Intelligent analysis of rehabilitation exercise robot auxiliary decision-making device and method

Abstract

The present invention discloses an intelligent analysis rehabilitation exercise robot auxiliary decision-making device and method, which relate to the field of exercise machines. The rehabilitation exercise robot auxiliary decision-making device comprises a carrier platform body, a monitoring camera, an exercise mechanical arm and a decision analysis unit. The carrier platform body is interactively connected with the monitoring camera, the exercise mechanical arm and the decision analysis unit through an electrical medium, wherein: the carrier platform body, as the mounting end of each functional component and functional module, performs network distribution and power supply authority opening; the exercise mechanical arm is used to receive the exercise plan submitted by the decision analysis unit, and pull a certain part of the patient's limbs according to the moving path and moving speed provided by the exercise plan; by real-time monitoring of the patient's physiological parameters and emotional state, an exercise plan for each patient is provided, the treatment effect is maximized and the risk in exercise is reduced, and the patient's emotional and physical state are dynamically evaluated, so as to timely adjust the exercise intensity and type.

Description

Technical Field

[0001] The present invention relates to the technical field of exercise machines, and in particular to an intelligent analysis rehabilitation exercise robot auxiliary decision-making device and method. Background Art

[0002] With the acceleration of global population aging, the rehabilitation needs of the elderly are increasing, and efficient and personalized rehabilitation solutions are needed to meet the needs of the elderly in terms of skill recovery and quality of life improvement. Especially in some remote areas and places with relatively scarce medical resources, the shortage of professional rehabilitation medical personnel and the limitations of traditional rehabilitation treatment models make it difficult for patients to obtain timely and effective rehabilitation services; With the development of sports medicine and bioengineering, scientific rehabilitation training concepts and technologies have gradually matured, such as digital motion analysis and virtual reality technology. Rehabilitation robot technology is also constantly improving, and a variety of intelligent devices that can assist patients in rehabilitation training have emerged. For example, a robotic arm can drive the patient's limbs to move along a certain trajectory, helping the patient to exercise according to a predetermined rehabilitation plan. Existing technologies often adopt a "one-size-fits-all" approach to provide patients with fixed rehabilitation exercise programs, which lack personalized adjustments. Although many rehabilitation plans are formulated based on the patient's basic information, they fail to provide real-time feedback on the user's physical condition and emotional changes, resulting in the medical plan not meeting the patient's actual needs. Emotional fluctuations may affect the patient's participation and rehabilitation effects. There is a lack of real-time monitoring and feedback of emotional data, and dynamic adjustments cannot be implemented; Current rehabilitation robots lack the ability to integrate and analyze data across patients and cases, making it difficult to effectively share knowledge and accumulate experience, thus limiting technological advancement and the optimization of rehabilitation programs. Summary of the invention

[0003] 1. Technical issues to be resolved In view of the above-mentioned shortcomings of the prior art, the present invention provides a rehabilitation exercise robot auxiliary decision-making device and method with intelligent analysis, which can effectively solve the problems of the prior art.

[0004] (II) Technical solution To achieve the above objectives, the present invention is implemented through the following technical solutions: The first aspect of the present invention discloses an intelligent analysis rehabilitation exercise robot auxiliary decision-making device and method, comprising a support platform body, a monitoring camera, an exercise mechanical arm and a decision analysis unit, wherein the support platform body is interactively connected with the monitoring camera, the exercise mechanical arm and the decision analysis unit through an electrical medium, wherein: The main body of the platform, as the carrier of various functional components and modules, is open for network distribution and power supply permissions; Monitoring camera, used to obtain image data of the user's rehabilitation training process in real time and perform preprocessing; The training robot arm is used to receive the training plan submitted by the decision analysis unit and to pull a certain part of the patient's limbs according to the moving path and moving speed provided by the training plan; The decision analysis unit is used to identify the risks of the current user's exercise plan, and based on the risk identification results, adjust and output the final exercise plan for the exercise robot arm.

