Old people physiological information emergency alarm system based on big data

Abstract

The invention relates to the technical field of medical instruments, and discloses an old people physiological information emergency alarm system based on big data, which comprises a data acquisition module, a data processing module, a signal data analysis module, a behavior characteristic analysis module, a physiological characteristic analysis module and an alarm module. The problems of incomplete data acquisition, insufficient signal interference correction capability, lagging behavior characteristic and physiological characteristic analysis, frequent false alarm and missing alarm of an alarm system and the like in the traditional technology are solved. Compared with the prior art, the system has the advantages that the comprehensiveness of data acquisition, the depth of analysis, the accuracy of alarm triggering and the like are remarkably improved. Particularly, by introducing a multi-dimensional screening mechanism of a data correction coefficient SQI and a physiological behavior judgment coefficient XWF, the detection capability of the system on abnormal conditions is optimized, the reliability and efficiency of health monitoring are remarkably improved, and therefore a powerful guarantee is provided for timely intervention of sudden health problems of old people.

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and particularly to an emergency alarm system for the physiological information of the elderly based on big data. Background Art

[0002] In the field of elderly health management, physiological monitoring systems based on big data have attracted wide attention. These systems can integrate various sensor technologies and data processing algorithms to real-time monitor key physiological parameters of the elderly, such as heart rate, blood oxygen, respiratory rate, etc., and can quickly issue an alarm when an abnormal situation occurs.

[0003] Although there are many intelligent devices on the market that can perform basic data collection at present, the existing systems still have significant deficiencies in aspects such as signal accuracy, multi-source data fusion, and accurate identification of abnormal situations. For example, improper use may lead to data distortion, and environmental interference is likely to affect the signal quality. Especially at night, the recognition accuracy of abnormal physiological states is relatively low. In addition, the existing alarm systems have the risk of false alarms and missed alarms, which may miss the best intervention opportunity.

[0004] Therefore, we propose an emergency alarm system for the physiological information of the elderly based on big data to solve the above-mentioned problems. Summary of the Invention

[0005] The purpose of the present invention is to provide an emergency alarm system for the physiological information of the elderly based on big data to solve the problems in the above-mentioned background art that improper use of intelligent devices may lead to data distortion, environmental interference is likely to affect the signal quality, especially at night, and the recognition accuracy of abnormal physiological states is relatively low.

[0006] To achieve the above purpose, the present invention provides the following technical solution: An emergency alarm system for the physiological information of the elderly based on big data, including a data acquisition module, a data processing module, a signal data analysis module, a behavior feature analysis module, a physiological feature analysis module, and an alarm module;

[0007] The data acquisition module is set in the mobile phone client, and is used to collect multi-source information data and input it into the data processing module. At the same time, it collects and sets the voice and work and rest time of the user, and sets alarm keywords;

[0008] The data processing module is set in the mobile phone client, and is used to preprocess the multi-source information data collected by the data acquisition module and classify it into a first data set, a second data set, and a third data set;

[0009] The signal data analysis module is set in the mobile phone client, and is used to analyze the first data set to generate a data correction coefficient SQI;

[0010] The behavior feature analysis module is used to analyze the second data set, so as to generate a physiological behavior determination coefficient XWF, a physiological intervention coefficient SLJ, and a response interval value XYS;

[0011] The physiological feature analysis module is used to generate an alarm reference coefficient according to a data correction coefficient SQI, a physiological intervention coefficient SLJ, a response interval value XYS, and a third data set;

[0012] The alarm module performs real-time alarm according to the alarm reference coefficient.

[0013] Preferably, the multi-source data collected by the data collection module includes: a skin contact signal index, an environmental light interference intensity, a real-time heart rate value, a real-time blood oxygen value, and a real-time breathing frequency value;

[0014] The data collection module obtains a skin contact signal index A, an environmental light interference intensity B, and a noise intensity C through a quality detector;

[0015] The data collection module obtains a movement amplitude value D and a movement time value E through an acceleration sensor;

[0016] The data collection module obtains a real-time heart rate value F, a real-time blood oxygen value G, and a real-time breathing frequency value H through a physiological sensor group.

[0017] Preferably, the first data set, the second data set, and the third data set generated by the data processing module are as follows:

[0018] The first data set includes a skin contact signal index A, an environmental light interference intensity B, and a noise intensity C;

[0019] The second data set includes a movement amplitude value D and a movement time value E;

[0020] The third data set includes a real-time heart rate value F, a real-time blood oxygen value G, and a real-time breathing frequency value H.

