Assessment method and device for joint rehabilitation training

Abstract

The invention discloses an evaluation method and device for joint rehabilitation training, and relates to the technical field of rehabilitation image processing. Receiving a monitoring request sent by a target user, and determining a to-be-evaluated part and rehabilitation duration according to the monitoring request; inputting the rehabilitation duration and the to-be-evaluated part into a preset training database for matching to obtain a first training plan; generating a first training video according to the first training plan, and obtaining a second training video corresponding to the target user; extracting a plurality of training images from the second training video, and processing a target training image to obtain a first training action; when the first training actions are in the preset action table, the first training actions are summarized into a first set, and a first number is obtained; and when the first number is not equal to a preset first number, determining that the target user is in a training abnormal state, and sending the training abnormal state to the target user. By implementing the technical scheme provided by the invention, the problem that the rehabilitation personnel are difficult to accurately evaluate the normalization of own actions in the training process is solved.

Description

Technical Field

[0001] This application relates to the technical field of rehabilitation image processing, and particularly relates to a method and device for evaluating joint rehabilitation training. Background Art

[0002] In the field of medical rehabilitation, rehabilitation treatment for patients with joint injuries plays a crucial role. After a joint is injured, the local area often exhibits symptoms such as swelling and pain. To effectively relieve these symptoms, rehabilitation treatment combines physical therapy and exercise therapy, aiming to promote blood circulation and thereby achieve the purpose of reducing swelling and pain. In addition, joint rehabilitation treatment also endeavors to improve the patient's daily activity ability, such as basic living skills like walking, going up and down stairs, dressing, and washing, thus significantly enhancing the patient's self-care ability.

[0003] However, during the implementation of joint rehabilitation treatment, since most joint rehabilitation training programs are executed by patients themselves, it is difficult for rehabilitation personnel to accurately evaluate the standardization of their own movements during the training process. This training mode lacking supervision and feedback may lead patients to practice with incorrect movements. Incorrect training movements not only fail to achieve the expected rehabilitation effect but may even delay the patient's rehabilitation process.

[0004] Therefore, there is an urgent need for a method and device for evaluating joint rehabilitation training that can solve the above technical problems. Summary of the Invention

[0005] This application provides a method and device for evaluating joint rehabilitation training, which effectively solves the problem that it is difficult for rehabilitation personnel to accurately evaluate the standardization of their own movements during the training process, thereby improving the accuracy of rehabilitation training.

[0006] In a first aspect, the present application provides a method for evaluating joint rehabilitation training, which is applied to a server. The method includes: receiving a monitoring request sent by a target user, determining the part to be evaluated and the rehabilitation duration according to the monitoring request, where the part to be evaluated includes the arm joint part, the thigh joint part, and the calf joint part, and the rehabilitation duration is the duration since the target user started rehabilitation training; inputting the rehabilitation duration and the part to be evaluated into a preset training database for matching to obtain a first training plan; generating a first training video according to the first training plan and sending the first training video to the target device so that the target user can view the first training video through the target device; obtaining a second training video corresponding to the target user, where the second training video is a video of the target user performing rehabilitation training according to the first training video; extracting a plurality of training images from the second training video and processing the target training image to obtain a first training action, where the target training image is any one of the plurality of training images; determining whether the first training action is in a preset action table, where the preset action table is a table made up of all actions in the first training video; when the first training action is in the preset action table, classifying the first training action into a first set and obtaining a first quantity, where the first quantity is the total number of first training actions in the first set; determining whether the first quantity is equal to a preset first quantity, where the preset first quantity is the total number of second training actions in the first training video; when the first quantity is not equal to the preset first quantity, determining that the target user is in a training abnormal state and sending the training abnormal state to the target user so that the target user can perform corresponding operations according to the training abnormal state.

[0007] By adopting the above technical solution, receiving the monitoring request of the target user, and matching the most suitable first training plan from the preset training database according to the part to be evaluated and the rehabilitation duration of the target user, this personalized training plan helps to ensure that the user receives professional guidance that meets their rehabilitation needs from the very beginning. Generating a first training video according to the first training plan and sending it to the target user, this visual training guidance method enables the user to clearly see the correct training actions. By obtaining the second training video of the target user performing rehabilitation training according to the first training video, the user's training actions can be monitored in real time. By extracting training images from the second training video and processing them to obtain the first training action, it can be determined whether the user's action is consistent with the standard action in the preset action table. When the first training action is consistent with the standard action, the first training action is classified into the first set and the first quantity of the first training actions in the first set is counted. When the first quantity is not equal to the preset first quantity, it is determined that the target user is in a training abnormal state, and a reminder of the training abnormal state is immediately sent to the target user. This automated evaluation ensures that the target user can promptly discover and correct incorrect training actions. Based on continuous monitoring and evaluation, the user can perform training according to the correct actions, thereby avoiding the impact caused by the user performing training according to incorrect actions.

[0008] Optionally, before matching the rehabilitation duration and the part to be evaluated with a preset training database to obtain a first training plan, the method further includes: obtaining personal information corresponding to the target user, where the personal information includes age information, gender information, and occupation information; receiving a target rehabilitation requirement sent by the target user, where the target rehabilitation requirement is the rehabilitation result expected by the target user for the part to be evaluated; analyzing the part to be evaluated according to the target rehabilitation requirement to obtain a training level; determining whether the training level is consistent with a preset level, where the preset level is a standard training level obtained by analyzing the part to be evaluated according to the personal information; when the training level is consistent with the preset level, inputting the target rehabilitation requirement, the rehabilitation duration, and the part to be evaluated into the preset training database for matching to obtain a second training plan.

[0009] By adopting the above technical solution, obtaining personal information such as the age, gender, and occupation of the target user can more comprehensively understand the user's physical condition and potential needs. Then, combined with the target rehabilitation requirement sent by the target user, the part to be evaluated is deeply analyzed to determine a suitable training level. The training level obtained by analyzing the target rehabilitation requirement is compared with the preset level obtained by analyzing the personal information. When the training level is not consistent with the preset level, the target rehabilitation requirement, the rehabilitation duration, and the part to be evaluated are input into the preset training database for precise matching. This matching method ensures that the training plan not only conforms to the user's physical condition but also meets the user's rehabilitation needs. The personalized training plan helps to avoid overtraining and thus improves the effectiveness of rehabilitation training.

[0010] Optionally, generating a first training video according to the first training plan specifically includes: determining a plurality of training contents from the first training plan; converting the plurality of training contents into a plurality of training actions according to the part to be evaluated; sorting the plurality of training actions in chronological order to obtain the first training video.