[0005] Furthermore, the decision analysis unit is deployed with submodules at a lower level, and the submodules include: A management module is used to coordinate and control various functional modules and manage access rights to the exercise robot arm; The instruction editing module is used to provide an interface for the user to define an exercise program including exercise goals and action instructions, convert the defined exercise program into commands executable by the robot arm, and upload it to the management module; User identification module, used to access the user's health database, extract medical records and physical examination data, obtain and analyze the current user's age, gender, medical records and immediate health status, and output the comprehensive physical status coefficient; The motion capture module is used to identify the image data captured by the monitoring camera, extract the movement amplitude, traction strength, number of repetitions in each group of movements and movement frequency parameters of the patient's traction limb, and form the traction movement coefficient; A state capture module is used to record the user's emotional state in a preset exercise cycle and obtain the emotional evaluation coefficient of the emotional state in the current cycle; A three-dimensional construction module is used to collect the user's historical exercise program, traction action coefficient and body state coefficient, model the body structure and traction movement trajectory, and generate a three-dimensional simulation model for each user; The instruction simulation module is used to obtain the three-dimensional simulation model constructed by the three-dimensional construction module, input the user's physical condition data, the defined exercise program and traction data, and perform modeling of a real-time dynamic three-dimensional simulation model; The risk identification module is used to perform risk analysis based on the real-time dynamic three-dimensional simulation model generated by the instruction simulation module, generate risk coefficient output, and determine whether the risk coefficient generated in the current cycle exceeds the preset standard safety threshold; The decision adjustment module is used to obtain the emotion assessment coefficient output by the state capture module, identify the exercise program parameters with risk coefficients exceeding the standard, and use the patient's emotion assessment coefficient as an adjustment reference to adjust the exercise program parameters with risk coefficients exceeding the standard upward or downward to the preset level parameters.

[0006] Furthermore, the instruction editing module is interactively connected to an associated sharing module via a wireless network, and the associated sharing module is used to store verified historical exercise program data, analyze and match similar physical state data of historical patients and their corresponding exercise programs based on the physical state data of the current patient, as the default recommended exercise program for the current patient.

[0007] Furthermore, the three-dimensional construction module is interactively connected to an interference module via a wireless network, and the interference module is used to provide management personnel with custom adjustment authority for parameters of the three-dimensional simulation model constructed by the three-dimensional construction module, and provide active adjustment of model parameters.

[0008] Furthermore, the risk identification module is interactively connected to a standard definition module via a wireless network, and the standard definition module is used to preset standard safety thresholds for the movement amplitude, traction strength, number of repetitions in each group of movements, and movement frequency parameters of the traction limb, preset and classify the standard safety thresholds for each user, and update them in real time.

[0009] Furthermore, during the operation stage, the decision adjustment module determines the risk parameters of movement amplitude, traction strength, number of repetitions in each set of exercise and exercise frequency, and determines the degree of influence on the adjustment of risk parameters according to the level of emotion assessment coefficient. When the emotion assessment coefficient is high, indicating that the patient has strong adaptability, the recommended adjustment direction is to increase one or more parameters. When the emotion assessment coefficient is low, indicating that the patient has poor tolerance or has negative emotions such as anxiety, the recommended adjustment direction is to reduce one or more parameters.

[0010] Furthermore, the management module is interactively connected to the instruction editing module, the user identification module, the motion capture module and the state capture module through a wireless network, the three-dimensional construction module is interactively connected to the user identification module, the motion capture module and the instruction simulation module through a wireless network, the risk identification module is interactively connected to the instruction simulation module and the decision adjustment module through a wireless network, and the state capture module is connected to the decision adjustment module through an electrical medium.