[0021] Preferably, the signal data analysis module includes a signal feature calculation unit and a signal feature comparison unit;

[0022] The signal feature calculation unit is used to calculate the first data set, so as to generate a signal analysis reference coefficient XHF and a data correction coefficient SQI;

[0023] The signal feature comparison unit is used to compare the signal analysis reference coefficient XHF with a preset signal analysis threshold Y1, and according to the comparison result, determine whether the data correction coefficient SQI needs to be used in subsequent calculations. The comparison results are as follows:

[0024] When XHF < Y1, it means that the data correction coefficient SQI is not required for subsequent calculations;

[0025] When XHF ≥ Y1, it means that the data correction coefficient SQI is required for subsequent calculations.

[0026] Preferably, the signal analysis reference coefficient XHF and the data correction coefficient SQI are respectively obtained by calculation through the following formulas:

[0027]

[0028] In the formula: a1 and a2 are weight values, A is the skin contact signal index, B is the ambient light interference intensity, C is the noise intensity, J, K, and L are respectively the correction smoothing values, and the values of a1, a2, J, K, and L are adjusted and set by the user.

[0029] Preferably, the behavior feature analysis module includes a behavior feature calculation unit and a behavior feature comparison unit;

[0030] The behavior feature calculation unit is used to perform integration calculations on the second data set, thereby generating a physiological behavior determination coefficient XWF;

[0031] The behavior feature comparison unit is used to compare the physiological behavior determination coefficient XWF with a preset physiological behavior determination threshold Y2, and based on the comparison result, determine whether the user's physiological behavior is normal. The specific comparison results are as follows:

[0032] When XWF ≤ Y2 × 60% or XWF ≥ Y2, it means that the user has a special physiological phenomenon, generates a response information prompt, and generates a response interval value XYS according to the response closing time and intervenes in subsequent calculations with the physiological intervention coefficient SLJ;

[0033] When Y2 × 60 < XWF < Y2, it means that the user does not have a special physiological phenomenon and does not need to use the physiological intervention coefficient SLJ.

[0034] Preferably, the physiological behavior determination coefficient XWF and the physiological intervention coefficient SLJ are respectively obtained by calculation through the following formulas:

[0035]

[0036] In the formula: c1 and c2 are weight values, D is the movement amplitude value, E is the movement time value, M and N are the correction smoothing values, and the values of c1, c2, M, and N are adjusted and set by the user.

[0037] Preferably, the physiological feature analysis module includes a physiological feature calculation unit and a physiological feature comparison unit;

[0038] The physiological feature calculation unit is used to integrate the third data set, the data correction coefficient SQI, the response interval value XYS, and the physiological intervention coefficient SLJ, so as to calculate and obtain the alarm reference coefficients. The alarm reference coefficients are divided into the first alarm reference coefficient TAR1, the second alarm reference coefficient TAR2, and the third alarm reference coefficient TAR3;

[0039] The physiological feature comparison unit is used to compare the first alarm reference coefficient TAR1, the second alarm reference coefficient TAR2, and the third alarm reference coefficient TAR3 with the preset alarm threshold Y3 respectively, so as to generate a comparison result, and judge whether an alarm needs to be made according to the comparison result. The specific comparison results are as follows:

[0040] When TAR1≤Y3, TAR2≤Y3, and TAR3≤Y3, it means that no alarm needs to be made currently;

[0041] When TAR1>Y3, TAR2>Y3, and TAR3>Y3, it means that an alarm needs to be made currently.

[0042] Preferably, the first alarm reference coefficient TAR1, the second alarm reference coefficient TAR2, and the third alarm reference coefficient TAR3 are respectively calculated and obtained through the following formulas:

[0043] TAR1 = d1×F + d2×G + d3×H;

[0044]

[0045] In the formula: d1, d2, and d3 are weight values, and the values of d1, d2, and d3 are adjusted and set by the user. log is the logarithmic function, e is the base function, XYS is the response interval value, SLJ is the physiological intervention coefficient, SQI is the data correction coefficient, F is the real-time heart rate value, G is the real-time blood oxygen value, and H is the real-time breathing frequency value.

