A method and system for assistive control of movement disorders

Abstract

The application relates to the medical technical field and provides a movement disorder disease movement auxiliary control method and system. The movement disorder disease movement auxiliary control method comprises the following steps: collecting first-limb movement information of a user of a movement auxiliary device in a first time period and first interaction force information between the movement auxiliary device and the user's body in the first time period; determining target scene information in which the user is located according to the first-limb movement information and the first interaction force information; determining target three-dimensional auxiliary force field information according to the target scene information, wherein the target three-dimensional auxiliary force field information is used for indicating target supporting force, target guiding force or target damping force distribution of the movement auxiliary device to the user's limbs in different directions; and configuring a three-dimensional auxiliary force field of the movement auxiliary device as a three-dimensional auxiliary force field corresponding to the target three-dimensional auxiliary force field information. The flexibility of controlling the movement auxiliary device can be improved.

Description

Technical Field

[0001] This application relates to the field of medical technology, and in particular to a method and system for assistive control of movement disorders. Background Technology

[0002] Assistive devices play a vital role in helping users with movement disorders regain motor function. By providing support and guidance, assistive devices can help users complete daily activities safely and confidently.

[0003] To control motion assistive devices, existing solutions typically use preset motion modes, with the device's actuators providing corresponding physical assistance to the user. However, user needs are often diverse, and preset motion modes cannot fully meet those needs. Consequently, existing solutions offer limited flexibility in controlling motion assistive devices. Summary of the Invention

[0004] This application provides a method and system for assistive control of movement disorders, which can improve the flexibility of controlling assistive devices.

[0005] To achieve the above objectives, this application adopts the following technical solution:

[0006] Firstly, a method for assistive control of movement disorders is provided. This method includes: collecting first limb movement information of a user using an assistive device during a first time period, and first interaction force information between the assistive device and the user's body during the first time period; determining the target scenario information of the user based on the first limb movement information and the first interaction force information; determining target three-dimensional assistive force field information based on the target scenario information, wherein the target three-dimensional assistive force field information is used to indicate the distribution of target support force, target guiding force, or target damping force of the assistive device on the user's limbs in different directions; and configuring the three-dimensional assistive force field of the assistive device to correspond to the three-dimensional assistive force field information of the target three-dimensional assistive force field.

[0007] Based on the solution proposed in this application, by collecting the user's first limb movement information and the first interaction force information between the device and the body in the first time period, the user's current movement state and interaction with the device can be comprehensively obtained. On this basis, the target scenario information of the user is determined according to this information, realizing intelligent recognition of the user's movement environment and task, overcoming the problem of the inapplicability of assistive strategies in complex daily scenarios in existing technologies. Furthermore, the target three-dimensional assistive force field information is determined based on the target scenario information. This force field information can indicate the distribution of target support force, target guidance force, or target damping force on the user's limbs in different directions, thereby dynamically adjusting the assistive strategy to highly match the user's actual needs, effectively solving the problem of mismatch between assistive force and user needs in multi-tasking activities. Finally, the three-dimensional assistive force field of the motion assistive device is configured to correspond to the three-dimensional assistive force field information of the target, realizing personalized and real-time adjustment of the assistive force, avoiding the inhibition of the user's active movement potential by fixed assistive strategies, thereby improving long-term rehabilitation effects and quality of life. This method, through scenario perception and adaptive force field reshaping, significantly improves the accuracy, adaptability, and effectiveness of motion assistance, providing a more intelligent and personalized motion assistance solution for users with movement disorders.

[0008] In conjunction with the first aspect, in some embodiments of the first aspect, determining the target scenario information of the user based on the first limb movement information and the first interaction force information includes: determining the user's first mechanical disturbance information, first postural stiffness information, and first step state rhythm and symmetry deviation information in a first time period based on the first limb movement information and the first interaction force information; for each scenario information among multiple scenario information, determining the first confidence score of the scenario information based on the weight information corresponding to the scenario information, the first mechanical disturbance information, the first postural stiffness information, and the first step state rhythm and symmetry deviation information; and determining the scenario information corresponding to the largest first confidence score as the target scenario information when the difference between the largest and smallest first confidence scores among multiple first confidence scores is greater than or equal to a preset difference threshold, and the largest first confidence score is greater than or equal to a preset confidence score.

[0009] By employing multi-dimensional feature extraction, weighted matching, and a dual threshold judgment mechanism, the aforementioned problem of insufficient accuracy in scenario recognition is effectively addressed. First, by determining the first mechanical perturbation information, first posture stiffness information, and first gait rhythm and symmetry deviation information, the system can comprehensively and meticulously capture the micro-perturbation patterns and abnormal features of users under the influence of movement disorders from multiple key dimensions such as mechanics, posture, and gait rhythm, avoiding the one-sidedness that may result from single-feature judgment. Second, for each scenario information, a weighted calculation is performed based on its corresponding weight information and the extracted multi-dimensional features to obtain a first confidence score. This makes the scenario matching process more flexible and precise, allowing adjustment of the importance of each feature according to the characteristics of different scenarios. Finally, by introducing a preset difference threshold and a preset confidence score, the scenario recognition results are double-verified. When the difference between the largest and smallest first confidence scores is greater than or equal to the preset difference threshold, it indicates that a scenario has a significantly better match with the current state than other scenarios, thus ensuring the discriminative power of the recognition results. Furthermore, when the highest initial confidence score is greater than or equal to the preset confidence score, the reliability of the identified scenario is further guaranteed, avoiding uncertain judgments when all scenario matching scores are low. Therefore, the solution of this application can achieve accurate and robust identification of the user's target scenario information.

[0010] In conjunction with the first aspect, in certain embodiments of the first aspect, determining the user's first mechanical disturbance information, first postural stiffness information, and first step state rhythm and symmetry deviation information in a first time period based on the first limb movement information and the first interaction force information includes: taking the interaction force information in the first interaction force information whose duration is less than a preset duration threshold and whose rate of change is greater than a preset rate of change threshold as the first mechanical disturbance information; calculating the user's first step frequency and the ratio of left and right limb swing time within the first step state cycle based on the first limb movement information, taking the percentage deviation between the first step frequency and the reference step frequency, and the absolute difference of the ratio of left and right limb swing time within the first step state cycle as the first step state rhythm and symmetry deviation information; and determining the peak value of the user's joint angle change rate, the limitation range of limb activity, and the change information of force sensor data at the connection between the device and the user's limb based on the first limb movement information and the first interaction force information to obtain the first postural stiffness information.

[0011] By specifically and quantitatively determining the first mechanical disturbance information, first postural stiffness information, and first step gait rhythm and symmetry deviation information, subtle changes and potential risks in the user's movement can be captured more precisely. By identifying short-duration, high-rate-of-change interactive forces as the first mechanical disturbance information, potential fall risks or sudden imbalances can be detected promptly. By calculating the percentage deviation of the first step frequency from the reference step frequency and the absolute difference in the ratio of left and right limb swing time, the user's gait rhythm disorder and gait symmetry deviation can be accurately assessed, reflecting their motor coordination. By determining the peak value of the joint angle change rate, the limitation range of limb range of motion, and changes in force sensor data, the user's postural stiffness can be comprehensively assessed, identifying limb stiffness or limited mobility. It is precisely because of these specific and multi-dimensional information acquisition methods that the subsequent scenario judgment module can reliably identify the user's situation based on more comprehensive and accurate data.