[0011] The second aspect of the present invention discloses a rehabilitation exercise robot assisted decision-making method of intelligent analysis, comprising the following steps: Step 1: Use sensors and cameras to obtain image data of the user during the training of the rehabilitation robot in a predetermined period in real time and perform preprocessing; Step 2: Access the user's health database, extract the user's age, gender, medical history and physical examination data, comprehensively analyze the current user's health status, and output the physical status coefficient; Step 3: The user defines the exercise goals and action instructions, converts these instructions into commands executable by the robotic arm, and uploads them to the rehabilitation exercise robot; Step 4: Extract the movement amplitude, traction strength, number of repetitions in each set of movements and movement frequency parameters of the patient's traction limb from the real-time acquired image data to form a traction action coefficient as the basic data for dynamic simulation; Step 5: construct a dynamic three-dimensional simulation model of the user based on the user's physical state data, the defined exercise program, and the extracted traction data; Step 6: Perform risk analysis on the exercise feedback data of the current cycle based on the generated real-time dynamic three-dimensional simulation model, calculate the risk factor and determine whether it exceeds the preset standard safety threshold; Step 7: Obtain the emotion assessment coefficient, identify the exercise program parameters of the items with excessive risk coefficients, and comprehensively consider the user's emotional state and physical state data, adjust the parameters of the items with excessive risk coefficients of the exercise program, calculate the adjustment parameters of the exercise program for the corresponding risk items, summarize the calculation results and output the final exercise program; Step 8: Store the verified historical exercise program data, and based on the current patient's physical condition data, analyze the physical condition data of similar historical patients to generate a default recommended exercise program.

[0012] Furthermore, the calculation process of adjusting the parameters of the exercise program corresponding to the risk item in step 7 is: ; In the formula, Represents the amount of parameter that needs to be adjusted, that is, the increase or decrease value. The adjustment amount generated based on the assessment of emotional and physical conditions determines the safety and appropriateness of the exercise program. represents the weight of the impact of physical condition assessment on the adjustment of exercise program, that is, the importance of physical condition factors in risk adjustment. Represents the risk factor of the project. Represents the maximum value allowed for the risk factor. represents the weight of the impact of emotional assessment on adjusting the parameters of the exercise program, that is, the importance of emotional factors in risk adjustment, Represents the emotional assessment coefficient. The lower the level, the higher the patient's anxiety, which increases the risk of exercise. Therefore, the parameters of the exercise program need to be adjusted to reduce the risk. It represents the physical condition coefficient. The lower it is, the worse the patient's physical condition is, and it is appropriate to reduce the intensity of exercise.

[0013] Furthermore, when the project risk factor R is significantly lower than T, that is, there is a higher safety margin, the current exercise program parameters are adjusted upwards; when the project risk factor R exceeds T, that is, there is no higher safety margin, the current exercise program parameters are adjusted upwards. The calculation adjusts the current exercise program parameters downward.

[0014] (III) Beneficial effects Compared with the known prior art, the technical solution provided by the present invention has the following beneficial effects: 1. By real-time monitoring of the patient's physiological parameters and emotional state, combined with personalized health records, and using machine learning algorithms to dynamically adjust the exercise plan, we can provide customized exercise plans for each patient's specific situation, maximize the treatment effect and reduce the risks during exercise, dynamically assess the patient's emotional and physical state, and adjust the exercise intensity and type in time when necessary to ensure that the patient can receive treatment both psychologically and physically.

[0015] 2. By setting a risk assessment model and combining the patient's emotions and physical condition, the risk factor is automatically calculated. When the risk exceeds the preset threshold, the system automatically lowers the exercise parameters, greatly reducing the possibility of patients encountering unexpected risks during exercise and improving the safety of the rehabilitation process. Intelligent analysis is performed based on the patient's long-term rehabilitation data, and continuous improvements are made in future decision-making, and the exercise plan and evaluation model are continuously optimized, thereby improving the overall treatment efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 It is a front view structural schematic diagram of the intelligent analysis rehabilitation exercise robot auxiliary decision-making device of the present invention; Figure 2 This is a schematic diagram of the framework of the intelligent analysis rehabilitation exercise robot auxiliary decision-making device in the present invention.

