42 results about "Fall risk" patented technology

The invention provides an old people falling risk monitoring analysis method and system, and the method comprises the steps: collecting multi-source heterogeneous signals, such as plantar pressure distribution, attitude trajectory output by an inertial measurement unit, electroencephalogram attention concentration ratio, galvanic skin response and the like, carrying out data synchronization and spatial normalization processing through a unified timestamp, and carrying out data synchronization and spatial normalization processing; extracting gait gravity center tracks and physiological state features; the gait deviation degree is matched by constructing an individual behavior baseline library and a dynamic time warping algorithm, the cognitive load state is evaluated in combination with a lightweight LSTM network, physical instability and cognitive risks are subjected to multi-dimensional fusion, a falling risk score is output through a fuzzy logic engine, and the system can achieve graded early warning response and emergency positioning. According to the invention, the accuracy, adaptability and early warning efficiency of fall risk assessment are significantly improved.

The invention discloses an intelligent anti-falling risk management system based on artificial intelligence, and relates to the technical field of artificial intelligence, the intelligent anti-falling risk management system comprises a management center, and the management center is connected with a monitoring acquisition module, a transmission processing module, a body position analysis module and a multi-dimensional supervision module; constructing a resting virtual space for the bedridden old person, and performing position marking on the collected bedridden state data through the resting virtual space based on the intelligent anti-falling bed to obtain a continuous track of the bedridden old person; boundary distance statistics is carried out according to the continuous track of the bedridden patient, the boundary distance is converted into a real-time track fluctuation map, range division is carried out on the real-time track fluctuation map, the range proportion is counted, and a curve judgment range is obtained; carrying out simulation diagnosis through the static lying virtual space to obtain an abnormal identification state, and carrying out dynamic feedback adjustment on the bedridden old people according to the abnormal identification state based on the static lying virtual space to obtain an anti-falling intervention measure; the occurrence of falling-off accidents of old people is effectively reduced, the nursing efficiency is improved, and the burden of nursing personnel is relieved.

An environmental monitoring system includes at least one sensor module. The at least one sensor module includes a housing, a power receiving module, a communication module, and at least one sensor. The at least one sensor is configured to detect a presence an occupant in the environment. A control system is configured to receive the detected presence from the at least one sensor over a first period of time to determine a movement velocity of the patient, detect abnormalities of the movement velocity of the occupant over a second period of time, and generate a notification of irregular travel.

The invention discloses an anti-falling robot and an anti-falling method and equipment, relates to the field of intelligent robots, and is used for realizing cliff identification and falling protection in a full scene. Identifying a falling risk based on a detection result of the sensor module by at least detecting whether a cliff exists in a first preset range and a second preset range around the robot body; and controlling the motion state of the robot body based on the falling risk. According to the method, the cliff is synchronously detected through the near end and the far end, cliff identification and falling protection in a high-speed moving state and in a full scene where the cliff is initially located at the edge of the cliff or runs close to the edge are achieved at the same time, reliability and safety are high, system operation is smooth, and universality is high.

A fall risk determination device (40) is provided with: an acquisition unit (42a) that acquires a moving image showing a current person (1); an estimation unit (42b) that estimates, on the basis of the moving image, the skeleton of the pedestrian (1) reflected in the moving image; a classification unit (42c) that, on the basis of the skeleton, classifies a period during which the pedestrian (1) walks in the moving image into a plurality of periods; an extraction unit (42d) that extracts one or more first feature quantities relating to the walking of the pedestrian (1) on the basis of the skeleton for each of the plurality of periods; a determination unit (42e) that determines the risk of falling of the pedestrian (1) on the basis of the one or more first feature quantities; and an output unit (42f) that outputs the determination result of the determination unit (42e).

