Patient fall monitoring system based on behavioral feature recognition

Abstract

The present invention discloses a patient fall monitoring system based on behavioral feature recognition, which belongs to the field of fall monitoring technology and includes: a data acquisition module for collecting real-time patient behavior data; a data processing module for processing real-time patient behavior data and determining patient behavior feature data; an analysis and identification module for predicting and analyzing patient fall behavior and identifying risks, and determining patient fall risk identification results; an early warning and control module for formulating patient fall early warning and control plans, and performing early warning and control on patient fall behavior. The present invention solves the problem that the existing system cannot effectively monitor and identify patient fall behavior based on behavioral features, resulting in low patient safety and increased medical costs. The present invention can realize the identification and early warning of patient fall behavior. When it is identified that a patient is at risk of falling, an alarm is automatically issued and measures are taken to prevent the fall from occurring, which can improve the safety of the patient and reduce medical costs.

Description

Technical Field

[0001] The present invention relates to the technical field of fall monitoring, and in particular to a patient fall monitoring system based on behavioral feature recognition. Background Art

[0002] When patients fall, it not only causes physical harm to the patients, but may also lead to waste of medical resources and medical safety issues.

[0003] Chinese patent publication number CN113456059A discloses the use of radar to monitor a patient's body, including: one or more radar sensors can be used to monitor the patient in various environments; the radar sensor can be used to monitor the patient's movement, including movement on the bed and movement around the room, and can monitor the patient's position in the bed; however, this patent has the following drawbacks:

[0004] The existing system cannot effectively monitor and identify patients' falls based on behavioral characteristics, nor can it provide timely early warning and control of patients' falls. It cannot effectively prevent patients from falling, resulting in low patient safety and increased medical costs. Summary of the Invention

[0005] The purpose of the present invention is to provide a patient fall monitoring system based on behavioral feature recognition, which can realize the recognition and early warning of patient fall behavior. When it is identified that the patient is at risk of falling, an alarm is automatically issued and measures are taken to prevent the fall from occurring, which can improve the safety of the patient and reduce medical costs, solving the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The patient fall monitoring system based on behavioral feature recognition includes:

[0008] The data acquisition module is used to use sensors to collect the patient's movements, postures and gait conditions to determine the patient's real-time behavior data;

[0009] The data processing module is used to clean, convert and extract features of real-time patient behavior data to determine patient behavior feature data;

[0010] The analysis and identification module is used to predict and analyze the patient's fall behavior and identify risks, determine whether the patient has a fall risk, and determine the patient's fall risk identification results;

[0011] The early warning and control module is used to formulate patient fall early warning and control plans, conduct early warning and control of patient fall behaviors, and prevent falls from occurring.

[0012] Preferably, the data acquisition module includes:

[0013] A motion monitoring unit, used to collect patient motion data;

[0014] Real-time monitoring and collection of patient movements based on sensors to obtain patient movement data;

[0015] a posture monitoring unit, for collecting patient posture data;

[0016] Monitor and collect the patient's posture in real time based on sensors to obtain patient posture data;

[0017] a gait monitoring unit, used to collect patient gait data;

[0018] Monitor and collect the patient's gait in real time based on sensors to obtain the patient's gait data;

[0019] Among them, the real-time data of patient behavior is determined based on the patient motion data, patient posture data and patient gait data.

[0020] Preferably, the data processing module includes:

[0021] Data cleaning unit, used to clean real-time patient behavior data;

[0022] Obtain real-time data on patient behavior;

[0023] Conduct consistency checks on real-time patient behavior data;

[0024] According to the data consistency requirements, each parameter in the real-time patient behavior data is checked one by one to check whether there is inconsistent data in the real-time patient behavior data that is useless for patient fall monitoring, and the inconsistent data in the real-time patient behavior data is removed;

[0025] Check invalid and missing values in real-time patient behavior data;

[0026] According to the requirements of data validity and integrity, each parameter in the real-time patient behavior data is checked one by one to check whether there are invalid values and missing values in the real-time patient behavior data that are useless for patient fall monitoring. The invalid values and missing values in the real-time patient behavior data are removed to determine the real-time patient behavior data that is useful for patient fall monitoring.

[0027] Preferably, the data processing module further includes:

[0028] A data conversion unit, used to convert real-time patient behavior data;

[0029] Obtain real-time patient behavior data useful for fall monitoring;

[0030] Converting real-time patient behavior data useful for patient fall monitoring to unify the formats of real-time patient behavior data useful for patient fall monitoring;

[0031] Eliminate the dimensional differences between real-time patient behavior data that are useful for patient fall monitoring and determine standardized real-time patient behavior data;

[0032] A feature extraction unit, used to extract features from real-time patient behavior data;

[0033] Obtain standardized real-time data on patient behavior;

[0034] Extract features from standardized real-time patient behavior data;

[0035] Features that can reflect patient falls and are related to patient falls are extracted from standardized real-time patient behavior data to determine patient behavior feature data.

[0036] Preferably, the analysis and identification module includes:

[0037] Model training unit, used to train patient fall risk identification model;

[0038] Collect patient behavior history data based on patient fall monitoring needs based on behavioral feature identification;

[0039] Define the patient's behavioral history data, define the behavioral characteristics related to patient falls, classify the behavioral characteristics, and determine the training set and test set;

[0040] Select a machine learning framework suitable for patient fall risk identification based on behavioral signature recognition;

[0041] Based on the training set, the selected machine learning framework suitable for patient fall risk identification based on behavioral feature recognition is trained to determine the patient fall risk identification model based on behavioral feature recognition.