[0018] The numbers in the figure represent, respectively, 1. the supporting platform body; 2. the monitoring camera; 3. the training robot arm; 4. the decision analysis unit; 41. the management module; 42. the instruction editing module; 43. the user identification module; 44. the motion capture module; 45. the state capture module; 46. the three-dimensional construction module; 47. the instruction simulation module; 48. the risk identification module; 49. the decision adjustment module; 410. the association sharing module; 411. the interference module; 412. the standard definition module. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0020] The present invention will be further described below in conjunction with the embodiments.

[0021] Example 1 The present embodiment is a rehabilitation exercise robot auxiliary decision-making device with intelligent analysis, such as Figure 1 and Figure 2 As shown, it includes a supporting platform body 1, a monitoring camera 2, an exercise mechanical arm 3 and a decision analysis unit 4, and the supporting platform body 1 is interactively connected with the monitoring camera 2, the exercise mechanical arm 3 and the decision analysis unit 4 through an electrical medium, wherein: The carrier body 1, as the carrying end of each functional component and functional module, opens the network distribution and power supply permissions; improves the scalability and flexibility of the system, and can easily add or change functional modules according to needs; Monitoring camera 2 is used to obtain image data of the user's rehabilitation training process in real time and perform preprocessing; real-time acquisition of image data ensures dynamic monitoring of the patient's rehabilitation process and can respond to abnormal situations during the exercise process in a timely manner; The training robot arm 3 is used to receive the training plan submitted by the decision analysis unit 4, and to traction a certain part of the patient's limbs according to the movement path and movement speed provided by the training plan; to perform precise limb traction according to the scientifically formulated training plan, so as to improve the treatment effect and reduce the patient's movement risk; The decision analysis unit 4 is used to identify the risks of the current user's exercise plan, and based on the risk identification results, adjust and output the final exercise plan for the exercise robot arm 3.