The utility model relates to hoist device technical field, a container hoist is with anti -fall security device, including hoist frame, the side surface fixed mounting of hoist frame has rotary machine, the output fixed mounting of rotary machine has rotating wheel, the side surface fixed mounting of hoist frame has connecting seat, the side surface of connecting seat is equipped with first pulley, the side surface fixed mounting of adjusting steel cable has mobile ball, the side surface fixed mounting of mobile ball has protective steel cable, the side surface of mobile ball is slid and is provided with track assembly, beneficial effect is: through to hoist equipment and join bottom protection track assembly, utilize the movement change of mobile ball in track assembly different position, thereby will protective steel cable in the bottom of hoist's box and carry out the function of unfolding, provide additional support and locking protection for container, ensure the firmness and stability of the connection between the spreader and the box, effectively avoid the container falling risk caused by the connection loosening of hoist frame and the top of the box.

The invention relates to the technical field of image monitoring, in particular to an elderly patient behavior image monitoring and falling risk analysis system and method, and the method comprises the steps: a front-end collection module collects a time sequence image of an activity area of an elderly patient; the posture detection module analyzes and extracts three-dimensional posture information of the elderly patient based on a differential geometry theory, and comprises a key point detection unit, a manifold mapping unit and a constraint optimization unit; the gait analysis module processes attitude parameters through a parameter extraction unit, a time sequence track unit and a curvature analysis unit; the risk assessment module calculates a fall risk level based on the gait feature data; according to the invention, an APMK-HCW algorithm is innovatively applied to realize high-precision 3D attitude estimation under a monocular camera, geodesic curvature analysis is introduced to quantify gait stability, and a personalized baseline assessment and adaptive optimization mechanism is adopted to realize early precise early warning of the falling risk of the elderly patient.

The invention provides a multi-source data fusion-based old people falling risk dynamic assessment method and system, and belongs to the technical field of health monitoring and intelligent wearable equipment. The method comprises an activity area calibration step, a fall risk identification step, a data acquisition mode updating step and a risk early warning step. The method comprises the following steps of: classifying an activity area into a high-risk area, a medium-risk area and a low-risk area, and updating a multi-source monitoring data acquisition mode of the area when identifying that the old people pass through the areas with different risk levels; performing fall risk identification based on the multi-source monitoring data acquired by the updated data acquisition mode; and when a falling risk is identified, a risk early warning signal is sent out. The system is used for implementing the method. According to the technical scheme, the activity area can be dynamically calibrated, the risk level can be accurately divided, the data acquisition mode can be adjusted according to the risk level, and the pertinence and timeliness of multi-source data fusion assessment of the falling risk are improved.

The application discloses a fall early warning and anti-falling protection vest and a detection method thereof, relates to the technical field of protection vests, and provides the most suitable protection vest for personalized protection, realizes personalized protection and preventive measures, meanwhile, through means such as real-time monitoring, multi-dimensional evaluation, alarm prompt and preventive measures, the safety and comfort of patients are effectively improved, the burden of medical staff is reduced, the efficiency and quality of medical care are improved, the off-bed situation and posture change of the target medical patient are monitored in real time, the off-bed or unstable posture of the patient is found in time, and thus the risk of falling is reduced, the risk of falling is early warned, the medical staff can take corresponding preventive measures, for example, adjusting the posture of the patient, providing auxiliary equipment and the like, so that the risk of falling is effectively reduced, the safety of the patient is protected, and according to the off-bed danger level and the falling risk level obtained through analysis, an alarm prompt is timely sent to the medical staff.

The application discloses a fall-prevention monitoring method and system based on an intelligent bed, relates to the technical field of intelligent beds with behavior feature recognition, and through the construction of a three-dimensional space monitoring framework, the accurate division of bed body and surrounding space coordinate ranges, the real-time collection of human motion data by fusing multi-sensor technology, the dynamic tracking of the changes of the center of mass trajectory, the calculation of the center of mass horizontal deviation rate and the center of mass deviation direction vector, the deep analysis of the limb suspension proportion and the posture inclination angle, the determination of the trend of the increase of the limb suspension duration, and the further evaluation of the fall risk probability value. The application realizes the establishment of an accurate three-dimensional space monitoring range around the bed body by the combination of the dynamic trajectory analysis of the center of mass and the multi-level monitoring grid, and realizes the real-time calculation of the dynamic relationship change rate of the center of mass and the bed body coordinates, and realizes the early positioning of the fall occurrence space.