[0011] By adopting the above technical solution, determining a plurality of training contents from the first training plan makes the training objectives more clear and specific. Each training content targets a specific muscle group or joint part, which helps the user to concentrate on targeted training. Converting the training contents into training actions according to the part to be evaluated ensures that the training actions are closely related to the user's rehabilitation needs. Sorting the plurality of training actions in chronological order ensures the orderliness and coherence of the training process. By generating the first training video, the training actions are presented to the user in an intuitive and dynamic way. This visual training guidance method makes it easier for the user to understand and imitate the correct training actions, improving the accuracy and efficiency of training.

[0012] Optionally, determining whether the first training action is in the preset action table specifically includes: extracting the action posture and motion parameters corresponding to the first training action from the target training image, where the motion parameters include angle parameters and displacement parameters; determining whether the action posture is in the preset posture table; when the action posture is in the preset posture table, determining whether the motion parameters are within the preset parameter range, and the preset parameter range is the motion parameter range corresponding to the action posture in the preset posture table; when the motion parameters are within the preset parameter range, determining that the first training action is in the preset action table.

[0013] By adopting the above technical solution, the action posture and motion parameters (including angle parameters and displacement parameters) corresponding to the first training action are extracted from the target training image, and the extracted action posture is compared with the preset posture table, so that it can be quickly identified whether the action posture belongs to the preset action set, thereby realizing the preliminary classification and recognition of the action. After confirming that the action posture is in the preset posture table, it is further determined whether the motion parameters are within the preset parameter range, ensuring the accuracy and compliance of the action. When the motion parameters are within the preset parameter range, it can be determined that the first training action is in the preset action table, which means that the first training action meets the preset standards and requirements.

[0014] Optionally, after when the motion parameters are within the preset parameter range, the method further includes: obtaining the body parameters corresponding to the target user, where the body parameters are the body change parameters of the target user in the first training action using the target sensor, and the body parameters include strength parameters and balance parameters; analyzing the first training action through the strength parameters and the balance parameters to obtain a standard level; determining whether the standard level is in the preset standard level table, and the preset standard level table is the standard level corresponding to each preset training action in the preset action table; when the standard level is in the preset standard level table, determining that the first training action is in the preset action table.

[0015] By adopting the above technical solution, the body parameters (including strength parameters and balance parameters) of the target user during the first training action are obtained, realizing the accurate evaluation of the quality of the training action; analyzing the first training action in combination with the strength parameters and the balance parameters can obtain the standard level of the action. By comparing the standard level of the first training action with the preset standard level table, it can be determined whether the first training action belongs to the standard actions in the preset action table. Accurately evaluating the training action can adjust the training plan according to the actual performance of the user, ensuring that the training content not only conforms to the physical condition of the user but also effectively improves the training effect.

[0016] Optionally, after determining that the target user is in an abnormal training state when the first quantity is not equal to the preset first quantity, the method further includes: obtaining a target difference, where the target difference is the difference between the first quantity and the preset first quantity; determining a to-be-trained action from a preset action table and a first set, where the to-be-trained action is an action that the target user trains irregularly in a second training video; determining a third training plan based on the to-be-trained action and a rehabilitation duration, and sending the third training plan to the target user.

[0017] By adopting the above technical solution, calculating the difference between the first quantity (the number of actions that the target user has trained in the second training video) and the preset first quantity (the expected or recommended number of training actions) can accurately identify the actions that the target user has not reached or has not been fully trained during the training process, that is, the to-be-trained actions. Then, a third training plan is formulated based on the to-be-trained actions and the rehabilitation duration. The third training plan helps the target user focus on the to-be-trained actions, avoid repeating the actions that have been mastered, and improve the training efficiency.

[0018] Optionally, after determining whether the first training action is in the preset action table, the method further includes: when the first training action is not in the preset action table, determining to classify the first training action into a second set; obtaining a second quantity from the second set and determining whether the second quantity is greater than a preset second quantity; when the second quantity is greater than the preset second quantity, determining to obtain a third training action from the second set and generating a fourth training plan according to the third training action.

[0019] By adopting the above technical solution, when the first training action is not in the preset action table, classifying the first training action into the second set and determining whether the second quantity in the second set is greater than the preset second quantity can intelligently identify which non-standard actions may need to be included in the training plan. When the second quantity is greater than the preset second quantity, obtaining the third training action from the second set and generating a fourth training plan according to these actions. The generation process of the fourth training plan fully considers the personalized needs and training history of the user, ensuring the pertinence and effectiveness of the training plan.

[0020] In the second aspect of the present application, an evaluation device for joint rehabilitation training is provided. The device is a server, which includes a receiving unit, a processing unit, and a sending unit. The receiving unit receives a monitoring request sent by a target user, determines the part to be evaluated and the rehabilitation duration according to the monitoring request. The part to be evaluated includes the arm joint part, the thigh joint part, and the calf joint part. The rehabilitation duration is the duration since the target user started rehabilitation training. The processing unit inputs the rehabilitation duration and the part to be evaluated into a preset training database for matching to obtain a first training plan; generates a first training video according to the first training plan and sends the first training video to the target device so that the target user can view the first training video through the target device; obtains a second training video corresponding to the target user, where the second training video is a video of the target user performing rehabilitation training according to the first training video; extracts multiple training images from the second training video and processes the target training image to obtain a first training action, where the target training image is any one of the multiple training images; determines whether the first training action is in a preset action table, and the preset action table is a table made up of all actions in the first training video; when the first training action is in the preset action table, incorporates the first training action into a first set and obtains a first quantity, where the first quantity is the total number of the first training actions in the first set; determines whether the first quantity is equal to a preset first quantity, and the preset first quantity is the total number of second training actions in the first training video; the sending unit, when the first quantity is not equal to the preset first quantity, determines that the target user is in an abnormal training state and sends the abnormal training state to the target user so that the target user can perform corresponding operations according to the abnormal training state.

[0021] Optionally, the receiving unit is used to obtain personal information corresponding to the target user, where the personal information includes age information, gender information, and occupation information; receive a target rehabilitation requirement sent by the target user, and the target rehabilitation requirement is the rehabilitation result expected by the target user for the part to be evaluated. The processing unit is used to analyze the part to be evaluated according to the target rehabilitation requirement to obtain a training level; determine whether the training level is consistent with a preset level, and the preset level is a standard training level obtained by analyzing the part to be evaluated according to the personal information; when the training level is consistent with the preset level, input the target rehabilitation requirement, the rehabilitation duration, and the part to be evaluated into a preset training database for matching to obtain a second training plan.

[0022] Optionally, the processing unit is used to determine multiple training contents from the first training plan; convert the multiple training contents into multiple training actions according to the part to be evaluated; sort the multiple training actions in chronological order to obtain a first training video.

