Stroke old person standing assisting control method and system based on multi-scene body position conversion

Abstract

The invention provides a multi-scene body position conversion-based standing-up assisting control method and system for the elderly suffering from stroke. According to the method, firstly, the standing-assisting device is controlled to obtain a fusion sensing result composed of body pressure distribution data and joint movement data, multi-feature coupling analysis is carried out to generate a combined recognition conclusion containing a body position state and a scene type, and then dynamic mode mapping is carried out according to the combined recognition conclusion. Outputting a target control mode matched with the current scene type and the body position, and finally performing power instruction synthesis by utilizing the target control mode to generate a cooperative control signal for driving the standing assisting equipment to execute body position conversion; according to the technical scheme provided by the invention, accurate conversion from standardized control to personalized control is realized, the suitability and the user experience of the standing assisting process are improved, the uncertainty and the individual difference in actual operation are overcome, and the stability, the safety and the adaptability of the body position conversion process are improved.

Description

Technical Field

[0001] The present application relates to the field of medical assistive device control technology, and in particular to a method and system for assisting elderly people with stroke to get up based on multi-scenario body position conversion. Background Art

[0002] Since stroke patients often suffer from hemiplegia of the limbs, abnormal muscle tone and decreased postural control ability due to damage to the central nervous system, the process of transitioning from lying to sitting and from sitting to standing is extremely difficult. There is an urgent need for an intelligent assistance technology that can replace or assist manual care.

[0003] One currently targeted solution is a lifting device based on a mechanical transmission and a flip plate structure. A servo motor drives a transmission wheel assembly, which rotates the flip plate upward to provide back support. Simultaneously, a retracting mechanism in the assist belt provides additional pulling force for the patient to rise. This device allows the patient to actively exert force to rise within a certain range, or passively rely solely on mechanical support for lifting, aiming to provide both lifting assistance and light motor function training.

[0004] However, these mechanical lifting devices still have significant drawbacks. Their control process relies heavily on pre-set mechanical programs and lacks dynamic perception and intelligent decision-making capabilities for the patient's real-time posture, muscle tone changes, movement intentions, and the surrounding environment (e.g., bed, wheelchair). This results in a rigid lifting pattern and makes it difficult to flexibly adjust to individual differences and actual needs. This not only limits the patient's active participation and training benefits, but also fails to effectively avoid the risk of secondary injury caused by improper posture or uncomfortable assistance. Summary of the Invention

[0005] The present application provides a method and system for assisting elderly people with stroke to rise based on multi-scenario body position conversion, which is used to solve the problems in the prior art of rigid control mode of the assisting device and lack of dynamic adaptation capability to the patient's real-time status and multi-scenario changes.

[0006] In the first aspect, the present application provides a method for assisting elderly people with stroke to stand up based on multi-scenario body position conversion, including: Control multiple sensors pre-arranged on the contact surface of the target person's lifting device to perform synchronous sensing to obtain a fusion sensing result consisting of body pressure distribution data and joint motion data; Perform multi-feature coupling analysis based on the fusion perception results to generate a joint recognition conclusion including body position state and scene type; Perform dynamic mode mapping based on the joint recognition conclusion and output a target control mode that matches the current scene type and body position; The target control mode is used to synthesize power instructions to generate a coordinated control signal for driving the auxiliary lifting device to perform body position conversion.

[0007] Optionally, multiple sensors pre-arranged on the contact surface of the lifting device of the target person are controlled to perform synchronous sensing to obtain a fusion sensing result consisting of body pressure distribution data and joint motion data, including: The original data of pressure distribution is collected through the pressure sensing array evenly distributed on the supporting surface of the lifting equipment; The raw data of joint motion is collected through motion sensing units fixed on the joints of the target person's limbs; Converting the pressure distribution raw data into continuous trajectory information reflecting the displacement of the pressure center; Converting the raw joint motion data into sequence information describing changes in joint flexion and extension angles; The continuous trajectory information and the change sequence information are integrated in a time-series association manner to obtain a fusion perception result representing the user's body posture characteristics.

[0008] Optionally, a multi-feature coupling analysis is performed based on the fused perception result to generate a joint recognition conclusion including body position state and scene type, including: extracting pressure distribution features and motion pattern features from the fused perception results; Matching the pressure distribution characteristics with a predefined pressure distribution pattern to obtain a preliminary body position determination result; Matching the movement pattern feature with a predefined movement pattern sequence to obtain an auxiliary body position judgment result; Determining a final body position state based on a combination of the preliminary body position determination result and the auxiliary body position determination result; Based on the contact characteristics between the final body position and the device support structure of the lifting assist device, identifying the current scene type of the target person; The final body position state and the current scene type of the target person are combined to form a joint recognition conclusion.