The present application relates to the technical field of electromyography, in particular to a multi-modal electromyography monitoring driven fall risk prediction method and system for the elderly. The method comprises the following steps: collecting electromyography sequence, comparing voltage changes to generate activity trajectory, calculating peak distribution based on the activity trajectory to generate discharge rhythm trajectory, extracting adjacent rhythm changes to generate change distribution record, comparing change position and time relationship to judge time continuity to generate change section record, and establishing association between change section record and gait cycle to generate risk prediction result. In the present application, dynamic trajectory is generated based on continuous sequence to extract microscopic rhythm characteristics, position adjacency relationship is verified during walking process to determine evolution continuity, continuous record is strictly compared with gait cycle to judge corresponding association, details of lower limb movement dynamic reflection are fully restored, defects of traditional truncation means covering lag phenomenon are effectively overcome, abnormal potential activity rules are accurately captured in complex scenes, and comprehensive reliability of risk prediction is effectively improved.

The application discloses a fall prevention method and device and a robot. The method comprises the following steps: in the process of following a target object, acquiring multi-modal data of a scene in which the target object is located; evaluating a risk parameter of the target object based on the multi-modal data; the risk parameter is used for reflecting a fall risk of the target object; generating a behavior strategy of the robot based on the risk parameter; and the behavior strategy is used for assisting the target object when the target object is about to fall.

This invention presents a YOLO-based intelligent method for identifying high-altitude fall hazards in building safety, comprising the following steps: S1: Using a drone to collect images of urban and rural buildings under natural lighting conditions; S2: Building a YOLOv12-ANS target detection model, training it using the high-altitude fall risk dataset from step S1, and validating the performance metrics of the improved model using a test set; S3: Using the trained target detection model to detect whether there are high-altitude fall hazards in the building images captured by the drone; assessing the severity through function quantification; S4: Transmitting the relevant information on the severity to personnel for timely handling of existing safety risks. This invention combines drone-collected building facade images to accurately identify potential fall hazard sources such as rusted components, overhanging objects, and areas of detached building decorations, achieving early risk location, classification, and warning, and promoting the transformation of building surface safety monitoring from "passive investigation" to "proactive prevention."

A fall prevention system provides intervention and distraction to attempt to prevent a “fall risk” patient from falling from bed while providing alerts to caregivers. The system provides verbal, visual and tactile interventions to create a distraction and time for a nurse or caregiver to intervene and prevent a fall.

The utility model discloses a low-pressure anti-falling control gas circuit for pneumatic lifting equipment, which relates to the application field of lifting or traction winch equipment and comprises a hand-operated direction valve, a start-stop module, a pressure setting valve, a pneumatic control valve and an automatic brake. The device is installed on equipment and has the advantages of being simple in structure, low in cost, sensitive in response to air pressure fluctuation, good in low-pressure locking performance and the like. When the main air inlet pressure is lower than the rated load required value of the lifting equipment, the operation of the equipment is limited; only when the main air inlet pressure meets the rated load requirement of equipment, normal operation can be carried out. Therefore, the risk of high-altitude falling caused by insufficient lifting force of the lifting equipment under high-altitude load is avoided, the requirement of the lifting operation equipment for safety is met to the maximum extent, and the applicability and safety of the equipment are improved.

