34 results about "Falling risk" patented technology

The invention discloses an old people falling risk assessment and dynamic protection intervention system and method, and relates to the technical field of computer vision, and the system comprises a hardware composition module, a software and algorithm module, an intervention mechanism module, a system integration and optimization module, and an application scene module. The hardware composition module is used for collecting motion postures, gaits and environment data of old people in real time through a multi-mode sensor, hardware support is provided for risk assessment and protection, deep fusion of vision, inertia and environment data is achieved through an attention mechanism, spatial-temporal features are rapidly extracted in combination with a lightweight CNN-LSTM network, and the accuracy of risk assessment and protection is improved. And then the dynamic relationship between the mass center and the supporting surface is accurately calculated based on a biomechanical model, so that the real-time performance of attitude analysis and the accuracy of fall risk assessment are effectively improved, the prediction accuracy of the system on the fall risk of the old people is greatly improved and the false alarm rate is reduced while the consumption of calculation resources is reduced, and a reliable basis is provided for a hierarchical protection strategy.

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.

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 invention provides a detection method and system for preventing wall falling, a medium and a product, which can comprehensively consider the difference between the personnel activity flow and the environmental interference factor and reasonably determine the falling detection period of a building wall. According to the method, the falling risk levels of the walls at different positions are divided according to the personnel activity flow data of the surrounding area of the building so as to express the probability that the walls fall off to cause danger to personnel; determining a first detection period of the wall body at different positions according to the falling risk level; adjusting the first detection period according to the historical environment interference data to obtain a final detection period; and based on the final detection period, performing falling risk detection on the walls at different positions. By dynamically adjusting the detection period, the method can focus on high-risk positions, optimize detection resource allocation, improve detection accuracy and efficiency, effectively reduce potential safety hazards, and realize scientific prevention and management of falling of the building wall.

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.

Described herein is the design and implementation of an instrumented user device to produce quantitative metrics of patient fall risk. In some embodiments, a regression algorithm is used to estimate postural sway velocity, which is an effective predictor of fall risk. The instrumented user device enables continuous patient monitoring outside of the clinic and could provide a long-term, quantitative measure of fall risk.

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 invention provides an intelligent early warning and protection method and system for falling of an inpatient based on multi-modal data fusion. According to the method, individual risk data, behavior posture data and equipment state data of an inpatient are collected, a tumble risk index of the patient is calculated from the three aspects of potential risk, behavior risk and environmental risk by using a tumble risk prediction model, the tumble risk level of the patient is comprehensively evaluated, and then corresponding protection measures are taken. Specifically, each risk factor is quantified through a weight coefficient and a risk mapping function, and finally, an S-type normalization function is utilized to obtain a comprehensive risk index, so that accurate and personalized early warning is realized. The system comprises a sensing layer, a data processing layer, an intelligent analysis layer and an intervention execution layer, and can realize full-process automation and intellectualization. According to the invention, the problems of inaccurate evaluation, incapability of personalized early warning, lack of active intervention and the like in the prior art are effectively solved, and the occurrence rate of tumble of the inpatient is remarkably reduced.

This invention discloses an intelligent fall monitoring device, belonging to the field of fall monitoring technology, aiming to solve the problem of accuracy in fall monitoring and prediction for the elderly. It employs a collaborative artificial intelligence model architecture, integrating two different-dimensional artificial intelligence models for risk assessment. Model AI1, based on fuzzy logic, classifies fall risk levels into five levels: normal, low, medium, high, and emergency by real-time monitoring of vital signs such as heart rate, blood pressure, and blood oxygen saturation. Model AI2, based on deep belief networks, predicts risk by analyzing daily living activity patterns such as sitting, standing, walking, running, and jumping. The prediction results of the two models are input into a meta-model for comprehensive decision-making, generating the final low, medium, and high risk level prediction. For real-time fall monitoring, this invention proposes a hybrid monitoring algorithm, combining rule-based triggering based on acceleration and posture angle thresholds with AI fine-grained classification to achieve low latency and high accuracy.