[0012] In conjunction with the first aspect, in certain embodiments of the first aspect, determining a first confidence score for the scenario information based on the weight information corresponding to the scenario information, the first mechanical disturbance information, the first attitude stiffness information, and the first gait rhythm and symmetry deviation information includes: determining a first similarity between the first mechanical disturbance information and the mechanical disturbance information corresponding to the scenario information; determining a second similarity between the first attitude stiffness information and the attitude stiffness information corresponding to the scenario information; determining a third similarity between the first gait rhythm and symmetry deviation information and the gait rhythm and symmetry deviation information corresponding to the scenario information; and using the sum of the product of the first similarity and the weights corresponding to the mechanical disturbance information of the scenario information, the product of the second similarity and the weights corresponding to the attitude stiffness information of the scenario information, and the product of the third similarity and the weights corresponding to the gait rhythm and symmetry deviation information of the scenario information as the first confidence score.

[0013] By calculating the similarity between the currently acquired first mechanical disturbance information, first posture stiffness information, first gait rhythm and symmetry deviation information and the corresponding mechanical disturbance information, posture stiffness information, gait rhythm and symmetry deviation information in the preset scenario information, and combining the weights of each feature in the specific scenario judgment, a weighted sum is used to calculate the first confidence score of the scenario information. This method can quantify the degree of matching between the current user state and each preset scenario, thus providing a reliable quantitative basis for subsequent target scenario determination. By introducing weights, adjustments can be made according to the importance of each feature under different scenarios, making scenario judgment more flexible and accurate.

[0014] In conjunction with the first aspect, in some embodiments of the first aspect, when the difference between the largest and smallest first confidence scores among a plurality of first confidence scores is less than a preset difference threshold, or the largest first confidence score is less than a preset confidence score, the method further includes: configuring the three-dimensional assistive force field of the motion assistive device as a three-dimensional assistive force field corresponding to preset three-dimensional assistive force field information; the preset three-dimensional assistive force field information is used to indicate that the motion assistive device provides stable support to the user's limbs; acquiring the user's target state information in a second time period; the target state information is used to indicate the stability of the user's body; the start time of the second time period is after the end time of the first time period; when the target state information indicates that the user's body is in a stable state, acquiring the user's second limb movement information in the second time period. The system obtains information on the second interaction force between the motion assistive device and the user's body during a second time period. Based on the second limb movement information and the second interaction force information, it determines the user's second mechanical disturbance information, second postural stiffness information, and second gait rhythm and symmetry deviation information during the second time period. For each scenario information among multiple scenario information, it determines the second confidence score of the scenario information based on the corresponding weight information, second mechanical disturbance information, second postural stiffness information, second gait rhythm and symmetry deviation information. If the difference between the largest and smallest second confidence scores among multiple second confidence scores is greater than or equal to a preset difference threshold, and the largest second confidence score is greater than a preset confidence threshold, the scenario information corresponding to the largest second confidence score is determined as the target scenario information.

[0015] By introducing a two-stage scenario recognition and auxiliary force field configuration mechanism, the problem of insufficient confidence in initial scenario recognition is effectively solved. When the user's scenario cannot be clearly determined in the first time period, instead of forcibly selecting an uncertain scenario, the three-dimensional auxiliary force field of the motion assistive device is first configured to the three-dimensional auxiliary force field corresponding to the preset three-dimensional auxiliary force field information, which provides stable support force. This measure can immediately provide basic safety assurance for the user, avoid potential risks caused by inaccurate scenario recognition, and ensure the user's safety and comfort during the transition period. Subsequently, an observation and re-evaluation phase is entered. By acquiring the user's target state information in the second time period, it can be determined whether the user has reached a relatively stable state under stable support force. Only when the user's body is in a stable state is the second data acquisition and scenario recognition performed. This strategy avoids inaccurate recognition when the user's state is unstable, improving the effectiveness of subsequent data acquisition and the accuracy of scenario recognition. After the user stabilizes, second limb movement information and second interaction force information are acquired, and based on these more reliable data, second mechanical disturbance information, second posture stiffness information, and second gait rhythm and symmetry deviation information are recalculated. The feature information acquired under stable conditions typically reflects the user's true movement patterns and needs more clearly, making the subsequently calculated second confidence score more discriminative and reliable. By conducting another scenario confidence assessment and setting the same judgment criteria as the first assessment—that is, the difference between the largest and smallest second confidence scores is greater than or equal to a preset difference threshold, and the largest second confidence score is greater than a preset confidence threshold—the final target scenario information can be determined with higher accuracy and confidence. This series of steps ensures that even in cases of initial identification difficulties, personalized and safe movement assistance can ultimately be provided to the user through iteration and verification.

[0016] In conjunction with the first aspect, in some embodiments of the first aspect, acquiring the user's target state information in a second time period includes: acquiring the user's gliding duration, gait rhythm disorder frequency, and stiffness in the second time period; and determining that the target state information indicates the user's body is in a stable state when the gliding duration is less than a preset gliding duration threshold, the gait rhythm disorder frequency is less than a preset disorder frequency threshold, and the stiffness is less than a preset stiffness threshold.

[0017] In conjunction with the first aspect, in some embodiments of the first aspect, determining the target three-dimensional auxiliary force field information based on the target scenario information includes: matching the target scenario information with a preset correspondence to obtain the target three-dimensional auxiliary force field information; the preset correspondence includes a one-to-one correspondence between multiple scenario information and multiple three-dimensional auxiliary force field information.

[0018] In conjunction with the first aspect, in some embodiments of the first aspect, collecting the first limb movement information of the user of the motion assistive device in a first time period and the first interaction force information between the motion assistive device and the user's body in the first time period includes: collecting the original first limb movement information of the user of the motion assistive device in the first time period and the original first interaction force information between the motion assistive device and the user's body in the first time period; performing time synchronization and outlier correction processing on the original first limb movement information and the original first interaction force information to obtain the first limb movement information and the first interaction force information.

[0019] In conjunction with the first aspect, in some embodiments of the first aspect, outlier correction processing is performed on the original first limb movement information and the original first interaction force information to obtain the first limb movement information and the first interaction force information, including: removing the maximum and minimum values ​​in the original first limb movement information and the original first interaction force information to obtain the initial first limb movement information and the initial first interaction force information; and filling in the null values ​​in the initial first limb movement information and the initial first interaction force information to obtain the first limb movement information and the first interaction force information.

