities includes at least: action videos of balance activities and action videos of gait activities.

[0041] Step S102: obtaining one or more first rehabilitation training video labels by inputting the first patient information into a pre-trained first random forest classification model;

[0042] In one embodiment of the present invention, the pre-trained first random forest classification model includes:

[0043] Collecting first patient information including basic information and health status information of a plurality of different patients;

[0044] By performing feature analysis on the basic information and health status information in the first patient information of each patient, one or more types of feature information contained in the first patient information of each patient is determined, and a corresponding first rehabilitation training video tag is configured for each type of feature information;

[0045] A first random forest classification model is constructed, and the first patient information of each patient and the corresponding one or more first rehabilitation training video labels are used as a set of training data sets to train the first random forest classification model to obtain a trained first random forest classification model.

[0046] Step S103: obtaining one or more second rehabilitation training video labels by inputting the second patient information into a pre-trained second random forest classification model;

[0047] In one embodiment of the present invention, the pre-trained second random forest classification model includes:

[0048] collecting second patient information including motion video information of a plurality of different patients including a plurality of activities;

[0049] By performing feature analysis on the action video information of multiple activities in the second patient information of each patient, one or more types of feature information contained in the second patient information of each patient is extracted, and a corresponding second rehabilitation training video tag is configured for each type of feature information;

[0050] A second random forest classification model is constructed, and the second patient information of each patient and the corresponding one or more second rehabilitation training video labels are used as a set of training data sets to train the second random forest classification model to obtain a trained second random forest classification model.

[0051] Step S104: querying the first rehabilitation training video data corresponding to each first rehabilitation training video tag from the first video library according to the one or more first rehabilitation training video tags, and querying the second rehabilitation training video data corresponding to each second rehabilitation training video tag from the second video library according to the one or more second rehabilitation training video tags;

[0052] In one embodiment of the present invention, the first video library includes a first rehabilitation training video tag and its corresponding first rehabilitation training video data; the second video library includes a second rehabilitation training video tag and its corresponding second rehabilitation training video data.

[0053] Step S105: playing each of the first rehabilitation training video data and each of the second rehabilitation training video data in sequence, so that the patient can perform rehabilitation guidance training based on each of the first rehabilitation training video data and each of the second rehabilitation training video data.

[0054] In one embodiment of the present invention, it also includes:

[0055] Calculating the patient's fall risk level using the one or more first rehabilitation training video tags and the one or more second rehabilitation training video tags, and determining an exercise standard range for rehabilitation guidance training based on the fall risk level;

[0056] During the playing of each of the first rehabilitation training video data or each of the second rehabilitation training video data, collecting the physiological detection data and the activity video data of the patient during each rehabilitation training in real time;

[0057] Based on the patient's physiological detection data and activity movement video data during each rehabilitation training process and the exercise standard range of the rehabilitation guidance training, the patient's rehabilitation training video guidance is evaluated for training effect to obtain an evaluation result.

[0058] In one embodiment of the present invention, the physiological detection data at least includes: heart rate data, blood pressure data, movement data of each key part and pressure data of each part of the sole of the foot.

[0059] The present invention provides personalized rehabilitation training video guidance by intelligently analyzing the physical condition and personal preferences of hospitalized elderly patients, helping patients improve their body balance and muscle strength and effectively reducing the risk of falling.

[0060] The present invention also provides a rehabilitation training video guidance system, which specifically includes a user information collection module, a personalized training plan generation module, a training video generation module, a user interaction interface, and an effect evaluation and feedback module.

[0061] User information collection module:

[0062] Basic information collection: collect the patient's age, gender, height, weight BMI (Body Mass Index) and other basic information through the hospital HIS (Hospital Information System) information system or questionnaire survey.

[0063] Health status collection: The patient's vision, hearing, cognitive history, fall experience within 6 months, and high-fall risk medications currently being taken are collected through hospital information systems and physiological parameter detection equipment (such as blood pressure monitors, heart rate monitors, etc.).

[0064] Activity pattern collection: Through wearable devices (accelerometers and gyroscopes), electrodes are placed on the patient's thighs and calves. The patient's balance and gait are monitored based on the Tinetti Balance and Gait Scale, and the action video information of various activities is obtained and saved through the camera, and the patient's final score in each activity is calculated. The various activities include: Figure 3 and Figure 4 Various activities and scoring criteria are shown.