[0023] Optionally, the processing unit is configured to extract the action posture and motion parameters corresponding to the first training action from the target training image, where the motion parameters include an angle parameter and a displacement parameter; determine whether the action posture is in a preset posture table; when the action posture is in the preset posture table, determine whether the motion parameters are within a preset parameter range, where the preset parameter range is the motion parameter range corresponding to the action posture in the preset posture table; when the motion parameters are within the preset parameter range, determine that the first training action is in the preset action table.

[0024] Optionally, the receiving unit is configured to obtain the body parameters corresponding to the target user, where the body parameters are the body change parameters of the target user in the first training action using the target sensor, and the body parameters include a strength parameter and a balance parameter; the processing unit is configured to analyze the first training action through the strength parameter and the balance parameter to obtain a standard level; determine whether the standard level is in a preset standard level table, where the preset standard level table is the standard level corresponding to each preset training action in the preset action table; when the standard level is in the preset standard level table, determine that the first training action is in the preset action table.

[0025] Optionally, the receiving unit is configured to obtain a target difference, where the target difference is the difference between a first quantity and a preset first quantity; the processing unit is configured to determine a to-be-trained action from the preset action table and a first set according to the target difference, where the to-be-trained action is an action that the target user trains irregularly in the second training video; the sending unit is configured to determine a third training plan based on the to-be-trained action and the rehabilitation duration, and send the third training plan to the target user.

[0026] Optionally, when the first training action is not in the preset action table, the processing unit is configured to determine to classify the first training action into a second set; the receiving unit is configured to obtain a second quantity from the second set and determine whether the second quantity is greater than a preset second quantity; when the second quantity is greater than the preset second quantity, the processing unit is configured to determine to obtain a third training action from the second set and generate a fourth training plan according to the third training action.

[0027] In a third aspect of the present application, an electronic device is provided, where the electronic device includes a processor, a memory, a user interface, and a network interface. The memory is configured to store instructions, the user interface and the network interface are configured to communicate with other devices, and the processor is configured to execute the instructions stored in the memory, so that the 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, where 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. Receive the monitoring request of the target user, match the most suitable first training plan from the preset training database according to the part to be evaluated and the rehabilitation duration of the target user. This personalized training plan helps to ensure that the user receives professional guidance that meets their rehabilitation needs from the very beginning. Generate a first training video according to the first training plan and send it to the target user. This visual training guidance method enables the user to clearly see the correct training actions. By obtaining the second training video of the target user's rehabilitation training according to the first training video, the training actions of the user can be monitored in real time. By extracting training images from the second training video and processing them to obtain the first training actions, it can be determined whether the user's actions are consistent with the standard actions in the preset action table. When the first training actions are consistent with the standard actions, the first training actions are classified into the first set, and the first quantity of the first training actions in the first set is counted. When the first quantity is not equal to the preset first quantity, it is determined that the target user is in an abnormal training state, and a reminder of the abnormal training state is immediately sent to the target user. This automated evaluation ensures that the target user can promptly discover and correct incorrect training actions. Based on continuous monitoring and evaluation, the user is trained according to the correct actions, thereby avoiding the impact caused by training according to incorrect actions.

[0030] 2. Obtain the body parameters (including strength parameters and balance parameters) of the target user during the first training actions to achieve accurate evaluation of the quality of the training actions; analyze the first training actions by combining the strength parameters and balance parameters to obtain the standard level of the actions. By comparing the standard level of the first training actions with the preset standard level table, it can be determined whether the first training actions belong to the standard actions in the preset action table. Accurately evaluating the training actions can adjust the training plan according to the actual performance of the user, ensuring that the training content not only conforms to the user's physical condition but also effectively improves the training effect. Description of the Drawings

[0031] Figure 1 is a schematic flowchart of a method for evaluating joint rehabilitation training provided by an embodiment of the present application; Figure 2 is a schematic structural diagram of an apparatus for evaluating joint rehabilitation training provided by an embodiment of the present application; Figure 3 is a schematic 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, sending 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 technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all of the embodiments.

[0034] In the description of the embodiments of this 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 this 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 the relevant concepts in a specific manner.

[0035] In the description of the embodiments of this application, the meaning of the term "plurality" refers to two or more. For example, a plurality of systems refers to two or more systems, and a plurality of screen terminals refers to 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 indicating the technical features indicated. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. The terms "include", "comprise", "have" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0036] In the field of medical rehabilitation, the rehabilitation treatment for patients with joint injuries occupies a crucial position. After a joint is damaged, the local area often exhibits symptoms of swelling and pain. In order to effectively relieve these symptoms, the rehabilitation treatment adopts a combination of physical therapy and exercise therapy, aiming to promote blood circulation and thereby achieve the purpose of reducing swelling and pain. In addition, joint rehabilitation treatment also endeavors to improve the patient's daily activity ability, such as basic life skills like walking, going up and down stairs, dressing and washing, thus significantly enhancing the patient's self-care ability.

[0037] However, during the implementation of joint rehabilitation treatment, since most joint rehabilitation training programs are executed by the patients themselves, and during the training process, it is difficult for rehabilitation personnel to accurately evaluate the standardization of their own movements. This training mode lacking supervision and feedback may lead to patients practicing with incorrect movements, and incorrect training movements not only fail to achieve the expected rehabilitation effect, but may instead delay the patient's rehabilitation process.

[0038] Therefore, how to solve the problem that it is difficult for rehabilitation personnel to accurately evaluate their own movement specifications during the training process. An evaluation method for joint rehabilitation training provided by an embodiment of the present application is applied to a server. The server of the present application can be a platform that provides monitoring services for joint rehabilitation training in the medical industry. Figure 1 It is a schematic flowchart of an evaluation method for joint rehabilitation training provided by an embodiment of the present application. Refer to Figure 1 and this method includes the following steps S101 - S108.

[0039] S101: Receive a monitoring request sent by a target user, and determine the part to be evaluated and the rehabilitation duration according to the monitoring request.

[0040] In the above S101, the target user refers to the rehabilitation personnel undergoing joint rehabilitation treatment. When the rehabilitation personnel carry out rehabilitation training according to the rehabilitation plan, in order to ensure the smooth progress of the rehabilitation process, they need to exercise according to the training actions corresponding to the rehabilitation plan. During the exercise process, it is impossible to ensure whether the training actions performed by the rehabilitation personnel are standardized. In the past, it was only possible to rely on medical personnel to evaluate the training effect of the rehabilitation personnel over a certain period of time, but this kind of evaluation is an after - operation, and it cannot solve the problem that it is difficult for rehabilitation personnel to evaluate the standardization of their own training actions during the training process, resulting in an impact on the rehabilitation progress of the rehabilitation personnel. To solve the problem that it is difficult to evaluate the standardization of their own training actions during the training process, the present application obtains the monitoring request sent by the rehabilitation personnel, analyzes the monitoring request, and then obtains the training plan. Then, it monitors the process of the rehabilitation personnel exercising according to the training plan, and further analyzes the monitored images to determine whether the training actions of the rehabilitation personnel are standardized. The rehabilitation personnel can monitor their training actions in real - time during the training process, which can avoid the rehabilitation personnel using non - standard training actions for exercise, thus affecting the rehabilitation progress. Next, it will be explained in detail how the present application evaluates the training of the rehabilitation personnel. The target user sends a monitoring request through an application program, a web page or a user device. After the server receives the monitoring request, it analyzes the information in the monitoring request to obtain the user's identity identifier, the part to be evaluated, and the rehabilitation duration. At this time, the identity identifier is the name of the target user, the part to be evaluated refers to the damaged joint part, and the parts to be evaluated include the arm joint part, the thigh joint part, and the calf joint part. The rehabilitation duration is the duration since the target user started rehabilitation training, that is, the duration from the start of rehabilitation training to the present.