[0009] Optionally, dynamic mode mapping is performed based on the joint recognition conclusion to output a target control mode that matches the current scene type and body position, including: Analyzing the current scene type and the current body position of the target person from the joint recognition conclusion; Matching the current scene type with scene classifications in a pre-stored assistance mode library to determine a set of candidate control modes; Performing matching screening based on the current body position state and the body position requirements in the candidate control mode set, and generating an adaptive control mode based on the matching screening result; A target control mode is determined based on the adaptation control mode and the preference characteristics of the user's historical operation records.

[0010] Optionally, determining a target control mode based on the adaptation control mode and preference characteristics of the user's historical operation records includes: Extracting preference data including assist speed, angle adjustment, and pause interval from the user's historical operation records; converting the preference data into a control parameter adjustment vector; Performing a combined operation on the basic parameters of the adaptive control mode and the control parameter adjustment vector; Generate a target control mode that meets the user's personalized needs based on the combined operation results.

[0011] Optionally, the target control mode is used to synthesize power instructions to generate a coordinated control signal for driving the assisting device to perform body position conversion, including: parsing the action sequence parameters of each power execution unit from the target control mode; Generate a basic driving instruction set according to the action sequence parameters; Converting the basic drive instruction set into multi-execution unit cooperative instructions with time sequence association through a motion coordination algorithm; Adjusting the multi-execution unit coordination instruction in real time according to the current state feedback of the device to obtain an adjusted multi-execution unit coordination instruction; According to the adjusted multi-execution unit coordination instruction, the coordination control signal including speed control, angle control and force control is generated.

[0012] Optionally, adjusting the multi-execution unit coordination instruction in real time according to the current state feedback of the device to obtain the adjusted multi-execution unit coordination instruction includes: The operating parameters and load parameters of each power actuator in the lifting device are obtained in real time through the status monitoring module on the lifting device; Comparing the operating parameters and the load parameters with expected parameters in the multi-execution unit coordination instruction to obtain a difference comparison result; Determine the parameter adjustment amount of each power actuator according to the difference comparison result; The parameter adjustment amount is applied to the multi-execution unit coordinated instruction to generate an adjusted multi-execution unit coordinated instruction.

[0013] In the second aspect, the present application provides a control system for assisting elderly people with stroke to stand up based on multi-scenario body position conversion, including: A control module is used to control multiple sensors pre-arranged on the contact surface of the target person's lifting device to perform synchronous sensing to obtain a fusion sensing result composed of body pressure distribution data and joint movement data; A coupling analysis module, configured to perform multi-feature coupling analysis based on the fusion perception results to generate a joint recognition conclusion including body position state and scene type; A pattern mapping module is used to perform dynamic pattern mapping based on the joint recognition conclusion and output a target control pattern that matches the current scene type and body position; The instruction synthesis module is used to use the target control mode to synthesize power instructions and generate a coordinated control signal for driving the auxiliary lifting device to perform posture conversion.

[0014] In a third aspect, the present application provides a computing device comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a method for assisting elderly people with stroke to rise up and control based on multi-scenario body posture conversion as described in the first aspect above.

[0015] In a fourth aspect, the present application provides a computer storage medium storing a computer program. When the computer program is executed by a computer, it implements a method for assisting elderly people with stroke to get up and control based on multi-scenario body posture conversion as described in the first aspect.

[0016] This application uses synchronized sensing from multiple sensors to obtain fused data, combines multi-feature coupling analysis to accurately identify body position and scenario type, and uses dynamic pattern mapping to generate a control mode that closely matches the current scenario and body position. Ultimately, collaborative control is achieved through dynamic command synthesis. This solution can adapt to various lifting scenarios, such as beds, wheelchairs, and chairs, and provides personalized body position transition assistance based on the real-time physical state of elderly people after stroke, effectively improving the safety and adaptability of the lifting process.

[0017] Furthermore, by monitoring the operating status of each power actuator in real time, comparing actual parameters with expected commands and dynamically adjusting control parameters, the system ensures that the various actuators in the lifting device maintain coordinated operation during position transitions. This real-time adjustment mechanism based on state feedback effectively responds to changes in device load and patient position, preventing overload or understaffing, and significantly improving the stability and safety of the lifting process.