[0065] Personalized training plan generation module:

[0066] Data processing: pre-process the collected basic information of patients and health status information, including processing missing values ​​and data standardization. Processing missing values: fill missing values ​​with mean values. Data standardization: use StandardScaler to standardize the data after processing missing values ​​to make it have zero mean and unit variance. Process the action video information of various activities obtained by the camera to obtain the processed action video information;

[0067] Split into training and test sets: The dataset is divided into training and test sets with a ratio of 80% training set and 20% test set.

[0068] Select Model: Select Random Forest Classifier as the model.

[0069] Model training: Use the training set data to train the model.

[0070] Model evaluation: Use the test set data to evaluate the performance of the model and calculate the accuracy and classification report.

[0071] Personalized training plan generation: The model is trained using the first machine learning algorithm (random forest), with the model input being the patient's basic information and health status information, and the output being the personalized first rehabilitation training video plan label. The model is trained using the second machine learning algorithm (random forest), with the model input being the patient's processed action video information, and the output being the personalized second rehabilitation training video plan label.

[0072] Alternatively, a first machine learning algorithm (random forest) is used to train a model, wherein the model input is the patient's basic information, health status information, and final activity scores of multiple activities, and the model output is a personalized first rehabilitation training video plan label.

[0073] That is to say, based on the model output, a personalized rehabilitation training plan is developed. For those without the risk of falling, physical activity and exercise are recommended to improve overall health. For those with the risk of falling, exercise is recommended to improve balance, gait and strength. For patients at high risk of falling, multi-factor intervention is conducted. The plan content includes but is not limited to balance training, muscle strengthening training, flexibility training, etc. Each training item includes action demonstrations, precautions, training frequency, etc.

[0074] Furthermore, the corresponding relationship between each rehabilitation training video plan label and patient information is as follows:

[0075] Warm-up exercises are associated with older age and higher BMI index; strength training is associated with lower BMI index and multiple falls; balance training is associated with the use of high-risk fall medications, a history of falls, cognitive decline, and visual and hearing impairments; gait training is associated with vision, hearing, and cognitive history; balance and gait are associated with low final activity scores (less than 19 points) for multiple activities; strength and balance are associated with final activity scores (greater than 19 points and less than 24 points) for multiple activities; gait is associated with abnormal gait; warm-up, strength, balance, and final activity scores (greater than 19 points and less than 24 points) for multiple activities are associated with a higher BMI index, etc.

[0076] Training video generation module:

[0077] Video selection: According to the generated first rehabilitation training video plan label, a corresponding training video is selected from the first video library, and according to the generated second rehabilitation training video plan label, a corresponding training video is selected from the second video library.

[0078] Or select a corresponding training video from a video library according to the generated first rehabilitation training video plan label.

[0079] Furthermore, a first video library and a second video library containing a variety of rehabilitation training programs are pre-established, and each video has detailed action demonstrations and precautions. The video library includes warm-up exercises, muscle strength training, balance training, and gait movement training. Warm-up exercises include head and neck exercises, back extension exercises, and trunk exercises. Muscle strength training includes: knee flexion and extension training—quadriceps femoris, hamstrings, ankle flexion and extension training—tibialis anterior, calf triceps, hip abduction training—gluteal muscles, balance training includes proprioception exercises + balance exercises, such as heel-toe standing exercises, single-leg standing exercises, backward walking exercises, 8-shaped walking exercises, etc. Gait movement training includes: lateral walking training, toe walking training, heel walking training, chair sit-up training, stair climbing and climbing training, etc.

[0080] Furthermore, if there is no completely matching video in the video library, a new training video can be generated through a video editing tool.

[0081] User interface:

[0082] Video Playback: Provides a user-friendly interface, allowing patients to easily view and play training videos.

[0083] Progress record: Patients record training time and feelings during training, and the system automatically saves the training records.

[0084] Furthermore, the patient's heart rate, blood oxygen saturation, exercise intensity and other data during training are monitored in real time through the electronic bracelet worn.

[0085] Feedback submission: Patients can submit their physical changes and suggestions after training through the interface, and nurses can also record the patient's training status.

[0086] Effect evaluation and feedback module:

[0087] Regular evaluation: The system regularly reminds patients to evaluate the effectiveness of their training, including improvements in body balance, muscle strength, flexibility, etc.

[0088] Data collection: Collect patient assessment results and feedback, and nurses can also provide professional advice.

[0089] Plan adjustment: Dynamically adjust the patient's rehabilitation training plan based on the evaluation results and feedback information to ensure the effectiveness and safety of the training.

