Hand function evaluation method and system applied to burn rehabilitation

Abstract

The invention discloses a hand function evaluation method and system applied to burn rehabilitation, and relates to the technical field of image processing. Receiving a monitoring request sent by a user; acquiring a target video according to the monitoring request; extracting a first joint position, corresponding to the first time point, of the target hand from the target video, and extracting a second joint position, corresponding to the second time point, of the target hand from the target video; analyzing the first joint position and the second joint position to obtain a joint motion range, and acquiring a muscle strength value uploaded by the target equipment; identifying a target hand in the target video to obtain a burn grade; and inputting the joint motion range, the muscle strength value and the burn grade into a preset evaluation model for processing to obtain a first analysis result, and displaying the first analysis result to the user. By implementing the technical scheme provided by the invention, the problem that the function evaluation of the burnt hand depends on the subjective judgment and the operation normalization of medical staff at present is solved, and the evaluation accuracy is improved.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and particularly to a hand function evaluation method and system applied to burn rehabilitation. Background Art

[0002] Burns, as a common and severe type of trauma, often cause varying degrees of damage to hand functions. The hand, as a crucial functional organ in the human body, its normal movement and sensory functions are of decisive significance for performing Activities of Daily Living (ADL), maintaining vocational capabilities, and improving the quality of life. Hand burns may affect multiple complex levels such as the skin, muscle tissue, tendons, joint structures, and even the nervous system. The degree of injury profoundly affects the hand's motor function, sensory feedback, and overall movement coordination.

[0003] Through a systematic function evaluation process, it is possible to comprehensively and accurately grasp the specific location of the burn, the affected area, the burn depth, and the scope of the surrounding tissues that may be affected. This information is crucial for formulating personalized rehabilitation treatment plans and provides a solid basis for scientific decision-making. However, in the current practical operation of evaluating the function of burned hands, it mainly relies on medical staff to directly test the hand function on-site and evaluate the recovery status of the hand function based on the test results. But this evaluation method has a certain degree of subjectivity, that is, the non-standard operation of medical staff during the test may have an adverse impact on the test results, thereby affecting the accuracy of the evaluation results.

[0004] Therefore, there is an urgent need for a hand function evaluation method and system applied to burn rehabilitation that can solve the above technical problems. Summary of the Invention

[0005] This application provides a hand function evaluation method and system applied to burn rehabilitation. This method effectively solves the problems of relying on the subjective judgment of medical staff and the standardization of operations in the current evaluation of the function of burned hands, and improves the accuracy of the evaluation.

[0006] First aspect, the present application provides a hand function evaluation method and system for burn rehabilitation. The method includes: receiving a monitoring request sent by a user, where the monitoring request is used to monitor a target hand with burns; obtaining a target video according to the monitoring request, where the target video is a video of the target hand taken in real time; extracting a first joint position corresponding to the target hand at a first time point from the target video, and extracting a second joint position corresponding to the target hand at a second time point from the target video, where the first time point is earlier than the second time point; analyzing the first joint position and the second joint position to obtain a joint range of motion, and obtaining a muscle strength value uploaded by a target device, where the muscle strength value is calculated from an electrical signal and a pressure value, the electrical signal is the signal generated by the target hand when performing a grip strength test, and the pressure value is the pressure value corresponding to the grip strength test; identifying the burn level of the target hand in the target video; inputting the joint range of motion, the muscle strength value, and the burn level into a preset evaluation model for processing to obtain a first analysis result, and presenting the first analysis result to the user.

[0007] By adopting the above technical solution, it is possible to automatically extract the hand joint positions from the target video taken in real time, without relying on manual measurement by medical staff. Based on video image analysis technology, human errors are reduced. The muscle strength value is calculated from the electrical signal and the pressure value, and the burn level is obtained through the image analysis technology in the target video, reducing the possibility of subjective judgment. Inputting the joint range of motion, the muscle strength value, and the burn level into the preset evaluation model for processing to obtain the first analysis result, the automated evaluation method greatly improves the evaluation efficiency, reduces human intervention in the evaluation process, and at the same time reduces the errors caused by subjectivity and non-standard operation, improving the accuracy of the evaluation result.

[0008] Optionally, analyzing the first joint position and the second joint position to obtain a joint range of motion specifically includes: identifying joints of the target hand in the target video to obtain multiple joint points; obtaining target joint points from the multiple joint points; obtaining a first joint position corresponding to the target joint points at the first time point, and obtaining a second joint position corresponding to the target joint points at the second time point; generating a first motion trajectory with the first joint position and the second joint position in chronological order; obtaining a reference position corresponding to the target joint points, and generating a second motion trajectory according to the reference position; analyzing the first motion trajectory and the second motion trajectory to obtain a bending angle; obtaining a first duration corresponding to the first motion trajectory, and calculating the first duration and the bending angle to obtain the joint range of motion, where the first duration is the duration between the first time point and the second time point.

[0009] By adopting the above technical solution, joint recognition is performed on the target hand in the target video, multiple joint points can be accurately recognized, the target joint points can be accurately obtained from the multiple joint points, a first motion trajectory is generated according to the joint positions corresponding to the target joint points at the first time point and the second time point, a reference position corresponding to the target joint point (such as the joint position in the normal state) is obtained, a second motion trajectory is generated, and the first motion trajectory and the second motion trajectory are analyzed to calculate the bending angle. The bending angle directly reflects the degree of joint bending. The first duration corresponding to the first motion trajectory (i.e., the time required for the joint to move from the first time point to the second time point) is obtained, and the joint range of motion is obtained by calculating in combination with the bending angle. The joint range of motion can objectively evaluate the flexibility and range of motion of the joint and improve the accuracy of the evaluation.

[0010] Optionally, after recognizing the target hand in the target video and obtaining the burn grade, the method further includes: obtaining a second duration, where the second duration is the duration corresponding to the target hand from the third time point to the current time point, and the third time point is the starting time point when the target hand was burned; obtaining a first image from the target video, extracting the first image to obtain the target burn feature; determining whether there is a scar feature in the target burn feature; when there is no scar feature in the target burn feature, inputting the second duration, the joint range of motion, the muscle strength value, and the burn grade into a preset evaluation model for processing to obtain a second analysis result.

[0011] By adopting the above technical solution, the second duration of the target hand from the burn starting time point to the current time point is obtained, the first image is extracted from the target video, and the image is analyzed in detail to identify the target burn feature. By determining whether there is a scar feature in the target burn feature, different stages after the burn can be distinguished. The presence of a scar often means a more severe burn or poor healing, which may have a long-term impact on hand function. When there is no scar feature in the target burn feature, inputting multiple pieces of information such as the second duration, the joint range of motion, the muscle strength value, and the burn grade into a preset evaluation model for processing can more accurately evaluate the function of the burned hand.

