Home fall alarm system based on mobile communication service

Abstract

This invention relates to the field of home fall detection technology and discloses a home fall alarm system based on mobile communication services, including a multi-dimensional acquisition module and an intelligent analysis module. The system acquires test data of the user's daily behavior, sensor data of activity behavior, and monitoring data of the activity space through the multi-dimensional acquisition module. The intelligent analysis module analyzes the activity status under each posture, generating daily data groups and feature data groups, emphasizing individual user differences, establishing a unique health baseline for each user, analyzing the user's activity status in real time, promptly identifying fall signs, analyzing safety hazards in each activity space, generating a danger index, and providing high accuracy in multi-dimensional assessment. This prevents users from lingering in high-risk environments. The intelligent analysis module assesses the user's activity status and the fall risk in the activity space, determines whether to activate mobile communication services, and executes corresponding inquiries and emergency measures, establishing a tiered response mechanism with rapid response and high sensitivity.

Description

Technical Field

[0001] This invention relates to the field of home fall detection technology, specifically a home fall alarm system based on mobile communication services. Background Technology

[0002] Home falls refer to accidental falls that occur in the home environment, and are particularly common among the elderly and those with mobility impairments. The causes are varied, mainly falling into two categories: environmental and physical factors. Environmental factors include slippery floors, insufficient lighting, improper furniture placement, and lack of handrails on stairs, while physical factors involve declining vision, decreased balance, weakened muscle strength, and the effects of chronic diseases.

[0003] To effectively prevent falls at home, fall alarm systems have emerged. By monitoring user behavior and environmental data in real time, these systems can issue an alarm the instant a fall occurs and quickly notify the user or their emergency contact. This not only provides comprehensive safety for the elderly and those with mobility impairments but also significantly reduces the risk of injury from falls, making it an indispensable tool in modern home care.

[0004] Currently, traditional home fall alarm systems lack in-depth analysis of users' daily behavior patterns, often ignoring individual differences among users, failing to establish a health baseline based on each user's behavioral habits, exhibiting low sensitivity in abnormal detection, and slow real-time alarm and emergency response speeds. Summary of the Invention

[0005] (a) Technical problems to be solved

[0006] To address the shortcomings of existing technologies, this invention provides a home fall alarm system based on mobile communication services, which has the advantages of high accuracy in multi-dimensional assessment and high sensitivity in rapid response. It solves the problems of low sensitivity in abnormal detection and slow speed in real-time alarm and emergency response of traditional home fall alarm systems.

[0007] (2) Technical solution

[0008] To achieve the above objectives, the present invention provides the following technical solution: a home fall alarm system based on mobile communication services, comprising a multi-dimensional acquisition module and an intelligent analysis module;

[0009] The multi-dimensional acquisition module consists of a test data unit, a sensor data unit, and an environmental data unit. The test data unit collects test datasets by connecting to a database via a network. The test datasets include test data of users' daily behavior. The sensor data unit collects sensor datasets by connecting to sensor devices via a network. The sensor datasets include sensor data of users' activity behavior. The environmental data unit collects environmental datasets by connecting to a camera via a network. The environmental datasets include monitoring data of the user's activity space.

[0010] The intelligent analysis module consists of a daily assessment unit, a real-time assessment unit, an environmental assessment unit, and a fall alarm unit. The daily assessment unit analyzes the user's activity status in each posture based on the test dataset, whereby each posture generates a corresponding daily data set. and feature data group The real-time evaluation unit analyzes the user's activity status in real time based on the sensor dataset and generates corresponding monitoring data sets. The environmental assessment unit analyzes the safety hazards of each activity space based on the environmental dataset and generates a corresponding hazard index. The fall alarm unit is equipped with a fixed range of danger zones. Combined with sensor datasets and daily data sets Feature data group Monitoring data group and risk index Assess the user's activity status and the risk of falls within the activity space, determine whether to activate mobile communication services, and execute corresponding inquiries and emergency measures.

[0011] Preferably, the test dataset includes several sets of standing test data, several sets of sitting test data, several sets of squatting test data, several sets of kneeling test data, and several sets of lying test data, and each set of test data includes heart rate, blood pressure, movement speed, tilt angle, and height off the ground.