[0022] As a preferred implementation in this embodiment, Figure 2 As shown, the decision analysis unit 4 is deployed with submodules at the lower level, and the submodules include: The management module 41 is used to coordinate and control various functional modules and manage access rights of the training robot arm 3; The instruction editing module 42 is used to provide an interface for the user to define an exercise program including exercise goals and action instructions, convert the defined exercise program into a command executable by the robot arm, and upload it to the management module 41; the instruction editing module 42 is interactively connected to the associated sharing module 410 through a wireless network, and the associated sharing module 410 is used to store verified historical exercise program data, analyze and match similar physical state data of historical patients and their corresponding exercise programs based on the physical state data of the current patient, and use them as the default recommended exercise program for the current patient; users can easily define their own exercise goals, making the exercise program more personalized and improving the patient's sense of participation. By analyzing historical data, patients are provided with recommended programs that are more in line with their physical conditions, thereby improving the scientific nature of the effect; The user identification module 43 is used to access the user's health database, extract medical records and physical examination data, obtain and analyze the current user's age, gender, medical records and immediate health status, and output the comprehensive physical status coefficient; by extracting multiple health information of the user, a comprehensive physical status coefficient is generated to provide a more scientific basis for the exercise program; The motion capture module 44 is used to identify the image data captured by the monitoring camera 2, extract the movement amplitude, traction strength, number of repetitions in each group of movements and movement frequency parameters of the patient's traction limbs, and form a traction movement coefficient; it can accurately extract the movement amplitude, traction strength and other parameters of the limbs to provide a basis for evaluating the exercise effect; The state capture module 45 is used to record the emotional state of the user in the preset exercise cycle and obtain the emotional evaluation coefficient of the emotional state in the current cycle; pay attention to the patient's emotional state, avoid exercise risks caused by negative emotions, and promote mental health; The three-dimensional construction module 46 is used to collect the user's historical exercise program, traction action coefficient and body state coefficient, model the body structure and traction movement trajectory, and generate a three-dimensional simulation model for each user; the three-dimensional construction module 46 is interactively connected to the interference module 411 through a wireless network, and the interference module 411 is used to provide the management personnel with the custom adjustment authority for the parameters of the three-dimensional simulation model constructed by the three-dimensional construction module 46, and provide active adjustment of the model parameters, so as to make the visualization and personalization of the rehabilitation process more effective; The instruction simulation module 47 is used to obtain the three-dimensional simulation model constructed by the three-dimensional construction module 46, input the user's physical condition data, the defined exercise program and traction data, and perform real-time dynamic three-dimensional simulation model building; The risk identification module 48 is used to perform risk analysis based on the real-time dynamic three-dimensional simulation model generated by the instruction simulation module 47, generate risk coefficient output, and determine whether the risk coefficient generated in the current cycle exceeds the preset standard safety threshold; the risk identification module 48 is interactively connected to the standard definition module 412 through a wireless network, and the standard definition module 412 is used to preset standard safety thresholds for the movement amplitude, traction strength, number of repetitions in each group of movements, and movement frequency parameters of the traction limb, preset and classify the standard safety thresholds of each user, and store them in a classified manner, and update them in real time; it can analyze the generated risk coefficient in real time to ensure that the exercise program meets the safety standards at any time; The decision adjustment module 49 is used to obtain the emotion assessment coefficient output by the state capture module 45, identify the exercise program parameters with excessive risk coefficients, and use the patient's emotion assessment coefficient as a reference for adjustment to adjust the exercise program parameters with excessive risk coefficients upward or downward by preset level parameters. During the operation stage, the decision adjustment module 49 determines the risk parameters of movement amplitude, traction strength, number of repetitions in each exercise group, and exercise frequency, and determines the degree of influence on the adjustment of risk parameters according to the emotion assessment coefficient. When the emotion assessment coefficient is high, indicating that the patient has strong adaptability, it is recommended to increase one or more parameters. When the emotion assessment coefficient is low, indicating that the patient has poor tolerance or has negative emotions such as anxiety, it is recommended to reduce one or more parameters. The exercise parameters are adjusted according to the emotion assessment, so that the program is more in line with the patient's actual tolerance, thereby improving the rehabilitation effect. like Figure 2 As shown, the management module 41 is interactively connected with the instruction editing module 42, the user identification module 43, the motion capture module 44 and the state capture module 45 through a wireless network, the three-dimensional construction module 46 is interactively connected with the user identification module 43, the motion capture module 44 and the instruction simulation module 47 through a wireless network, the risk identification module 48 is interactively connected with the instruction simulation module 47 and the decision adjustment module 49 through a wireless network, and the state capture module 45 is connected with the decision adjustment module 49 through an electrical medium.

[0023] Compared with existing technologies, real-time data processing and analysis have improved sensitivity to patient conditions, and the exercise program can be adjusted according to the user's health data and emotional state to provide patients with customized rehabilitation treatment. Through risk identification and assessment mechanisms, the safety of patients during exercise is effectively guaranteed, and users are provided with more intuitive rehabilitation process monitoring and feedback, which is conducive to enhancing patients' sense of participation and confidence.

[0024] Example 2 In other aspects, this embodiment also provides a rehabilitation exercise robot assisted decision-making method with intelligent analysis, comprising the following steps: Step 1: Use sensors and cameras to obtain image data of the user during the training of the rehabilitation robot in a predetermined period in real time and perform preprocessing; Step 2: Access the user's health database, extract the user's age, gender, medical history and physical examination data, comprehensively analyze the current user's health status, and output the physical status coefficient; Step 3: The user defines the exercise goals and action instructions, converts these instructions into commands executable by the robotic arm, and uploads them to the rehabilitation exercise robot; Step 4: Extract the movement amplitude, traction strength, number of repetitions in each set of movements and movement frequency parameters of the patient's traction limb from the real-time acquired image data to form a traction action coefficient as the basic data for dynamic simulation; Step 5: construct a dynamic three-dimensional simulation model of the user based on the user's physical state data, the defined exercise program, and the extracted traction data; Step 6: Perform risk analysis on the exercise feedback data of the current cycle based on the generated real-time dynamic three-dimensional simulation model, calculate the risk factor and determine whether it exceeds the preset standard safety threshold; Step 7: Obtain the emotion assessment coefficient, identify the exercise program parameters of the items with excessive risk coefficients, and comprehensively consider the user's emotional state and physical state data, adjust the parameters of the items with excessive risk coefficients of the exercise program, calculate the adjustment parameters of the exercise program for the corresponding risk items, summarize the calculation results and output the final exercise program; Step 8: Store the verified historical exercise program data, and based on the current patient's physical condition data, analyze the physical condition data of similar historical patients to generate a default recommended exercise program.