[0046] Preferably, the specific alarm method of the alarm module is as follows:

[0047] Adjust the color of the LED screen of the smart device to red. At the same time, the smart device emits an alarm prompt sound and gives a sound prompt at a frequency of once per second, and dials the emergency contact number. At the same time, through the GPS function, it sends the location to the emergency contact. If it is not turned off within three seconds, the alarm prompt is upgraded. The color of the LED screen is increased by 15%, the volume of the alarm prompt sound is increased by 25%, and the alarm is given at a frequency of twice per second, and the emergency contact number is dialed. At the same time, through the GPS function carried by the smart device, the location is sent to the emergency contact. If it is not turned off within three seconds, the alarm prompt is upgraded again. The color of the LED screen is increased by 35%, the volume of the alarm prompt sound is increased by 50%, and the alarm is given at a frequency of five times per second, and the emergency contact number is dialed. At the same time, through the GPS function, the location is sent to the emergency contact;

[0048] By collecting the user's voice, when the smart device detects that the user triggers a preset keyword, the color of the LED screen is increased by 35%, the volume of the alarm prompt sound is increased by 50%, and the alarm is given at a frequency of five times per second, and the emergency contact number is dialed. At the same time, through the GPS function, the location is sent to the emergency contact;

[0049] By detecting the personal schedule set by the user, when the user shows abnormal behavior that violates the time, the emergency contact number is dialed. At the same time, through the GPS function, the location is sent to the emergency contact.

[0050] Compared with the prior art, the beneficial effects of the present invention are:

[0051] 1. Through the coordinated operation of multiple modules, this system overcomes the problems in the traditional technology such as incomplete data collection, insufficient signal interference correction ability, lag in the analysis of behavior characteristics and physiological characteristics, and frequent false alarms and missed alarms in the alarm system. Compared with the prior art, this system has achieved significant improvements in the comprehensiveness of data collection, the depth of analysis, and the accuracy of alarm triggering. In particular, by introducing the multi-dimensional screening mechanism of the data correction coefficient SQI and the physiological behavior determination coefficient XWF, the detection ability of the system for abnormal situations is optimized, and the reliability and efficiency of health monitoring are significantly improved, thus providing a strong guarantee for the timely intervention of the sudden health problems of the elderly.

[0052] 2. This system intelligently determines whether to use the physiological intervention coefficient SLJ, avoiding misjudgment and over-intervention. When the movement amplitude and movement time parameters are normal, the system will not intervene, thus avoiding unnecessary data processing. When the behavior is abnormal, the application of the physiological intervention coefficient SLJ can quickly adjust the data to ensure the accuracy of subsequent analysis. This intelligent judgment mechanism greatly improves the response efficiency and accuracy of the alarm system, ensures that the abnormal physiological behavior of the elderly is responded to in a timely manner, and thus enhances the stability of health monitoring.

[0053] 3. By introducing multiple alarm reference coefficients and combining the physiological intervention coefficient SLJ and the data correction coefficient SQI, the system can comprehensively evaluate the physiological health status of the elderly from multiple dimensions. This multi-dimensional evaluation method effectively reduces misjudgments caused by single factors and can more comprehensively reflect health risks. In addition, by correcting and smoothing the physiological data, the accuracy of data analysis is improved, ensuring that the alarm judgment is more in line with the actual physiological state. Brief Description of the Drawings

[0054] Figure 1 It is a schematic diagram of the overall three-dimensional structure of the present invention.

[0055] In the figure: 1. Data acquisition module; 2. Data processing module; 3. Signal data analysis module; 31. Signal feature calculation unit; 32. Signal feature comparison unit; 4. Behavior feature analysis module; 41. Behavior feature calculation unit; 42. Behavior feature comparison unit; 5. Physiological feature analysis module; 51. Physiological feature calculation unit; 52. Physiological feature comparison unit; 6. Alarm module. Detailed Embodiments

[0056] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0057] Embodiment 1: Please refer to Figure 1 , a physiological information emergency alarm system for the elderly based on big data, including a data acquisition module 1, a data processing module 2, a signal data analysis module 3, a behavior feature analysis module 4, a physiological feature analysis module 5, and an alarm module 6;

[0058] The data acquisition module 1 is used to collect multi-source information data and input it into the data processing module 2. At the same time, it collects and sets the voice and work and rest time of the user and sets alarm keywords;

[0059] The data processing module 2 is used to preprocess the multi-source information data collected by the data acquisition module 1 and classify it into a first data set, a second data set, and a third data set;

[0060] The signal data analysis module 3 is set in the mobile phone client and is used to analyze the first data set to generate a data correction coefficient SQI;

[0061] The behavioral feature analysis module 4 is set in the mobile client and is used to analyze the second data set to generate a physiological behavior determination coefficient XWF, a physiological intervention coefficient SLJ, and a response interval value XYS.