[0012] Preferably, the expression for the sensor dataset is: , to This represents the sensor data from the user's first to the nth activity. The sensor data includes heart rate, blood pressure, movement speed, tilt angle, and height above the ground. s represents the time point at which the user's activity sensor data was acquired.

[0013] Preferably, the expression for the environmental dataset is: , to This represents the monitoring data for the first to the mth activity spaces. The monitoring data includes ambient brightness, ground flatness, humidity, and storage density. j represents the time point at which the monitoring data for the user's activity space is acquired.

[0014] Preferably, the daily data group The calculation process is as follows:

[0015] Based on the test dataset, the heart rate in the standing posture test data is labeled as... , to This represents the heart rate during the first to the *a*th standing posture tests. The heart rate data from the sitting posture tests is labeled as follows: , to This represents the heart rate during the first to the bth sitting tests. The heart rate data from the squatting tests is labeled as... , to This represents the heart rate during the first to the cth squatting tests. The heart rate data from the kneeling test is labeled as... , to This represents the heart rate during the first to the dth kneeling tests. The heart rate data from the lying-down test is marked as... , to This represents the heart rate during the first to the eth lying position tests;

[0016] ;

[0017] In the formula, This represents the average heart rate of users during prolonged standing activities. This represents the average heart rate of users during sedentary daily activities. This represents the average heart rate of users during prolonged squatting activities. This indicates the average heart rate of users during prolonged kneeling activities. This represents the average heart rate of users during prolonged periods of lying down. This represents the user's active heart rate in standing, sitting, squatting, kneeling, and lying positions, which is the daily data set corresponding to the user's daily heart rate test.

[0018] Preferably, the feature data group The calculation process is as follows:

[0019] ;

[0020] In the formula, This indicates the user's highest heart rate during prolonged standing activities. This indicates the user's highest heart rate during sedentary daily activities. This represents the difference in the user's highest heart rate when changing from a standing to a sitting position. This indicates the user's highest heart rate during prolonged squatting activities. This represents the difference in the user's highest heart rate when changing from a standing to a squatting posture. This indicates the user's highest heart rate during prolonged kneeling activities. This represents the difference in the user's highest heart rate when changing from a standing to a kneeling position. This indicates the user's highest heart rate during prolonged lying down. This represents the difference in the user's highest heart rate when changing from a standing to a lying position. This indicates the lowest heart rate a user experiences during prolonged standing. This indicates the user's lowest heart rate during sedentary daily activities. This represents the minimum heart rate difference when a user changes from a standing to a sitting position. This indicates the lowest heart rate a user experiences during prolonged squatting activities. This represents the minimum heart rate difference when a user changes from a standing to a squatting position. This indicates the user's lowest heart rate during prolonged kneeling activities. This represents the lowest heart rate difference when a user changes from a standing to a kneeling position. This indicates the lowest heart rate a user experiences during prolonged periods of lying down. This represents the lowest heart rate difference when a user changes from a standing to a lying position. This represents the extreme changes in heart rate when a user changes from a standing position to a sitting, squatting, kneeling, or lying position; it is the feature data set corresponding to the user's daily heart rate test.

[0021] Preferably, the monitoring data set The calculation process is as follows:

[0022] Based on the sensor dataset, extract sensor data for the user's i-th activity behavior and label the user's heart rate during the i-th activity behavior as... The user's blood pressure during the i-th activity is marked as The movement speed of the user's i-th activity is marked as The tilt angle of the user's i-th activity is marked as Mark the ground height of the user's i-th activity as ;

[0023] Following the chronological order, sensor data for the user's (i+1)th activity behavior is extracted from the sensor dataset, where the user's (i)th activity behavior precedes the (i+1)th activity behavior. The heart rate of the user's (i+1)th activity behavior is then labeled as... Mark the user's blood pressure during the (i+1)th activity as Mark the movement speed of the user's (i+1)th activity as The tilt angle of the user's (i+1)th activity is marked as Mark the height above the ground of the user's (i+1)th activity as ;