[0025] In the specific implementation of this embodiment, the user's image data is obtained in real time through sensors and cameras, and the user's exercise status can be dynamically monitored, and the training plan can be adjusted in time to improve the rehabilitation effect. According to the user's health database information such as age, gender, medical history and physical examination data, a comprehensive analysis can be performed to accurately evaluate the physical condition of each user and provide a more personalized rehabilitation plan; Users can define their own exercise goals and action instructions. This flexibility enables the robot to better meet user needs and enhance user participation. A dynamic three-dimensional simulation model is established based on the acquired data, which can provide more intuitive feedback on the user's exercise performance. Through risk analysis, potential safety hazards in exercise are discovered in time to ensure the safety of training. A dynamic three-dimensional simulation model is established based on the acquired data, which can provide more intuitive feedback on the user's exercise performance. Through risk analysis, potential safety hazards in exercise are discovered in time to ensure the safety of training. A dynamic three-dimensional simulation model is established based on the acquired data, which can provide more intuitive feedback on the user's exercise performance, timely discover potential safety hazards in exercise through risk analysis, and ensure the safety of training. With the continuous accumulation and updating of user data, the system can achieve self-learning and optimization, and gradually improve the service quality and the accuracy of personalized recommendations.

[0026] Example 3 In this embodiment, a calculation process of adjusting parameters of the training program for risky items is provided, which is specifically as follows: ; In the formula, Represents the amount of parameter that needs to be adjusted, that is, the increase or decrease value. The adjustment amount generated based on the assessment of emotional and physical conditions determines the safety and appropriateness of the exercise program. represents the weight of the impact of physical condition assessment on the adjustment of exercise program, that is, the importance of physical condition factors in risk adjustment. Represents the risk factor of the project. Represents the maximum value allowed for the risk factor. represents the weight of the impact of emotional assessment on adjusting the parameters of the exercise program, that is, the importance of emotional factors in risk adjustment, Represents the emotional assessment coefficient. The lower the level, the higher the patient's anxiety, which increases the risk of exercise. Therefore, the parameters of the exercise program need to be adjusted to reduce the risk. Represents the physical condition coefficient. The lower the coefficient, the worse the patient's physical condition is, and it is appropriate to reduce the intensity of exercise. When the project risk factor R is significantly lower than T, that is, there is a higher safety margin, the current exercise program parameters are adjusted upward. When the project risk factor R exceeds T, that is, there is no higher safety margin, through The calculation adjusts the current exercise program parameters downward.

[0027] In summary, the present invention monitors the patient's physiological parameters and emotional state in real time, combines personalized health records, uses machine learning algorithms to dynamically adjust the exercise program, provides customized exercise programs for each patient's specific situation, maximizes the treatment effect and reduces the risk of exercise, and dynamically evaluates the patient's emotional and physical state, so as to adjust the intensity and type of exercise in time when necessary, ensuring that the patient can accept the treatment both psychologically and physically; By setting a risk assessment model and combining the patient's emotions and physical condition, the risk factor is automatically calculated. When the risk exceeds the preset threshold, the system automatically lowers the exercise parameters, greatly reducing the possibility of patients encountering unexpected risks during exercise and improving the safety of the rehabilitation process. Intelligent analysis is performed based on the patient's long-term rehabilitation data, and continuous improvements are made in future decision-making, continuously optimizing exercise plans and evaluation models, thereby improving overall treatment efficiency.