[0018] These and other aspects of the present application will become more readily apparent from the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the present application or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0020] Figure 1 A flowchart of a method for controlling the assisting of an elderly person with stroke to stand up based on multi-scenario body position conversion provided by the present application is shown; Figure 2 The present invention provides a structural diagram of a control system for assisting elderly people with stroke to stand up based on multi-scenario body position conversion; Figure 3 A schematic structural diagram of a computing device provided by the present application is shown. DETAILED DESCRIPTION

[0021] In order to enable people skilled in the art to better understand the solution of this application, the technical solution of this application will be clearly and completely described below in conjunction with the drawings in this application.

[0022] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this document or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any order of execution. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to being different types.

[0023] The following will be combined with the accompanying drawings to clearly and completely describe the technical solutions in this application. Obviously, the embodiments described are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of this application.

[0024] Figure 1 This application provides a flowchart of a method for assisting elderly people with stroke to stand up based on multi-scene posture conversion, such as Figure 1 As shown, the method includes: Step 101: Control multiple sensors pre-arranged on the contact surface of the assistive device of the target person to perform synchronous perception to obtain a fusion perception result consisting of body pressure distribution data and joint movement data.

[0025] Optionally, step 101 may specifically include the following steps: Step 1011, collecting raw pressure distribution data through a pressure sensing array evenly distributed on the supporting surface of the lifting aid device; Step 1012, collecting raw joint motion data through motion sensing units fixed to the target person's limb joints; Step 1013: converting the raw pressure distribution data into continuous trajectory information reflecting the displacement of the pressure center; Step 1014, converting the raw joint motion data into sequence information describing changes in joint flexion and extension angles; Step 1015 : Integrate the continuous trajectory information and the change sequence information in a time-series association manner to obtain a fusion perception result representing the user's body posture characteristics.

[0026] In the above scheme, the contact surface of the lifting aid device refers to the part where the device is in direct contact with the user's body to provide support. The surface is evenly distributed with a pressure sensing array for collecting raw pressure distribution data, which reflects the magnitude and distribution of pressure exerted by various parts of the user's body on the contact surface. The body pressure distribution data is information obtained by analyzing the raw pressure distribution data, which describes the overall distribution characteristics of the pressure of the user's body on the lifting aid device. The joint motion data describes the motion state of the user's limb joints, and is converted after the motion sensing units fixed at the limb joints collect the raw joint motion data. The fused perception result is comprehensive data that can characterize the user's body characteristics, formed by integrating the continuous trajectory information reflecting the displacement of the pressure center and the sequence information describing the changes in the joint flexion and extension angles in a time-series association manner.

[0027] In this solution, first, step 1011 collects the original data of pressure distribution through pressure sensing arrays evenly distributed on the supporting surface of the lifting device. These arrays can continuously measure the pressure value applied by the user's body to the surface of the device. Secondly, step 1012 collects the original data of joint movement through motion sensing units fixed at the joints of the target person's limbs. These units can track the movement angle and direction of the joints. Then step 1013 converts the original data of pressure distribution into continuous trajectory information reflecting the displacement of the pressure center. This process realizes the description of the dynamic change of the pressure center by analyzing the moving path of the pressure point. Then, step 1014 converts the original data of joint movement into change sequence information describing the flexion and extension angle of the joint, and forms an angle change sequence by analyzing the continuous data points of the joint movement. Finally, step 1015 integrates the continuous trajectory information and the change sequence information through time association, so that the pressure center movement and the joint angle change are aligned on the time axis, thereby forming a fusion perception result that can fully characterize the user's body characteristics.

[0028] For example, in the application scenario of the assistive device at Rehabilitation Center A, a pressure sensing array is laid on the supporting surface of the device. When the elderly person with stroke uses the device, the array continuously collects the raw data of the pressure distribution on their back and buttocks. At the same time, the motion sensing units installed at the elderly's knee and hip joints synchronously collect the raw data of joint movement. After processing these raw data, the pressure distribution data is converted into continuous trajectory information reflecting the movement path of the pressure center from sitting to standing up, and the joint movement data is converted into change sequence information recording the changes in the flexion and extension angles of the knee and hip joints. After integrating the two types of information through the time series association algorithm, the system generates a fusion perception result that accurately reflects the changes in the elderly's posture during standing up, providing data support for subsequent assistive control.