[0012] Optionally, after determining whether there is a scar feature in the target burn feature, the method further includes: when there is a scar feature in the target burn feature, obtaining the scar area of the scar feature in the target burn feature and receiving the pain grade uploaded by the user; determining the scar grade according to the scar area and the pain grade, and inputting the scar grade, the joint range of motion, the muscle strength value, and the burn grade into a preset evaluation model for processing to obtain a third analysis result.

[0013] By adopting the above technical solution, when there is a scar feature in the target burn feature, a more detailed quantitative evaluation of the scar is carried out by obtaining the scar area. The size of the scar area directly reflects the severity of the burn injury. Then, by receiving the pain level uploaded by the user, the subjective pain feeling of the patient is included in the evaluation scope. Combining the scar area and the pain level can more accurately determine the scar level. Subsequently, multiple pieces of information such as the scar level, joint range of motion, muscle strength value, and burn level are input into a preset evaluation model for processing, comprehensively considering multiple aspects of the burn injury, including physical injury, functional impact, and the patient's subjective feeling, so as to provide a more comprehensive and objective evaluation result.

[0014] Optionally, identifying the target hand in the target video to obtain the burn level specifically includes: obtaining a second image from the target video, identifying the second image to obtain a first area, where the first area is the area corresponding to the complete target hand; intercepting a second area from the first area, where the second area is the area corresponding to the burned position on the target hand; obtaining the burn area corresponding to the second area, and using a preset method to judge the depth of the burned position to obtain the burn depth; determining the burn level according to the burn depth and the burn area.

[0015] By adopting the above technical solution, a second image is obtained from the target video and identified to accurately locate the first area containing the complete target hand. A second area corresponding to the burned position on the target hand is further intercepted within the first area. The interception is to focus on the burned part. By obtaining the burn area corresponding to the second area and using a preset method to judge the depth of the burned position to obtain the burn depth, and combining the burn depth and the burn area, according to a certain evaluation standard or algorithm, the burn level is determined. Through automated processing and recognition technology, the evaluation time is greatly shortened and the evaluation efficiency is improved.

[0016] Optionally, after inputting the joint range of motion, muscle strength value, and burn level into a preset evaluation model for processing to obtain a first analysis result and presenting the first analysis result to the user, the method further includes: receiving a training request sent by the user, where the training request is the state in which the user expects the target hand to recover; matching the first analysis result and the training request in a preset recommendation database to obtain a first rehabilitation plan; obtaining training steps from the first rehabilitation plan and converting the training steps into a preset training form; obtaining the burn source corresponding to the target hand, and determining prohibited training information according to the burn source, where the burn source includes thermal burn, electrical burn, and chemical burn; judging whether there is prohibited training information in the preset training form; when there is no prohibited training information in the preset training form, recommending the first rehabilitation plan to the user.

[0017] By adopting the above technical solution, a training request sent by a user is received, that is, the rehabilitation state expected by the user for the target hand. The first analysis result is combined with the training request and input into a preset recommendation database for matching. By leveraging the advantages of big data and machine learning technologies, the most suitable rehabilitation plan for the user can be quickly and accurately screened out from a large amount of data. The training steps are obtained from the first rehabilitation plan and converted into a preset training form. The source of the burn corresponding to the target hand is obtained, and the prohibited training information is determined according to the burn source. Considering the special risks and limitations that different burn types may bring, it is ensured that the recommended rehabilitation plan will not cause further harm to the patient. Before recommending the rehabilitation plan to the user, it is first determined whether there is any prohibited training information in the preset training form. When there is no prohibited training information in the preset training form, the first rehabilitation plan is recommended to the user, improving the user's satisfaction and participation.

[0018] Optionally, after determining whether there is any prohibited training information in the preset training form, the method further includes: when there is prohibited training information in the preset training form, the suitable training information is determined according to the burn source, the first rehabilitation plan is adjusted according to the suitable training information to obtain a second rehabilitation plan, and the second rehabilitation plan is recommended to the user.

[0019] By adopting the above technical solution, based on the identification of prohibited training information, it is possible to avoid recommending training steps that may have an adverse impact on a specific burn type or aggravate the injury. At the same time, by determining the suitable training information according to the burn source, it is ensured that the recommended training content not only meets the patient's rehabilitation needs but also does not pose a further threat to their health. Then, the first rehabilitation plan is adjusted according to the suitable training information to obtain a second rehabilitation plan, which can reduce the discomfort during the rehabilitation process, thereby improving the user's rehabilitation enthusiasm.

[0020] In the second aspect of the present application, a hand function evaluation system for burn rehabilitation is provided. The system includes a receiving unit, a processing unit, and a display unit. The receiving unit receives a monitoring request sent by a user, and the monitoring request is used to monitor a target hand with burns. The processing unit obtains a target video according to the monitoring request, and the target video is a video obtained by taking a real-time shot of the target hand. The first joint position corresponding to the target hand at the first time point is extracted from the target video, and the second joint position corresponding to the target hand at the second time point is extracted from the target video. The first time point is earlier than the second time point. The first joint position and the second joint position are analyzed to obtain the joint range of motion, and the muscle strength value uploaded by the target device is obtained. The muscle strength value is calculated from an electrical signal and a pressure value. The electrical signal is the signal generated by the target hand when performing a grip strength test, and the pressure value is the pressure value corresponding to the grip strength test. The target hand in the target video is identified to obtain the burn grade. The display unit inputs the joint range of motion, the muscle strength value, and the burn grade into a preset evaluation model for processing to obtain a first analysis result, and displays the first analysis result to the user.

[0021] Optionally, the processing unit is used to perform joint recognition on the target hand in the target video to obtain a plurality of joint points. The receiving unit is used to obtain target joint points from the plurality of joint points. The first joint position corresponding to the target joint points at the first time point is obtained, and the second joint position corresponding to the target joint points at the second time point is obtained. The processing unit is used to generate a first motion trajectory from the first joint position and the second joint position in chronological order. The receiving unit is used to obtain a reference position corresponding to the target joint points and generate a second motion trajectory according to the reference position. The processing unit is used to analyze the first motion trajectory and the second motion trajectory to obtain the bending angle. The receiving unit is used to obtain the first duration corresponding to the first motion trajectory, and calculate the joint range of motion from the first duration and the bending angle. The first duration is the duration between the first time point and the second time point.

[0022] Optionally, the receiving unit is used to obtain a second duration, and the second duration is the duration corresponding to the target hand from the third time point to the current time point. The third time point is the starting time point when the target hand was burned. The first image is obtained from the target video, and the target burn feature is extracted from the first image. The processing unit is used to determine whether there is a scar feature in the target burn feature. When there is no scar feature in the target burn feature, the second duration, the joint range of motion, the muscle strength value, and the burn grade are input into a preset evaluation model for processing to obtain a second analysis result.