[0020] Secondly, a movement assistive control system for movement disorders is provided. This system includes: a data acquisition device for acquiring first limb movement information of a user using a movement assistive device during a first time period, and first interaction force information between the movement assistive device and the user's body during the first time period; a processing device for determining target scenario information of the user based on the first limb movement information and the first interaction force information; the processing device for determining target three-dimensional assistive force field information based on the target scenario information, wherein the target three-dimensional assistive force field information indicates the distribution of target support force, target guiding force, or target damping force of the movement assistive device on the user's limbs in different directions; and the processing device for configuring the three-dimensional assistive force field of the movement assistive device to correspond to the three-dimensional assistive force field information of the target three-dimensional assistive force field. Attached Figure Description

[0021] Figure 1 A flowchart illustrating a method for assistive control of movement disorders provided in this application;

[0022] Figure 2 A flowchart illustrating yet another method for assistive control of movement disorders provided in this application;

[0023] Figure 3 A flowchart illustrating yet another method for assistive control of movement disorders provided in this application;

[0024] Figure 4 This is a schematic diagram of the architecture of another motion assistive control system for movement disorders provided in this application. Detailed Implementation

[0025] In the description of this application, unless otherwise stated, "multiple" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0026] Furthermore, to facilitate a clear description of the technical solutions in the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish identical or similar items with substantially the same function and effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and the terms "first" and "second" are not necessarily different.

[0027] In this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being better or more advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner to facilitate understanding.

[0028] It is understood that the term "embodiment" used throughout the specification means that a specific feature, structure, or characteristic related to an embodiment is included in at least one embodiment of this application. Therefore, various embodiments throughout the specification do not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It is understood that in the various embodiments of this application, the sequence number of each process does not imply the order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0029] It is understood that in this application, "when," "if," and "if" all refer to the corresponding processing that will be carried out under certain objective circumstances, and are not limited to a specific time, nor do they require that there must be a judgment action when implemented, nor do they imply any other limitations.

[0030] It is understood that some optional features in the embodiments of this application can be implemented independently in certain scenarios without relying on other features, such as the current solution on which they are based, to solve the corresponding technical problems and achieve the corresponding effects. Alternatively, they can be combined with other features as needed in certain scenarios. Correspondingly, the apparatus given in the embodiments of this application can also implement these features or functions, which will not be elaborated here.

[0031] In this application, unless otherwise specified, the same or similar parts between the various embodiments can be referred to each other. In the various embodiments and implementation methods of the various embodiments in this application, unless otherwise specified or logically conflicting, the terminology and / or descriptions between different embodiments and between the implementation methods of the various embodiments are consistent and can be mutually referenced. The technical features in different embodiments and between the implementation methods of the various embodiments can be combined according to their inherent logical relationships to form new embodiments, implementation methods, implementation methods, or implementation approaches. The following embodiments of this application do not constitute a limitation on the scope of protection of this application.

[0032] To better understand the movement-assisted control method for movement disorders proposed in this application, the key terms and implementation environment involved will be explained in detail below.

[0033] "Motion assistive devices" refer to intelligent devices that provide physical support, guidance, or damping for users with movement disorders, such as exoskeleton robots, smart canes, or rehabilitation training equipment. These devices typically integrate multiple sensors and actuators to monitor the user's movement status in real time and apply corresponding assistive forces.

[0034] "Limb motion information" refers to data describing the user's limb movement state, such as joint angles, joint angular velocities, joint accelerations, and limb trajectories. This information can be acquired through inertial measurement units (IMUs), optical motion capture systems, or electromyography (EMG) sensors in motion-assisted devices.

[0035] "Interactive force information" refers to the mechanical data generated between the motion assistive device and the user's body, such as the supporting force, guiding force, and damping force of the device on the limbs, as well as the user's reaction force on the device. This information is usually obtained through force sensors, pressure sensors, or torque sensors in the motion assistive device.

[0036] "Contextual information" refers to comprehensive information describing the user's current environment and task status, such as standing, walking, climbing stairs, turning, obstacle avoidance, retrieving objects, difficulty starting, gait freeze, and balance disorder. Contextual information indicates the characteristics of the physical environment as well as the user's physical state and movement intentions.

[0037] "Three-dimensional assistive force field information" refers to a virtual force field model used to describe the distribution of support, guiding, or damping forces exerted on the user's limbs by assistive devices in three-dimensional space.

[0038] Assistive devices play a vital role in helping users with movement disorders regain motor function. By providing support and guidance, assistive devices can help users complete daily activities safely and confidently.

[0039] To control assistive devices, existing solutions typically use preset movement patterns, with the device's actuators providing corresponding physical assistance. Traditional assistive devices, when helping users with movement disorders, are usually calibrated and parameter-set in standard environments. This makes the assistance strategies inapplicable in complex daily scenarios, and may even hinder movement. Furthermore, existing devices fail to recognize and adapt to movement pattern adjustments caused by multitasking, potentially resulting in a mismatch between the assistive force and the user's actual needs. Simultaneously, the lack of adaptive assistive control fails to provide truly personalized and context-appropriate assistance, potentially inhibiting the user's active movement potential, leading to unhealthy exercise habits, and impacting long-term rehabilitation outcomes and quality of life. User needs are often diverse, and preset movement patterns cannot fully meet all user needs; therefore, existing solutions for controlling assistive devices have low flexibility.

[0040] Figure 1 This application provides a flowchart illustrating a method for assistive control of movement disorders, as shown below. Figure 1 As shown, the method includes the following steps:

[0041] S101, The control device collects the first limb movement information of the user of the motion assistive device in the first time period, and the first interaction force information between the motion assistive device and the user's body in the first time period.

[0042] As one possible implementation, the control device collects the user's original first limb movement information and the original first interaction force information between the motion assistive device and the user's body during the first time period; and performs time synchronization and outlier correction processing on the original first limb movement information and the original first interaction force information to obtain the first limb movement information and the first interaction force information.

[0043] This can improve the accuracy of the first limb movement information and the first interaction force information.

[0044] As an example, the control device can acquire the user's initial limb movement information in real time during a first time period through the inertial measurement unit (IMU) and joint angle sensors integrated within the motion assistive device. This information includes, for example, the real-time angles, angular velocities, and angular accelerations of the knee and hip joints. Simultaneously, force and pressure sensors installed at the connection points between the device and the user's limbs can collect initial interaction force information, such as the supporting force and guiding force exerted by the device on the limbs, as well as the user's reaction force on the device.

[0045] Subsequently, the control device removes the maximum and minimum values ​​from the original first limb movement information and the original first interaction force information to obtain the initial first limb movement information and the initial first interaction force information.

[0046] Understandably, during actual data collection, due to sensor malfunctions, environmental interference, or sudden shocks, abnormal data points (i.e., maxima or minima) may appear far exceeding the normal range. These outliers can severely affect the accuracy of subsequent data analysis and model judgment. For example, by setting a threshold range based on statistics (such as the three-standard-deviation principle) or experience (such as physical limits), data points exceeding this range can be identified as outliers and removed. After removal, the resulting data, referred to as initial first limb movement information and initial first interaction force information, can eliminate significant outlier interference to a certain extent.