[0024] ;

[0025] In the formula, This represents the change in heart rate when a user transitions from the i-th activity to the (i+1)-th activity. This represents the change in a user's blood pressure when they transition from the i-th activity to the (i+1)-th activity. This represents the change in a user's movement speed when transitioning from the i-th activity to the (i+1)-th activity. This represents the change in tilt angle when a user transitions from the i-th activity to the (i+1)-th activity. This represents the change in ground altitude when a user transitions from their i-th activity to their (i+1)-th activity. This represents the monitoring data group when a user changes from the i-th activity to the (i+1)-th activity.

[0026] Preferably, the danger index The calculation process is as follows:

[0027] Based on the environmental dataset, the monitoring data of the k-th activity space is extracted, and the ambient brightness of the k-th activity space is marked as... The flatness of the ground in the k-th activity space is marked as... The humidity of the kth activity space is marked as The storage density of the k-th activity space is marked as ;

[0028] ;

[0029] In the formula, This represents a standard value used to measure ambient brightness. This indicates the weighting of the ratio of the standard value to the ambient brightness. This represents the standard value used to measure the flatness of the ground. This indicates the weight of the ratio of ground flatness to the standard value. This represents the standard value used to measure humidity. This indicates the weighting of the ratio of humidity to the standard value. This indicates the weight given by the storage density. , , and All are constants, and , Indicates according to , , and The weights are used to calculate the danger index of the k-th activity space. .

[0030] Preferably, in the sensor dataset, the heart rate during any user activity is lower than that in the daily heart rate test data set. If all values ​​are present, it indicates an abnormal heart rate and a high risk of falling. The system will contact the user via mobile communication service to inquire if they are feeling unwell. If no response is received within 5 seconds, the system will contact the user's emergency contact via mobile communication service. (The monitoring data group...) Heart rate variability exceeds heart rate test characteristic data set If all values ​​are present, it indicates that the user's heart rate is abnormal and there is a high risk of falling. The system will ask the user if they have fallen via mobile communication service. If no response is received from the user within 5 seconds, the system will contact the user's emergency contact via mobile communication service.

[0031] Preferably, the danger index Beyond the danger zone If the activity space is found to have many safety hazards and a high risk of falling, the user will be alerted to safety via mobile communication service. If no response is received from the user within 5 seconds, the user's emergency contact will be notified via mobile communication service.

[0032] Compared with the prior art, the present invention provides a home fall alarm system based on mobile communication services, which has the following beneficial effects:

[0033] 1. This invention uses a multi-dimensional acquisition module to connect a database, sensing devices, and cameras via a network to acquire test data of users' daily behavior, sensor data of users' activity behavior, and monitoring data of the user's activity space. The intelligent analysis module analyzes the user's activity state under each posture based on the test dataset, with each posture generating a corresponding set of daily data. and feature data group It establishes a unique health baseline for each user, significantly improving the sensitivity of anomaly detection. It emphasizes individual user differences, and the intelligent analysis module analyzes the user's activity status in real time based on sensor datasets, generating corresponding monitoring data sets. It dynamically tracks real-time data, promptly identifies signs of falls, and the intelligent analysis module analyzes safety hazards in each activity space based on environmental datasets, generating corresponding hazard indices. It dynamically quantifies safety hazards in activity spaces, provides high accuracy in multi-dimensional assessment, and prevents users from lingering in high-risk environments.

[0034] 2. This invention uses an intelligent analysis module to set a fixed range of dangerous zones. Combined with sensor datasets and daily data sets Feature data group Monitoring data group and risk index The system assesses the user's activity status and the risk of falls within their activity space, determines whether to activate mobile communication services, and executes corresponding inquiries and emergency measures. If no response is received from the user within 5 seconds, the system contacts the user's emergency contact through mobile communication services, establishing a tiered response mechanism to ensure efficient emergency handling. The tiered strategy avoids excessive disturbance to users while providing effective protection at critical moments, demonstrating rapid response and high sensitivity. Attached Figure Description