[0042] Preferably, the analysis and identification module further includes:

[0043] Testing and optimization unit, used to test and optimize the patient fall risk identification model;

[0044] Obtain a patient fall risk identification model based on behavioral feature recognition;

[0045] Based on the test set, the performance of the patient fall risk identification model based on behavioral feature recognition is tested to determine whether the patient fall risk identification model based on behavioral feature recognition can achieve the expected effect;

[0046] Determine the performance test results of the patient fall risk identification model;

[0047] According to the performance test results of the patient fall risk identification model, the patient fall risk identification model based on behavioral feature recognition was analyzed, and the parameters of the patient fall risk identification model based on behavioral feature recognition were adjusted and the structure was optimized. After repeated iterations, the optimal patient fall risk identification model was determined.

[0048] Preferably, the analysis and identification module further includes:

[0049] Analysis and identification unit, used to perform risk analysis and identification of patient falling behavior;

[0050] Obtain the optimal patient fall risk identification model;

[0051] Deploy the optimal patient fall risk identification model in an actual patient fall monitoring environment;

[0052] Inputting patient behavioral characteristic data into an optimal patient fall risk identification model;

[0053] Based on the optimal patient fall risk identification model, predictive analysis and risk identification are performed on patient behavioral characteristic data to determine whether the patient is at risk of falling and determine the patient fall risk identification result;

[0054] The patient fall risk identification result is that the patient has a fall risk or the patient does not have a fall risk.

[0055] Preferably, the early warning control module includes:

[0056] Plan formulation unit, used to formulate patient fall warning and control plans;

[0057] Obtain patient fall risk identification results;

[0058] When a patient is at risk of falling, the patient's behavioral characteristic data is analyzed to develop a personalized patient fall warning and control plan for the patient;

[0059] Early warning and control unit, used for early warning and control of patient falling behavior;

[0060] Among them, based on the personalized patient fall warning and control plan, early warning and control of patient fall behavior are carried out. For patient fall behavior, an alarm is automatically issued and measures are taken to prevent falls from occurring, reminding people around the patient to protect the patient.

[0061] Preferably, the patient fall monitoring system based on behavioral feature recognition further includes:

[0062] Environmental assessment module, used to obtain environmental data of the monitoring space and evaluate the environmental data to obtain environmental assessment data;

[0063] A patient assessment module is used to obtain the patient's physical condition data and evaluate the physical condition data to obtain patient assessment data;

[0064] A model configuration module is used to configure a model used by the analysis and identification module to predict and analyze patient fall behaviors and identify risks based on environmental assessment data and patient assessment data;

[0065] The environmental assessment module performs the following operations:

[0066] When receiving an environmental assessment request, output a preset environmental simulation construction interface;

[0067] Receive a call for a three-dimensional model corresponding to each object on the environment simulation construction interface and construct the environment simulation model in a construction area of the environment simulation construction interface;

[0068] Performing risk assessment on each three-dimensional model involved in constructing the environmental simulation model to obtain first risk assessment data;

[0069] Based on a preset association library, each three-dimensional model is associated with an evaluation to obtain second risk assessment data;

[0070] Extract features from the environmental simulation model and conduct a comprehensive evaluation based on the preset comprehensive analysis library to obtain the third risk assessment data;

[0071] Combining the first risk assessment data, the second risk assessment data, and the third risk assessment data to obtain environmental assessment data;

[0072] Among them, the patient assessment module performs the following operations:

[0073] When receiving a patient assessment application, output a preset data input interface;

[0074] Receive basic condition data input in the basic condition input area of the data input interface, case data input in the historical case data input area, and current test data input in the current test data input area;

[0075] Comprehensively analyze basic condition data, case data and current test data to obtain patient assessment data.

[0076] Preferably, the model configuration module performs the following operations:

[0077] Performing feature extraction on the first risk assessment data, the second risk assessment data, and the third risk assessment data respectively to obtain a plurality of first feature parameters;

[0078] performing feature extraction on the patient assessment data to obtain a plurality of second feature parameters;

[0079] The plurality of first characteristic parameters and the plurality of second characteristic parameters are sequentially filled into a preset array template to form an analysis data set and the data in the analysis data set are normalized. The normalization formula is as follows:

[0080]

[0081] Where, The first Rank The value of the column; is the first in the analysis data set before normalization Rank The value of the column; is the first in the analysis data set before normalization Rank Column values; analyze the data in the dataset OK List;

[0082] The analysis dataset is matched with the call datasets corresponding to the models used for predictive analysis and risk identification of patient fall behavior in the pre-configured model call library. The matching is performed by calculating the similarity between the two. The similarity calculation formula is as follows:

[0083]

[0084] Where, Indicates similarity; The first Rank The value of the column; To call the first Rank The value of the column;

[0085] The model associated with the calling dataset with the largest similarity that is greater than the preset similarity threshold is retrieved.