[0047] The missing values ​​in the initial first limb movement information and the initial first interaction force information are filled in to obtain the first limb movement information and the first interaction force information.

[0048] Understandably, due to data transmission interruptions, temporary sensor malfunctions, or omissions during data processing, null values ​​may exist in the original first limb movement information and the original first interaction force information. To ensure data integrity and continuity, these null values ​​need to be appropriately filled. There are various methods for null value completion, such as interpolation methods (e.g., linear interpolation, spline interpolation), mean filling, median filling, mode filling, or prediction filling based on time series prediction models (e.g., ARIMA models). Choosing an appropriate completion method can maximize the restoration of data authenticity and ensure the accuracy of subsequent scenario judgments. Through null value completion, the first limb movement information and the first interaction force information used for subsequent processing are finally obtained.

[0049] S102. The control device determines the target scenario information of the user based on the first limb movement information and the first interaction force information.

[0050] As one possible implementation, such as Figure 2 As shown, this implementation method includes the following steps:

[0051] S201. The control device determines the user's first mechanical disturbance information, first posture stiffness information, and first step state rhythm and symmetry deviation information in the first time period based on the first limb movement information and the first interaction force information.

[0052] As an example, the control device uses the interaction force information in the first interaction force information whose duration is less than a preset duration threshold and whose rate of change is greater than a preset rate of change threshold as the first mechanical disturbance information.

[0053] The first mechanical disturbance information refers to the brief but intense interaction force generated between the motion assist device and the user's body during movement due to external interference or sudden actions. To accurately identify this disturbance, a preset duration threshold and a preset rate of change threshold can be set. When the duration of a certain interaction force in the first interaction force information is less than the preset duration threshold and its rate of change is greater than the preset rate of change threshold, it can be identified as the first mechanical disturbance information. For example, the preset duration threshold can be set to 0.1 seconds to 0.5 seconds, and the preset rate of change threshold can be adjusted according to the actual application scenario and device sensitivity to effectively distinguish between normal motion forces and sudden disturbance forces.

[0054] Secondly, based on the first limb movement information, the control device calculates the user's first step frequency, the ratio of left and right limb swing time within the first step state cycle, and uses the percentage deviation of the first step frequency from the reference step frequency, as well as the absolute difference of the left and right limb swing time ratio within the first step state cycle, as the first step state rhythm and symmetry deviation information.

[0055] First step rhythm and symmetry deviation information is used to quantify the stability and coordination of a user's gait. This information can be obtained by analyzing first limb movement information. Specifically, the user's first step frequency (steps taken per unit time) can be calculated and compared with a baseline step frequency to obtain the percentage deviation. Simultaneously, the ratio of the swing time of the left and right limbs within the first step cycle can be calculated, and the absolute difference can be taken. These indicators can intuitively reflect whether the rhythmicity of the user's gait is disordered and whether the left and right limb movements are symmetrical. For example, the baseline step frequency can be set based on the average step frequency of healthy individuals or the user's historical stable gait data.

[0056] Secondly, the control device determines the peak value of the user's joint angle change rate, the limitation range of limb movement range, and the change information of force sensor data at the connection between the device and the user's limb based on the first limb movement information, the first interaction force information, and obtains the first posture stiffness information.

[0057] The first postural stiffness information reflects the stiffness and range of motion of the user's limbs. This information can be determined by comprehensively analyzing the first limb motion information and the first interaction force information. For example, based on the first limb motion information, the peak value of the rate of change of angle of each joint of the user can be calculated; a smaller peak value may indicate more restricted joint movement. Simultaneously, the limitation range of limb movement can be determined, i.e., the maximum or minimum angle that the limb can achieve in a specific direction. Furthermore, changes in force sensor data at the connection between the device and the user's limb, such as fluctuations in torque or pressure data, can also serve as a basis for assessing postural stiffness. Together, these information depict the flexibility and resistance characteristics of the user's limbs during movement.

[0058] Based on this example, by specifically and quantitatively determining the first mechanical disturbance information, the first postural stiffness information, and the first step gait rhythm and symmetry deviation information, it is possible to capture subtle changes and potential risks of the user during movement more precisely. By identifying short-duration, high-rate-of-change interactive forces as the first mechanical disturbance information, the user's potential risk of falling or sudden imbalance can be detected in a timely manner. By calculating the percentage deviation of the first step frequency from the reference step frequency and the absolute difference in the ratio of left and right limb swing time, it is possible to accurately assess whether the user's gait rhythm is disordered and whether there is a deviation in gait symmetry, thereby reflecting their motor coordination. By determining the peak value of the joint angle change rate, the limitation range of limb range of motion, and the changes in force sensor data, the user's postural stiffness can be comprehensively assessed, identifying situations of limb stiffness or limited movement. It is precisely because of these specific and multi-dimensional information acquisition methods that the subsequent scenario judgment module can reliably identify the user's situation based on more comprehensive and accurate data.

[0059] S202. For each scenario information among multiple scenario information, the control device determines the first confidence score of the scenario information based on the weight information, the first mechanical disturbance information, the first attitude stiffness information, and the first step state rhythm and symmetry deviation information corresponding to the scenario information.

[0060] As an example, the control device determines a first similarity between the first mechanical disturbance information and the mechanical disturbance information corresponding to the scenario information.

[0061] The first similarity refers to the degree of matching or proximity between the currently collected first mechanical disturbance information and the preset mechanical disturbance information associated with specific scenario information. For example, it can be quantified by calculating the Euclidean distance, cosine similarity, or correlation coefficient between the two.

[0062] Secondly, the control device determines the second similarity between the first attitude stiffness information and the attitude stiffness information corresponding to the scenario information.

[0063] The second similarity refers to the degree of matching or closeness between the currently acquired first attitude stiffness information and the preset attitude stiffness information associated with specific scenario information. Its calculation method can be similar to the first similarity, for example, using Euclidean distance or correlation coefficient.

[0064] Secondly, the control device determines the third similarity between the first step gait rhythm and symmetry deviation information and the gait rhythm and symmetry deviation information corresponding to the scenario information.

[0065] The third similarity refers to the degree of matching or closeness between the currently collected gait rhythm and symmetry deviation information and the preset gait rhythm and symmetry deviation information associated with specific contextual information. Similarly, it can be obtained by calculating the distance or correlation between the two.

[0066] Secondly, the control device uses the sum of the weights corresponding to the first similarity and the mechanical disturbance information of the context information, the weights corresponding to the second similarity and the posture stiffness information of the context information, and the weights corresponding to the third similarity and the gait rhythm and symmetry deviation information of the context information as the first confidence score.

[0067] Each piece of contextual information is pre-set with corresponding weights, reflecting the relative importance of different features (such as mechanical perturbations, posture stiffness, gait rhythm, and symmetry deviation) in the context judgment. For example, in judging a specific context, mechanical perturbations may be more decisive than gait rhythm, so their weight is set higher. The final first confidence score is obtained by multiplying each similarity by its corresponding feature weight and then summing all the products. This is a weighted average or weighted summation method designed to comprehensively consider the contribution of each feature to the context judgment.