The application relates to the field of robots, and discloses a robot anti-falling method, a robot and a readable storage medium. The robot anti-falling method can acquire the distance between a robot and a supporting surface detected by an anti-falling sensor, determine whether the distance meets a preset anti-falling condition, and when the distance meets the preset anti-falling condition, determine whether the robot is in a safe area where falling does not occur according to the environment, and send a stop motion instruction to the robot when the robot is not in the safe area. Therefore, the falling risk of the robot can be confirmed again when it is determined that the robot has a falling risk according to the distance data provided by the anti-falling sensor, the misjudgment of the falling risk in a specific scenario is avoided, and the operation efficiency of the robot is improved.

The present invention provides a fall risk indicator measuring device that can measure an index of the biological reflex response based on the sensing of changes in acceleration of the otolith organs of a subject, in relation to the risk of falling when the subject falls. [Solution] The fall risk index measuring device 1 comprises a ride section 10 on which a subject sits, a support device 20 that supports the ride section, a release device 22 that releases the support of the ride section by the support device and allows the ride section to fall freely, a handrail section 14 for the subject's fingers to grasp, a pressure sensor 15 that measures the pressure of the fingers, and a control unit 60. The control unit 60 comprises a first reaction measuring unit 61 that measures a first reaction time from the time of release by the release device to the time of reaching a first pressure, based on the finger pressure value measured by the pressure sensor.

The application discloses a fall risk classification method, medium and equipment based on daily walking foot pressure data, and belongs to the technical field of data classification and prediction. The method comprises the following steps: collecting foot pressure data in a target daily walking process; pre-processing and extracting features of the foot pressure data to obtain foot pressure feature data; taking the foot pressure feature data as a sample to be classified, and using a trained fuzzy classifier to obtain a fall risk classification result; and calculating the membership degree between samples to obtain the fall risk classification result for the foot pressure feature data. The application has low complexity, high execution efficiency, small required computing power, can be processed in real time on an edge terminal, and is more widely applied.

The invention relates to a positioning anti-falling method and anti-falling system based on multimode signal processing and wearable equipment. In order to solve the problems that in the prior art, multi-source signal noise influence is large, time sequence alignment occurs frequently, and judgment errors occur frequently, two-dimensional Gaussian kernel smoothing and normalization are conducted on plantar pressure array data, a pressure distribution matrix with continuous space is generated, then a pressure center track and motion manifold characteristics of the pressure center track are extracted, and a gait phase coordinate system is established. The method comprises the following steps: calculating the dominant phase and offset of each signal through nonlinear time-phase mapping in combination with acceleration, a gyroscope and a gravity center offset signal, completing multi-modal signal confidence scoring by using an offset penalty and stability weight mechanism, and finally realizing risk grade judgment and providing physical alarm by using a lightweight decision tree model. According to the method, the time sequence consistency and data robustness of different sensing source signals are improved, accurate and rapid early warning of the falling risk is achieved, meanwhile, the dynamic self-adaptive calibration capability is achieved, and the false alarm and leakage alarm probability is reduced.

The application belongs to the technical field of fall risk prediction, and relates to a fall risk prediction method for the elderly based on multiple signal features, comprising the following steps: collecting surface electromyography signals, inertial signals and plantar pressure signals of a human body in real time, and performing time-frequency analysis on the surface electromyography signals to obtain a time-frequency spectrum of the surface electromyography signals; extracting feature vectors of corresponding signals in the same time period according to the signals and the time-frequency spectrum; obtaining a feature matrix by weighted fusion of the feature vectors; and inputting the feature matrix into a long short-term memory network model for processing, and outputting a fall risk probability.The scheme of the application can accurately output a fall risk probability by fusing multiple signal features, and can realize early prediction and real-time alarm, thereby preventing the elderly from falling.