[0086] Preferably, the patient fall monitoring system based on behavioral feature recognition further includes:

[0087] Visual monitoring module, used to realize visual monitoring of patients;

[0088] Among them, the visual monitoring module includes:

[0089] A scene model building unit, used to build a scene model according to scene data input by the user;

[0090] A personnel model construction module is used to retrieve a corresponding personnel model from a pre-configured personnel model library based on the patient's motion data, posture data, and gait data;

[0091] The positioning module is used to obtain the patient's position in the scene and place the person model into the scene model according to the obtained position to form a visual monitoring model;

[0092] The real-time risk analysis module is used to analyze the visual monitoring model, identify risk items, and issue corresponding reminders;

[0093] The real-time risk analysis module analyzes the visual monitoring model to identify risk items, including:

[0094] Extract various risk objects within the preset area around the person model in the visual monitoring model;

[0095] Retrieve the risk assessment items corresponding to each risk object as items to be screened; record each item to be screened as ; Indicates the The first risk risk assessment items;

[0096] Analyze the patient's motion data, posture data, and gait data to determine the behavior set;

[0097] Based on the pre-configured association library, the association between each behavior in the behavior set and the risk object is determined and the association coefficient is retrieved, which is recorded as and ; Indicates the Behavior and The first risk The correlation coefficient of distance between risk assessment items; Indicates the Behavior and The first risk The correlation coefficient between the risk assessment items with respect to the angle;

[0098] Based on the correlation coefficient, the assessment value between each behavior and each risk assessment item is determined. The calculation formula is as follows: ;in, Indicates the The distance between the risk object and the patient; Indicates the The angle between the risk object and the patient;

[0099] Extract risk assessment items with assessment values greater than a preset assessment threshold as risk items;

[0100] The patient's motion data, posture data, and gait data are analyzed to determine a behavior set, including: retrieving a corresponding behavior set based on a preset behavior analysis library;

[0101] The behavior set in the behavior analysis library is matched with the first call parameter of the corresponding action data, the second call parameter of the corresponding posture, and the third call parameter of the corresponding gait data. The specific matching is performed by the following formula:

[0102]

[0103] Where TD is the matching degree; is the dth action feature parameter after feature extraction of action data; The first call parameter for the dth one; is the jth posture feature parameter after feature extraction of posture data; Get the parameter for the jth second call; is the u-th posture feature parameter after feature extraction of gait data; is the uth third call parameter; D is the total number of first call parameters; J is the total number of second call parameters; U is the total number of third call parameters; 、 、 is the pre-configured weight coefficient;

[0104] The behavior set corresponding to the first calling parameter, the second calling parameter, and the third calling parameter with the greatest matching degree is called.

[0105] Compared with the prior art, the present invention has the following beneficial effects:

[0106] The present invention uses sensors to collect the patient's movements, posture and gait, and determines the real-time data of the patient's behavior. By cleaning, converting and extracting features from the real-time data of the patient's behavior, the patient's behavior feature data is determined. Based on the optimal patient fall risk identification model, the patient's behavior feature data is predictively analyzed and risk identified, and it is judged whether the patient has a fall risk. The patient's fall risk identification result is determined, and a patient fall early warning and control plan is formulated to perform early warning and control on the patient's fall behavior. The identification and early warning of the patient's fall behavior can be realized. When it is identified that the patient is at risk of falling, an alarm is automatically issued and measures are taken to prevent the fall from occurring, which can improve the patient's safety and reduce medical costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0107] Figure 1 This is a module framework diagram of the patient fall monitoring system based on behavioral feature recognition of the present invention;

[0108] Figure 2This is an algorithm flow chart of the patient fall monitoring system based on behavioral feature recognition of the present invention. DETAILED DESCRIPTION

[0109] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0110] In order to solve the existing problems of not being able to effectively monitor and identify patient falls based on behavioral characteristics, not being able to provide timely early warning and control of patient falls, and not being able to effectively prevent patient falls, resulting in low patient safety and increased medical costs, please refer to Figure 1-Figure 2 , this embodiment provides the following technical solutions:

[0111] The patient fall monitoring system based on behavioral feature recognition includes: a data acquisition module, a data processing module, an analysis and recognition module, and an early warning and control module.

[0112] Specifically, the patient's movements, postures and gait are collected through the data acquisition module to determine the patient's real-time behavior data; the patient's real-time behavior data is cleaned, converted and feature extracted through the data processing module to determine the patient's behavior feature data; the patient's fall behavior is predictively analyzed and risk identified through the analysis and identification module to determine whether the patient has a fall risk and determine the patient's fall risk identification result; the patient's fall warning control plan is formulated through the early warning control module to carry out early warning control of the patient's fall behavior to prevent falls.

[0113] In this embodiment, the data acquisition module includes:

[0114] A motion monitoring unit, used to collect patient motion data;

[0115] Real-time monitoring and collection of patient movements based on sensors to obtain patient movement data;

[0116] a posture monitoring unit, for collecting patient posture data;

[0117] Monitor and collect the patient's posture in real time based on sensors to obtain patient posture data;

[0118] a gait monitoring unit, used to collect patient gait data;

[0119] Monitor and collect the patient's gait in real time based on sensors to obtain the patient's gait data;

[0120] Among them, the real-time data of patient behavior is determined based on the patient motion data, patient posture data and patient gait data.

[0121] It should be noted that by setting infrared sensors, accelerometers, gyroscopes and magnetometers on and around the patient, the patient's movements, postures and gait are collected through the infrared sensors, accelerometers, gyroscopes and magnetometers, thereby determining the real-time data of the patient's behavior.

[0122] Among them, the infrared sensor is a sensor that uses infrared rays to process data. It has the advantages of high sensitivity. The infrared sensor can collect the patient's movements, postures and gait.