[0068] Based on this example, the similarity between the currently acquired first mechanical disturbance information, first posture stiffness information, first gait rhythm and symmetry deviation information and the corresponding mechanical disturbance information, posture stiffness information, gait rhythm and symmetry deviation information in the preset scenario information is calculated. Then, combining the weights of each feature in the specific scenario judgment, a weighted sum is used to calculate the first confidence score of the scenario information. This method can quantify the degree of matching between the current user state and each preset scenario, thus providing a reliable quantitative basis for subsequent target scenario determination. By introducing weights, adjustments can be made according to the importance of each feature under different scenarios, making scenario judgment more flexible and accurate.

[0069] S203. If the difference between the largest and smallest first confidence scores among multiple first confidence scores is greater than or equal to a preset difference threshold, and the largest first confidence score is greater than or equal to a preset confidence score, the control device determines the scenario information corresponding to the largest first confidence score as the target scenario information.

[0070] In practical applications, preset difference thresholds and pre-set reliability scores are key parameters for ensuring the accuracy and robustness of scenario identification. The preset difference threshold is used to determine the discriminative power between different scenario confidence scores. When the difference between the highest and lowest first confidence scores is sufficiently large, it indicates that one scenario has a significantly higher match with the current state than others, thus allowing for more reliable scenario identification. Pre-set reliability scores ensure that the selected scenario meets a minimum matching standard with the current state, avoiding uncertain judgments when all scenario matches are low. The aim is to avoid misjudgments or uncertain judgments, thereby improving the accuracy and reliability of scenario identification.

[0071] Based on S201-S203, the solution of this application effectively solves the problem of insufficient accuracy in scenario recognition by using multi-dimensional feature extraction, weighted matching, and a dual threshold judgment mechanism. First, by determining the first mechanical perturbation information, the first posture stiffness information, and the first step gait rhythm and symmetry deviation information, it can comprehensively and meticulously capture the micro-perturbation patterns and abnormal features of users under the influence of movement disorders from multiple key dimensions such as mechanics, posture, and gait rhythm, avoiding the one-sidedness that may result from single feature judgment. Second, for each scenario information, a weighted calculation is performed based on its corresponding weight information and the extracted multi-dimensional features to obtain a first confidence score. This makes the scenario matching process more flexible and precise, allowing adjustment of the importance of each feature according to the characteristics of different scenarios. Finally, by introducing a preset difference threshold and a preset confidence score, the scenario recognition results are double-verified. When the difference between the largest and smallest first confidence scores is greater than or equal to the preset difference threshold, it indicates that a scenario has a significantly better match with the current state than other scenarios, thus ensuring the discriminative power of the recognition results. Furthermore, when the highest initial confidence score is greater than or equal to the preset confidence score, the reliability of the identified scenario is further guaranteed, avoiding uncertain judgments when all scenario matching scores are low. Therefore, the solution of this application can achieve accurate and robust identification of the user's target scenario information.

[0072] After S203, the target scenario information corresponding to the user can be determined, and S103 can be executed subsequently.

[0073] S103. The control device determines the target three-dimensional auxiliary force field information based on the target scenario information. The target three-dimensional auxiliary force field information is used to indicate the distribution of target support force, target guidance force or target damping force of the motion assist device on the user's limbs in different directions.

[0074] As one possible approach, target scenario information is matched with a preset correspondence to obtain target three-dimensional auxiliary force field information; the preset correspondence includes a one-to-one correspondence between multiple scenario information and multiple three-dimensional auxiliary force field information.

[0075] Target scenario information refers to the specific movement state or demand situation currently occupied by the user, identified by analyzing the user's first limb movement information and the first interaction force information between the motion assistive device and the user's body during the first time period. For example, target scenario information might include "unsteadiness," "difficulty initiating gait," "turning imbalance," or "risk of falling." The preset correspondence can be understood as a pre-established mapping table, database, or rule set, storing the association between various identified scenario information and the optimized three-dimensional assistive force field information designed for these scenarios. Multiple scenario information refers to all possible scenario categories included in the preset correspondence, while multiple three-dimensional assistive force field information refers to the predefined set of parameters for these scenario categories, used to guide the motion assistive device to provide specific support, guiding, or damping force distributions to the user's limbs. The one-to-one correspondence ensures that each specific scenario information uniquely corresponds to a specific three-dimensional assistive force field, thereby guaranteeing the determinism and consistency of the assistive strategy.

[0076] S104. The control device configures the three-dimensional auxiliary force field of the motion assist device to the three-dimensional auxiliary force field corresponding to the target three-dimensional auxiliary force field information.

[0077] As one possible implementation, the control device sends target three-dimensional assistive force field information to the control unit of the motion assistive device. Upon receiving this information, the control unit converts it into control commands for the various joint actuators (such as motors). For example, if the target three-dimensional assistive force field information indicates that a specific torque or force is needed at a certain joint, the control unit calculates the corresponding current or voltage signal to drive the motor to generate the required assistive force. These control commands are sent to the actuators in real time, enabling the device to dynamically adjust its support, guidance, or damping of the user's limbs.

[0078] As another possible implementation, the control device sends the target three-dimensional auxiliary force field information to the control unit of the motion assistive device. After receiving the target three-dimensional auxiliary force field information, the control unit of the motion assistive device sets some joints to force control mode to precisely apply supporting or guiding forces, and sets other joints to position control mode to limit the range of motion of the limbs or provide damping. This hybrid control method can more flexibly realize complex three-dimensional auxiliary force fields.

[0079] Based on S101-S104, by collecting the user's first limb movement information and the first interaction force information between the device and the body in the first time period, the user's current movement state and interaction with the device can be comprehensively obtained. On this basis, the target scenario information of the user is determined according to this information, realizing intelligent recognition of the user's movement environment and task, overcoming the problem of the inapplicability of assistive strategies in complex daily scenarios in existing technologies. Furthermore, the target three-dimensional assistive force field information is determined based on the target scenario information. This force field information can indicate the distribution of target support force, target guidance force, or target damping force on the user's limbs in different directions, thereby dynamically adjusting the assistive strategy to highly match the user's actual needs, effectively solving the problem of mismatch between assistive force and user needs in multi-tasking activities. Finally, the three-dimensional assistive force field of the motion assistive device is configured to correspond to the three-dimensional assistive force field information of the target, realizing personalized and real-time adjustment of the assistive force, avoiding the inhibition of the user's active movement potential by fixed assistive strategies, thereby improving long-term rehabilitation effects and quality of life. This method significantly improves the accuracy, adaptability, and effectiveness of motion assistance through context awareness and adaptive force field reshaping, providing users with movement disorders with a more intelligent and personalized motion assistance solution.

[0080] The above is a general description of the method provided in this application. The method provided in this application will be further described below.