[0029] This solution achieves a comprehensive perception of the user's body characteristics by collaboratively collecting pressure and joint motion data and converting them into time-related trajectory and sequence information. It provides a high-precision and synchronized multimodal data foundation for assisted control, ensuring the accuracy of subsequent user status judgment and the effectiveness of control strategies.

[0030] Step 102: Perform multi-feature coupling analysis based on the fusion perception result to generate a joint recognition conclusion including body posture state and scene type.

[0031] Optionally, step 102 may specifically include the following steps: Step 1021: extracting pressure distribution features and motion pattern features from the fused sensing result; Step 1022, matching the pressure distribution characteristics with a predefined pressure distribution pattern to obtain a preliminary body position determination result; Step 1023, matching the motion pattern feature with a predefined motion pattern sequence to obtain an auxiliary body position determination result; Step 1024, determining a final body position state based on a combination of the preliminary body position determination result and the auxiliary body position determination result; Step 1025: Identify the current scene type of the target person based on the contact characteristics between the final body position and the device support structure of the lifting assist device; Step 1026: Combine the final body position state and the current scene type of the target person to form a joint recognition conclusion.

[0032] In the above scheme, multi-feature coupling analysis refers to the process of jointly processing the pressure distribution features and motion pattern features in the fused perception results to identify the user's body position and scene type. The body position describes the user's body posture (e.g., lying, sitting, or standing), while the scene type refers to the support environment of the assistive device (e.g., bed, wheelchair, or chair). The joint recognition conclusion is a judgment result formed by combining the final body position and the current scene type. The pressure distribution features are data extracted from the fused perception results that reflect the body's pressure distribution pattern, while the motion pattern features are data that describe the joint movement patterns. The preliminary body position determination result is an initial body position classification obtained by matching the pressure distribution features with predefined pressure distribution patterns. The predefined pressure distribution patterns are a set of pre-stored pressure distribution patterns, and the predefined motion pattern sequences are a set of pre-stored typical joint motion patterns. The auxiliary body position determination result is an auxiliary classification obtained by matching the motion pattern features with the pre-defined motion pattern sequences. The final body position is the precise body position classification determined by combining the preliminary and auxiliary body position determination results. The contact characteristics of the device support structure describe the contact method between the device and the supporting surface (such as a mattress or wheelchair cushion) and are used to distinguish scenario types.

[0033] In this solution, first, pressure distribution features and motion pattern features are separated from the fused perception results at step 1021. The pressure distribution features reflect the pressure intensity distribution across various body parts, while the motion pattern features describe the temporal patterns of joint angle changes. Secondly, at step 1022, the pressure distribution features are compared with a pre-stored library of pressure distribution patterns, and a preliminary body position determination result (e.g., "sitting") is obtained by calculating similarity. Next, at step 1023, the motion pattern features are matched with a predefined motion pattern sequence, and a supplementary body position determination result (e.g., "standing transition state") is obtained using a sequence alignment algorithm. Finally, at step 1024, the preliminary and supplementary body position determination results are weightedly fused, and the final body position state (e.g., "sitting to standing transition") is determined based on predefined decision rules (e.g., majority voting or confidence weighting). Subsequently, at step 1025, contact features of the device support structure (e.g., pressure center location and support surface shape) are analyzed based on the final body position state, matching them to predefined scene templates (e.g., bed scenes typically have a large, uniform pressure distribution) to identify the current scene type (e.g., "wheelchair scene"). Finally, the final body posture state and the current scene type are combined into a joint recognition conclusion (such as "sitting state in a wheelchair scene") through 1026.

[0034] Continuing from the previous solution, in the application scenario of an assistive lifting device at Rehabilitation Center A, the system extracts pressure distribution features (showing concentrated pressure on the buttocks and thighs) and movement pattern features (indicating a slow extension pattern of the knee and hip joints) from the fused perception results. The pressure distribution features closely match the pre-stored "sitting" pattern, generating a preliminary body position determination result of "sitting." The movement pattern features match the pre-defined "sitting to standing transition" sequence, generating an auxiliary body position determination result of "standing transition." Combining these two determination results, the system determines the final body position as "sitting to standing transition." By analyzing the contact features of the device's support structure (discovering a rectangular pressure distribution and the presence of moving wheels), the system identifies the current scenario as a "wheelchair scenario." Finally, the system generates a joint identification conclusion, "sitting to standing transition in a wheelchair scenario," providing precise input for subsequent assistive lifting control.