The embodiment of the invention provides a quantifiable fall risk determination method, electronic equipment, a storage medium and a product, and relates to the technical field of data processing, and the method comprises the steps: obtaining a preliminary screening result of a fall risk of a target object, and obtaining a body function evaluation parameter, collected by timing equipment, of the target object; based on a preset quantitative scoring rule, calculating a body function scoring result of the target object; obtaining maximum angle range data, limb function quantitative data and gravity center displacement quantitative data of a specific body part of the target object in a preset motion test action; based on a preset weight coefficient and a quantitative fusion model, obtaining a quantifiable fall risk value of the target object; and determining the fall risk level of the target object according to a preset risk level division rule and the quantifiable fall risk value of the target object. The embodiment of the invention is used for providing a technical scheme capable of observably and accurately quantifying the falling risk of the old people.

The application discloses an old people fall risk assessment and dynamic protection intervention system and method, relates to the technical field of computer vision, and comprises a hardware component module, a software and algorithm module, an intervention mechanism module, a system integration and optimization module and an application scenario module.The hardware component module is used for collecting the motion posture, gait and environment data of old people in real time through a multi-modal sensor, and providing hardware support for risk assessment and protection.The application realizes the deep fusion of visual, inertial and environment data through an attention mechanism, combines a light-weight CNN-LSTM network to quickly extract space-time features, and then accurately calculates the dynamic relationship between the center of mass and the support surface based on a biomechanical model, thereby effectively improving the real-time performance of posture analysis and the accuracy of fall risk assessment, reducing the consumption of computing resources, greatly improving the prediction accuracy of the system for the fall risk of old people, reducing the false alarm rate, and providing a reliable basis for a graded protection strategy.

The invention discloses a community old people falling risk identification and intervention method based on machine learning, and relates to the technical field of old people falling risk identification, and the method comprises the steps: collecting the social economy, health condition, perceived environment and falling information data of old people by a system through offline questionnaire survey, and carrying out the data processing and statistics; based on the processed data, taking the tumble information data as a dependent variable, and utilizing a machine learning algorithm to build a tumble risk identification model; explaining the tumble risk identification model through an SHAP method to obtain a risk factor identification result; and based on a risk factor identification result, formulating a targeted anti-falling intervention measure for a corresponding community. Therefore, the method for identifying and intervening the falling risk of the old people in the community based on the machine learning is beneficial to finding the nonlinear relationship and the threshold value between the risk factor and the falling, so that different communities output targeted anti-falling measures for the old people.

The present disclosure provides a video game-based fall risk assessment system (100) designed for individuals (120) The system comprises sensor-equipped insoles (102) embedded in gaming slippers, featuring pressure sensors to monitor plantar foot pressure at key locations. An electronic control unit (104) processes this data and a video gaming application on a smart device (106) uses real-time pressure data to facilitate gameplay, evaluating skills relevant to fall prevention, such as balance and reaction time. A server (108) receives gameplay data, extract specific performance parameters (including reaction time and success rate) using a machine learning model (116), and analyze these parameters to assess the individual's balance and stability. The machine learning model (116) evaluates fall risk based on seated or a combination of seated / standing data, employing statistical analysis techniques. Finally, the system classifies individuals into "no / low risk of falls" or "high risk of falls" categories, considering posture-specific risks for accurate fall risk assessment.

The invention relates to the technical field of data prediction, in particular to a tumble risk detection method based on multi-modal health data. For the feature data of the user, tumble risk prediction is carried out through an XGboost method, and a first tumble risk probability corresponding to the current moment is obtained; for the feature data of the user, the prediction accuracy of the large model is improved through an SFT fine tuning mode, and a second fall risk probability corresponding to the current moment is obtained; fusing the first tumble risk probability and the second tumble risk probability to obtain a comprehensive tumble risk probability; and taking the comprehensive fall risk probability as a prior probability in the Bayesian theorem, and obtaining a fall prediction probability through the Bayesian theorem. According to the method, multi-modal fusion and dynamic Bayesian updating are realized, the sign time sequence and the static health information are subjected to fusion analysis for the first time, the model robustness is improved, individualized risk tracking is realized, and the method adapts to health changes.

The application discloses an intelligent shoe capable of identifying falling risk of ascending and descending steps and an identification method, and the method comprises the following steps: calculating a step force risk assessment value of ascending and descending steps according to force information of a force foot when ascending and descending steps; calculating a step emptying risk assessment value of ascending and descending steps according to emptying information of an empty foot when ascending and descending steps; calculating a step alternation risk assessment value of ascending and descending steps according to switching information of the force foot and the empty foot when ascending and descending steps; and calculating a risk assessment value of ascending and descending steps according to the step force risk assessment value of ascending and descending steps and / or the step emptying risk assessment value of ascending and descending steps and / or the step alternation risk assessment value of ascending and descending steps, and judging whether there is falling risk when ascending and descending steps according to the risk assessment value. The application solves the problem of how to identify falling hazards caused by deviation of a force foot and an empty foot when ascending and descending steps, thereby effectively reminding personnel to avoid falling.