[0081] like Figure 3 As shown, after S202, when the difference between the largest and smallest first confidence scores among multiple first confidence scores is less than a preset difference threshold, or when the largest first confidence score is less than a preset confidence score, the method provided in this application may further include the following steps:

[0082] S301, The control device configures the three-dimensional auxiliary force field of the motion assist device to the three-dimensional auxiliary force field corresponding to the preset three-dimensional auxiliary force field information; the preset three-dimensional auxiliary force field information is used to instruct the motion assist device to provide stable support to the user's limbs.

[0083] When the confidence level of the initial scene recognition is insufficient, the three-dimensional assistive force field of the motion assist device will be configured to correspond to the three-dimensional assistive force field information preset. This preset three-dimensional assistive force field information aims to provide a stable support force for the user's limbs. For example, it can be a uniform, low-intensity, omnidirectional support force to ensure that the user can still obtain basic safety protection when the scene is unclear, and avoid discomfort or the risk of falling due to an inappropriate assistive force field.

[0084] S302, The control device acquires the user's target state information in the second time period; the target state information is used to indicate the stability of the user's body; the start time of the second time period is after the end time of the first time period.

[0085] One possible implementation is to acquire the user's gliding duration, gait rhythm disorder frequency, and stiffness during a second time period. If the gliding duration is less than a preset gliding duration threshold, the gait rhythm disorder frequency is less than a preset disorder frequency threshold, and the stiffness is less than a preset stiffness threshold, the target state information is determined to indicate that the user's body is in a stable state.

[0086] Slip duration refers to the length of time during which a user's limbs undergo unintended relative displacement with respect to the ground or supporting surface during exercise. This duration can be monitored and calculated in real time using devices such as force sensors and inertial measurement units (IMUs) installed on the soles of exercise aids or the user's shoes. For example, when a sensor detects a sudden decrease in friction between the limb and the supporting surface or a deviation in the velocity vector from expectations, slippage can be identified and its duration recorded. The purpose is to quantify the degree to which the user loses balance or control during exercise.

[0087] Gait rhythm disturbance frequency refers to the number of times a user's gait parameters, such as gait cycle, stride length, and cadence, significantly deviate from the normal or baseline pattern within a specific time period. This can be identified by analyzing limb movement information, such as data on limb swing frequency and ground contact time obtained through sensors like accelerometers and gyroscopes. When fluctuations in these parameters exceed preset physiological ranges or statistical thresholds, it is counted as one disturbance. The purpose is to assess the stability and coordination of the user's gait.

[0088] Stiffness refers to the degree of resistance or limited range of motion exhibited by a user's limb joints during movement. This can be determined by measuring changes in the rate of change of joint angle, limb range of motion, and changes in force sensor data at the connection between the device and the user's limb. For example, when a joint requires greater force to achieve the desired angle when attempting movement, or when the range of motion is significantly less than normal, stiffness is considered high. Its purpose is to reflect the user's muscle tone, joint flexibility, and motor control.

[0089] The preset gliding duration threshold, preset disorder frequency threshold, and preset stiffness threshold are determined based on a comprehensive analysis of clinical data from a large number of users with movement disorders, physiological parameters of healthy individuals, and the performance characteristics of assistive devices. These thresholds can be individually adjusted according to different disease types, disease severity, individual user differences, and rehabilitation goals. For example, the stiffness threshold may be set relatively leniently for Parkinson's disease users, while the gliding duration threshold may be set more strictly for users with balance disorders. These thresholds are designed to accurately distinguish between stable and unstable states of the user's body, ensuring the accuracy of subsequent assistive strategies.

[0090] When the duration of slippage, the number of gait rhythm disturbances, and stiffness are all less than their respective preset thresholds, the user's body is considered to be in a stable state. This means that the user did not experience significant slippage during movement, maintained a good gait rhythm, and the stiffness of the limb joints was within an acceptable range, indicating that their body posture and motor control ability were relatively stable.

[0091] Based on this implementation method, by comprehensively evaluating three key indicators—glide duration, gait rhythm disturbance frequency, and stiffness—the stability of the user's body can be fully and objectively reflected. Glide duration is directly related to the immediate risk of balance control failure; the frequency of gait rhythm disturbances reflects the long-term stability of motor coordination and rhythm; and stiffness reveals the motor capacity and flexibility of the musculoskeletal system. It is precisely because these three indicators capture the stability characteristics of the user's body from different dimensions that the judgment of target state information is more accurate and reliable. When these indicators are all within safe thresholds, it can be assured that the user's body is in a stable state, thus providing a reliable basis for subsequent adjustment of the auxiliary force field and avoiding unnecessary or potentially instability-enhancing force field configurations when the user's body is unstable.

[0092] S303. When the target state information indicates that the user's body is in a stable state, the control device acquires the user's second limb movement information in the second time period and the second interaction force information between the motion assist device and the user's body in the second time period.

[0093] When the target state information indicates that the user's body is in a stable state, the system will again acquire the user's second limb movement information and second interaction force information in the second time period. This information is similar to the information collected in the first time period, but it reflects the user's state information under stabilization assistance.

[0094] S304. The control device determines the user's second mechanical disturbance information, second postural stiffness information, and second gait rhythm and symmetry deviation information in the second time period based on the second limb movement information and the second interaction force information.

[0095] Based on this new motion and interaction force information, the user's second mechanical perturbation information, second postural stiffness information, and second gait rhythm and symmetry deviation information can be determined in the second time period. This information represents the user's physiological and motor characteristics in a relatively stable state, helping to more accurately reflect their true needs.

[0096] S305. For each scenario information among multiple scenario information, the control device determines the second confidence score of the scenario information based on the weight information, second mechanical disturbance information, second attitude stiffness information, second gait rhythm and symmetry deviation information corresponding to the scenario information.

[0097] For each of the multiple preset scenario information, a second confidence score is calculated based on the corresponding weight information, the newly determined second mechanical perturbation information, the second attitude stiffness information, and the second gait rhythm and symmetry deviation information. This process is similar to the first scenario recognition, but uses more reliable data collected with stabilization assistance.

[0098] S306. If the difference between the largest and smallest second confidence scores among multiple second confidence scores is greater than or equal to a preset difference threshold, and the largest second confidence score is greater than a preset confidence threshold, the control device determines the scenario information corresponding to the largest second confidence score as the target scenario information.

[0099] Among multiple second confidence scores, if the difference between the highest and lowest second confidence scores is greater than or equal to a preset difference threshold, and the highest second confidence score is greater than a preset confidence threshold, then the scenario information corresponding to the highest second confidence score is determined as the final target scenario information. This means that after stabilization assistance and secondary evaluation, the user's most likely scenario has been successfully identified, allowing for the configuration of a more precise personalized assistance field.