[0023] Optionally, when there is a scar feature in the target burn feature, the receiving unit is configured to obtain the scar area of the scar feature in the target burn feature and receive the pain level uploaded by the user; the processing unit is configured to determine the scar level according to the scar area and the pain level, and input the scar level, joint range of motion, muscle strength value, and burn level into a preset evaluation model for processing to obtain a third analysis result.

[0024] Optionally, the receiving unit is configured to obtain a second image from the target video, identify the second image to obtain a first region, where the first region is the region corresponding to the complete target hand; the processing unit is configured to intercept a second region from the first region, where the second region is the region corresponding to the burned position on the target hand; the receiving unit is configured to obtain the burn area corresponding to the second region, and use a preset method to determine the burn depth of the burned position to obtain the burn depth; the processing unit is configured to determine the burn level according to the burn depth and the burn area.

[0025] Optionally, the receiving unit is configured to receive a training request sent by the user, where the training request is the state in which the user expects the target hand to recover; the processing unit is configured to match the first analysis result and the training request in a preset recommendation database to obtain a first rehabilitation plan; obtain training steps from the first rehabilitation plan and convert the training steps into a preset training form; the receiving unit is configured to obtain the burn source corresponding to the target hand, determine prohibited training information according to the burn source, and the burn source includes thermal burn, electric burn, and chemical burn; determine whether there is prohibited training information in the preset training form; the display unit is configured to recommend the first rehabilitation plan to the user when there is no prohibited training information in the preset training form.

[0026] Optionally, when there is prohibited training information in the preset training form, the display unit is configured to determine appropriate training information according to the burn source, adjust the first rehabilitation plan according to the appropriate training information to obtain a second rehabilitation plan, and recommend the second rehabilitation plan to the user.

[0027] In a third aspect of the present application, an electronic device is provided. The electronic device includes a processor, a memory, a user interface, and a network interface. The memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that an electronic device executes the method according to any one of the above in the present application.

[0028] In a fourth aspect of the present application, a computer-readable storage medium is provided. The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of the above in the present application is executed.

[0029] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. It can automatically extract the hand joint positions from the real-time captured target video, without relying on manual measurement by medical staff. Based on video image analysis technology, it reduces human error. The muscle strength value is calculated through electrical signals and pressure values, and the burn grade is obtained through image analysis technology in the target video, reducing the possibility of subjective judgment. The joint range of motion, muscle strength value, and burn grade are input into a preset evaluation model for processing to obtain the first analysis result. The automated evaluation method greatly improves the evaluation efficiency, reduces human intervention in the evaluation process, and at the same time reduces errors caused by subjectivity and non-standard operation, improving the accuracy of the evaluation results.

[0030] 2. Receive the training request sent by the user, that is, the rehabilitation state expected by the user for the target hand. The first analysis result is combined with the training request and input into a preset recommendation database for matching. Utilizing the advantages of big data and machine learning technologies, it can quickly and accurately screen out the most suitable rehabilitation plan for the user from a large amount of data. Obtain the training steps from the first rehabilitation plan and convert them into a preset training form. Obtain the burn source corresponding to the target hand, and determine the prohibited training information according to the burn source, considering the special risks and limitations that different burn types may bring, ensuring that the recommended rehabilitation plan will not cause further harm to the patient. Before recommending the rehabilitation plan to the user, first judge whether there is prohibited training information in the preset training form. When there is no prohibited training information in the preset training form, recommend the first rehabilitation plan to the user, improving the user's satisfaction and participation. Description of the Drawings

[0031] Figure 1 is a flowchart of a hand function evaluation method applied to burn rehabilitation provided by an embodiment of the present application; Figure 2 is a structural diagram of a hand function evaluation system applied to burn rehabilitation provided by an embodiment of the present application; Figure 3 is a structural diagram of an electronic device disclosed by an embodiment of the present application.

[0032] Description of the reference numerals: 201, receiving unit; 202, processing unit; 203, display unit; 300, electronic device; 301, processor; 302, memory; 303, user interface; 304, network interface; 305, communication bus. Detailed Embodiments

[0033] In order to enable those skilled in the art to better understand the technical solutions in this specification, the following will clearly and completely describe the technical solutions in the embodiments of this specification in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments.

[0034] In the description of the embodiments of the present application, words such as "for example" or "for instance" are used to give examples, illustrations or explanations. Any embodiment or design solution described as "for example" or "for instance" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "for example" or "for instance" is intended to present relevant concepts in a specific manner.

[0035] In the description of the embodiments of the present application, the term "a plurality of" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. The terms "comprise", "include", "have" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0036] Burns, as a common and severe type of trauma, often cause varying degrees of damage to hand function. The hand, as a crucial functional organ in the human body, its normal motor and sensory functions are decisive for performing activities of daily living (ADL), maintaining vocational ability and improving the quality of life. Hand burns can affect multiple complex levels such as the skin, muscle tissue, tendons, joint structures and even the nervous system, and the degree of injury profoundly affects the hand's motor function, sensory feedback and overall motor coordination.

[0037] Through a systematic functional assessment process, it is possible to comprehensively and accurately grasp the specific location of the burn, the affected area, the burn depth and the range of surrounding tissues that may be affected. This information is crucial for formulating personalized rehabilitation treatment plans and provides a solid basis for scientific decision-making. However, in the current practical operation of functional assessment of burned hands, it mainly relies on medical staff to directly test hand function on-site and evaluate the recovery status of hand function based on the test results. But this assessment method has a certain degree of subjectivity, that is, the medical staff may not operate standardly during the test, which may have an adverse impact on the test results and thus affect the accuracy of the assessment results.

[0038] Therefore, how to solve the problem of relying on the subjective judgment and operation standardization of medical staff in the current functional assessment of burned hands. A hand function assessment method applied to burn rehabilitation provided by the embodiments of the present application Figure 1It is a schematic flowchart of a hand function evaluation method applied to burn rehabilitation provided by an embodiment of the present application. Refer to Figure 1 , this method includes the following steps S101 - step S106.

[0039] S101: Receive a monitoring request sent by the user. The monitoring request is used to monitor the target hand with burns.

[0040] In the above S101, after the hand of the current user is burned, since the burn will affect the movement mechanism of the hand, it is necessary to evaluate the function of the burned hand of the user, and then determine the impact of the burn on the hand. The present application provides a method for evaluating the burned hand, which can solve the problem that the current subjective judgment of the burned hand by medical staff is inaccurate. The user refers to the patient to be evaluated, and the patient refers to the user whose hand is burned. The user sends a monitoring request to the server through the application program. After receiving the monitoring request, the server parses the monitoring request to confirm that it is to monitor the target hand with burns. The target hand refers to the burned hand, that is, whether the burned hand is the left hand or the right hand.

[0041] S102: Obtain the target video according to the monitoring request. The target video is a video taken in real time of the target hand.