The present application relates to the field of Chinese wisdom pension and old-age care, and discloses a fall early warning method and system for old-age care, which comprises the following modules: an old person individualized baseline modeling and system initialization module, a multi-source synchronous data acquisition and local preprocessing module, a multi-dimensional fall risk feature extraction and quantification module, a two-stage cascaded fall risk grading and pre-judgment module, a graded early warning and multi-linkage joint intervention module, and an event review and model dynamic iteration optimization module; and comprises the following steps: S1, a system initialization and baseline modeling stage; S2, a multi-source data acquisition and preprocessing stage; S3, a multi-dimensional risk feature extraction and quantification stage; S4, a two-stage cascaded risk pre-judgment stage; S5, a graded early warning and joint intervention stage; and S6, an event review and model iteration stage; the present application realizes pre-fall risk pre-judgment and intervention, reserves sufficient risk avoidance time for the old people, and reduces the occurrence probability of fall injuries from the source.

The application relates to the field of nursing of the disabled and the elderly, in particular to a nursing bed anti-falling guardrail. The nursing bed anti-falling guardrail comprises two supporting rods, the two supporting rods are arranged on one side of a bed frame, the two supporting rods can be close to or far away from the bed frame, an angle steel is fixed on the bed frame, the two supporting rods are provided with insertion grooves I, one side of a flat plate can be placed on the angle steel, and the other side of the flat plate can be inserted into the two insertion grooves I; the flat plate is used for widening the nursing bed; the upper portions of the two supporting rods are fixed with hinged seats; the two hinged seats are hinged with connecting rods; the upper ends of the two connecting rods are respectively hinged with two ends of a main guardrail; and the main guardrail is lifted or folded through rotation of the two connecting rods. The bed surface outside can be widened, the patient activity area is increased, and the bed falling risk is reduced.

The application discloses a fall risk early assessment method based on multi-modal information fusion, which comprises the following steps: simultaneously collecting video data and sensor data of a person to be measured when walking; obtaining a first assessment result based on the video data; obtaining a second assessment result based on the sensor data; and obtaining a final assessment result by comprehensively integrating the first assessment result and the second assessment result. The fall risk early assessment method based on multi-modal information fusion utilizes multi-modal information in two ways, comprehensively assesses walking posture information of the person to be measured, and combines the advantages of both.

This invention discloses a computer vision-based method and system for fall detection and alarm in elderly Alzheimer's patients. To address the difficulty in accurately identifying patient instability and falls in the presence of assistive devices such as canes, walkers, and wall handrails, this invention employs video preprocessing and online camera parameter estimation, implicit 3D reconstruction of the human body and assistive devices, construction of a ternary hypergraph of the human-assistive device-ground relationship with risk-gated attention, inference of contact state and grip stability using a dwell state memory unit in a contact Transformer, calculation of stability index, risk rate, and time to instability based on a differentiable physics model, and setting an adaptive alarm threshold for tiered alarm output. This achieves real-time identification of patient instability and fall risk under conditions of carrying or using assistive devices, improving accuracy and reducing false alarms.

This utility model relates to the field of power transmission tower technology and discloses a power transmission tower with fall protection function, comprising: a concrete base, on which the main body of the power transmission tower is fixedly installed; a fall protection climbing mechanism, which is installed on the main body of the power transmission tower and is used for fall protection; and a climbing and de-icing mechanism, which is installed on the top of the concrete base. This utility model, through the design of the protective plate, can shield the user from falling vertically, avoiding the fatal fall risk caused by a hole below, thus increasing safety. The protective plate is rotatably connected to the central crossbar via a rotating assembly. During user movement, the protective plate can be rotated open for passage. The opening angle of the protective plate is less than 90 degrees, and it automatically closes after opening. The design of the rubber block can buffer the impact force when the protective plate closes.