[0035] This solution achieves high-precision body posture and scene type recognition through multi-feature coupling analysis, reduces the possibility of misjudgment through a dual verification mechanism of pressure and motion features, and enhances scene differentiation capabilities through analysis of the contact features of the equipment support structure. The final joint recognition conclusion provides a comprehensive and accurate environmental perception basis for subsequent assisted control.

[0036] Step 103 : Perform dynamic mode mapping based on the joint recognition conclusion, and output a target control mode that matches the current scene type and body position.

[0037] Optionally, step 103 may specifically include the following steps: Step 1031: parse the current scene type and the current body position of the target person from the joint recognition conclusion; Step 1032: Match the current scene type with the scene classification in the pre-stored assistance mode library to determine a candidate control mode set; Step 1033, performing matching screening based on the current body position state and the body position requirements in the candidate control mode set, and generating an adaptive control mode based on the matching screening result; Step 1034: Determine a target control mode based on the adaptive control mode and the preference characteristics of the user's historical operation records.

[0038] Step 1034 may specifically include the following steps: Preference data including assist speed, angle adjustment and pause interval are extracted from the user's historical operation records; the preference data is converted into a control parameter adjustment vector; the basic parameters of the adaptive control mode are combined with the control parameter adjustment vector; and a target control mode that meets the user's personalized needs is generated based on the combined operation result.

[0039] In the above scheme, dynamic mode mapping refers to the process of matching and generating a control strategy appropriate to the current situation from a pre-stored lifting assistance mode library based on the scenario type and body position determined by the joint recognition results. The target control mode is the finalized set of specific control instructions used to drive the lifting assistance device to perform body position transitions. The pre-stored lifting assistance mode library contains standardized control mode templates for different scenarios (e.g., bed, wheelchair, chair) and body positions (e.g., lying, sitting, standing). The candidate control mode set is a set of potentially applicable control modes initially screened through scenario classification and matching. The adapted control mode is a control mode that is further selected from the candidate set based on body position requirements and is more closely aligned with the current body position. The user's preference characteristics for lifting assistance speed, angle adjustment, and pause interval reflect the user's personalized usage habits for parameters such as lifting assistance speed, angle adjustment, and pause interval. Lifting assistance speed refers to the user's preferred range of lifting speeds in historical operations; angle adjustment refers to the user's preferred adjustment preferences for back support, leg lift, and other angles; and pause interval refers to the preferred length of pauses during body position transitions. The control parameter adjustment vector is a set of parameter adjustment instructions formed by quantizing these preference data. The basic parameters are the standard control parameters preset in the adaptive control mode.

[0040] In this solution, first, step 1031 separates the current scene type (e.g., wheelchair scene) and the target person's current body position (e.g., transitioning from sitting to standing) from the joint recognition conclusion. Next, step 1032 matches the current scene type with the scene classifications in a pre-stored library of assist-to-rise patterns (e.g., matching a wheelchair scene with wheelchair-related scene patterns in the library), screening all potentially applicable patterns to form a set of candidate control patterns. Next, step 1033 matches the current body position with the body position requirements of each pattern in the set of candidate control patterns (e.g., matching a sitting-to-standing transition state with the body position requirements in the candidate patterns). Unmatched patterns are eliminated to generate an adaptive control pattern. Finally, step 1034 extracts preference data for assist-to-rise speed, angle adjustment, and pause interval from the user's historical operation records. This preference data is converted into a control parameter adjustment vector (e.g., quantizing the preference data into a speed increase coefficient, an angle adjustment coefficient, etc.). The basic parameters of the adaptive control pattern are combined with the control parameter adjustment vector (e.g., multiplying the basic speed parameter by the speed adjustment coefficient). Based on the calculation results, a target control pattern that meets the user's personalized needs is generated.

[0041] Continuing with the previous solution, in the lifting assistance device application scenario at rehabilitation center A, the system analyzes the joint recognition results to determine that the current scenario type is a wheelchair scenario and the current body position is transitioning from sitting to standing. The system matches the wheelchair scenario with the scenario classifications in the pre-stored lifting assistance mode library, selecting all control modes applicable to wheelchair scenarios to form a candidate control mode set. The sitting-to-standing transition state is then matched with the body position requirements of each mode in the candidate set to select an adaptive control mode designed specifically for sit-to-stand applications in wheelchair scenarios. The system then extracts user B's historical operation data, identifying preferences for faster lifting speed, smaller back angle adjustment, and shorter pauses. This data is converted into a control parameter adjustment vector (e.g., a speed coefficient of 1.2, an angle coefficient of 0.9, and a pause time of 0.5 seconds). This vector is combined with the basic parameters of the adaptive control mode to generate a target control mode that meets user B's personalized needs.