[0090] Figure 2 Schematic diagram of a rehabilitation training video guidance system provided by the present invention. Figure 2 As shown, including:

[0091] A collection module, used for collecting first patient information including basic information and health status information of the patient and second patient information including action video information of various activities;

[0092] An acquisition module, configured to obtain one or more first rehabilitation training video labels by inputting the first patient information into a pre-trained first random forest classification model; and obtain one or more second rehabilitation training video labels by inputting the second patient information into a pre-trained second random forest classification model;

[0093] A query module, configured to query the first rehabilitation training video data corresponding to each first rehabilitation training video tag from the first video library according to the one or more first rehabilitation training video tags, and query the second rehabilitation training video data corresponding to each second rehabilitation training video tag from the second video library according to the one or more second rehabilitation training video tags;

[0094] The rehabilitation guidance training module is used to play each of the first rehabilitation training video data and each of the second rehabilitation training video data so that the patient can perform rehabilitation guidance training based on each of the first rehabilitation training video data and each of the second rehabilitation training video data.

[0095] An embodiment of the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the rehabilitation training video guidance method when executing the computer program.

[0096] An embodiment of the present invention further 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 steps of the rehabilitation training video guidance method are implemented.

[0097] The present invention is explained below with specific embodiments.

[0098] User Information Collection

[0099] After Mr. Zhang was admitted to the hospital, the nurse filled in his basic information and health status through the hospital information system. The specific steps are as follows:

[0100] Basic information collection:

[0101] Age: 75

[0102] Gender: Male

[0103] Height: 170 cm

[0104] Weight: 75 kg

[0105] BMI: 26.2

[0106] Health status collection:

[0107] Visual condition: Mild myopia

[0108] Hearing status: Normal

[0109] Cognitive history: None

[0110] Fall experience within 6 months: Yes

[0111] High-risk medications currently being taken: antihypertensive drugs, hypoglycemic drugs

[0112] Active Mode Collection:

[0113] Balance score: 18 points (based on Figure 3 and Figure 4 )

[0114] Generate a personalized training plan

[0115] The system generates a personalized rehabilitation training plan based on Mr. Zhang's information. Assume that the generated training plan is "balance training".

[0116] Training plan refinement

[0117] The system refines the "balance training" plan and generates specific training items and guidance:

[0118] Training items:

[0119] ◇Standing single-leg support exercise: 2 sets per day, 10 times per set

[0120] ◇Single-leg standing with eyes closed: 2 sets per day, 10 seconds per set

[0121] ◇Heel-toe standing exercise: 2 sets per day, 10 seconds per set

[0122] Note:

[0123] Pay attention to safety during training, avoid excessive exertion, and stop immediately if you feel uncomfortable

[0124] Perform proper warm-up and cool-down exercises before and after training

[0125] Patients watch training videos

[0126] Uncle Zhang watched the training video, which included action demonstrations and precautions.

[0127] Start training

[0128] Mr. Zhang trained according to the video instructions, and the nurse observed and provided necessary guidance and support.

[0129] Record training progress

[0130] During the training, Mr. Zhang recorded the training time and feelings, and monitored the heart rate and blood oxygen saturation data. The system automatically saved the training records. For example:

[0131] ◇Training date: 2024-10-01

[0132] ◇Training time: 10 minutes

[0133] ◇Training experience: Feeling good, leg muscles are stronger

[0134] Submit Feedback

[0135] Mr. Zhang submitted his physical changes and suggestions after training via a tablet computer. For example:

[0136] Feedback: After training, I feel my leg muscles are stronger, but sometimes I feel slightly tired.

[0137] Regular evaluation

[0138] The system regularly reminds Mr. Zhang to evaluate the effectiveness of his training, including improvements in body balance, muscle strength, flexibility, etc. The nurse records the evaluation results and provides professional advice.

[0139] Plan Adjustment

[0140] Based on the evaluation results and feedback information, the system dynamically adjusts Mr. Zhang's rehabilitation training plan to ensure the effectiveness and safety of the training. For example:

[0141] Adjustment content: increase training intensity, increase training frequency, or adjust training items

[0142] Results: Through the above steps, Mr. Zhang received a personalized rehabilitation training plan and carried out effective training under the guidance of the nurse. During the training, the system recorded Mr. Zhang's training progress and feedback to ensure the safety and effectiveness of the training. After a period of training, Mr. Zhang's muscle strength and balance ability were significantly improved, and the risk of falling was significantly reduced.