[0041] S102: Input the rehabilitation duration and the part to be evaluated into a preset training database for matching to obtain a first training plan.

[0042] In the above S102, when determining the rehabilitation duration and the part to be evaluated of the target user, before inputting the rehabilitation duration and the part to be evaluated into the preset training database for matching, it is necessary to construct the preset training database, which contains training plans for different parts and different rehabilitation durations. Use the part to be evaluated and the rehabilitation duration as query conditions to search for a matching training plan in the preset training database, and take the obtained matching training plan as the first training plan.

[0043] In addition, in addition to determining the training plan through the part to be evaluated and the rehabilitation duration, a personalized training plan can also be formulated according to the rehabilitation needs and personal circumstances of the user, so as to provide the target user with a rehabilitation training plan that meets their own needs. Specifically, before inputting the rehabilitation duration and the part to be evaluated into the preset training database for matching to obtain the first training plan, the method further includes: obtaining the personal information corresponding to the target user, where the personal information includes age information, gender information, and occupation information; receiving the target rehabilitation needs sent by the target user, where the target rehabilitation needs are the rehabilitation results expected by the target user for the part to be evaluated; analyzing the part to be evaluated according to the target rehabilitation needs to obtain a training level; determining whether the training level is consistent with the preset level, where the preset level is the standard training level obtained by analyzing the part to be evaluated according to the personal information; when the training level is consistent with the preset level, input the target rehabilitation needs, the rehabilitation duration, and the part to be evaluated into the preset training database for matching to obtain the second training plan.

[0044] Specifically, the target user can register on the platform in advance. When registering, the user needs to upload personal birth month information and gender information for subsequent extraction of the target user's personal information. When the target user has already registered on the platform, the age information can be extracted from the user database based on the target user's name or account, and then the gender information can be extracted from the user database. Occupational information is not required to be filled in by the user during registration, and the occupational information of the target user can be obtained through questionnaires and self-filling by the user. Occupational information is crucial for subsequent analysis of the target user's rehabilitation needs and formulation of personalized rehabilitation plans. The target user can send their rehabilitation needs to the platform through the system interface, mobile application, phone, or other means. The rehabilitation needs should be clear and specific. For example, when the part to be evaluated is the hand, the rehabilitation need is "expecting to restore the basic motor function of the upper limb within three months". Based on the rehabilitation needs provided by the target user, determine the part to be evaluated, such as the upper limb, lower limb, waist, etc. Conduct a detailed medical evaluation of the part to be evaluated, including examinations of the degree of dysfunction, muscle strength, joint range of motion, etc. Based on the medical evaluation results, combined with the target user's personal information (such as age, gender, occupation, etc.), determine the training level. The training level should reflect the target user's rehabilitation potential for the part to be evaluated and the required training intensity. The preset level is a standard training level formulated based on the rehabilitation data of a large number of similar patients and medical expertise. It reflects the training intensity that the part to be evaluated should reach under different personal information and target rehabilitation needs. At this time, the preset level is the maximum training intensity determined based on the target user's personal information and the part to be evaluated. For example, when the target user is older, considering the actual situation, the preset level needs to be set lower because older rehabilitation personnel cannot adapt to a large training intensity. Compare the target user's training level with the preset level to determine whether they are consistent. If they are consistent, it means that the target user's rehabilitation needs and training intensity are in line with the preset standard, and a rehabilitation plan can be further formulated. Input information such as the target rehabilitation needs, rehabilitation duration (such as three months), and the part to be evaluated into the preset training database. The preset training database automatically matches the most suitable rehabilitation plan based on the input information. The rehabilitation plan should include specific training content, training frequency, training intensity, etc. Output the matched second training plan to the target user and guide them to execute it.

[0045] S103: Generate a first training video according to the first training plan and send the first training video to the target device so that the target user can view the first training video through the target device.

[0046] In the above S103, after obtaining the first training plan, according to the first training plan, a corresponding first training video is generated. The first training video involves animations, live demonstrations, or mixed content. Generating the first training video according to the first training plan specifically includes: determining multiple training contents from the first training plan; converting the multiple training contents into multiple training actions according to the part to be evaluated; sorting the multiple training actions in chronological order to obtain the first training video. Specifically, the first training plan is usually a comprehensive plan that contains a series of training suggestions and requirements for the part to be evaluated. First, it is necessary to conduct a detailed analysis of the first training plan to understand each part and key point therein. Based on the analysis, specific training contents are extracted from the first training plan. These training contents may be exercises for a certain muscle group, training of a certain motor skill, or activities designed to achieve specific rehabilitation goals. The extracted training contents are classified and sorted for better subsequent conversion into training actions. Conduct a detailed medical and physiological analysis of the part to be evaluated to understand its structure, function, possible problems, and rehabilitation goals. This helps determine which training actions are suitable for this part and how these actions should be performed to achieve the best results. According to the analysis results of the part to be evaluated, convert the previously extracted training contents into specific training actions. This process may require combining professional knowledge and experience to ensure that the converted training actions not only meet the rehabilitation goals but also suit the actual situation of the target users. During the conversion process, it may be necessary to optimize and adjust the training actions to ensure their safety, effectiveness, and feasibility. This may include adjusting parameters such as the difficulty, amplitude, and speed of the actions, or adding some auxiliary actions to enhance the effect. Before sorting, it is necessary to determine some sorting principles, such as from easy to difficult, from simple to complex, from local to whole body, etc. These principles should be determined according to the characteristics of the part to be evaluated, the rehabilitation goals, and the actual situation of the target users. According to the determined sorting principles, sort the multiple training actions obtained by conversion. Ensure that the connection between each action is smooth and conforms to logic and the rehabilitation process. After sorting is completed, the production of the first training video can begin. That is, each training action is input into the video database for query. When obtaining the sub-video corresponding to a single training action, then integrate and add subtitles to each sub-video according to the sorting principles, and then obtain the combined training video. During the production process, it is necessary to ensure that the video content is clear, accurate, easy to understand, and conforms to the viewing habits and preferences of the target users. After production is completed, review the combined training video to ensure that it meets all requirements and there are no omissions or errors. After passing the review, output the combined training video as the first training video. By determining training contents from the first training plan, converting training actions according to the part to be evaluated, and producing a training video by sorting in chronological order, a personalized rehabilitation training plan is provided for the target users.Avoid presenting training content to users only through text, which may lead to misunderstandings by users.