[0028] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent analysis rehabilitation robot decision-making device, characterized in that: The invention comprises a support platform body (1), a monitoring camera (2), a training mechanical arm (3) and a decision analysis unit (4), wherein the support platform body (1), the monitoring camera (2), the training mechanical arm (3) and the decision analysis unit (4) are interconnected via an electrical medium, wherein: The carrier body (1) serves as the mounting end for each functional component and functional module, and is open for network distribution and power supply permissions; A monitoring camera (2) is used to obtain image data of the user's rehabilitation training process in real time and perform pre-processing; The training robot arm (3) is used to receive the training plan submitted by the decision analysis unit (4) and to pull a certain part of the patient's limb according to the movement path and movement speed provided by the training plan; The decision analysis unit (4) is used to identify the risk of the current user's exercise plan, and based on the risk identification result, adjust and output the final exercise plan of the exercise robot arm (3).

2. The intelligent analysis rehabilitation robot decision-making device according to claim 1, characterized in that: The decision analysis unit (4) is provided with submodules at the lower level, and the submodules include: A management module (41) for coordinating and controlling the various functional modules and managing access rights to the training robot arm (3); An instruction editing module (42) is used to provide an interface for a user to define an exercise program including an exercise target and action instructions, convert the defined exercise program into commands executable by the robot arm, and upload the commands to the management module (41); A user identification module (43) is used to access the user's health database, extract medical records and physical examination data, obtain and analyze the current user's age, gender, medical records and immediate health status, and output the comprehensive output as a physical status coefficient; A motion capture module (44) is used to identify the image data captured by the monitoring camera (2), extract the movement amplitude, traction strength, number of repetitions in each set of movements and movement frequency parameters of the patient's traction limb, and form a traction movement coefficient; A state capture module (45) is used to record the user's emotional state in a preset exercise cycle and obtain an emotional evaluation coefficient of the emotional state in the current cycle; A three-dimensional construction module (46) is used to collect the user's historical exercise program, traction action coefficient and body state coefficient, model the body structure and traction movement trajectory, and generate a three-dimensional simulation model for each user; The instruction simulation module (47) is used to obtain the three-dimensional simulation model constructed by the three-dimensional construction module (46), input the user's physical condition data, the defined exercise program and traction data, and perform real-time dynamic three-dimensional simulation model building; A risk identification module (48) is used to perform risk analysis based on the real-time dynamic three-dimensional simulation model generated by the instruction simulation module (47), generate a risk coefficient output, and determine whether the risk coefficient generated in the current cycle exceeds a preset standard safety threshold; The decision adjustment module (49) is used to obtain the emotion assessment coefficient output by the state capture module (45), identify the exercise program parameters with risk coefficients exceeding the standard, and use the patient's emotion assessment coefficient as an adjustment reference to adjust the exercise program parameters with risk coefficients exceeding the standard upward or downward by a preset level parameter.

3. The intelligent analysis rehabilitation robot decision-making device according to claim 2, characterized in that: The instruction editing module (42) is interactively connected to the associated sharing module (410) via a wireless network. The associated sharing module (410) is used to store verified historical exercise program data, analyze and match similar physical state data of historical patients and their corresponding exercise programs based on the physical state data of the current patient, and use them as the default recommended exercise program for the current patient.

4. The intelligent analysis rehabilitation robot decision-making device according to claim 2, characterized in that: The three-dimensional construction module (46) is interactively connected to an interference module (411) via a wireless network, and the interference module (411) is used to provide management personnel with the authority to customize the parameters of the three-dimensional simulation model constructed by the three-dimensional construction module (46), thereby providing active adjustment of the model parameters.

5. The intelligent analysis rehabilitation robot decision-making device according to claim 2, characterized in that: The risk identification module (48) is interactively connected to a standard definition module (412) via a wireless network. The standard definition module (412) is used to preset standard safety thresholds for the movement amplitude, traction strength, number of repetitions in each group of movements, and movement frequency parameters of the traction limb, preset the standard safety thresholds for each user, store them by category, and update them in real time.