[0042] This solution achieves a precise transition from standardized control to personalized control through dynamic mode mapping, ensures the basic applicability of the control mode through dual matching of scene and body position, and further refines the control parameters by introducing user historical preference data, so that the generated target control mode not only meets the current environmental requirements but also meets the user's personalized needs, significantly improving the adaptability and user experience of the assistance process.

[0043] Step 104: synthesize power instructions using the target control mode to generate a coordinated control signal for driving the assisting device to perform body position conversion.

[0044] Optionally, step 104 may specifically include the following steps: Step 1041, parsing the action sequence parameters of each power execution unit from the target control mode; Step 1042, generating a basic driving instruction set according to the action sequence parameters; Step 1043 , converting the basic driving instruction set into multi-execution unit coordinated instructions with time sequence association through a motion coordination algorithm; Step 1044: adjusting the multi-execution unit coordination instruction in real time according to the current state feedback of the device to obtain an adjusted multi-execution unit coordination instruction; Step 1044 may specifically include the following steps: The operating parameters and load parameters of each power actuator in the lifting assist device are obtained in real time through the status monitoring module on the lifting assist device; the operating parameters and the load parameters are compared with the expected parameters in the multi-execution unit coordination instruction to obtain a difference comparison result; the parameter adjustment amount of each power actuator is determined according to the difference comparison result; the parameter adjustment amount is applied to the multi-execution unit coordination instruction to generate an adjusted multi-execution unit coordination instruction.

[0045] Step 1045 : Generate the coordinated control signal including speed control, angle control, and force control according to the adjusted multi-execution unit coordinated instruction.

[0046] In the above scheme, power command synthesis refers to the process of generating specific drive commands based on the target control mode. The coordinated control signal is the final output, a set of control commands used to coordinate multiple actuators to complete body position changes. Each power actuator refers to the independent component (such as a motor or hydraulic cylinder) responsible for generating the assistive force in the lifting device. The motion sequence parameters describe the sequence, amplitude, and timing requirements of the movements required of each actuator. The basic drive command set is a preliminary set of control commands converted from the motion sequence parameters. The motion coordination algorithm is a processing logic used to convert basic commands into commands for the coordinated coordination of multiple actuators. Multi-actor coordinated commands are a set of control commands with precise timing relationships, generated after processing by the motion coordination algorithm. The adjusted multi-actor coordinated commands are the final commands after the coordinated commands are modified based on real-time status feedback. The state monitoring module is a sensing unit used to collect the operating status of the equipment. The operating parameters and load parameters of each power actuator reflect the actual motion state and the force / torque data experienced by the actuator, respectively. The expected parameters are the ideal operating values ​​preset in the collaborative instructions. The difference comparison results are the deviation analysis results between the actual parameters and the expected values. The parameter adjustment amount is the numerical amount that needs to be corrected calculated based on the difference.

[0047] In this scheme, the motion sequence parameters of each actuator are first extracted from the target control pattern at 1041. These parameters specify the motion sequence, travel range, and timing requirements of each actuator. Secondly, at 1042, the motion sequence parameters are converted into a specific basic drive instruction set. This conversion process transforms the abstract motion parameters into electrical signals or digital commands that directly drive the actuators. Next, at 1043, the basic drive instruction set is processed using a motion coordination algorithm. By establishing a spatiotemporal relationship model between actuators, the algorithm integrates independent instructions into multi-actuator coordinated instructions with precise timing coordination, ensuring synchronized and conflict-free motion. Then, at 1044, the state monitoring module collects the operating parameters (e.g., speed, position) and load parameters (e.g., pressure, torque) of each actuator in real time. These actual parameters are compared with the expected parameters in the multi-actuator coordinated instructions to obtain a difference comparison result. Based on the difference results, the required parameter adjustments for each actuator are calculated and applied to the coordinated instructions to generate the adjusted multi-actuator coordinated instructions. Finally, 1045 generates a collaborative control signal including speed control (adjusting movement speed), angle control (adjusting joint angle) and force control (adjusting output force / torque) according to the adjusted multi-execution unit collaborative instruction. This signal can directly drive the assistive device to perform posture conversion.