[0047] In addition, after generating the first training video, send the generated first training video to the target device via the network. The target device refers to smartphones, tablets, smart TVs, rehabilitation screens, etc. After receiving the first training video, the target device displays the first training video on the screen for the target user to view.

[0048] S104: Obtain the second training video corresponding to the target user. The second training video is a video of the target user performing rehabilitation training according to the first training video.

[0049] In the above S104, the target user selects an appropriate rehabilitation time based on the actual situation and then views the first training video through the target device. When the target user views the first training video through the target device, it is assumed that the target user starts exercising, and the status of the target user can be captured by a pre-installed camera. The camera can be installed in the target device. The camera records the video of the target user performing rehabilitation training according to the first training video and outputs the recorded video as the second training video. At this time, the second training video is a video for real-time monitoring of the training process of the target user. The target device then sends the captured second training video to the server.

[0050] S105: Extract multiple training images from the second training video, process the target training image to obtain the first training action, and determine whether the first training action is in the preset action table.

[0051] In the above S105, after receiving the second training video, use video processing technology to sort the second training video into multiple training images, with one training image corresponding to one complete training action. Process each training image to identify and extract the training action of the target user. Computer vision technology such as pose estimation or action recognition can be used. Taking any one of the multiple training images as an example, that is, the target training image, first preprocess the target training image, then recognize the action in the target training image, and then output the recognized action, which is the first training action. After obtaining the first training action, compare the extracted first training action with the actions in the preset action table. The preset action table contains the characteristics of all actions in the first training video, and by comparing, it is determined whether the actual training action of the target user is correct or standard.

[0052] In addition, determining whether the first training action is in the preset action table specifically includes: extracting the action posture and motion parameters corresponding to the first training action from the target training image, where the motion parameters include angle parameters and displacement parameters; determining whether the action posture is in the preset posture table; when the action posture is in the preset posture table, determining whether the motion parameters are within the preset parameter range, and the preset parameter range is the motion parameter range corresponding to the action posture in the preset posture table; when the motion parameters are within the preset parameter range, determining that the first training action is in the preset action table. Specifically, first, preprocess the target training image, including operations such as denoising, enhancing contrast, and adjusting brightness, to improve the accuracy of subsequent processing. Use computer vision techniques, such as edge detection, corner detection, or deep learning models, to detect feature points related to the first training action from the image. These feature points may represent human joints, bones, or other key parts. According to the detected feature points, construct the action posture of the human body. This usually involves connecting the feature points into bone lines or contours to form a representation of the human body's action posture. Calculate the motion parameters related to the first training action, including angle parameters and displacement parameters. The angle parameters may involve the angle changes between joints, that is, record the angle changes of each joint (such as shoulders, elbows, hips, knees, etc.) of the user in the actual action, and the displacement parameters may involve the position changes of the feature points in the image, that is, measure the speed changes of the user when performing the action, including the starting speed, maximum speed, and average speed, etc. Then calculate the similarity between the extracted action posture and the standard action postures in the preset posture table. This can be achieved by comparing the positions of the feature points, the lengths and angles of the bone lines, etc. The preset posture table is a database containing various standard action postures. These standard action postures may be stored in the form of images, bone models, or parameterized forms. According to the similarity calculation results, determine whether the extracted action posture matches a certain standard action posture in the preset posture table. If the similarity exceeds a certain threshold, it is considered a successful match. When the action posture is in the preset posture table, for each standard action posture in the preset posture table, a motion parameter range is defined. This range may involve the maximum and minimum values of the angle parameters, as well as the threshold of the displacement parameters, etc. Compare the extracted motion parameters with the preset parameter range. This includes comparing whether the angle parameters are between the specified maximum and minimum values, and whether the displacement parameters exceed a certain threshold. If the extracted motion parameters are all within the preset parameter range, it is considered that these parameters are valid and conform to the standard action postures in the preset posture table. The preset action table is a database containing various standard training actions. These standard training actions may be stored in the form of action postures and motion parameters and are associated with specific training objectives or tasks. When a matching item is found for the extracted action posture in the preset posture table and the motion parameters are also within the preset parameter range, it can be determined that the first training action is in the preset action table. This means that the first training action conforms to a certain standard training action in the preset action table.

[0053] Further, when the action posture is not in the preset posture table, it is determined that the first training action is not in the preset action table.

[0054] Furthermore, in addition to judging the training actions of the target user from the images, the body parameters of the target user can be obtained, and the training actions can be compared according to the measured body parameters, which helps to accurately identify and evaluate the first training action, provide personalized training guidance for the target user, improve the training effect and reduce the training risk. Specifically, it includes: obtaining the body parameters corresponding to the target user, where the body parameters are the body change parameters of the target user in the first training action measured by the target sensor, and the body parameters include strength parameters and balance parameters; analyzing the first training action through the strength parameters and balance parameters to obtain a standard level; judging whether the standard level is in the preset standard level table, and the preset standard level table is the standard level corresponding to each preset training action in the preset action table; when the standard level is in the preset standard level table, determining that the first training action is in the preset action table. Specifically, ensure that the target user is in a state suitable for performing the training action, such as having done appropriate warm-up, wearing suitable sports equipment, and understanding the basic requirements of the upcoming training action. Select appropriate target sensors that can accurately measure the body change parameters of the target user in the first training action. Common sensors include force sensors (for measuring strength parameters), balance sensors (for measuring balance parameters), etc. Correctly install the sensors on the target user to ensure that they can accurately capture the required body change parameters. Let the target user perform the first training action while starting the sensors to collect data. The sensors will record in real time the strength parameters (such as muscle strength, explosive power, etc.) and balance parameters (such as body stability, balance control, etc.) of the target user during the execution of the training action. Process and analyze the collected data to extract the specific values of the strength parameters and balance parameters. It may be necessary to perform preprocessing operations such as filtering and denoising on the data to improve the accuracy of the analysis. Evaluate the standard level of the first training action according to the values of the strength parameters and balance parameters. This may involve comparing the actual parameters with the preset standard range or threshold to determine whether the training action has reached a certain specific standard level. The determination of the standard level may need to refer to professional training guidelines, sports physiology knowledge, or the opinions of experts in related fields. The preset standard level table is a database containing the standard levels corresponding to each preset training action. These standard levels may be formulated based on professional training guidelines, sports physiology knowledge, or the opinions of experts in related fields. When constructing the preset standard level table, it is necessary to ensure that each preset training action has a corresponding standard level, and these levels can accurately reflect the difficulty and requirements of the training action. Compare the standard level obtained through the evaluation of the strength parameters and balance parameters with the levels in the preset standard level table. If the evaluated standard level matches a certain level in the preset standard level table, it indicates that the first training action meets the requirements of that level.When the obtained standard level matches the level in the preset standard level table, further confirm that the first training action is in the preset action table.