6. The intelligent analysis rehabilitation robot decision-making device according to claim 2, characterized in that: During the operation phase, the decision adjustment module (49) determines the risk parameters of movement amplitude, traction strength, number of repetitions in each exercise group, and exercise frequency, and determines the degree of influence on the risk parameter adjustment according to the level of the emotion assessment coefficient. When the emotion assessment coefficient is high, indicating that the patient has strong adaptability, the recommended adjustment direction is to increase one or more parameters. When the emotion assessment coefficient is low, indicating that the patient has poor tolerance or has negative emotions such as anxiety, the recommended adjustment direction is to reduce one or more parameters.

7. The intelligent analysis rehabilitation robot decision-making device according to claim 2, characterized in that: The management module (41) is interactively connected to the instruction editing module (42), the user identification module (43), the motion capture module (44) and the state capture module (45) via a wireless network; the three-dimensional construction module (46) is interactively connected to the user identification module (43), the motion capture module (44) and the instruction simulation module (47) via a wireless network; the risk identification module (48) is interactively connected to the instruction simulation module (47) and the decision adjustment module (49) via a wireless network; and the state capture module (45) is connected to the decision adjustment module (49) via an electrical medium.

8. A method for assisting decision-making by an intelligent analysis rehabilitation robot, the method being an implementation method of an intelligent analysis rehabilitation robot assisting decision-making device based on any one of claims 1 to 7, characterized in that: The following steps are involved: Step 1: Use sensors and cameras to obtain image data of the user during the training of the rehabilitation robot in a predetermined period in real time and perform preprocessing; Step 2: Access the user's health database, extract the user's age, gender, medical history and physical examination data, comprehensively analyze the current user's health status, and output the physical status coefficient; Step 3: The user defines the exercise goals and action instructions, converts these instructions into commands executable by the robotic arm, and uploads them to the rehabilitation exercise robot; Step 4: Extract the movement amplitude, traction strength, number of repetitions in each set of movements and movement frequency parameters of the patient's traction limb from the real-time acquired image data to form a traction action coefficient as the basic data for dynamic simulation; Step 5: construct a dynamic three-dimensional simulation model of the user based on the user's physical state data, the defined exercise program, and the extracted traction data; Step 6: Perform risk analysis on the exercise feedback data of the current cycle based on the generated real-time dynamic three-dimensional simulation model, calculate the risk factor and determine whether it exceeds the preset standard safety threshold; Step 7: Obtain the emotion assessment coefficient, identify the exercise program parameters of the items with excessive risk coefficients, and comprehensively consider the user's emotional state and physical state data, adjust the parameters of the items with excessive risk coefficients of the exercise program, calculate the adjustment parameters of the exercise program for the corresponding risk items, summarize the calculation results and output the final exercise program; Step 8: Store the verified historical exercise program data, and based on the current patient's physical condition data, analyze the physical condition data of similar historical patients to generate a default recommended exercise program.

9. The intelligent analysis rehabilitation robot-assisted decision-making method according to claim 8, characterized in that: The calculation process of the adjustment parameters of the training program for the risky project in step 7 is: ； In the formula, Represents the parameter amount that needs to be adjusted. Represents the weight of the impact of physical condition assessment on adjusting the exercise program, Represents the risk factor of the project. Represents the maximum value allowed for the risk factor. represents the weight of the impact of emotional evaluation on adjusting the parameters of the exercise program, represents the emotion evaluation coefficient, Represents the body condition coefficient.

10. The intelligent analysis rehabilitation robot-assisted decision-making method according to claim 8, characterized in that: When the project risk factor R is significantly lower than T, that is, there is a higher safety margin, the current exercise program parameters are adjusted upward. When the project risk factor R exceeds T, that is, there is no higher safety margin, the current exercise program parameters are adjusted upward. The calculation adjusts the current exercise program parameters downward.

Images