[0048] Continuing with the specific implementation of the previous solution, in the lifting assistance device application scenario at Rehabilitation Center A, the system extracts the motion sequence parameters (including extension angle, movement speed, and force requirements) for the back support unit and leg lifting unit from the target control model. These parameters are converted into a basic set of drive instructions to control motor speed and stroke. Through a motion coordination algorithm, multi-executor unit coordinated instructions are generated to ensure synchronization of back and leg movements (for example, when the back is raised 30 degrees, the legs are simultaneously raised 15 degrees). The status monitoring module detects in real time that the actual pressure value of the back support unit is lower than the expected value and the movement speed of the leg unit is higher than expected. The system calculates the parameter adjustments required to increase the back output force and reduce the leg speed. After applying these adjustments, the adjusted multi-executor unit coordinated instructions are generated, ultimately outputting a coordinated control signal with appropriate speed, angle, and force control, enabling the device to smoothly complete the transition from sitting to standing.

[0049] This solution transforms abstract control patterns into precise and executable drive signals through power command synthesis and real-time adjustment mechanisms. It ensures the synchronization and coordination of multiple execution units through motion coordination algorithms and overcomes the uncertainty and individual differences in actual operation through state feedback adjustment. The resulting collaborative control signal combines multiple control dimensions of speed, angle, and force, significantly improving the smoothness, safety, and adaptability of the body position transition process.

[0050] Figure 2This application provides a structural diagram of a control system for elderly people with stroke to help them get up based on multi-scene posture conversion, such as Figure 2 As shown, the system includes: A control module 21 is used to control multiple sensors pre-arranged on the contact surface of the lifting device of the target person to perform synchronous sensing to obtain a fusion sensing result composed of body pressure distribution data and joint movement data; A coupling analysis module 22 is configured to perform multi-feature coupling analysis based on the fusion perception results to generate a joint recognition conclusion including body position state and scene type; A pattern mapping module 23 is configured to perform dynamic pattern mapping based on the joint recognition conclusion and output a target control pattern that matches the current scene type and body position; The instruction synthesis module 24 is used to synthesize power instructions using the target control mode to generate a coordinated control signal for driving the assisting device to perform body position conversion.

[0051] Figure 2 The above-mentioned control system for assisting the elderly with stroke to stand up based on multi-scene posture conversion can be implemented Figure 1 The implementation principle and technical effects of the multi-scenario body position conversion-based control method for assisting elderly people with stroke to get up described in the illustrated embodiment will not be elaborated on here. The specific manner in which each module and unit performs operations in the multi-scenario body position conversion-based control system for assisting elderly people with stroke to get up in the above embodiment has been described in detail in the embodiments of the method and will not be elaborated on here.

[0052] In one possible design, Figure 2 The embodiment shown is a control system for assisting elderly people with stroke to stand up based on multi-scenario body position conversion, which can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32; The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0053] The processing component 32 is used for the above Figure 1 The embodiment provides a method for controlling the assistance of elderly people with stroke based on multi-scenario body position conversion.

[0054] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above method.

[0055] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile memory device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0056] Of course, a computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0057] The input / output interface provides an interface between the processing component and the peripheral interface module, which can be an output device, an input device, etc.

[0058] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0059] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0060] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The embodiment shown is a method for controlling the assistance of elderly people with stroke based on multi-scenario body position conversion.

[0061] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0062] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0063] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0064] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for assisting elderly people with stroke to stand up based on multi-scenario body position conversion, characterized in that: include: Control multiple sensors pre-arranged on the contact surface of the target person's lifting device to perform synchronous sensing to obtain a fusion sensing result consisting of body pressure distribution data and joint motion data; Perform multi-feature coupling analysis based on the fusion perception results to generate a joint recognition conclusion including body position state and scene type; Perform dynamic mode mapping based on the joint recognition conclusion and output a target control mode that matches the current scene type and body position; The target control mode is used to synthesize power instructions to generate a coordinated control signal for driving the auxiliary lifting device to perform body position conversion.