[0123] Infrared sensors work based on the principle of infrared radiation. They can sense infrared radiation emitted by the human body and convert it into electrical signals for processing and analysis. This type of sensor can detect information such as the movement, position, and posture of the human body, thereby monitoring human movements, postures, and gait. Specifically:

[0124] ‌Motion data‌: Infrared sensors can detect the human body's motion state, such as speed and direction, which is very useful for monitoring the patient's activity; ‌Position data‌: By analyzing the intensity and direction of infrared radiation, the human body's position in space can be determined, which is very helpful for tracking the patient's position changes; ‌Posture data‌: It can detect the human body's posture, such as standing, sitting, lying, etc., which is very useful for assessing the patient's physical condition; ‌Gait data‌: By monitoring the changes in the human body's gait, the patient's walking pattern can be analyzed, which is of great significance for medical monitoring and rehabilitation training.

[0125] Infrared sensors have a variety of application scenarios in the medical field. They can also be used in medical monitoring: monitoring patients' vital signs such as body temperature and respiration to detect abnormalities in a timely manner; in rehabilitation training: monitoring patients' gait and posture to assist in rehabilitation training and effect evaluation; and in smart homes: used in conjunction with household appliances to achieve intelligent control and improve quality of life. In short, infrared sensors are widely used in the medical field, providing rich motion, posture, and gait data, providing strong support for medical monitoring and rehabilitation training.

[0126] Among them, an accelerometer is a sensor that measures the acceleration of an object. It works by measuring the acceleration caused by gravity or other forces. It can be used to detect the patient's movement status, posture, etc. In gait analysis, accelerometers and gyroscopes are used to capture movement information. By measuring the position and status information of multiple parts of the leg at each moment, after data processing, biomechanical simulation and analysis can be completed with the assistance of computer software.

[0127] Among them, the gyroscope is an angular velocity detection device that uses the angular velocity of a high-speed rotating body's angular velocity relative to the inertial space around one or two axes orthogonal to the axis of rotation. The gyroscope plays a key role in gait detection by measuring and maintaining direction and is not affected by environmental factors such as atmosphere and light. It can accurately measure key data such as acceleration and angular velocity during walking. These data are crucial for evaluating key indicators such as walking stability, cadence, and step length.

[0128] Specifically, the applications of gyroscopes in gait detection are as follows: 1) Accurate measurement of walking data: Gyroscopes can accurately measure key data such as acceleration and angular velocity during walking. These data are crucial for evaluating key indicators such as walking stability, cadence, and step length; 2) Identification of walking patterns and abnormalities: By analyzing the data collected by the gyroscope, different walking patterns can be effectively identified, such as normal gait, abnormal gait, etc. This is of great significance for timely detection and correction of bad gait and prevention of sports injuries; 3) Evaluation of rehabilitation effects: In rehabilitation medicine, gyroscopes are also widely used to evaluate the rehabilitation effects of patients. By comparing gait data before and after treatment, doctors can intuitively understand the patient's recovery status and adjust the treatment plan.

[0129] Among them, the magnetometer can be used to test the strength and direction of the magnetic field and locate the patient's orientation. The principle of the magnetometer is similar to that of the compass, and can measure the angle between the patient and the four directions of east, south, west and north.

[0130] The magnetometer measures changes in the Earth's magnetic field and, combined with data from the accelerometer and gyroscope, can accurately analyze a patient's movements, posture, and gait.

[0131] In this embodiment, the data processing module includes:

[0132] Data cleaning unit, used to clean real-time patient behavior data;

[0133] Obtain real-time data on patient behavior;

[0134] Conduct consistency checks on real-time patient behavior data;

[0135] According to the data consistency requirements, each parameter in the real-time patient behavior data is checked one by one to check whether there is inconsistent data in the real-time patient behavior data that is useless for patient fall monitoring, and the inconsistent data in the real-time patient behavior data is removed;

[0136] Check invalid and missing values in real-time patient behavior data;

[0137] According to the requirements of data validity and integrity, each parameter in the real-time patient behavior data is checked one by one to check whether there are invalid values and missing values in the real-time patient behavior data that are useless for patient fall monitoring. The invalid values and missing values in the real-time patient behavior data are removed to determine the real-time patient behavior data that is useful for patient fall monitoring.

[0138] It should be noted that data cleaning refers to the process of processing and organizing raw data during data analysis to improve the quality and usability of the data.

[0139] Therefore, by cleaning the real-time patient behavior data, inconsistent data, invalid values and missing values that are useless for patient fall monitoring can be removed from the real-time patient behavior data, and then the real-time patient behavior data that is useful for patient fall monitoring can be determined, which can improve the subsequent processing accuracy and efficiency of the real-time patient behavior data.

[0140] In this embodiment, the data processing module further includes:

[0141] A data conversion unit, used to convert real-time patient behavior data;

[0142] Obtain real-time patient behavior data useful for fall monitoring;

[0143] Converting real-time patient behavior data useful for patient fall monitoring to unify the formats of real-time patient behavior data useful for patient fall monitoring;

[0144] Eliminate the dimensional differences between real-time patient behavior data that are useful for patient fall monitoring and determine standardized real-time patient behavior data;

[0145] A feature extraction unit, used to extract features from real-time patient behavior data;

[0146] Obtain standardized real-time data on patient behavior;

[0147] Extract features from standardized real-time patient behavior data;

[0148] Features that can reflect patient falls and are related to patient falls are extracted from standardized real-time patient behavior data to determine patient behavior feature data.