[0035] Figure 1 This is a system flowchart of the present invention. Detailed Implementation

[0036] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0037] Traditional home fall alarm systems lack in-depth analysis of users' daily behavioral patterns, often neglecting individual differences and failing to establish a health baseline based on each user's habits. They also suffer from low sensitivity in anomaly detection and slow real-time alarm and emergency response speeds. Therefore, a home fall alarm system based on mobile communication services is proposed. Please refer to [link to relevant documentation]. Figure 1 A home fall alarm system based on mobile communication services, including a multi-dimensional data acquisition module and an intelligent analysis module;

[0038] The multi-dimensional acquisition module consists of a test data unit, a sensor data unit, and an environmental data unit. Specifically, the multimodal data is collected through wearable devices, which can more comprehensively reflect the user's physical condition and the safety level of the environment, reducing the probability of misjudgment.

[0039] The test data unit collects test datasets by connecting to a database via a network. The test datasets include test data on users' daily behaviors, including several sets of standing test data, several sets of sitting test data, several sets of squatting test data, several sets of kneeling test data, and several sets of lying test data. Each set of test data includes heart rate, blood pressure, movement speed, tilt angle, and height off the ground.

[0040] The sensing data unit collects sensing datasets via a network connection to sensing devices. These datasets include sensing data related to user activity and behavior. The expression for the sensing dataset is: , to This represents the sensor data of the user's first to nth activity behavior. The sensor data includes heart rate, blood pressure, movement speed, tilt angle and height above the ground. s represents the time point when the user's activity behavior sensor data was acquired.

[0041] The environmental data unit collects environmental datasets via a network connection to cameras. These datasets include monitoring data of the user's activity space, and the expression for the environmental dataset is as follows: , to This represents the monitoring data for the first to the mth activity spaces. The monitoring data includes ambient brightness, ground flatness, humidity, and storage density. j represents the time point at which the monitoring data for the user's activity space is acquired.

[0042] The intelligent analysis module consists of a daily assessment unit, a real-time assessment unit, an environmental assessment unit, and a fall alarm unit. The daily assessment unit analyzes the user's activity status in each posture based on the test dataset, with each posture generating a corresponding daily data set. and feature data group Specifically, the standing posture test corresponds to a daily heart rate test data set. Heart rate test feature data group There are daily data sets for blood pressure testing, blood pressure test characteristic data sets, daily data sets for movement speed testing, daily data sets for movement speed testing, daily data sets for tilt angle testing, daily data sets for tilt angle testing, daily data sets for height off the ground testing, and so on. There are also corresponding daily data sets for sitting, squatting, kneeling, and lying positions. and feature data group And each group of daily data groups and feature data group The calculation logic is consistent;

[0043] Daily Data Group The calculation process is as follows:

[0044] Based on the test dataset, the heart rate in the standing posture test data is labeled as... , to This represents the heart rate during the first to the *a*th standing posture tests. The heart rate data from the sitting posture tests is labeled as follows: , to This represents the heart rate during the first to the bth sitting tests. The heart rate data from the squatting tests is labeled as... , to This represents the heart rate during the first to the cth squatting tests. The heart rate data from the kneeling test is labeled as... , to This represents the heart rate during the first to the dth kneeling tests. The heart rate data from the lying-down test is marked as... , to This represents the heart rate during the first to the eth lying position tests;

[0045] ;

[0046] In the formula, This represents the average heart rate of users during prolonged standing activities. This represents the average heart rate of users during sedentary daily activities. This represents the average heart rate of users during prolonged squatting activities. This indicates the average heart rate of users during prolonged kneeling activities. This represents the average heart rate of users during prolonged periods of lying down. It represents the user's active heart rate in standing, sitting, squatting, kneeling and lying positions, which is the daily data set corresponding to the user's daily heart rate test. It establishes a unique health baseline for each user and significantly improves the sensitivity of abnormality detection.