[0042] In the above S102, after determining the target hand, a start instruction can be sent to the camera or other video acquisition devices. The start instruction includes the position of the hand to be monitored, that is, whether the hand is the left hand or the right hand. The camera or other video acquisition devices are connected to the server. The camera is aimed at the target hand. When the target hand is the left hand, the camera is aimed at the left side of the user, and it is determined that the left hand is in the shooting lens of the camera. After determining that the camera is aimed at the target hand, start shooting the video in real time, mainly shooting the actions performed by the target hand, and output the shot video as the target video.

[0043] S103: Extract the first joint position of the target hand corresponding to the first time point from the target video, and extract the second joint position of the target hand corresponding to the second time point from the target video.

[0044] In the above S103, after obtaining the target video, computer vision technology can be used to process the target video to identify the hand contour and joint points. At the first time point (for example, a certain frame at the start of the video), record the positions of each joint of the hand as the first joint positions. At the second time point (for example, a certain frame at the end of the video or a specific time point), also record the positions of each joint of the hand as the second joint positions. The first time point is earlier than the second time point, that is, the second time point refers to any time point after the first time point. The movement trajectory of the target hand can be captured one by one according to the activity changes of the target hand in the target video, and then the corresponding joint positions of the target hand can be obtained.

[0045] S104: Analyze the first joint positions and the second joint positions to obtain the joint range of motion, and obtain the muscle strength value uploaded by the target device.

[0046] In the above S104, after obtaining the first joint position and the second joint position from the target video, analyze the first joint position and the second joint position to obtain the joint range of motion, specifically including: performing joint recognition on the target hand in the target video to obtain multiple joint points; obtaining target joint points from the multiple joint points; obtaining the first joint position corresponding to the target joint point at the first time point, and obtaining the second joint position corresponding to the target joint point at the second time point; generating a first motion trajectory of the first joint position and the second joint position in chronological order; obtaining the reference position corresponding to the target joint point, and generating a second motion trajectory according to the reference position; analyzing the first motion trajectory and the second motion trajectory to obtain the bending angle; obtaining the first duration corresponding to the first motion trajectory, and calculating the first duration and the bending angle to obtain the joint range of motion, where the first duration is the duration between the first time point and the second time point. Specifically, preprocess the target video, including denoising, enhancing contrast, etc., to improve the accuracy of joint recognition. Adopt a deep learning-based joint recognition algorithm, such as Alphapose or OpenPose, etc. These algorithms can detect the skeletal joint points of the hand in the video frame and label the coordinates and confidence levels of these joint points in the video frame. Extract multiple joint points of the hand from the output of the joint recognition algorithm, and these joint points usually include fingertip, knuckle, wrist joint, etc. Then, according to actual needs, select the target joint points to be analyzed from the extracted multiple joint points. For example, if you want to analyze the bending degree of the finger, you can select the knuckle as the target joint point. Determine the first time point and the second time point in the target video, and these two time points can be determined by means of video frame index, timestamp, etc. For each time point, extract the position information of the target joint point from the output of the joint recognition algorithm, including the abscissa and the ordinate. Connect the joint positions corresponding to the first time point and the second time point in chronological order to form the first motion trajectory of the target joint point. Determine the reference position corresponding to the target joint point according to ergonomics or experimental data, and the reference position is used to represent the position of the target joint point in a certain standard or ideal state. Generate the second motion trajectory of the target joint point according to the reference position and a certain motion law (such as uniform motion, sine motion, etc.). This trajectory can be a theoretical and hypothetical motion trajectory for comparison with the actual motion trajectory of the target joint point. Compare the first motion trajectory with the second motion trajectory to find the difference between the two. The bending angle of the target joint point in the first motion trajectory can be calculated by methods such as geometric calculation or vector calculation. This angle can represent the bending degree of the target joint point during the motion. By calculating the time difference between the first time point and the second time point, obtain the first duration corresponding to the first motion trajectory, and the first duration can also be understood as the duration required for the first motion trajectory.The first motion trajectory does not only exist at the first time point and the second time point. This application only uses two other time points to illustrate how to construct a motion trajectory. Combining with the bending angle and the first duration, according to a certain calculation formula (such as joint range of motion = bending angle / first duration × a certain constant) or methods such as look-up table method, etc., the joint range of motion of the target joint point is calculated. This index can represent the motion range, motion speed and other characteristics of the target joint point within a certain period of time.

[0047] In addition, after determining the joint range of motion of the target hand, a grip strength test can be performed on the user. The electrical signals and pressure values during the test are recorded by sensors. The electrical signals come from electromyogram (EMG) sensors, which record the electrical activities generated during muscle activities. When using an electromyography sensor (such as a surface electrode or a needle electrode) to collect the electrical signals during muscle activities. The collected EMG signals are filtered and denoised to improve the signal-to-noise ratio of the signals. Features related to muscle strength, such as the amplitude and frequency of the signals, are extracted from the preprocessed EMG signals. The pressure value may come from a dynamometer or other pressure sensors, and various sensors can be used to measure the pressure generated during muscle contraction. The pressure value can be time-synchronized with the EMG signal to accurately analyze the relationship between the two. Analyze the distribution of pressure in the muscle group to understand the muscle contraction pattern and force distribution. A preset model can be established, which is used to predict the pressure value and the electrical signal, and then obtain the muscle strength value. The preset model requires a large amount of experimental data for training and verification. The fusion model is verified through experimental data to evaluate its prediction accuracy. The model is optimized according to the verification results to improve the prediction performance. In addition to the above calculations, a pinch meter can also be used to measure the two-finger pinch strength, three-finger pinch strength, side pinch strength, etc., and then obtain the hand muscle strength value. Which specific method to choose to obtain the hand muscle strength value can be selected based on the actual situation, and no more limitations are made here.

[0048] S105: Identify the target hand in the target video to obtain the burn grade.

[0049] In the above S105, image processing techniques (such as color analysis, texture analysis, etc.) are used to process the hand image in the video. The burn grade is evaluated according to the characteristics of the burn (such as redness, skin damage, color change, etc.). The burn grade can also be determined according to the burn depth and burn area. Identify the target hand in the target video to obtain the burn grade, which specifically includes: obtaining a second image from the target video, identifying the second image to obtain a first region, and the first region is the region corresponding to the complete target hand; cutting out a second region from the first region, and the second region is the region corresponding to the burn position on the target hand; obtaining the burn area corresponding to the second region, and using a preset method to judge the depth of the burn position to obtain the burn depth; determining the burn grade according to the burn depth and the burn area.