[0149] It should be noted that by converting and extracting features from real-time patient behavior data, the patient's behavior feature data can be determined, which facilitates subsequent risk analysis and identification of the patient's fall behavior.

[0150] In this embodiment, the analysis and identification module includes:

[0151] Model training unit, used to train patient fall risk identification model;

[0152] Collect patient behavior history data based on patient fall monitoring needs based on behavioral feature identification;

[0153] Define the patient's behavioral history data, define the behavioral characteristics related to patient falls, classify the behavioral characteristics, and determine the training set and test set;

[0154] Select a machine learning framework suitable for patient fall risk identification based on behavioral signature recognition;

[0155] Based on the training set, the selected machine learning framework suitable for patient fall risk identification based on behavioral feature recognition is trained to determine the patient fall risk identification model based on behavioral feature recognition.

[0156] In this embodiment, the analysis and identification module further includes:

[0157] Testing and optimization unit, used to test and optimize the patient fall risk identification model;

[0158] Obtain a patient fall risk identification model based on behavioral feature recognition;

[0159] Based on the test set, the performance of the patient fall risk identification model based on behavioral feature recognition is tested to determine whether the patient fall risk identification model based on behavioral feature recognition can achieve the expected effect;

[0160] Determine the performance test results of the patient fall risk identification model;

[0161] According to the performance test results of the patient fall risk identification model, the patient fall risk identification model based on behavioral feature recognition was analyzed, and the parameters of the patient fall risk identification model based on behavioral feature recognition were adjusted and the structure was optimized. After repeated iterations, the optimal patient fall risk identification model was determined.

[0162] In this embodiment, the analysis and identification module further includes:

[0163] Analysis and identification unit, used to perform risk analysis and identification of patient falling behavior;

[0164] Obtain the optimal patient fall risk identification model;

[0165] Deploy the optimal patient fall risk identification model in an actual patient fall monitoring environment;

[0166] Inputting patient behavioral characteristic data into an optimal patient fall risk identification model;

[0167] Based on the optimal patient fall risk identification model, predictive analysis and risk identification are performed on patient behavioral characteristic data to determine whether the patient is at risk of falling and determine the patient fall risk identification result;

[0168] The patient fall risk identification result is that the patient has a fall risk or the patient does not have a fall risk.

[0169] It should be noted that based on the optimal patient fall risk identification model, the patient behavior characteristic data is predicted and analyzed and risks are identified to determine whether the patient is at risk of falling and determine the patient fall risk identification results. Among them, when the patient is at risk of falling, an alarm is automatically issued for the patient's fall behavior and measures are taken to prevent the fall from occurring, reminding people around the patient to protect the patient.

[0170] In this embodiment, the early warning control module includes:

[0171] Plan formulation unit, used to formulate patient fall warning and control plans;

[0172] Obtain patient fall risk identification results;

[0173] When a patient is at risk of falling, the patient's behavioral characteristic data is analyzed to develop a personalized patient fall warning and control plan for the patient;

[0174] Early warning and control unit, used for early warning and control of patient falling behavior;

[0175] Among them, based on the personalized patient fall warning and control plan, early warning and control of patient fall behavior are carried out. For patient fall behavior, an alarm is automatically issued and measures are taken to prevent falls from occurring, reminding people around the patient to protect the patient.

[0176] When the model is actually applied to monitor patient falls, the same model may not be applicable to all situations due to the influence of objective environmental factors and subjective factors of the patient. In response to specific application scenarios of this model, in one embodiment, the patient fall monitoring system based on behavioral feature recognition further includes:

[0177] Environmental assessment module, used to obtain environmental data of the monitoring space and evaluate the environmental data to obtain environmental assessment data;

[0178] A patient assessment module is used to obtain the patient's physical condition data and evaluate the physical condition data to obtain patient assessment data;

[0179] A model configuration module is used to configure a model used by the analysis and identification module to perform predictive analysis and risk identification of patient fall behaviors based on environmental assessment data and patient assessment data;

[0180] This embodiment comprehensively analyzes the environment and patients and calls the model based on the evaluation to ensure the accuracy and effectiveness of the test;

[0181] The environmental assessment module performs the following operations:

[0182] When receiving an environmental assessment request, output a preset environmental simulation construction interface;

[0183] Receiving a call for a three-dimensional model corresponding to each object on the environment simulation construction interface and constructing the environment simulation model in the construction area of the environment simulation construction interface; the environment simulation model may include a three-dimensional model of the real environment;

[0184] Performing a risk assessment on each three-dimensional model involved in constructing the environmental simulation model to obtain first risk assessment data; that is, performing an assessment on each individual object in the environment to assess whether it will cause the patient to fall. This can be performed using a pre-configured object risk analysis library, which contains first risk assessment data corresponding to each object. For example, a stool may be considered to pose a risk of inducing a patient to fall.

[0185] Based on a pre-set association library, each 3D model is evaluated for association to obtain second risk assessment data. Objects are associated (linked) with each other, and the combination of two or more objects may be more dangerous or safer. For example, a stool and a table: when the stool is placed under the table, it eliminates the risk of inducing a patient fall when placed alone; the association between the stool and the aisle: this association increases the risk of inducing a patient fall, etc.