[0055] S106: When the first training action is in the preset action table, classify the first training action into the first set and obtain the first quantity.

[0056] In S106 above, when a matching item for the first training action is found in the preset action table, classify the first training action into the first set. Then, in accordance with the above processing method for the first training action, process each training action in multiple training images in sequence and classify the processed results into their respective corresponding sets. After determining that all training actions in the multiple training images have been processed, obtain the quantity of all training actions included in the first set, that is, the first quantity.

[0057] Further, when the first training action is not in the preset action list, it is determined to classify the first training action into the second set; obtain the second quantity from the second set, and determine whether the second quantity is greater than the preset second quantity; when the second quantity is greater than the preset second quantity, it is determined to obtain the third training action from the second set, and generate the fourth training plan according to the third training action. Specifically, after performing the previous steps (such as determining whether the first training action is in the preset action list), if it is found that the first training action is not in the preset action list, this means that the action may be a new, unclassified action, or an action that does not conform to the current training plan. The second set is a set used to store these training actions that are not in the preset action list. If this is the first time an action not in the preset action list is encountered, a new second set may need to be created. If there has been a similar situation before, then this new first training action can be added to the existing second set. When classifying the first training action into the second set, relevant information about the action, such as the action name, description, execution method, etc., needs to be recorded. After classifying all the training actions in multiple training images, obtain the second quantity from the second set. The second quantity refers to the number of training actions stored in the second set. This can be obtained by counting the elements in the second set. The preset second quantity is a threshold used to determine whether the number of actions in the second set has reached a level that requires further action. This threshold may be set based on various factors, such as the update frequency of the training plan, the training needs of the target user, etc. Compare the calculated second quantity with the preset second quantity. If the second quantity is greater than the preset second quantity, it means that enough incorrect actions have accumulated in the second set, and further action needs to be taken to handle these actions. By analyzing all the incorrect actions in the second set, all the standard actions corresponding to all the incorrect actions are obtained, and then a new training plan, that is, the fourth training plan, is generated according to the action difficulty. This training plan includes key information such as specific training actions, training frequencies, and training durations. Send the generated fourth training plan to the target user and remind them to train according to the plan. After sending, the training progress and effects of the target user can be followed up regularly to provide necessary support and guidance.

[0058] S107: Determine whether the first quantity is equal to the preset first quantity, where the preset first quantity is the total number of second training actions in the first training video.

[0059] In the above S107, after obtaining the first quantity from the first set, then obtain the preset first quantity from the first training video. The preset first quantity refers to the total number corresponding to all the training actions in the first training video. Compare the first quantity with the preset first quantity to determine whether they are equal.

[0060] S108: When the first quantity is not equal to the preset first quantity, determine that the target user is in an abnormal training state, and send the abnormal training state to the target user so that the target user can perform corresponding operations according to the abnormal training state.

[0061] In the above S108, if the first quantity is not equal to the preset first quantity, determine that the target user is in an abnormal training state. Generate a message containing the abnormal training state information according to the abnormal training state, and send it to the target user through the network. The target user receives the message and performs corresponding operations according to the provided abnormal training state information, such as adjusting the training plan, seeking professional guidance, etc.

[0062] In addition, after receiving the abnormal training state, the target user needs to formulate a new training plan according to the actual situation. The new training plan needs to be generated according to the target quantity. Since there are two cases for not equal, the first case is that the first quantity is less than the preset first quantity, that is, the number of training actions of the target user in the second training video is less than the number of standard actions in the first training video. At this time, it is defaulted that there are missing training actions when the target user exercises according to the first training video. It is necessary to determine the missing training actions, and then formulate a new training plan for the target user to retrain. The second case is that the first quantity is greater than the preset first quantity, that is, the number of training actions of the target user in the second training video exceeds the number of standard actions in the first training video. At this time, it is defaulted that there are extra training actions when the target user exercises according to the first training video. It is necessary to check each training action in the second training video one by one, and then find out the extra or incorrect training actions, and formulate a new training plan according to the incorrect training actions for the target user to retrain.

[0063] Furthermore, by obtaining the target difference between the first quantity and the preset first quantity, generating a third training plan based on the target difference, and sending the third training plan to the target user, precise guidance and personalized support for the training process of the target user are achieved, which helps to improve the training effect and promote the physical rehabilitation of the target user. Specifically, it includes: obtaining the target difference, which is the difference between the first quantity and the preset first quantity; determining the actions to be trained from the preset action table and the first set, where the actions to be trained are the actions that the target user trained irregularly in the second training video; determining the third training plan based on the actions to be trained and the rehabilitation duration, and sending the third training plan to the target user. Specifically, the first quantity usually refers to the number of times the target user correctly completed a certain or certain training actions in the second training video, that is, obtained from the first set. The preset first quantity is a standard value, which represents the total number of training actions that the target user should correctly complete according to the first training video. The target difference is the difference between the first quantity and the preset first quantity. This difference can be obtained through simple mathematical operations. According to the target difference, determine the actions to be trained from the preset action table and the first set. That is, compare each first training action in the first set with the preset action table in turn to determine whether all the first training actions in the first set appear in the preset action table. If there is a standard action in the preset action table that does not match each training action in the first set, the unmatched standard action can be screened out and used as the action to be trained for output. The actions to be trained are the actions that the target user trained irregularly or did not complete the expected number of times in the second training video. Through comparison and analysis, these actions can be determined and used as the focus of subsequent training. When all the standard actions in the preset action table match each training action in the first set, it can be defaulted that there are no actions to be trained. Then, analyze according to the actions to be trained and the rehabilitation duration (the duration since the target user started rehabilitation) to obtain the third training plan, which should include key information such as specific training actions, the number of repetitions of each action, training frequency (such as how many times to train per day), and training duration (such as how long to train each time). When designing the plan, it is necessary to ensure that the difficulty and intensity of the training actions are appropriate, which can challenge the ability of the target user without causing excessive physical burden. Organize the third training plan into a format that is easy to understand and operate, such as text description, chart, or video tutorial, etc. According to the preferences of the target user and the available devices, select a suitable sending method. This may include email, text message, social media message, in-rehabilitation application notification, etc. Send the third training plan to the target user and remind them to train according to the plan. After sending, the training progress and effect of the target user can be followed up regularly to provide necessary support and guidance.