[0143] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the present invention is not limited thereby. Any modification, equivalent substitution and improvement made by those skilled in the art without departing from the scope and essence of the present invention shall be within the scope of the present invention.

Claims

1. A rehabilitation training video guidance method, characterized in that: include: Collecting first patient information including basic information and health status information of the patient and second patient information including action video information of various activities; Obtaining one or more first rehabilitation training video labels by inputting the first patient information into a pre-trained first random forest classification model; Obtaining one or more second rehabilitation training video labels by inputting the second patient information into a pre-trained second random forest classification model; According to the one or more first rehabilitation training video tags, query the first rehabilitation training video data corresponding to each first rehabilitation training video tag from the first video library, and according to the one or more second rehabilitation training video tags, query the second rehabilitation training video data corresponding to each second rehabilitation training video tag from the second video library; Each of the first rehabilitation training video data and each of the second rehabilitation training video data are played in sequence, so that the patient can perform rehabilitation guidance training based on each of the first rehabilitation training video data and each of the second rehabilitation training video data.

2. The method according to claim 1, characterized in that The basic information includes at least: age, gender, height, weight and body mass index (BMI); the health status information includes at least: vision status, hearing status, perception status, depression status, cognitive history, falls within the year and high-fall risk medications taken; the action video information of the various activities includes at least: action videos of balance activities and action videos of gait activities.

3. The method according to claim 2, characterized in that The pre-trained first random forest classification model includes: Collecting first patient information including basic information and health status information of a plurality of different patients; By performing feature analysis on the basic information and health status information in the first patient information of each patient, one or more types of feature information contained in the first patient information of each patient is determined, and a corresponding first rehabilitation training video tag is configured for each type of feature information; A first random forest classification model is constructed, and the first patient information of each patient and the corresponding one or more first rehabilitation training video labels are used as a set of training data sets to train the first random forest classification model to obtain a trained first random forest classification model.

4. The method according to claim 3, characterized in that The pre-trained second random forest classification model includes: collecting second patient information including motion video information of a plurality of different patients including a plurality of activities; By performing feature analysis on the action video information of multiple activities in the second patient information of each patient, one or more types of feature information contained in the second patient information of each patient is extracted, and a corresponding second rehabilitation training video tag is configured for each type of feature information; A second random forest classification model is constructed, and the second patient information of each patient and the corresponding one or more second rehabilitation training video labels are used as a set of training data sets to train the second random forest classification model to obtain a trained second random forest classification model.

5. The method according to claim 4, characterized in that The first video library includes a first rehabilitation training video tag and its corresponding first rehabilitation training video data; the second video library includes a second rehabilitation training video tag and its corresponding second rehabilitation training video data.

6. The method according to claim 5, characterized in that Also includes: Calculating the patient's fall risk level using the one or more first rehabilitation training video tags and the one or more second rehabilitation training video tags, and determining an exercise standard range for rehabilitation guidance training based on the fall risk level; During the playing of each of the first rehabilitation training video data or each of the second rehabilitation training video data, collecting the physiological detection data and the activity video data of the patient during each rehabilitation training in real time; Based on the patient's physiological detection data and activity movement video data during each rehabilitation training process and the exercise standard range of the rehabilitation guidance training, the patient's rehabilitation training video guidance is evaluated for training effect to obtain an evaluation result.

7. The method according to claim 6, characterized in that The physiological detection data at least includes: heart rate data, blood pressure data, movement data of each key part and pressure data of each part of the sole of the foot.

8. A rehabilitation training video guidance system, characterized in that: include: A collection module, used for collecting first patient information including basic information and health status information of the patient and second patient information including action video information of various activities; an acquisition module, configured to obtain one or more first rehabilitation training video labels by inputting the first patient information into a pre-trained first random forest classification model; Obtaining one or more second rehabilitation training video labels by inputting the second patient information into a pre-trained second random forest classification model; A query module, configured to query the first rehabilitation training video data corresponding to each first rehabilitation training video tag from the first video library according to the one or more first rehabilitation training video tags, and query the second rehabilitation training video data corresponding to each second rehabilitation training video tag from the second video library according to the one or more second rehabilitation training video tags; The rehabilitation guidance training module is used to play each of the first rehabilitation training video data and each of the second rehabilitation training video data so that the patient can perform rehabilitation guidance training based on each of the first rehabilitation training video data and each of the second rehabilitation training video data.

9. A computer device, characterized in that: The computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the rehabilitation training video guidance method according to any one of claims 1 to 7 are implemented.

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

Images