[0186] Extracting features from the environmental simulation model and performing a comprehensive evaluation based on a preset comprehensive analysis library to obtain third risk assessment data; extracting features from the environmental simulation model includes: segmenting the environmental simulation model based on a segmentation grid, determining the three-dimensional model number corresponding to each segmentation unit, arranging the three-dimensional model numbers based on the positions of the segmentation units, and forming a feature data set corresponding to the environmental simulation model; matching the feature data set with the analysis data set corresponding to each third risk assessment data in the comprehensive analysis library, and retrieving the matched third risk assessment data; the third risk assessment data includes: a comprehensive risk assessment value, the location and area of the risk area, etc.;

[0187] Combining the first risk assessment data, the second risk assessment data, and the third risk assessment data to obtain environmental assessment data;

[0188] Among them, the patient assessment module performs the following operations:

[0189] When receiving a patient assessment application, output a preset data input interface;

[0190] Receive basic condition data input in the basic condition input area of the data input interface, case data input in the historical case data input area, and current test data input in the current test data input area;

[0191] Comprehensively analyze basic condition data, case data and current test data to obtain patient assessment data.

[0192] Among them, the model configuration module performs the following operations:

[0193] Performing feature extraction on the first risk assessment data, the second risk assessment data, and the third risk assessment data to obtain a plurality of first feature parameters; quantizing the first risk assessment data, the second risk assessment data, and the third risk assessment data according to a preconfigured quantization model to obtain quantization parameter values corresponding to each risk assessment item, the first feature parameters including an average value, a maximum value, and a minimum value of the quantization parameter values;

[0194] Performing feature extraction on the patient assessment data to obtain a plurality of second feature parameters; the second feature parameters include a parameter indicating age, a parameter indicating weight, a parameter indicating gender, a parameter indicating the presence and type of a disease, a parameter indicating whether a disease has ever existed and the type of the disease, etc.;

[0195] The plurality of first characteristic parameters and the plurality of second characteristic parameters are sequentially filled into a preset array template to form an analysis data set and the data in the analysis data set are normalized. The normalization formula is as follows:

[0196]

[0197] Where, The first Rank The value of the column; is the first in the analysis data set before normalization Rank The value of the column; is the first in the analysis data set before normalization Rank Column values; analyze the data in the dataset OK List;

[0198] The analysis dataset is matched with the call datasets corresponding to the models used for predictive analysis and risk identification of patient fall behavior in the pre-configured model call library. The matching is performed by calculating the similarity between the two. The similarity calculation formula is as follows:

[0199]

[0200] Where, Indicates similarity; The first Rank The value of the column; To call the first Rank The value of the column;

[0201] The model associated with the calling dataset with the largest similarity that is greater than the preset similarity threshold is retrieved.

[0202] This embodiment performs analysis calling through a pre-configured model calling library. The principle to be followed is that the greater the risk of the patient being assessed or the greater the risk of the environment, the greater the sensitivity requirement of the adopted model.

[0203] In one embodiment, the patient fall monitoring system based on behavioral feature recognition further includes:

[0204] Visual monitoring module, used to realize visual monitoring of patients;

[0205] Among them, the visual monitoring module includes:

[0206] The scene model construction unit is used to construct a scene model based on the scene data input by the user. The user can upload an image of the scene, and the platform will analyze the image and construct the corresponding scene model framework. The user can adjust the parameters of the scene model accordingly to form the final scene model.

[0207] A personnel model construction module is used to retrieve a corresponding personnel model from a pre-configured personnel model library based on the patient's motion data, posture data, and gait data;

[0208] The positioning module is used to obtain the patient's position in the scene and place the person model into the scene model based on the obtained position to form a visual monitoring model. The positioning module can use image analysis positioning or positioning methods of the positioning module on the terminal worn by the patient. Among them, the image positioning method analyzes the image in the scene and locates the patient based on the relative position relationship between each marker in the scene and the patient. The positioning method of the positioning module is an existing mature technology and will not be explained in detail here.

[0209] The real-time risk analysis module is used to analyze the visual monitoring model, identify risk items, and issue corresponding reminders;

[0210] The real-time risk analysis module analyzes the visual monitoring model to identify risk items, including:

[0211] Extract various risk objects within the preset area around the person model in the visual monitoring model;

[0212] Retrieve the risk assessment items corresponding to each risk object as items to be screened; record each item to be screened as ; Indicates the The first risk risk assessment items;

[0213] Analyze the patient's motion data, posture data, and gait data to determine the behavior set;

[0214] Based on the pre-configured association library, determine the association between each behavior in the behavior set and the risk object and retrieve the association coefficient; denoted as and ; Indicates the Behavior and The first risk The correlation coefficient of distance between risk assessment items; Indicates the Behavior and The first risk The correlation coefficient between the risk assessment items with respect to the angle;

[0215] Based on the correlation coefficient, the assessment value between each behavior and each risk assessment item is determined. The calculation formula is as follows: ;in, Indicates the The distance between the risk object and the patient; Indicates the The angle between the risk object and the patient;

[0216] Extract risk assessment items with assessment values greater than a preset assessment threshold as risk items;

[0217] The patient's motion data, posture data, and gait data are analyzed to determine a behavior set, including: retrieving a corresponding behavior set based on a preset behavior analysis library;

[0218] The behavior set in the behavior analysis library is matched with the first call parameter of the corresponding action data, the second call parameter of the corresponding posture, and the third call parameter of the corresponding gait data. The specific matching is performed by the following formula:

[0219]

[0220] Where TD is the matching degree; is the dth action feature parameter after feature extraction of action data; The first call parameter for the dth one; is the jth posture feature parameter after feature extraction of posture data; Get the parameter for the jth second call; is the u-th posture feature parameter after feature extraction of gait data; is the uth third call parameter; D is the total number of first call parameters; J is the total number of second call parameters; U is the total number of third call parameters; 、 、 is the pre-configured weight coefficient;

[0221] The behavior set corresponding to the first calling parameter, the second calling parameter, and the third calling parameter with the greatest matching degree is called.