This invention discloses a method, system, device, and medium for handling fall incidents of home service robots, belonging to the field of robot fall handling technology. The method includes: determining the intervention time window ratio based on the user's center of gravity predicted trajectory and the robot's positioning action time; calculating a fall risk score by integrating the user's center of gravity normal mechanical state, ground friction state, and gait deviation state; dynamically adjusting the weight of the path planning cost function based on the fall risk score and the intervention time window ratio; in response to the fall risk exceeding the warning threshold and the positioning conditions being met, controlling the robotic arm to switch to passive support mode to perform physical intervention; and after fall confirmation, determining the self-rescue ability level and injury severity level based on multimodal passive assessment and performing differentiated treatment. This invention, by incorporating the robot's intervention capability into the fall handling decision-making system, achieves a complete closed-loop handling process from risk prediction and physical intervention to post-fall triage treatment.

This invention provides a risk assessment-based fall prevention and management system for hospitalized patients, relating to the fields of smart healthcare and patient safety technology. It includes a multi-source data fusion module, which collects and processes diverse patient data to form a comprehensive dataset; the multi-source data fusion module includes an IoT sensor array; and a behavioral intent recognition module, which performs collaborative fusion processing on the IoT sensor array to form behavioral intent tags. This risk assessment-based fall prevention and management system for hospitalized patients, through multi-source data fusion and behavioral intent recognition modules, captures real-time changes in the patient's physiological and behavioral states, dynamically assesses fall risk, and forms an accurate dynamic risk profile of the patient. The fall prevention and management system for hospitalized patients overcomes the limitations of traditional static assessment methods, implements precise intervention for high-risk patients, and significantly reduces the probability of falls.

The present invention relates to a method and wearable device for monitoring and analyzing user movements to predict fall risk. The method involves retrieving motion data recorded by an Inertial Measurement Unit (IMU) and a pedometer, followed by processing the data once it exceeds a predefined threshold. A first trained machine learning (ML) model predicts the fall risk based on the processed data. A confidence score is determined from the fall prediction, and a second trained ML model analyzes successive data frames to confirm the fall if the score is above a threshold. If a fall is confirmed, a distress signal is transmitted. The wearable device comprises a processor and memory that stores program instructions to perform the method, including motion data retrieval, processing, fall prediction, confidence scoring, and fall confirmation, along with distress signal transmission. This invention enables timely fall detection and emergency response, improving user safety.

The application discloses a fall-preventing system for an exoskeleton robot, which comprises an exoskeleton robot body and further comprises a sensing unit, a multi-stage execution module, a magneto-rheological fluid active damper serving as an exoskeleton robot body adjusting joint, an inflation valve group for inflating air bags, and a central processing unit. The multi-stage execution module comprises an air bag unit composed of multiple air bags and is distributed outside the exoskeleton robot body. The neural network inference unit (NPU, such as Edge TPU) runs an ST-GCN risk prediction model. The NPU is connected with the MCU through a PCIe or high-speed USB interface, receives a fused feature vector, and returns P_fall. The central processing unit is used for feature extraction and fusion after data acquisition of the sensing unit, and then fall risk probability calculation is performed. It is specified that "updating adaptive parameters" refers to updating state parameters such as T_stride, phi and v_walk in the S_th(t) formula, and fine-tuning S0, A and B after long-term wearing of the user. The fall risk can be predicted in advance, and hierarchical active protection can be implemented.

The invention discloses a community power distribution control and elderly anti-falling linkage system and method based on the Internet of Things. The system comprises an elderly anti-falling monitoring subsystem (bracelet, 5G positioning and falling detection prediction), a community power distribution control subsystem (cloud side monitoring, cloud storage and AI power distribution processing) and a linkage control center (data interaction, strategy library and instruction issuing). The method comprises the steps of system initialization networking, drop resistance and power distribution data acquisition, fall detection and prediction, linkage triggering judgment, strategy matching generation, power distribution and rescue instruction execution, process monitoring recording, system reset and the like, and deep linkage of the two is achieved. According to the scheme, the splitting problem in the prior art is solved, the rescue response efficiency and safety are remarkably improved, the falling risk is reduced, resource utilization is optimized, and the method is suitable for aging community safety management.