[0047] Feature Data Set The calculation process is as follows:

[0048] ;

[0049] In the formula, This indicates the user's highest heart rate during prolonged standing activities. This indicates the user's highest heart rate during sedentary daily activities. This represents the difference in the user's highest heart rate when changing from a standing to a sitting position. This indicates the user's highest heart rate during prolonged squatting activities. This represents the difference in the user's highest heart rate when changing from a standing to a squatting posture. This indicates the user's highest heart rate during prolonged kneeling activities. This represents the difference in the user's highest heart rate when changing from a standing to a kneeling position. This indicates the user's highest heart rate during prolonged lying down. This represents the difference in the user's highest heart rate when changing from a standing to a lying position. This indicates the lowest heart rate a user experiences during prolonged standing. This indicates the user's lowest heart rate during sedentary daily activities. This represents the minimum heart rate difference when a user changes from a standing to a sitting position. This indicates the lowest heart rate a user experiences during prolonged squatting activities. This represents the minimum heart rate difference when a user changes from a standing to a squatting position. This indicates the user's lowest heart rate during prolonged kneeling activities. This represents the lowest heart rate difference when a user changes from a standing to a kneeling position. This indicates the lowest heart rate a user experiences during prolonged periods of lying down. This represents the lowest heart rate difference when a user changes from a standing to a lying position. This represents the extreme changes in heart rate when a user changes from a standing to a sitting, squatting, kneeling, or lying position. It is the characteristic data set corresponding to the user's daily heart rate test. It focuses on individual differences among users and analyzes the extreme changes in heart rate, blood pressure, movement speed, tilt angle, and height above the ground between different user activities according to a unified calculation logic based on each user's behavioral habits. This provides data support for subsequent multi-dimensional comparisons.

[0050] The real-time evaluation unit analyzes the user's activity status in real time based on the sensor dataset and generates corresponding monitoring data sets. The calculation process is as follows:

[0051] Based on the sensor dataset, extract sensor data for the user's i-th activity behavior and label the user's heart rate during the i-th activity behavior as... The user's blood pressure during the i-th activity is marked as The movement speed of the user's i-th activity is marked as The tilt angle of the user's i-th activity is marked as Mark the ground height of the user's i-th activity as ;

[0052] Following the chronological order, sensor data for the user's (i+1)th activity behavior is extracted from the sensor dataset, where the user's (i)th activity behavior precedes the (i+1)th activity behavior. The heart rate of the user's (i+1)th activity behavior is then labeled as... Mark the user's blood pressure during the (i+1)th activity as Mark the movement speed of the user's (i+1)th activity as The tilt angle of the user's (i+1)th activity is marked as Mark the height above the ground of the user's (i+1)th activity as ;

[0053] ;

[0054] In the formula, This represents the change in heart rate when a user transitions from the i-th activity to the (i+1)-th activity. This represents the change in a user's blood pressure when they transition from the i-th activity to the (i+1)-th activity. This represents the change in a user's movement speed when transitioning from the i-th activity to the (i+1)-th activity. This represents the change in tilt angle when a user transitions from the i-th activity to the (i+1)-th activity. This represents the change in ground altitude when a user transitions from their i-th activity to their (i+1)-th activity. This represents the monitoring data group when a user transitions from the i-th activity to the (i+1)-th activity, dynamically tracking real-time data and promptly identifying signs of a fall;

[0055] The environmental assessment unit analyzes the safety hazards of each activity space based on the environmental dataset and generates a corresponding hazard index. The calculation process is as follows:

[0056] Based on the environmental dataset, the monitoring data of the k-th activity space is extracted, and the ambient brightness of the k-th activity space is marked as... The flatness of the ground in the k-th activity space is marked as... The humidity of the kth activity space is marked as The storage density of the k-th activity space is marked as ;

[0057] ;

[0058] In the formula, This represents a standard value used to measure ambient brightness. This indicates the weighting of the ratio of the standard value to the ambient brightness. This represents the standard value used to measure the flatness of the ground. This indicates the weight of the ratio of ground flatness to the standard value. This represents the standard value used to measure humidity. This indicates the weighting of the ratio of humidity to the standard value. This indicates the weight given by the storage density. , , and All are constants, and , Indicates according to , , and The weights are used to calculate the danger index of the k-th activity space. It dynamically quantifies safety hazards in activity spaces, provides high accuracy in multi-dimensional assessment, and prevents users from lingering in high-risk environments.