[0050] Specifically, select a clear image frame from the target video that can fully display the target hand as the second image. This image frame should preferably be selected at the moment when the hand burn situation is most obvious or representative. Preprocess the second image, including denoising, enhancing contrast, adjusting brightness and color balance, etc., to improve the accuracy of subsequent image recognition. Use a hand recognition algorithm based on deep learning or computer vision to recognize the second image. These algorithms can usually recognize the contour, shape, and position of the hand, thereby determining the area containing the complete hand. According to the output result of the hand recognition algorithm, determine the area containing the complete hand as the first area. This first area can clearly display all the key features and details of the hand. Within the first area, use an automatic annotation tool to mark the specific range of the burned position on the target hand. The annotation should be as accurate as possible to ensure the accuracy of subsequent burn area and burn depth calculations. During the annotation process, the target hand in the first area can be compared with a preset hand, and the areas in the first area that are inconsistent with the preset hand can be marked. According to the marked range of the burned position, extract the area containing the burned position from the first area as the second area. This second area should closely surround the burned position and avoid containing too much irrelevant information. Use an image processing software or algorithm to calculate the area of the second area. This can be achieved by counting the pixels of the second area and converting them into actual area units (such as square centimeters). Verify the calculated burn area to ensure the accuracy and reliability of the result. Different calculation methods or tools can be used for multiple calculations and the consistency of the results can be compared. Then use a preset burn depth judgment method, such as clinical criteria, image analysis algorithms, or the three-degree and four-category method, etc. These methods usually judge the burn depth based on features such as the color, texture, and blister formation of the burned area. According to the image features of the second area, use the depth judgment method to evaluate the burn depth at the burned position. The evaluation result should be able to accurately reflect the severity of the burn and the impact on hand tissues. Establish a burn grade classification standard in advance, which comprehensively considers two factors: burn depth and burn area. The burn grade can be divided into different levels such as mild, moderate, and severe, and each level corresponds to different burn characteristics and impact degrees. The mild level can be set as a small area and a depth less than the preset depth, the moderate level can be set as a small or large area but a depth equal to the preset depth, and the severe level is a large area and a depth greater than the pre-reviewed depth. According to the specific values of the burn depth and burn area, combined with the burn grade classification standard, determine the burn grade.

[0051] S106: Input the joint range of motion, muscle strength value, and burn grade into a preset evaluation model for processing to obtain a first analysis result, and display the first analysis result to the user.

[0052] In the above S106, the joint range of motion, muscle strength value, and burn grade are used as input data and input into a pre-trained evaluation model. The preset evaluation model is a machine learning or deep learning model that predicts the recovery of hand function, the risk of possible complications, or other relevant indicators based on the input data. The preset evaluation model outputs a first analysis result, which includes hand function evaluation, recovery status, and rehabilitation suggestions, etc. Data on the rehabilitation process of burn patients can be collected from reliable medical databases, clinical records, or professional research institutions first. The data should cover multiple aspects such as joint range of motion, muscle strength value, burn grade, and rehabilitation effect. Preprocess the collected data to improve the training efficiency of the model. Select useful features for the model from the original data, such as joint range of motion, muscle strength value, and burn grade, etc. Then extract the selected features. Select a suitable machine learning model according to the evaluation requirements and data characteristics. For the analysis of joint range of motion, muscle strength value, and burn grade, a regression model, classification model, or clustering model, etc. can be selected. Divide the dataset into a training set, a validation set, and a test set. The training set is used to train the model, the validation set is used to adjust the model's parameters and perform model selection, and the test set is used to evaluate the model's performance. Use the training set to train the model and adjust the model's parameters to minimize the loss function. Optimization algorithms such as gradient descent and stochastic gradient descent can be used for model training. Use the validation set or test set to evaluate the model and calculate evaluation metrics such as the accuracy, precision, and recall of the model. According to the evaluation results, optimize the model and output the optimized model as the preset evaluation model. Then input the joint range of motion, muscle strength value, and burn grade, etc. into the trained model. The preset evaluation model analyzes the input data and outputs a first analysis result. The first analysis result includes the hand improvement rate, recovery degree, and abnormal changes, etc. The first analysis result can also be output in a clear and intuitive way, which may include forms such as numerical changes, chart displays, and grade ratings. Display the first analysis result to the user in a graphical interface, report, or other forms. The user can understand the hand condition based on the analysis result and make decisions accordingly, such as seeking medical help, rehabilitation plans, etc.

[0053] In addition, the duration of the target hand being burned can be obtained. Based on the original, the time factor after the burn and a detailed analysis of the burn characteristics are further considered, achieving a more comprehensive and accurate assessment of the functional recovery of the burned hand, improving the accuracy and practicality of the assessment. Specifically, it includes: obtaining a second duration, which is the duration corresponding to the target hand from a third time point to the current time point, and the third time point is the starting time point when the target hand was burned; obtaining a first image from the target video, extracting the first image to obtain the target burn characteristics; determining whether there is a scar feature in the target burn characteristics; when there is no scar feature in the target burn characteristics, inputting the second duration, joint range of motion, muscle strength value, and burn grade into a preset evaluation model for processing to obtain a second analysis result. Specifically, first obtain the starting time point when the target hand was burned, that is, the third time point, which usually needs to be determined through medical records, patient self-report, or on-site first aid records. Then obtain the current time point, which can be obtained through the system clock. Then calculate the difference between the third time point and the current time point, that is, the second duration, and the second duration is the duration that the target hand has passed from the burn starting time point to the current time point. Select a clear image frame that can represent the hand burn condition from the target video as the first image. Usually, it is extracted at the beginning stage of the video or the stage where the burn characteristics are the most obvious. Preprocess the first image, including denoising, enhancing contrast, adjusting brightness, etc., to improve the accuracy of feature extraction. Use image processing techniques (such as edge detection, color analysis, texture analysis, etc.) to extract features from the first image. The extracted features should include features related to the target burn such as the area, color, shape, texture, etc. of the burn. Then establish a scar feature library, which contains the image features and description information of various scars. It can be established by collecting and analyzing a large number of scar images and using machine learning techniques for feature extraction and classification. Match the extracted target burn characteristics with the characteristics in the scar feature library. Use similarity calculation or classification algorithms to determine whether there is a scar feature in the target burn characteristics. When it is determined that there is no scar feature in the target burn characteristics, prepare the following data: the second duration (representing the recovery time after the burn), joint range of motion (representing the movement ability of the hand joints), muscle strength value (representing the strength condition of the hand muscles), and burn grade (representing the severity of the burn). The preset evaluation model is a trained machine learning or deep learning model used to evaluate the functional recovery of the hand and possible rehabilitation needs based on the input data. Input the prepared data into the preset evaluation model. After the model finishes processing, output the second analysis result. This result may include information such as the evaluation score of the hand function, the improvement rate of the hand, the degree of recovery, and abnormal changes. The second analysis result is mainly to compare the current monitoring situation of the user's target hand with the historical monitoring situation, and then analyze the rehabilitation situation of the target hand, etc.