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 invention discloses a working well platform personnel falling hidden danger early warning method, system and equipment, and relates to the technical field of falling risk monitoring. The method comprises the following steps: acquiring and preprocessing personnel-edge dynamic data, constraint effectiveness data and protection environment and process data, and respectively calculating an edge exposure index, a constraint effectiveness index and a protection environment and process index; dynamic weighted mapping is carried out based on the indexes to obtain a continuous risk score, a scene triggering threshold is combined to obtain a falling risk score, and the scene triggering threshold is deduced based on human kinematics and a falling protector braking mechanism; according to the falling risk score, graded early warning and linkage disposal are executed, prompt / alarm / emergency stop is triggered, and an event log is recorded. The method is used for solving the problems that the existing falling risk assessment is difficult to quantify the multi-source risk cumulative effect, and the response to typical high-risk scenes such as untied and hung, falling protector danger triggering and protection deficiency is insufficient.

The invention discloses an old people falling risk assessment method and system based on human body posture estimation, relates to the technical field of computers, and solves the technical problem that old people falling risk assessment according to gait data is not accurate enough. And calculating and processing the gait features in the video frame, and obtaining an old people falling risk assessment result according to the gait features. No professional equipment or sensor wearing is needed, and the elderly can complete video shooting and risk assessment autonomously to adapt to family scenes. The elderly and family members have an opportunity to take corresponding prevention measures in advance, and serious consequences caused by falling down are avoided to the greatest extent; and the falling risk of the old people can be accurately classified and evaluated.

A tipping risk detecting device (100) includes a first-attitude-angle information acquirer (101), second-attitude-angle calculator (102), attitude variation calculator (103), and tipping risk detector (104). The first-attitude-angle information acquirer (101) acquires first-attitude-angle information on a first attitude angle of a probe (1) in the inertial system. The second-attitude-angle calculator (102) calculates a second attitude angle of the probe (1) relative to the gravitational-acceleration direction of the astronomical object, based on the attitude-angle information, gravitational-acceleration direction relative to the inertial system, and probe's (1) shape information. The attitude variation calculator (103) calculates an attitude variation of the probe (1), based on the second attitude angles at the current time and preceding start time. The tipping risk detector (104) detects risk of the probe (1) tipping during its landing on the astronomical object, based on the attitude variation and positional relationship of a landed leg's (20) tip and the probe's (1) gravity center.

A computer-implemented method for assessing a fall risk of a user is provided. The computer-implemented method includes obtaining data indicative of the user engaging in a fall risk activity. The computer-implemented method includes adjusting a fall detection threshold of a wearable computing device worn by the user based, at least in part, on the data indicative of the user engaging in the fall risk activity. The method includes providing a notification indicative of the user being at risk of falling due, at least in part, to the user engaging in the fall risk activity.

The invention relates to the technical field of house outer wall facing layer potential safety hazard detection, in particular to a detection method for evaluating the falling risk of an outer wall facing layer. The method comprises the following steps: a modeling step, an acquisition step, a preliminary acquisition step, a preliminary judgment step, a hollowing number acquisition step, a preliminary judgment step, a risk value calculation step, a risk judgment step, an alarm step and a processing suggestion step. The method has the effect of improving the accuracy of outer wall facing layer falling risk detection.

A virtual system of fall prevention and home safety and optionally hospital discharge, comprising an application to implement a method comprising obtaining data on a resident of the resident's home environment and obtaining data on the resident's health;analyzing said data with an algorithm and generating a Personalized Fall Risk Index (PFRI) and an Environmental Fall Risk Index (EFRI), thereby allowing a clinician and / or an artificial intelligence (“AI”) system to assess the resident's fall risk at the home environment and to generate a list of personalized recommendations;suggesting products to said user and / or said resident, connecting said user and / or resident to local contractors, installers and other professionals, and / or connect the user and / or resident to source of grant funding. The PFRI is generated through applied coefficients to predictor variables. The EFRI is derived first as unbound score by averaging three individual scores: weighted average response score, room score, and occupancy score.