[0064] Through the above method, receive the monitoring request of the target user, match the most suitable first training plan from the preset training database according to the part to be evaluated and the rehabilitation duration of the target user. This personalized training plan helps to ensure that the user receives professional guidance that meets their rehabilitation needs from the very beginning. Generate the first training video according to the first training plan and send it to the target user. This visual training guidance method enables the user to clearly see the correct training actions. By obtaining the second training video of the target user's rehabilitation training according to the first training video, the training actions of the user can be monitored in real time. By extracting training images from the second training video and processing them to obtain the first training actions, it is possible to determine whether the user's actions are consistent with the standard actions in the preset action table. When the first training actions are consistent with the standard actions, the first training actions are classified into the first set, and the first quantity of the first training actions in the first set is counted. When the first quantity is not equal to the preset first quantity, it is determined that the target user is in an abnormal training state, and an alert of the abnormal training state is immediately sent to the target user. This automated evaluation ensures that the target user can promptly discover and correct incorrect training actions. Based on continuous monitoring and evaluation, enabling the user to train according to the correct actions not only helps to achieve the expected rehabilitation effect but also avoids the impact of incorrect training actions.

[0065] The embodiment of the present application also provides an evaluation device for joint rehabilitation training. Figure 2 It is a structural schematic diagram of an evaluation device for joint rehabilitation training provided by the embodiment of the present application. Refer to Figure 2 The device is a server, and the server includes a receiving unit 201, a processing unit 202, and a sending unit 203.

[0066] The receiving unit 201 receives the monitoring request sent by the target user, determines the part to be evaluated and the rehabilitation duration according to the monitoring request. The part to be evaluated includes the arm joint part, the thigh joint part, and the calf joint part, and the rehabilitation duration is the duration since the target user started rehabilitation training.

[0067] The processing unit 202 inputs the rehabilitation duration and the part to be evaluated into a preset training database for matching to obtain a first training plan; generates a first training video according to the first training plan, and sends the first training video to the target device so that the target user can view the first training video through the target device; obtains a second training video corresponding to the target user, where the second training video is a video of the target user performing rehabilitation training according to the first training video; extracts a plurality of training images from the second training video, and processes the target training image to obtain a first training action, where the target training image is any one of the plurality of training images; determines whether the first training action is in a preset action table, and the preset action table is a table made up of all actions in the first training video; when the first training action is in the preset action table, classifies the first training action into a first set, and obtains a first quantity, where the first quantity is the total number of the first training actions in the first set; determines whether the first quantity is equal to a preset first quantity, and the preset first quantity is the total number of second training actions in the first training video.

[0068] The sending unit 203, when the first quantity is not equal to the preset first quantity, determines that the target user is in an abnormal training state, and sends the abnormal training state to the target user so that the target user can perform corresponding operations according to the abnormal training state.

[0069] In a possible implementation manner, the receiving unit 201 is used to obtain personal information corresponding to the target user, where the personal information includes age information, gender information, and occupation information; receives a target rehabilitation requirement sent by the target user, and the target rehabilitation requirement is the rehabilitation result expected by the target user for the part to be evaluated; the processing unit 202 is used to analyze the part to be evaluated according to the target rehabilitation requirement to obtain a training level; determines whether the training level is consistent with a preset level, and the preset level is a standard training level obtained by analyzing the part to be evaluated according to the personal information; when the training level is consistent with the preset level, inputs the target rehabilitation requirement, the rehabilitation duration, and the part to be evaluated into a preset training database for matching to obtain a second training plan.

[0070] In a possible implementation manner, the processing unit 202 is used to determine a plurality of training contents from the first training plan; convert the plurality of training contents into a plurality of training actions according to the part to be evaluated; sort the plurality of training actions in chronological order to obtain a first training video.

[0071] In a possible implementation, the processing unit 202 is configured to extract the action posture and motion parameters corresponding to the first training action from the target training image, where the motion parameters include an angle parameter and a displacement parameter; determine whether the action posture is in the preset posture table; when the action posture is in the preset posture table, determine whether the motion parameters are within the preset parameter range, and the preset parameter range is the motion parameter range corresponding to the action posture in the preset posture table; when the motion parameters are within the preset parameter range, determine that the first training action is in the preset action table.

[0072] In a possible implementation, the receiving unit 201 is configured to obtain the body parameters corresponding to the target user, where the body parameters are the body change parameters of the target user in the first training action using the target sensor, and the body parameters include a strength parameter and a balance parameter; the processing unit 202 is configured to analyze the first training action through the strength parameter and the balance parameter to obtain a standard level; determine whether the standard level is in the preset standard level table, and the preset standard level table is the standard level corresponding to each preset training action in the preset action table; when the standard level is in the preset standard level table, determine that the first training action is in the preset action table.

[0073] In a possible implementation, the receiving unit 201 is configured to obtain a target difference, where the target difference is the difference between a first quantity and a preset first quantity; the processing unit 202 is configured to determine a training action to be trained from the preset action table and a first set according to the target difference, and the training action to be trained is an action with non-standard training of the target user in the second training video; the sending unit 203 is configured to determine a third training plan based on the training action to be trained and the rehabilitation duration, and send the third training plan to the target user.

[0074] In a possible implementation, when the first training action is not in the preset action table, the processing unit 202 is configured to determine to classify the first training action into a second set; the receiving unit 201 is configured to obtain a second quantity from the second set and determine whether the second quantity is greater than a preset second quantity; when the second quantity is greater than the preset second quantity, the processing unit 202 is configured to determine to obtain a third training action from the second set and generate a fourth training plan according to the third training action.

[0075] It should be noted that: when the device provided in the above embodiments implements its functions, only the above-mentioned division of each functional module is used for illustration. In practical 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 device and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be seen in the method embodiments, which will not be repeated here.

[0076] This application also discloses an electronic device. Refer toFigure 3 , Figure 3 This embodiment of the present application provides a schematic structural diagram of an electronic device. 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.

[0077] Among them, the communication bus 305 is used to realize the connection and communication between these components.

[0078] 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.

[0079] Among them, the network interface 304 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0080] 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 data stored in the memory 302, it executes various functions of the server and processes data. Optionally, the processor 301 may be implemented in at least one of the following hardware forms: Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). The processor 301 may integrate one or several combinations 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 the rendering and drawing of the content to be displayed on the display screen; the modem is used to process wireless communication. It can be understood that the above-mentioned modem may not be integrated into the processor 301 and may be implemented separately by a single chip.

[0081] Among them, the memory 302 may include a Random Access Memory (RAM), or may also include a 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, codes, 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 method embodiments, etc.; the data storage area can store the data involved in the above-mentioned method embodiments. Optionally, the memory 302 may also be at least one storage device located far from the aforementioned processor 301.

[0082] 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 evaluating joint rehabilitation training.