[0054] Furthermore, based on the scar grade, a detailed analysis of the post-burn scar was further considered on the original basis, constituting a complete burn scar monitoring and evaluation process, which specifically includes: when there are scar features in the target burn features, obtaining the scar area of the scar features in the target burn features and receiving the pain level uploaded by the user; determining the scar grade according to the scar area and the pain level, and inputting the scar grade, joint range of motion, muscle strength value, and burn grade into a preset evaluation model for processing to obtain a third analysis result. Specifically, among the already extracted target burn features, scar features are identified through image analysis techniques (such as pixel counting, color recognition, texture analysis, etc.). Scar features usually manifest as color changes (such as red, purple, or white), abnormal skin texture (such as roughness, depression, or elevation), and irregular shapes. Using image processing software or algorithms, the area of the identified scar features is calculated. This can be achieved by counting the pixels in the scar area and converting them into actual area units (such as square centimeters). The calculation of the scar area is crucial for evaluating the severity of the scar and its impact on hand function. When it is determined that there are scar features at the burn location of the target hand, an upload request is sent to the corresponding device of the user, and this upload request is used to prompt the user to upload the corresponding pain level when touching this burn location. The pain level can be represented in ways such as a numerical rating scale, visual analogue scale, and written description. Then, the data uploaded by the user is verified to ensure that the pain level is within a reasonable range. Then, a scar grade evaluation standard is established, which comprehensively considers factors such as the scar area, pain level, and other possible factors (such as the location, color, texture, etc. of the scar). The scar grade can be divided into different levels such as mild, moderate, and severe, and each level corresponds to different scar features and degrees of impact. According to the scar area and the pain level, combined with the scar grade evaluation standard, the grade of the scar is determined. The data such as the scar grade, joint range of motion, muscle strength value, and burn grade are integrated and preprocessed. The prepared data is input into a preset evaluation model. After the model processing is completed, a third analysis result is output. This result may include information such as the specific impact of the scar on hand function, rehabilitation suggestions, treatment priorities, and whether further medical evaluation is required. The third analysis result is presented to the user or medical professionals in the form of a graphical interface, report, or other forms, so that they can make decisions based on the result. By inputting different factors into the preset evaluation model, analysis information on different aspects can be obtained, so that the analysis information can be sent to the user or medical staff, so as to provide more professional suggestions to the user according to the analysis information.

[0055] In a possible implementation, in addition to evaluating the function of the target hand, this application can also recommend a rehabilitation plan that meets the user's needs according to the rehabilitation training request input by the user, ensuring that the user can select a suitable one from the recommended rehabilitation plans for training. Specifically, it includes: receiving the training request sent by the user, where the training request is the state that the user expects the target hand to correspond to for rehabilitation; inputting the first analysis result and the training request into a preset recommendation database for matching to obtain the first rehabilitation plan; obtaining the training steps from the first rehabilitation plan and converting the training steps into a preset training form; obtaining the burn source corresponding to the target hand, and determining the prohibited training information according to the burn source, where the burn source includes thermal burn, electrical burn, and chemical burn; judging whether there is prohibited training information in the preset training form; when there is no prohibited training information in the preset training form, recommending the first rehabilitation plan to the user. Specifically, receiving the training request input by the user, the training request includes the rehabilitation state that the user expects the target hand to achieve, which may include specific indicators such as the degree of function recovery, range of motion, and strength level. In order to make the recommended rehabilitation plan more in line with the actual situation of the user, the user can also provide other relevant information, such as personal health status, past medical history, hand injury situation, etc. Verify the training request input by the user to ensure the accuracy and integrity of the information. Since the function of the target hand has been evaluated in real time in advance, after obtaining the first analysis result, the first analysis result and the training request can be input into the preset recommendation database for matching. The preset recommendation database is a database containing various rehabilitation plans and training programs. These plans are formulated according to different burn situations, rehabilitation needs, and user characteristics. Use a matching algorithm to match the first analysis result and the training request with the rehabilitation plans in the database. Multiple factors need to be considered during matching, such as burn grade, scar location, expected rehabilitation state, etc., to find the most suitable rehabilitation plan for the user. According to the matching result, output one or more rehabilitation plans that meet the user's needs as the first rehabilitation plan. Then extract each training step in detail from the first rehabilitation plan. These steps may include specific actions, range of motion, duration, number of repetitions, etc. Organize the extracted training steps into a clear and easy-to-understand training form. The training form should contain detailed descriptions, execution order, precautions, etc. of each step. Through the detection results input by the user, obtain the burn source of the target hand. The burn source may include thermal burn, electrical burn, chemical burn, etc. According to the burn source, determine whether there are certain training steps that are prohibited or require special attention. For example, for some chemical burns, it may be prohibited to contact certain substances or perform certain movements. For thermal burns, it is prohibited to massage, knead, or apply long-term pressure on the burn area. And for the joints near the burn area, their excessive movement should be restricted. For electrical burns, it is prohibited to directly touch the wound and avoid using electrical appliances that may generate electrical stimulation. Different burn sources correspond to different prohibited actions. Compare and analyze the training steps in the preset training form with the prohibited training information.Check whether each step involves prohibited activities or substances. If there are training steps in the preset training table that conflict with the prohibited training information, corresponding adjustments or modifications are required. When the preset training table is verified to ensure that it does not contain any prohibited training information, recommend the first rehabilitation plan to the user. The recommended method can be email, text message, in-app notification, etc. The user can view and accept the recommended rehabilitation plan.

[0056] In addition, when there is prohibited training information in the preset training table, determine the appropriate training information according to the source of the burn, adjust the first rehabilitation plan according to the appropriate training information to obtain the second rehabilitation plan, and recommend the second rehabilitation plan to the user. Specifically, carefully review each training step in the preset training table and compare it with the known prohibited training information. Identify any training steps that may cause problems or aggravate the injury. Record the identified prohibited training information in detail, including the specific training steps, the reasons for the prohibition, and the possible risks. Deeply understand the source of the burn on the target hand, including thermal burns, electrical burns, chemical burns, etc. According to the characteristics and impacts of the burn source, determine which training steps are appropriate, that is, the training steps that will not cause further harm to the hand or aggravate the injury. The appropriate training steps should help promote the recovery of hand function, improve joint mobility and muscle strength. Replace the training steps in the preset training table that conflict with the prohibited training information with appropriate training steps. Ensure that the modified training steps not only meet the rehabilitation goals but also avoid potential harm to the hand. Appropriately adjust the intensity and frequency of training according to the recovery situation after the burn and the patient's physical tolerance. Combine the patient's specific situation and rehabilitation needs to develop a personalized rehabilitation plan. This plan should include detailed training steps, time arrangements, precautions, and rehabilitation goals, etc. Comprehensively evaluate the adjusted rehabilitation plan to ensure that it not only conforms to the principles of rehabilitation science but also meets the actual situation and needs of the patient. Organize the evaluated rehabilitation plan into the second rehabilitation plan and prepare to recommend it to the user. Provide the user with detailed rehabilitation guidance, including explanations of training steps, execution order, precautions, and possible problems and solutions, etc. Encourage the user to actively participate in the rehabilitation process, train according to the second rehabilitation plan, and provide feedback and evaluation regularly. During the user's execution of the second rehabilitation plan, provide continuous follow-up and support, promptly answer the user's questions, and adjust the rehabilitation plan to adapt to the patient's recovery situation. When there is prohibited training information in the preset training table, determine the appropriate training information through the burn source and adjust the first rehabilitation plan to obtain the second rehabilitation plan that meets the actual situation and needs of the patient.