[0100] Based on S301-S306, a two-stage scenario recognition and auxiliary force field configuration mechanism is introduced to effectively solve the problem of insufficient confidence in initial scenario recognition. When the user's scenario cannot be clearly determined in the first time period, instead of forcibly selecting an uncertain scenario, the three-dimensional auxiliary force field of the motion assistive device is first configured to the three-dimensional auxiliary force field corresponding to the preset three-dimensional auxiliary force field information, which provides stable support force. This measure can immediately provide basic safety assurance for the user, avoid potential risks caused by inaccurate scenario recognition, and ensure the user's safety and comfort during the transition period. Subsequently, an observation and re-evaluation phase is entered. By acquiring the user's target state information in the second time period, it can be determined whether the user has reached a relatively stable state under stable support force. Only when the user's body is in a stable state is the second data acquisition and scenario recognition performed. This strategy avoids inaccurate recognition when the user's state is unstable, improving the effectiveness of subsequent data acquisition and the accuracy of scenario recognition. After the user stabilizes, second limb movement information and second interaction force information are acquired, and based on these more reliable data, second mechanical disturbance information, second posture stiffness information, and second gait rhythm and symmetry deviation information are recalculated. The feature information acquired under stable conditions typically reflects the user's true movement patterns and needs more clearly, making the subsequently calculated second confidence score more discriminative and reliable. By conducting another scenario confidence assessment and setting the same judgment criteria as the first assessment—that is, the difference between the largest and smallest second confidence scores is greater than or equal to a preset difference threshold, and the largest second confidence score is greater than a preset confidence threshold—the final target scenario information can be determined with higher accuracy and confidence. This series of steps ensures that even in cases of initial identification difficulties, personalized and safe movement assistance can ultimately be provided to the user through iteration and verification.

[0101] The above technical solution effectively solves the problem of insufficient confidence in scenario recognition, which may lead to inadequate assistance or potential safety hazards. First, configuring a preset three-dimensional auxiliary force field provides users with immediate and basic stable support, significantly improving safety and user experience in uncertain situations. Second, introducing target state information as a trigger condition for secondary evaluation ensures that re-identification only occurs when the user's body reaches a stable state, avoiding invalid or erroneous judgments in unstable states, thereby improving the effectiveness of data collection and scenario recognition. Finally, by performing a second scenario recognition in a stable state and reapplying the confidence judgment mechanism, the target scenario information can be determined with higher accuracy and reliability, allowing for the configuration of a more personalized auxiliary force field that better meets the user's actual needs. This not only enhances the robustness and adaptability of assistive devices but also greatly improves the assistive effect and safety for users with movement disorders.

[0102] In some preferred embodiments, it is assumed that a Parkinson's disease user is using a motor assistive device for walking training. During a first time period, the user's limb movement information and interaction force information are collected, and first mechanical disturbance information, first postural stiffness information, and first step gait rhythm and symmetry deviation information are calculated. However, during scenario recognition, the first confidence scores for the three scenarios of "difficulty initiating," "gait freeze," and "balance disorder" are found to be 0.45, 0.42, and 0.40, respectively. At this point, the difference of 0.05 between the largest first confidence score (0.45) and the smallest first confidence score (0.40) is less than a preset difference threshold, for example, 0.1, and the largest first confidence score (0.45) is also less than a preset confidence score, for example, 0.6. According to the scheme of this application, due to insufficient confidence in the initial scenario recognition, a scenario is not forcibly selected. Instead, the three-dimensional assistive force field of the motor assistive device is immediately configured to the three-dimensional assistive force field corresponding to the preset three-dimensional assistive force field information. This force field provides the user with uniform and stable support to prevent the user from falling due to unclear scenarios. After providing stable support, the system enters a second time period to acquire the user's target state information. For example, by monitoring the user's center of gravity swing amplitude, limb tremors, and gait stability, it is determined that the user's body is gradually stabilizing. Once the target state information indicates that the user's body is in a stable state, the system again acquires the user's second limb movement information and second interaction force information in the second time period. Based on this new data, the second mechanical disturbance information, second posture stiffness information, and second gait rhythm and symmetry deviation information are recalculated. Using this updated feature information, the second confidence score is recalculated for scenarios such as "difficulty initiating," "gait freeze," and "balance imbalance." Assume that the calculated second confidence scores at this time are 0.75, 0.15, and 0.10, respectively. At this point, the difference of 0.65 between the largest second confidence score of 0.75 and the smallest second confidence score of 0.10 is greater than the preset difference threshold of 0.1, and the largest second confidence score of 0.75 is also greater than the preset confidence threshold of 0.6. Therefore, it is possible to identify "starting difficulty" scenarios as target scenario information with high confidence, and configure personalized assistive force fields accordingly, such as providing forward guiding force to help users take the first step. Through this two-stage identification and assistance mechanism, even in situations where the initial scenario is complex or the data is unclear, it is possible to ultimately provide users with accurate and safe movement assistance.

[0103] This application also provides a motor assistive control system for movement disorders, such as... Figure 4As shown, the system includes: a data acquisition device for acquiring first limb movement information of a user of a motion assistive device in a first time period and first interaction force information between the motion assistive device and the user's body in the first time period; a processing device for determining target scenario information of the user based on the first limb movement information and the first interaction force information; a processing device for determining target three-dimensional auxiliary force field information based on the target scenario information, wherein the target three-dimensional auxiliary force field information is used to indicate the distribution of target support force, target guiding force, or target damping force of the motion assistive device on the user's limb in different directions; and a processing device for configuring the three-dimensional auxiliary force field of the motion assistive device to the three-dimensional auxiliary force field corresponding to the target three-dimensional auxiliary force field information.

[0104] Although this application has been described herein in conjunction with various embodiments, those skilled in the art will understand and implement other variations of the disclosed embodiments by reviewing the accompanying drawings and the disclosure in carrying out the claimed application.

[0105] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the spirit and scope of this application. Accordingly, this specification and drawings are merely illustrative examples of this application and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from the spirit and scope of this application. Thus, if such modifications and modifications of this application fall within the scope of equivalent technology of this application, this application also intends to include such modifications and modifications.

Claims

1. A movement assistance control method for a movement disorder disease, characterized by, The motion disorder disease motion auxiliary control method comprises: Collecting first limb motion information of a user of a motion auxiliary device in a first time period, and first interaction force information between the motion auxiliary device and the user's body in the first time period; Determining target scenario information in which the user is located according to the first limb motion information and the first interaction force information; Determining target three-dimensional auxiliary force field information according to the target scenario information, the target three-dimensional auxiliary force field information being used to indicate target support force, target guiding force or target damping force distribution of the motion auxiliary device to the user's limb in different directions; Configuring a three-dimensional auxiliary force field of the motion auxiliary device as a three-dimensional auxiliary force field corresponding to the target three-dimensional auxiliary force field information; The determining of the target scenario information in which the user is located according to the first limb motion information and the first interaction force information comprises: Determining first mechanical disturbance information, first attitude stiffness information and first gait rhythm and symmetry deviation information of the user in the first time period according to the first limb motion information and the first interaction force information; For each scenario information in a plurality of scenario information, determining a first confidence score of the scenario information according to weight information corresponding to the scenario information, the first mechanical disturbance information, the first attitude stiffness information and the first gait rhythm and symmetry deviation information; In a case that a difference between a maximum first confidence score and a minimum first confidence score in a plurality of first confidence scores is greater than or equal to a preset difference threshold value, and the maximum first confidence score is greater than or equal to a preset confidence score, the scenario information corresponding to the maximum first confidence score is determined as the target scenario information.