The invention discloses an old people falling risk assessment system based on big data. The old people falling risk assessment system comprises a data acquisition module, a falling risk multi-dimensional feature screening module, an old people falling risk assessment model building module and an old people falling risk intelligent assessment module. The invention relates to the technical field of health data processing, in particular to an old people falling risk assessment system based on big data, innovatively introduces a norm sparse constraint feature screening objective function, and proposes a weighted divergence matrix reconstruction strategy based on a risk level weighted mean value. By combining a two-dimensional dynamic robust weight updating mechanism of a sample weight and a risk level pair weight, the stability and the reliability of a feature screening result are improved, redundant features are reduced, an improved clustering algorithm based on double-space collaborative mapping, a self-adaptive hyperbolic distance and a self-adaptive truncation distance is provided, and the clustering algorithm is suitable for being used in a large scale. The robustness and stability of the clustering algorithm are enhanced, and the accuracy of the output result of the old people falling risk assessment model is improved.

The invention relates to the technical field of electric power system early warning, and particularly discloses an electric power high-altitude operation falling risk dynamic assessment and early warning method and system, and the method comprises the steps: obtaining real-time personnel state data, equipment state data, environment data and operation flow data of a plurality of operation links in an electric power high-altitude operation process; extracting a risk factor corresponding to each operation link according to the real-time personnel state data and the equipment state data, and obtaining an initial risk feature vector of each operation link according to the risk factors; and dynamically correcting the initial risk feature vector according to the environment data and the operation process data to obtain a calibration risk feature vector corresponding to each operation link. Through multi-source real-time data acquisition (personnel state, equipment state, environment and process data), the problems of single dimension and poor timeliness of traditional assessment data are solved, and a comprehensive and dynamic data basis is provided for risk assessment.

SYSTEM AND METHOD FOR PREDICTING AN INDIVIDUAL'S FALL The invention relates to a system and method for predicting an individual's fall, comprising: a casing (10) worn by an individual (8) in which is housed a plurality of sensors for acquiring measurements representative of the individual's posture and / or movements; a processing unit (100) for the measurements provided by said plurality of sensors and comprising: a module (110) for determining a profile score, based on data representative of the individual's specific characteristics; a module (120) for calculating motor cursors, based on the measurements provided by said plurality of sensors, and representative of the individual's activity over a predetermined time interval; a module (130) for calculating a fall risk score, based on said motor cursors and said profile score;a module (140) for determining a fall risk, a function of a variation of said fall risk score beyond a predetermined threshold over a predetermined time interval. Figure for the abstract: figure 1;

This invention discloses a teaching method for intelligent simulation analysis of fall risk in elderly hypertensive patients based on machine learning, belonging to the field of fall risk simulation analysis technology. It includes: acquiring patients' frailty data to obtain a frailty dataset; classifying patients into at least three risk levels based on the frailty dataset, with each risk level corresponding to a different time folding coefficient, thus obtaining a frailty level classification item. This invention establishes a triangular assessment system of age, comorbidities, and cognition, and dynamically compensates for the underestimation of elderly or multi-disease patients by traditional models through a frailty adjustment coefficient, thereby improving the accuracy of high-risk patient identification. Furthermore, through intelligent time window compression technology, the monitoring period is automatically scaled based on the frailty level, shifting the golden window for patient intervention earlier, increasing the monitoring frequency for severely frail individuals, and improving the high-risk event capture rate.

An embodiment of the present invention relates to a method and apparatus for managing patient fall risk using SPPB test results, wherein the method and apparatus can predict the patient's fall risk based on SPPB test results and manage the patient's fall risk factors accordingly.

The invention relates to the technical field of tumble risk prediction, and discloses a community elderly female tumble risk prediction model construction method and system, and the method comprises the steps: carrying out the construction of a tumble risk prediction model of a community elderly female based on the standard specific values of a plurality of original evaluation indexes corresponding to each community elderly female tester in combination with an LASSO regression method; determining a plurality of target evaluation indexes from all the original evaluation indexes; respectively training each preset model by using the standard specific values of the plurality of target evaluation indexes corresponding to the elderly female testers in each community and using a machine learning algorithm to obtain a plurality of fall risk prediction models; and determining an optimal tumble risk prediction model according to the specific value of each performance evaluation index of each tumble risk prediction model. The method can effectively solve the defects of a traditional fall assessment tool, can accurately predict the fall risk of the elderly women in the community, has high reliability and accuracy, and is convenient to quickly deploy and popularize in primary medical and community environments.