[0057] The embodiment of the present application also provides a hand function evaluation system applied to burn rehabilitation, Figure 2 which is a schematic structural diagram of a hand function evaluation system applied to burn rehabilitation provided by the embodiment of the present application. Refer toFigure 2 , the system includes a receiving unit 201, a processing unit 202, and a display unit 203.

[0058] The receiving unit 201 receives a monitoring request sent by a user, and the monitoring request is used to monitor the target hand with burns.

[0059] The processing unit 202 obtains a target video according to the monitoring request, where the target video is a video of real-time shooting of the target hand; extracts the first joint position corresponding to the target hand at a first time point from the target video, and extracts the second joint position corresponding to the target hand at a second time point from the target video, where the first time point is earlier than the second time point; analyzes the first joint position and the second joint position to obtain the joint range of motion, and obtains the muscle strength value uploaded by the target device, where the muscle strength value is calculated from an electrical signal and a pressure value, the electrical signal is the signal generated by the target hand when performing a grip strength test, and the pressure value is the pressure value corresponding to the grip strength test; identifies the target hand in the target video to obtain the burn grade.

[0060] The display unit 203 inputs the joint range of motion, the muscle strength value, and the burn grade into a preset evaluation model for processing to obtain a first analysis result, and displays the first analysis result to the user.

[0061] In a possible implementation manner, the processing unit 202 is used to perform joint recognition on the target hand in the target video to obtain a plurality of joint points; the receiving unit 201 is used to obtain target joint points from the plurality of joint points; obtain the first joint position corresponding to the target joint point at the first time point, and obtain the second joint position corresponding to the target joint point at the second time point; the processing unit 202 is used to generate a first motion trajectory from the first joint position and the second joint position in chronological order; the receiving unit 201 is used to obtain a reference position corresponding to the target joint point and generate a second motion trajectory according to the reference position; the processing unit 202 is used to analyze the first motion trajectory and the second motion trajectory to obtain the bending angle; the receiving unit 201 is used to obtain the first duration corresponding to the first motion trajectory, and calculate the first duration and the bending angle to obtain the joint range of motion, where the first duration is the duration between the first time point and the second time point.

[0062] In a possible implementation, the receiving unit 201 is configured to obtain a second duration, where the second duration is the duration corresponding to the target hand from a third time point to the current time point, and the third time point is the starting time point when the target hand is burned; obtain a first image from the target video, extract the first image to obtain target burn features; the processing unit 202 is configured to determine whether there are scar features in the target burn features; when there are no scar features in the target burn features, input the second duration, joint range of motion, muscle strength value, and burn grade into a preset evaluation model for processing to obtain a second analysis result.

[0063] In a possible implementation, when there are scar features in the target burn features, the receiving unit 201 is configured to obtain the scar area of the scar features in the target burn features and receive the pain grade uploaded by the user; the processing unit 202 is configured to determine the scar grade according to the scar area and the pain grade, and input the scar grade, joint range of motion, muscle strength value, and burn grade into a preset evaluation model for processing to obtain a third analysis result.

[0064] In a possible implementation, the receiving unit 201 is configured to obtain a second image from the target video, identify the second image to obtain a first region, where the first region is the region corresponding to the complete target hand; the processing unit 202 is configured to intercept a second region from the first region, where the second region is the region corresponding to the burned position on the target hand; the receiving unit 201 is configured to obtain the burn area corresponding to the second region, use a preset method to determine the depth of the burned position to obtain the burn depth; the processing unit 202 is configured to determine the burn grade according to the burn depth and the burn area.

[0065] In a possible implementation, the receiving unit 201 is configured to receive a training request sent by the user, where the training request is the state in which the user expects the target hand to recover; the processing unit 202 is configured to match the first analysis result and the training request in a preset recommendation database to obtain a first rehabilitation plan; obtain training steps from the first rehabilitation plan and convert the training steps into a preset training table; the receiving unit 201 is configured to obtain the burn source corresponding to the target hand, determine prohibited training information according to the burn source, and the burn source includes thermal burn, electric burn, and chemical burn; determine whether there is prohibited training information in the preset training table; the display unit 203 is configured to recommend the first rehabilitation plan to the user when there is no prohibited training information in the preset training table.

[0066] In a possible implementation, when there is prohibited training information in the preset training table, the display unit 203 is configured to determine appropriate training information according to the burn source, adjust the first rehabilitation plan according to the appropriate training information to obtain a second rehabilitation plan, and recommend the second rehabilitation plan to the user.

[0067] It should be noted that when the system provided in the above embodiments realizes its functions, only the division of the above functional modules is used for illustration. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiments belong to the same concept. For the specific implementation process, please refer to the method embodiments and will not be elaborated here.

[0068] This application also discloses an electronic device. Referring to Figure 3 , Figure 3 FIG. 1 is a schematic structural diagram of an electronic device provided by an embodiment of the present application. The electronic device 300 may include: at least one processor 301, at least one network interface 304, a user interface 303, a memory 302, and at least one communication bus 305.

[0069] Among them, the communication bus 305 is used to realize the connection and communication between these components.

[0070] Among them, the user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may further include a standard wired interface and a wireless interface.

[0071] Among them, the network interface 304 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0072] Among them, the processor 301 may include one or more processing cores. The processor 301 connects various parts within the entire server through various interfaces and lines. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 302, and by calling the data stored in the memory 302, it performs various functions of the server and processes data. Optionally, the processor 301 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 301 may integrate a combination of one or several of a central processing unit (CPU), a graphics processing unit (GPU), and a modem, etc. Among them, the CPU mainly processes the operating system, user interface, and application requests, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301 and may be implemented separately through a single chip.

[0073] Among them, the memory 302 may include random access memory (RAM) and may also include read-only memory. Optionally, the memory 302 includes a non-transitory computer-readable storage medium. The memory 302 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 302 may include a program storage area and a data storage area. Among them, the program storage area can store instructions for implementing the operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area can store the data involved in the above-mentioned various method embodiments. Optionally, the memory 302 may also be at least one storage device located far from the aforementioned processor 301.

[0074] As Figure 3 shown, the memory 302, as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for hand function assessment in burn rehabilitation.

[0075] In Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an interface for the user to input and obtain the data input by the user; and the processor 301 can be used to call the application program stored in the memory 302 and applied to the hand function evaluation for burn rehabilitation. When executed by one or more processors, the electronic device performs one or more of the methods described in the above embodiments.