[0083] In Figure 3 the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user to obtain the data input by the user; and the processor 301 can be used to call the application program for evaluating joint rehabilitation training stored in the memory 302. When executed by one or more processors, the electronic device is enabled to execute the methods described in one or more of the above embodiments.

[0084] 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.

[0085] In the above embodiments, the descriptions of the respective 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.

[0086] 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 merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may 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 coupling, direct coupling, or communication connection between each other can be through some service interfaces. The indirect coupling or communication connection of the device or unit can be in electrical or other forms.

[0087] 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 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.

[0088] In addition, in each embodiment of this application, each functional unit can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0089] If the above-mentioned 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 to enable 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 each embodiment of this application. And the aforementioned memory includes: various media such as USB flash drives, mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0090] The above are only exemplary embodiments of the present disclosure and should not be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure still fall within the scope covered by the present disclosure. Those skilled in the art will easily think of other implementation schemes of the present disclosure after considering the specification and the practice 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 common general knowledge or conventional technical means in the technical field not recorded in the present disclosure.

Claims

1. A method for evaluating joint rehabilitation training, characterized in that: Applied in a server, the method comprises: Receive a monitoring request sent by a target user, and determine a part to be evaluated and a rehabilitation time according to the monitoring request, wherein the part to be evaluated includes an arm joint part, a thigh joint part, and a calf joint part, and the rehabilitation time is the time when the target user starts rehabilitation training; Inputting the rehabilitation duration and the part to be evaluated into a preset training database for matching to obtain a first training plan; generating a first training video according to the first training plan, and sending the first training video to a target device so that the target user can view the first training video through the target device; Acquire a second training video corresponding to the target user, where the second training video is a video of the target user performing rehabilitation training according to the first training video; Extracting a plurality of training images from the second training video, and processing a target training image to obtain a first training action, wherein the target training image is any one of the plurality of training images; Determine whether the first training action is in a preset action table, where the preset action table is a table of all actions in the first training video; When the first training action is in the preset action table, the first training action is summarized into a first set to obtain a first quantity, where the first quantity is the total quantity of the first training actions in the first set; Determining whether the first number is equal to a preset first number, where the preset first number is the total number of second training movements in the first training video; When the first number is not equal to the preset first number, it is determined that the target user is in a training abnormality state, and the training abnormality state is sent to the target user so that the target user performs a corresponding operation according to the training abnormality state.

2. The method according to claim 1, characterized in that Before inputting the rehabilitation duration and the part to be evaluated into a preset training database for matching to obtain a first training plan, the method further includes: Obtaining personal information corresponding to the target user, the personal information including age information, gender information and occupation information; receiving a target rehabilitation requirement sent by the target user, where the target rehabilitation requirement is a rehabilitation result corresponding to the part to be evaluated that the target user expects; Analyze the part to be evaluated according to the target rehabilitation needs to obtain a training level; Determining whether the training level is consistent with a preset level, where the preset level is a standard training level obtained by analyzing the part to be evaluated based on the personal information; When the training level is consistent with the preset level, the target rehabilitation demand, the rehabilitation duration and the part to be evaluated are input into the preset training database for matching to obtain a second training plan.

3. The method according to claim 1, characterized in that Generating a first training video according to the first training plan specifically includes: Determining a plurality of training contents from the first training plan; Converting the plurality of training contents into a plurality of training movements according to the part to be evaluated; The plurality of training actions are sorted in chronological order to obtain the first training video.

4. The method according to claim 1, characterized in that: The determining whether the first training action is in a preset action table specifically includes: Extracting the action posture and motion parameters corresponding to the first training action from the target training image, wherein the motion parameters include angle parameters and displacement parameters; Determine whether the action posture is in a preset posture table; When the action posture is in the preset posture table, determining whether the motion parameter is within a preset parameter range, the preset parameter range being a motion parameter range corresponding to the action posture in the preset posture table; When the motion parameter is within the preset parameter range, it is determined that the first training action is in the preset action table.

5. The method according to claim 4, characterized in that After the motion parameter is within the preset parameter range, the method further includes: Acquire body parameters corresponding to the target user, where the body parameters are body change parameters of the target user in the first training action using a target sensor, and the body parameters include strength parameters and balance parameters; Analyze the first training action by using the strength parameter and the balance parameter to obtain a standard level; Determine whether the standard level is in a preset standard level table, wherein the preset standard level table is the standard level corresponding to each preset training action in the preset action table; When the standard level is in the preset standard level table, it is determined that the first training action is in the preset action table.

6. The method according to claim 1, characterized in that After determining that the target user is in an abnormal training state when the first number is not equal to the preset first number, the method further includes: Acquire a target difference, where the target difference is the difference between the first quantity and the preset first quantity; Determining a to-be-trained action from the preset action table and the first set according to the target difference, wherein the to-be-trained action is an irregular action performed by the target user in the second training video; A third training plan is determined based on the to-be-trained movement and the rehabilitation duration, and the third training plan is sent to the target user.

7. The method according to claim 1, characterized in that After determining whether the first training action is in the preset action table, the method further includes: When the first training action is not in the preset action table, determining to include the first training action in a second set; Obtaining a second quantity from the second set, and determining whether the second quantity is greater than a preset second quantity; When the second number is greater than the preset second number, it is determined to obtain a third training action from the second set, and a fourth training plan is generated according to the third training action.

8. An evaluation device for joint rehabilitation training, characterized in that: The device is a server, comprising a receiving unit (201), a processing unit (202) and a sending unit (203). The receiving unit (201) receives a monitoring request sent by a target user, and determines a part to be evaluated and a rehabilitation time according to the monitoring request, wherein the part to be evaluated includes an arm joint part, a thigh joint part and a calf joint part, and the rehabilitation time is the time when the target user starts rehabilitation training; The processing unit (202) inputs the rehabilitation duration and the part to be evaluated into a preset training database for matching, thereby obtaining a first training plan; generating a first training video according to the first training plan, and sending the first training video to a target device so that the target user can view the first training video through the target device; Acquire a second training video corresponding to the target user, where the second training video is a video of the target user performing rehabilitation training according to the first training video; Extracting a plurality of training images from the second training video, and processing a target training image to obtain a first training action, wherein the target training image is any one of the plurality of training images; Determine whether the first training action is in a preset action table, where the preset action table is a table of all actions in the first training video; When the first training action is in the preset action table, the first training action is summarized into a first set to obtain a first quantity, where the first quantity is the total quantity of the first training actions in the first set; and whether the first quantity is equal to a preset first quantity, where the preset first quantity is the total quantity of the second training actions in the first training video; The sending unit (203) determines that the target user is in a training abnormality state when the first number is not equal to the preset first number, and sends the training abnormality state to the target user so that the target user performs a corresponding operation according to the training abnormality state.

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