2. The motion impairment disease motion assist control method according to claim 1, characterized by, The determining of the first mechanical disturbance information, the first attitude stiffness information and the first gait rhythm and symmetry deviation information of the user in the first time period according to the first limb motion information and the first interaction force information comprises: Interaction force information with a duration less than a preset duration threshold value and a change rate greater than a preset change rate threshold value in the first interaction force information is taken as the first mechanical disturbance information; A left-right limb swing time ratio in a first step frequency and a first gait cycle of the user, a deviation percentage of the first step frequency from a reference step frequency, and an absolute difference value of the left-right limb swing time ratio in the first gait cycle are taken as the first gait rhythm and symmetry deviation information according to the first limb motion information; A peak value of a joint angle change rate, a limitation range of a limb activity range, and change information of force sensor data at a connection between the device and the user's limb are obtained as the first attitude stiffness information according to the first limb motion information and the first interaction force information.

3. The motion impairment disease motion assist control method according to claim 1, characterized by, The determining of the first confidence score of the scenario information according to the weight information corresponding to the scenario information, the first mechanical disturbance information, the first attitude stiffness information and the first gait rhythm and symmetry deviation information comprises: A first similarity between the first mechanical disturbance information and mechanical disturbance information corresponding to the scenario information is determined. determine a second similarity between the first posture stiffness information and posture stiffness information corresponding to the scenario information; determine a third similarity between the first gait rhythm and symmetry deviation information and gait rhythm and symmetry deviation information corresponding to the scenario information; determine a first confidence score as a sum of a product of the first similarity and a weight corresponding to mechanical disturbance information of the scenario information, a product of the second similarity and a weight corresponding to posture stiffness information of the scenario information, and a product of the third similarity and a weight corresponding to gait rhythm and symmetry deviation information of the scenario information.

4. The movement disorder disease movement assistance control method according to claim 1, characterized by, When a difference between a largest first confidence score and a smallest first confidence score among a plurality of first confidence scores is less than a preset difference threshold, or the largest first confidence score is less than a preset confidence score, the method further includes: configuring a three-dimensional assistive force field of the motion assistive device as a three-dimensional assistive force field corresponding to preset three-dimensional assistive force field information, the preset three-dimensional assistive force field information being used to instruct the motion assistive device to provide a stable support force to the user's limb; obtain target state information of the user in a second time period, the target state information being used to indicate a stability degree of the user's body, a start time of the second time period being after an end time of the first time period; when the target state information indicates that the user's body is in a stable state, obtain second limb movement information of the user in the second time period and second interaction force information between the motion assistive device and the user's body in the second time period; determine second mechanical disturbance information, second posture stiffness information, and second gait rhythm and symmetry deviation information of the user in the second time period according to the second limb movement information and the second interaction force information; for each scenario information in a plurality of scenario information, determine a second confidence score of the scenario information according to weight information corresponding to the scenario information, the second mechanical disturbance information, the second posture stiffness information, and the second gait rhythm and symmetry deviation information; when a difference between a largest second confidence score and a smallest second confidence score among a plurality of second confidence scores is greater than or equal to the preset difference threshold, and the largest second confidence score is greater than a preset confidence threshold, determine the scenario information corresponding to the largest second confidence score as the target scenario information.

5. The motion impairment disease motion assist control method according to claim 4, characterized by, The obtaining of the target state information of the user in the second time period includes: obtaining a slip duration, a gait rhythm disorder frequency, and a rigidity degree of the user in the second time period; when the slip duration is less than a preset slip duration threshold, the gait rhythm disorder frequency is less than a preset disorder frequency threshold, and the rigidity degree is less than a preset rigidity degree threshold, determining that the target state information indicates that the user's body is in a stable state.

6. The motion impairment disease motion assist control method according to any one of claims 1 to 5, characterized by, The determining of the target three-dimensional assistive force field information according to the target scenario information includes: The target scenario information is matched with a preset corresponding relationship to obtain the target three-dimensional auxiliary force field information; the preset corresponding relationship includes a one-to-one corresponding relationship between a plurality of scenario information and a plurality of three-dimensional auxiliary force field information.

7. The motion impairment disease motion assist control method according to any one of claims 1 to 5, characterized by, The first limb movement information of the user of the motion assistance device in a first time period and the first interaction force information between the motion assistance device and the user's body in the first time period are collected, including: The first limb movement information of the user of the motion assistance device in a first time period and the first interaction force information between the motion assistance device and the user's body in the first time period are collected, including: The first limb movement information of the user of the motion assistance device in a first time period and the first interaction force information between the motion assistance device and the user's body in the first time period are collected, including:

8. The motion impairment disease motion assist control method according to claim 7, characterized by, The first limb movement information of the user of the motion assistance device in a first time period and the first interaction force information between the motion assistance device and the user's body in the first time period are collected, including: The extreme maximum value and the extreme minimum value in the original first limb movement information and the original first interaction force information are removed to obtain initial first limb movement information and initial first interaction force information. The extreme maximum value and the extreme minimum value in the original first limb movement information and the original first interaction force information are removed to obtain initial first limb movement information and initial first interaction force information.

9. A movement disorder disease movement assistance control system characterized by, The extreme maximum value and the extreme minimum value in the original first limb movement information and the original first interaction force information are removed to obtain initial first limb movement information and initial first interaction force information. The system comprises: A collection device is configured to collect first limb movement information of a user of a motion assistance device in a first time period and first interaction force information between the motion assistance device and the user's body in the first time period. A processing device is further configured to determine target scenario information in which the user is located according to the first limb movement information and the first interaction force information. The processing device is further configured to determine target three-dimensional auxiliary force field information according to the target scenario information, wherein the target three-dimensional auxiliary force field information is used to indicate target support force, target guiding force or target damping force distribution of the motion assistance device on the user's limb in different directions. The processing device is further configured to configure a three-dimensional auxiliary force field of the motion assistance device as a three-dimensional auxiliary force field corresponding to the target three-dimensional auxiliary force field information. The processing device is further configured to determine target scenario information in which the user is located according to the first limb movement information and the first interaction force information, including: The processing device is further configured to determine first mechanical disturbance information, first attitude stiffness information, first gait rhythm and symmetry deviation information of the user in the first time period according to the first limb movement information and the first interaction force information. For each scenario information in a plurality of scenario information, a first confidence score of the scenario information is determined according to weight information corresponding to the scenario information, the first mechanical disturbance information, the first attitude stiffness information and the first gait rhythm and symmetry deviation information. In a case where a difference between a maximum first confidence score and a minimum first confidence score among the plurality of first confidence scores is greater than or equal to a preset difference threshold, and the maximum first confidence score is greater than or equal to a preset confidence score, the scenario information corresponding to the maximum first confidence score is determined as the target scenario information.

Images