[0076] It should be noted that, for the foregoing 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 this application is not limited by the described action sequence, because according to this 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 and modules involved are not necessarily essential to this application.

[0077] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0078] In several embodiments provided by this application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling, direct coupling, or communication connection can be through some service interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical or other form.

[0079] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0080] In addition, in each embodiment of this application, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0081] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media that can store program codes, such as USB flash drives, mobile hard disks, magnetic disks, or optical discs.

[0082] The foregoing are only exemplary embodiments of the present disclosure, and the scope of the present disclosure cannot be limited thereby. That is, any equivalent changes and modifications made in accordance with the teachings of the present disclosure still fall within the scope covered by the present disclosure. After considering the specification and the disclosure of the practical truth, those skilled in the art will easily think of other implementation manners of the present disclosure. This application aims to cover any variations, uses, or adaptive changes of the present disclosure, and these variations, uses, or adaptive changes follow the general principles of the present disclosure and include the common general knowledge or conventional technical means in the technical field not recorded in the present disclosure.

Claims

1. A hand function assessment method for burn rehabilitation, characterized in that: The method comprises: receiving a monitoring request sent by a user, wherein the monitoring request is used to monitor a target hand that is burned; Acquire a target video according to the monitoring request, where the target video is a video captured in real time of the target hand; Extracting a first joint position of the target hand at a first time point from the target video, and extracting a second joint position of the target hand at a second time point from the target video, wherein the first time point is earlier than the second time point; Analyze the first joint position and the second joint position to obtain the joint range of motion, and obtain the muscle strength value uploaded by the target device, wherein the muscle strength value is calculated by an electrical signal and a pressure value, wherein the electrical signal is a signal generated by the target hand when the target hand performs a grip strength test, and the pressure value is a pressure value corresponding to the grip strength test; Identifying the target hand in the target video to obtain a burn grade; The joint range of motion, the muscle strength value, and the burn grade are input into a preset assessment model for processing to obtain a first analysis result, and the first analysis result is displayed to the user.

2. The method according to claim 1, characterized in that The analyzing the first joint position and the second joint position to obtain the joint range of motion specifically includes: Performing joint recognition on the target hand in the target video to obtain multiple joint points; Acquire a target joint point from the plurality of joint points; Acquire the first joint position corresponding to the target joint point at the first time point, and acquire the second joint position corresponding to the target joint point at the second time point; Generating a first motion trajectory from the first joint position and the second joint position in chronological order; Acquire a reference position corresponding to the target joint point, and generate a second motion trajectory according to the reference position; Analyzing the first motion trajectory and the second motion trajectory to obtain a bending angle; A first duration corresponding to the first motion trajectory is obtained, and the first duration and the bending angle are calculated to obtain the joint range of motion, where the first duration is the duration from the first time point to the second time point.

3. The method according to claim 1, characterized in that After identifying the target hand in the target video and obtaining the burn grade, the method further includes: Acquire a second duration, where the second duration is the duration of the target hand from a third time point to the current time point, and the third time point is the starting time point when the target hand is burned; Acquire a first image from the target video, extract the first image, and obtain a target burn feature; Determining whether there is a scar feature in the target burn feature; When the scar feature does not exist in the target burn feature, the second duration, the joint range of motion, the muscle strength value and the burn grade are input into the preset evaluation model for processing to obtain a second analysis result.

4. The method according to claim 3, characterized in that: After determining whether scar features exist in the target burn features, the method further includes: When the scar feature exists in the target burn feature, obtaining the scar area of ​​the scar feature in the target burn feature, and receiving the pain level uploaded by the user; The scar grade is determined according to the scar area and the pain grade, and the scar grade, the joint range of motion, the muscle strength value and the burn grade are input into the preset evaluation model for processing to obtain a third analysis result.

5. The method according to claim 1, characterized in that The identifying the target hand in the target video to obtain the burn grade specifically includes: Acquire a second image from the target video, and identify the second image to obtain a first region, where the first region is a region corresponding to the complete target hand; Cutting out a second area from the first area, the second area being an area corresponding to the burn position in the target hand; Obtaining a burn area corresponding to the second region, and determining the depth of the burn position using a preset method to obtain a burn depth; The burn grade is determined according to the burn depth and the burn area.

6. The method according to claim 1, characterized in that After the joint range of motion, the muscle strength value and the burn grade are input into a preset assessment model for processing, a first analysis result is obtained, and the first analysis result is displayed to the user, the method further includes; receiving a training request sent by the user, wherein the training request is a state that the user expects the target hand to be rehabilitated accordingly; Inputting the first analysis result and the training request into a preset recommendation database for matching to obtain a first rehabilitation program; Acquire training steps from the first rehabilitation program, and convert the training steps into a preset training table; Obtaining a burn source corresponding to the target hand, and determining prohibited training information according to the burn source, wherein the burn source includes thermal burns, electrical burns, and chemical burns; Determine whether the prohibited training information exists in the preset training table; When the prohibited training information does not exist in the preset training table, the first rehabilitation program is recommended to the user.

7. The method according to claim 6, characterized in that After determining whether the prohibited training information exists in the preset training table, the method further includes: When the prohibited training information exists in the preset training table, appropriate training information is determined according to the source of the burn, the first rehabilitation plan is adjusted according to the appropriate training information to obtain a second rehabilitation plan, and the second rehabilitation plan is recommended to the user.

8. A hand function assessment system for burn rehabilitation, characterized in that: The system comprises a receiving unit (201), a processing unit (202) and a display unit (203). The receiving unit (201) receives a monitoring request sent by a user, wherein the monitoring request is used to monitor a target hand that has been burned; The processing unit (202) acquires a target video according to the monitoring request, the target video being a video shot in real time of the target hand; extracts a first joint position of the target hand corresponding to a first time point from the target video, and extracts a second joint position of the target hand corresponding to a second time point from the target video, the first time point being earlier than the second time point; The first joint position and the second joint position are analyzed to obtain the joint range of motion, and the muscle strength value uploaded by the target device is obtained, wherein the muscle strength value is calculated by an electrical signal and a pressure value, wherein the electrical signal is a signal generated by the target hand when the target hand is subjected to a grip strength test, and the pressure value is a pressure value corresponding to the grip strength test; the target hand in the target video is identified to obtain a burn grade; The display unit (203) inputs the joint range of motion, the muscle strength value and the burn grade into a preset assessment model for processing, obtains a first analysis result, and displays the first analysis result to the user.

9. An electronic device, characterized in that: The electronic device (300) comprises a processor (301), a memory (302), a user interface (303) and a network interface (304), wherein the memory (302) is used to store instructions, the user interface (303) and the network interface (304) are used to communicate with other devices, and the processor (301) is used to execute the instructions stored in the memory (302) so that the electronic device (300) executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is executed.

Images