[0059] The fall alarm unit is set with a fixed range of danger zones. Combined with sensor datasets and daily data sets Feature data group Monitoring data group and risk index It assesses the risk of falls in the user's activity status and activity space, determines whether to activate mobile communication services, and executes corresponding inquiries and emergency measures, establishing a tiered response mechanism to ensure emergency handling efficiency.

[0060] Sensor dataset, user heart rate during any activity is lower than heart rate test daily data set If all values ​​are present, it indicates that the user's heart rate is abnormal and there is a high risk of falling. The system will ask the user if they are feeling unwell via mobile communication service. If no response is received within 5 seconds, the system will contact the user's emergency contact via mobile communication service to ensure that rescue can still be provided in an emergency where no one responds.

[0061] Monitoring data group Heart rate variability exceeds heart rate test characteristic data set If all values ​​are present, it indicates that the user's heart rate is abnormal and there is a high risk of falling. The user will be asked via mobile communication service if they have fallen. If no response is received from the user within 5 seconds, the user's emergency contact will be contacted via mobile communication service.

[0062] Risk Index Beyond the danger zone When a user is alerted to a potential safety hazard in their activity space, indicating a high risk of falls, the system alerts them via mobile communication. If no response is received within 5 seconds, the system alerts their emergency contact via mobile communication. This tiered approach avoids excessive disruption to the user while providing effective protection in critical moments, demonstrating rapid response and high sensitivity.

[0063] Example 1: In this experiment, elderly people aged 70 years were selected as the experimental subjects. Tests showed that when the elderly transitioned from a standing to a sitting posture, their heart rate increased from 70 beats / minute to 75 beats / minute, blood pressure changed from 120 / 80 mmHg to 125 / 85 mmHg, moving speed increased from 0.5 m / s to 1.0 m / s, tilt angle changed from 0 degrees to 15 degrees, and height off the ground decreased from 1.7 meters to 0.5 meters. The monitoring data set for the elderly transitioning from a standing to a sitting posture is as follows. The calculation process is as follows:

[0064] ;

[0065] In the formula, This indicates the change in heart rate when an elderly person changes from a standing to a sitting position. This indicates the change in blood pressure in older adults when they transition from a standing to a sitting position. This indicates the change in movement speed of an elderly person when transitioning from a standing to a sitting posture. This indicates the change in tilt angle when an elderly person transitions from a standing to a sitting posture. This represents the change in ground clearance when an elderly person transitions from a standing to a sitting position, given a set of known heart rate test data for that elderly person. for Based on the assessment, the monitoring data group Heart rate variability This exceeds the heart rate test feature data set. If all values ​​are present, it indicates that the user's heart rate is abnormal and there is a high risk of falling. The system will ask the user if they have fallen via mobile communication service. If no response is received from the user within 5 seconds, the system will contact the user's emergency contact via mobile communication service.

[0066] Example 2: In this experiment, the living room in a family's living space was selected as the experimental subject. The ambient brightness of the living room was 800 lumens, the floor flatness was 0.6 mm / ㎡, the humidity was 40%, and the storage density was 10%. The danger index of this living room was... The calculation process is as follows:

[0067] ;

[0068] In the formula, This represents a standard value used to measure ambient brightness. This indicates the weighting of the ratio of the standard value to the ambient brightness. This represents the standard value used to measure the flatness of the ground. This indicates the weight of the ratio of ground flatness to the standard value. This represents the standard value used to measure humidity. This indicates the weighting of the ratio of humidity to the standard value. This indicates the weight given by the storage density. , , and All are constants, and ,according to , , and The risk index of the living room is calculated by weighting. Approximately 0.65, danger zone The risk level was set to 0-0.5. Based on this assessment, the danger level of this living room is... It has exceeded the danger zone. This indicates that there are many safety hazards in the living room and a high risk of falling. The system will remind the user to pay attention to safety via mobile communication service. If no response is received from the user within 5 seconds, the system will remind the user's emergency contact via mobile communication service.