[0222] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0223] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A patient fall monitoring system based on behavioral feature recognition, characterized in that: include: The data acquisition module is used to use sensors to collect the patient's movements, postures and gait conditions to determine the patient's real-time behavior data; The data processing module is used to clean, convert and extract features of real-time patient behavior data to determine patient behavior feature data; The analysis and identification module is used to predict and analyze the patient's fall behavior and identify risks, determine whether the patient has a fall risk, and determine the patient's fall risk identification results; The early warning and control module is used to formulate a patient fall early warning and control plan, conduct early warning and control of patient fall behaviors, and prevent falls from happening; Also includes: Environmental assessment module, used to obtain environmental data of the monitoring space and evaluate the environmental data to obtain environmental assessment data; A patient assessment module is used to obtain the patient's physical condition data and evaluate the physical condition data to obtain patient assessment data; A model configuration module is used to configure a model used by the analysis and identification module to perform predictive analysis and risk identification of patient fall behaviors based on environmental assessment data and patient assessment data; The environmental assessment module performs the following operations: When receiving an environmental assessment request, output a preset environmental simulation construction interface; Receive calls to three-dimensional models corresponding to various objects on the environment simulation construction interface and construct the environment simulation model within a construction area of the environment simulation construction interface; Performing risk assessment on each three-dimensional model involved in constructing the environmental simulation model to obtain first risk assessment data; Based on a preset association library, each three-dimensional model is associated with an evaluation to obtain second risk assessment data; Extract features from the environmental simulation model and conduct a comprehensive evaluation based on the preset comprehensive analysis library to obtain the third risk assessment data; Combining the first risk assessment data, the second risk assessment data, and the third risk assessment data to obtain environmental assessment data; Among them, the patient assessment module performs the following operations: When receiving a patient assessment application, output a preset data input interface; Receive basic condition data input in the basic condition input area of the data input interface, case data input in the historical case data input area, and current test data input in the current test data input area; Comprehensively analyze basic condition data, case data and current test data to obtain patient assessment data; The model configuration module performs the following operations: Performing feature extraction on the first risk assessment data, the second risk assessment data, and the third risk assessment data respectively to obtain a plurality of first feature parameters; performing feature extraction on the patient assessment data to obtain a plurality of second feature parameters; The plurality of first characteristic parameters and the plurality of second characteristic parameters are sequentially filled into a preset array template to form an analysis data set and the data in the analysis data set are normalized. The normalization formula is as follows: ； Where, The first Rank The value of the column; is the first in the analysis data set before normalization Rank The value of the column; is the first in the analysis data set before normalization Rank Column values; analyze the data in the dataset OK List; The analysis dataset is matched with the call datasets corresponding to the models used for predictive analysis and risk identification of patient fall behavior in the pre-configured model call library. The matching is performed by calculating the similarity between the two. The similarity calculation formula is as follows: ； Where, Indicates similarity; The first Rank The value of the column; To call the first Rank The value of the column; The model associated with the calling dataset with the largest similarity that is greater than the preset similarity threshold is retrieved.

2. The patient fall monitoring system based on behavioral feature recognition according to claim 1, characterized in that: The data acquisition module includes: A motion monitoring unit, used to collect patient motion data; Real-time monitoring and collection of patient movements based on sensors to obtain patient movement data; a posture monitoring unit, for collecting patient posture data; Monitor and collect the patient's posture in real time based on sensors to obtain patient posture data; a gait monitoring unit, used to collect patient gait data; Monitor and collect the patient's gait in real time based on sensors to obtain the patient's gait data; Among them, the real-time data of patient behavior is determined based on the patient motion data, patient posture data and patient gait data.

3. The patient fall monitoring system based on behavioral feature recognition according to claim 2, characterized in that: The data processing module includes: Data cleaning unit, used to clean real-time patient behavior data; Obtain real-time data on patient behavior; Conduct consistency checks on real-time patient behavior data; According to the data consistency requirements, each parameter in the real-time patient behavior data is checked one by one to check whether there is inconsistent data in the real-time patient behavior data that is useless for patient fall monitoring, and the inconsistent data in the real-time patient behavior data is removed; Check invalid and missing values in real-time patient behavior data; According to the requirements of data validity and integrity, each parameter in the real-time patient behavior data is checked one by one to check whether there are invalid values and missing values in the real-time patient behavior data that are useless for patient fall monitoring. The invalid values and missing values in the real-time patient behavior data are removed to determine the real-time patient behavior data that is useful for patient fall monitoring.

4. The patient fall monitoring system based on behavioral feature recognition according to claim 3, characterized in that: The data processing module further includes: A data conversion unit, used to convert real-time patient behavior data; Obtain real-time patient behavior data useful for fall monitoring; Converting real-time patient behavior data useful for patient fall monitoring to unify the formats of real-time patient behavior data useful for patient fall monitoring; Eliminate the dimensional differences between real-time patient behavior data that are useful for patient fall monitoring and determine standardized real-time patient behavior data; A feature extraction unit, used to extract features from real-time patient behavior data; Obtain standardized real-time data on patient behavior; Extract features from standardized real-time patient behavior data; Features that can reflect patient falls and are related to patient falls are extracted from standardized real-time patient behavior data to determine patient behavior feature data.