2. The method according to claim 1, characterized in that Control multiple sensors pre-arranged on the contact surface of the target person's assistive device to perform synchronous perception to obtain a fusion perception result consisting of body pressure distribution data and joint motion data, including: The original data of pressure distribution is collected through the pressure sensing array evenly distributed on the supporting surface of the lifting equipment; The raw data of joint motion is collected through motion sensing units fixed on the joints of the target person's limbs; Converting the pressure distribution raw data into continuous trajectory information reflecting the displacement of the pressure center; Converting the raw joint motion data into sequence information describing changes in joint flexion and extension angles; The continuous trajectory information and the change sequence information are integrated in a time-series association manner to obtain a fusion perception result representing the user's body posture characteristics.

3. The method according to claim 1, characterized in that Based on the fusion perception results, a multi-feature coupling analysis is performed to generate a joint recognition conclusion including body position and scene type, including: extracting pressure distribution features and motion pattern features from the fused perception results; Matching the pressure distribution characteristics with a predefined pressure distribution pattern to obtain a preliminary body position determination result; Matching the movement pattern feature with a predefined movement pattern sequence to obtain an auxiliary body position judgment result; Determining a final body position state based on a combination of the preliminary body position determination result and the auxiliary body position determination result; Based on the contact characteristics between the final body position and the device support structure of the lifting assist device, identifying the current scene type of the target person; The final body position state and the current scene type of the target person are combined to form a joint recognition conclusion.

4. The method according to claim 1, wherein Dynamic mode mapping is performed based on the joint recognition conclusion to output a target control mode that matches the current scene type and body position, including: Analyzing the current scene type and the current body position of the target person from the joint recognition conclusion; Matching the current scene type with scene classifications in a pre-stored assistance mode library to determine a set of candidate control modes; Performing matching screening based on the current body position state and the body position requirements in the candidate control mode set, and generating an adaptive control mode based on the matching screening result; A target control mode is determined based on the adaptation control mode and the preference characteristics of the user's historical operation records.

5. The method according to claim 4, characterized in that Determining a target control mode based on the adaptation control mode and the preference characteristics of the user's historical operation records includes: Extracting preference data including assist speed, angle adjustment, and pause interval from the user's historical operation records; converting the preference data into a control parameter adjustment vector; Performing a combined operation on the basic parameters of the adaptive control mode and the control parameter adjustment vector; Generate a target control mode that meets the user's personalized needs based on the combined operation results.

6. The method according to claim 1, characterized in that The target control mode is used to synthesize power instructions to generate a coordinated control signal for driving the assisting device to perform body position conversion, including: parsing the action sequence parameters of each power execution unit from the target control mode; Generate a basic driving instruction set according to the action sequence parameters; Converting the basic drive instruction set into multi-execution unit cooperative instructions with time sequence association through a motion coordination algorithm; Adjusting the multi-execution unit coordination instruction in real time according to the current state feedback of the device to obtain an adjusted multi-execution unit coordination instruction; According to the adjusted multi-execution unit coordination instruction, the coordination control signal including speed control, angle control and force control is generated.

7. The method according to claim 6, characterized in that The multi-execution unit coordination instruction is adjusted in real time according to the current state feedback of the device to obtain the adjusted multi-execution unit coordination instruction, including: The operating parameters and load parameters of each power actuator in the lifting device are obtained in real time through the status monitoring module on the lifting device; Comparing the operating parameters and the load parameters with expected parameters in the multi-execution unit coordination instruction to obtain a difference comparison result; Determine the parameter adjustment amount of each power actuator according to the difference comparison result; The parameter adjustment amount is applied to the multi-execution unit coordinated instruction to generate an adjusted multi-execution unit coordinated instruction.

8. A multi-scenario body position conversion-based control system for elderly people with stroke, characterized by: include: A control module is used to control multiple sensors pre-arranged on the contact surface of the target person's lifting device to perform synchronous sensing to obtain a fusion sensing result composed of body pressure distribution data and joint movement data; A coupling analysis module, configured to perform multi-feature coupling analysis based on the fusion perception results to generate a joint recognition conclusion including body position state and scene type; A pattern mapping module is used to perform dynamic pattern mapping based on the joint recognition conclusion and output a target control pattern that matches the current scene type and body position; The instruction synthesis module is used to use the target control mode to synthesize power instructions and generate a coordinated control signal for driving the auxiliary lifting device to perform posture conversion.

9. A computing device, characterized in that It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a control method for assisting elderly people with stroke to get up based on multi-scenario body posture conversion as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that A computer program is stored, and when the computer program is executed by a computer, it implements a method for assisting the elderly with stroke to stand up based on multi-scenario body posture conversion as described in any one of claims 1 to 7.

Images