[0069] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A home fall alarm system based on mobile communication services, characterized in that: Includes a multi-dimensional data acquisition module and an intelligent analysis module; The multi-dimensional acquisition module consists of a test data unit, a sensor data unit, and an environmental data unit. The test data unit collects test datasets by connecting to a database via a network. The test datasets include test data of users' daily behavior. The sensor data unit collects sensor datasets by connecting to sensor devices via a network. The sensor datasets include sensor data of users' activity behavior. The environmental data unit collects environmental datasets by connecting to a camera via a network. The environmental datasets include monitoring data of the user's activity space. The intelligent analysis module consists of a daily assessment unit, a real-time assessment unit, an environmental assessment unit, and a fall alarm unit. The daily assessment unit analyzes the user's activity status in each posture based on the test dataset, whereby each posture generates a corresponding daily data set. and feature data group The real-time evaluation unit analyzes the user's activity status in real time based on the sensor dataset and generates corresponding monitoring data sets. The environmental assessment unit analyzes the safety hazards of each activity space based on the environmental dataset and generates a corresponding hazard index. ; The danger index The calculation process is as follows: Based on the environmental dataset, the monitoring data of the k-th activity space is extracted, and the ambient brightness of the k-th activity space is marked as... The flatness of the ground in the k-th activity space is marked as... The humidity of the kth activity space is marked as The storage density of the k-th activity space is marked as ; ， In the formula, This represents a standard value used to measure ambient brightness. This indicates the weighting of the ratio of the standard value to the ambient brightness. This represents the standard value used to measure the flatness of the ground. This indicates the weight of the ratio of ground flatness to the standard value. This represents the standard value used to measure humidity. This indicates the weighting of the ratio of humidity to the standard value. This indicates the weight given by the storage density. , , and All are constants, and , Indicates according to , , and The weights are used to calculate the danger index of the k-th activity space. ; The fall alarm unit is configured with a fixed range of danger zones. Combined with sensor datasets and daily data sets Feature data group Monitoring data group and risk index Assess the user's activity status and the risk of falls within the activity space, determine whether to activate mobile communication services, and execute corresponding inquiries and emergency measures; The sensor dataset shows that the user's heart rate during any activity is lower than the heart rate test daily data set. If all values ​​are present, it indicates an abnormal heart rate and a high risk of falling. The system will contact the user via mobile communication service to inquire if they are feeling unwell. If no response is received within 5 seconds, the system will contact the user's emergency contact via mobile communication service. (The monitoring data group...) Heart rate variability exceeds heart rate test characteristic data set If all values ​​are present, it indicates that the user's heart rate is abnormal and there is a high risk of falling. The user will be asked via mobile communication service if they have fallen. If no response is received from the user within 5 seconds, the user's emergency contact will be contacted via mobile communication service. The danger index Beyond the danger zone If the activity space is found to have many safety hazards and a high risk of falling, the user will be alerted to safety via mobile communication service. If no response is received from the user within 5 seconds, the user's emergency contact will be notified via mobile communication service.

2. The home fall alarm system based on mobile communication services according to claim 1, characterized in that: The test dataset includes several sets of standing test data, several sets of sitting test data, several sets of squatting test data, several sets of kneeling test data, and several sets of lying test data. Each set of test data includes heart rate, blood pressure, movement speed, tilt angle, and height off the ground.

3. The home fall alarm system based on mobile communication services according to claim 2, characterized in that: The expression for the sensing dataset is: , to This represents the sensor data from the user's first to the nth activity. The sensor data includes heart rate, blood pressure, movement speed, tilt angle, and height above the ground. s represents the time point at which the user's activity sensor data was acquired.

4. The home fall alarm system based on mobile communication services according to claim 3, characterized in that: The expression for the environmental dataset is: , to This represents the monitoring data for the first to the mth activity spaces. The monitoring data includes ambient brightness, ground flatness, humidity, and storage density. j represents the time point at which the monitoring data for the user's activity space is acquired.