5. The patient fall monitoring system based on behavioral feature recognition according to claim 4, characterized in that: The analysis and identification module includes: Model training unit, used to train patient fall risk identification model; Collect patient behavior history data based on patient fall monitoring needs based on behavioral feature identification; Define the patient's behavioral history data, define the behavioral characteristics related to patient falls, classify the behavioral characteristics, and determine the training set and test set; Select a machine learning framework suitable for patient fall risk identification based on behavioral signature recognition; Based on the training set, the selected machine learning framework suitable for patient fall risk identification based on behavioral feature recognition is trained to determine the patient fall risk identification model based on behavioral feature recognition.

6. The patient fall monitoring system based on behavioral feature recognition according to claim 5, characterized in that: The analysis and identification module further includes: Testing and optimization unit, used to test and optimize the patient fall risk identification model; Obtain a patient fall risk identification model based on behavioral feature recognition; Based on the test set, the performance of the patient fall risk identification model based on behavioral feature recognition is tested to determine whether the patient fall risk identification model based on behavioral feature recognition can achieve the expected effect; Determine the performance test results of the patient fall risk identification model; According to the performance test results of the patient fall risk identification model, the patient fall risk identification model based on behavioral feature recognition was analyzed, and the parameters of the patient fall risk identification model based on behavioral feature recognition were adjusted and the structure was optimized. After repeated iterations, the optimal patient fall risk identification model was determined.

7. The patient fall monitoring system based on behavioral feature recognition according to claim 6, characterized in that: The analysis and identification module further includes: Analysis and identification unit, used to perform risk analysis and identification of patient falling behavior; Obtain the optimal patient fall risk identification model; Deploy the optimal patient fall risk identification model in an actual patient fall monitoring environment; Inputting patient behavioral characteristic data into an optimal patient fall risk identification model; Based on the optimal patient fall risk identification model, predictive analysis and risk identification are performed on patient behavioral characteristic data to determine whether the patient is at risk of falling and determine the patient fall risk identification result; The patient fall risk identification result is that the patient has a fall risk or the patient does not have a fall risk.

8. The patient fall monitoring system based on behavioral feature recognition according to claim 7, characterized in that: The early warning control module includes: Plan formulation unit, used to formulate patient fall warning and control plans; Obtain patient fall risk identification results; When a patient is at risk of falling, the patient's behavioral characteristic data is analyzed to develop a personalized patient fall warning and control plan for the patient; Early warning and control unit, used for early warning and control of patient falling behavior; Among them, based on the personalized patient fall warning and control plan, early warning and control of patient fall behavior are carried out. For patient fall behavior, an alarm is automatically issued and measures are taken to prevent falls from occurring, reminding people around the patient to protect the patient.

9. The patient fall monitoring system based on behavioral feature recognition according to claim 1, characterized in that: The patient fall monitoring system based on behavioral feature recognition also includes: Visual monitoring module, used to realize visual monitoring of patients; Among them, the visual monitoring module includes: A scene model building unit, used to build a scene model according to scene data input by the user; A personnel model construction module is used to retrieve a corresponding personnel model from a pre-configured personnel model library based on the patient's motion data, posture data, and gait data; The positioning module is used to obtain the patient's position in the scene and place the person model into the scene model according to the obtained position to form a visual monitoring model; The real-time risk analysis module is used to analyze the visual monitoring model, identify risk items, and issue corresponding reminders; The real-time risk analysis module analyzes the visual monitoring model to identify risk items, including: Extract various risk objects within the preset area around the person model in the visual monitoring model; Retrieve the risk assessment items corresponding to each risk object as items to be screened; record each item to be screened as ; Indicates the The first risk risk assessment items; Analyze the patient's motion data, posture data, and gait data to determine the behavior set; Based on the pre-configured association library, the association between each behavior in the behavior set and the risk object is determined and the association coefficient is retrieved, which is recorded as and ; Indicates the Behavior and The first risk The correlation coefficient of distance between risk assessment items; Indicates the Behavior and The first risk The correlation coefficient between the risk assessment items with respect to the angle; Based on the correlation coefficient, the assessment value between each behavior and each risk assessment item is determined. The calculation formula is as follows: ;in, Indicates the The distance between the risk object and the patient; Indicates the The angle between the risk object and the patient; Extract risk assessment items with assessment values greater than a preset assessment threshold as risk items; The patient's motion data, posture data, and gait data are analyzed to determine a behavior set, including: retrieving a corresponding behavior set based on a preset behavior analysis library; The behavior set in the behavior analysis library is matched with the first call parameter of the corresponding action data, the second call parameter of the corresponding posture, and the third call parameter of the corresponding gait data. The specific matching is performed by the following formula: ； Where, is the matching degree; After feature extraction of action data Action characteristic parameters; For the The first call parameter; After feature extraction of posture data posture feature parameters; For the The second call parameter; After feature extraction of gait data posture feature parameters; For the A third call parameter; is the total number of first call parameters; The total number of the second call parameters; The total number of the third call parameters; 、 、 is the pre-configured weight coefficient; The behavior set corresponding to the first calling parameter, the second calling parameter, and the third calling parameter with the greatest matching degree is called.

Images