5. The home fall alarm system based on mobile communication services according to claim 4, characterized in that: The daily data group The calculation process is as follows: Based on the test dataset, the heart rate in the standing posture test data is labeled as... , to This represents the heart rate during the first to the *a*th standing posture tests. The heart rate data from the sitting posture tests is labeled as follows: , to This represents the heart rate during the first to the bth sitting tests. The heart rate data from the squatting tests is labeled as... , to This represents the heart rate during the first to the cth squatting tests. The heart rate data from the kneeling test is labeled as... , to This represents the heart rate during the first to the dth kneeling tests. The heart rate data from the lying-down test is marked as... , to This represents the heart rate during the first to the eth lying position tests; ； In the formula, This represents the average heart rate of users during prolonged standing activities. This represents the average heart rate of users during sedentary daily activities. This represents the average heart rate of users during prolonged squatting activities. This indicates the average heart rate of users during prolonged kneeling activities. This represents the average heart rate of users during prolonged periods of lying down. This represents the user's active heart rate in standing, sitting, squatting, kneeling, and lying positions, which is the daily data set corresponding to the user's daily heart rate test.

6. The home fall alarm system based on mobile communication services according to claim 5, characterized in that: The feature data group The calculation process is as follows: ； In the formula, This indicates the user's highest heart rate during prolonged standing activities. This indicates the user's highest heart rate during sedentary daily activities. This represents the difference in the user's highest heart rate when changing from a standing to a sitting position. This indicates the user's highest heart rate during prolonged squatting activities. This represents the difference in the user's highest heart rate when changing from a standing to a squatting posture. This indicates the user's highest heart rate during prolonged kneeling activities. This represents the difference in the user's highest heart rate when changing from a standing to a kneeling position. This indicates the user's highest heart rate during prolonged lying down. This represents the difference in the user's highest heart rate when changing from a standing to a lying position. This indicates the lowest heart rate a user experiences during prolonged standing. This indicates the user's lowest heart rate during sedentary daily activities. This represents the minimum heart rate difference when a user changes from a standing to a sitting position. This indicates the lowest heart rate a user experiences during prolonged squatting activities. This represents the minimum heart rate difference when a user changes from a standing to a squatting position. This indicates the user's lowest heart rate during prolonged kneeling activities. This represents the lowest heart rate difference when a user changes from a standing to a kneeling position. This indicates the lowest heart rate a user experiences during prolonged periods of lying down. This represents the lowest heart rate difference when a user changes from a standing to a lying position. This represents the extreme changes in heart rate when a user changes from a standing position to a sitting, squatting, kneeling, or lying position; it is the feature data set corresponding to the user's daily heart rate test.

7. The home fall alarm system based on mobile communication services according to claim 6, characterized in that: The monitoring data group The calculation process is as follows: Based on the sensor dataset, extract sensor data for the user's i-th activity behavior and label the user's heart rate during the i-th activity behavior as... The user's blood pressure during the i-th activity is marked as The movement speed of the user's i-th activity is marked as The tilt angle of the user's i-th activity is marked as Mark the ground height of the user's i-th activity as ; Following the chronological order, sensor data for the user's (i+1)th activity behavior is extracted from the sensor dataset, where the user's (i)th activity behavior precedes the (i+1)th activity behavior. The heart rate of the user's (i+1)th activity behavior is then labeled as... Mark the user's blood pressure during the (i+1)th activity as Mark the movement speed of the user's (i+1)th activity as The tilt angle of the user's (i+1)th activity is marked as Mark the height above the ground of the user's (i+1)th activity as ; ； In the formula, This represents the change in heart rate when a user transitions from the i-th activity to the (i+1)-th activity. This represents the change in a user's blood pressure when they transition from the i-th activity to the (i+1)-th activity. This represents the change in a user's movement speed when transitioning from the i-th activity to the (i+1)-th activity. This represents the change in tilt angle when a user transitions from the i-th activity to the (i+1)-th activity. This represents the change in ground altitude when a user transitions from their i-th activity to their (i+1)-th activity. This represents the monitoring data group when a user changes from the i-th activity to the (i+1)-th activity.

Images