[0062] The physiological feature analysis module 5 is set in the mobile client and is used to generate an alarm reference coefficient according to a data correction coefficient SQI, a physiological intervention coefficient SLJ, a response interval value XYS, and a third data set.

[0063] The alarm module 6 performs real-time alarming according to the alarm reference coefficient.

[0064] In this embodiment: The data acquisition module 1, as the core basic module of the system, integrates a variety of sensor technologies to collect multi-source information data of the elderly in real time. It ensures the comprehensiveness, real-time nature, and accuracy of data acquisition, providing high-quality raw data support for subsequent analysis. Through high-precision data acquisition, this module effectively reduces the risk of data loss or acquisition error, laying a solid foundation for the overall accuracy of the system.

[0065] The data processing module 2 is responsible for preprocessing and classifying the multi-source information data collected by the data acquisition module 1. This module classifies the data into a first data set, a second data set, and a third data set through data cleaning, denoising, and formatting processes. This module significantly improves the effectiveness and consistency of the data, while optimizing the calculation efficiency of subsequent modules, providing efficient data support for achieving accurate analysis.

[0066] The signal data analysis module 3 deeply analyzes the first data set to calculate a signal analysis reference coefficient XHF and a data correction coefficient SQI. This module quantifies the signal quality, identifies and corrects signal anomalies caused by improper use or external interference, thereby improving the accuracy of subsequent calculations. By effectively reducing false alarms and missed alarms, this module provides technical guarantee for the overall reliability of the system.

[0067] The behavioral feature analysis module 4 analyzes the second data set to generate a physiological behavior determination coefficient XWF. By analyzing the movement amplitude value and movement time value of the elderly, this module can identify normal nighttime activities, such as turning over and adjusting sleeping positions, to avoid misjudging them as abnormal situations. In addition, when this module detects special behaviors, it can generate response prompt information and dynamically adjust response parameters, thereby improving the adaptability and sensitivity of the system to behavioral anomalies.

[0068] The physiological feature analysis module 5 generates an alarm reference coefficient by comprehensively analyzing the data correction coefficient SQI, the physiological behavior determination coefficient XWF, and the third data set. By deeply integrating multi-dimensional physiological data, this module can accurately distinguish normal physiological fluctuations from potential health risks, thereby improving the accuracy of alarms. This module realizes the efficient conversion from multi-source data to specific health statuses and is an important functional unit for the system to achieve comprehensive health monitoring.

[0069] Based on the alarm reference coefficient generated by the physiological feature analysis module 5, the alarm module 6 triggers the alarm mechanism in real time and ensures that abnormal situations can be quickly noticed by gradually increasing the alarm intensity. The multi-level alarm mechanism of this module effectively reduces the interference of false alarms and ensures timely response in case of sudden health conditions, providing strong support for the health and safety of the elderly.

[0070] Through the collaborative operation of multiple modules, this system overcomes problems in traditional technologies such as incomplete data collection, insufficient signal interference correction ability, lag in analyzing behavioral and physiological features, and frequent false alarms and missed alarms in the alarm system. Compared with existing technologies, this system has achieved significant improvements in terms of the comprehensiveness of data collection, the depth of analysis, and the accuracy of alarm triggering. In particular, by introducing the multi-dimensional screening mechanism of the data correction coefficient SQI and the physiological behavior determination coefficient XWF, the detection ability of the system for abnormal situations is optimized, and the reliability and efficiency of health monitoring are significantly improved, thus providing strong guarantee for the timely intervention of sudden health problems of the elderly.

[0071] Example 2: Please refer to Figure 1 , the multi-source data collected by the data collection module 1 includes: the skin contact signal index and the environmental light interference intensity, the real-time heart rate value, the real-time blood oxygen value, and the real-time breathing frequency value of the skin contact signal index and the environmental light interference intensity;

[0072] The data collection module 1 obtains the skin contact signal index A, the environmental light interference intensity B, and the noise intensity C through a quality detector.

[0073] The data collection module 1 obtains the movement amplitude value D and the movement time value E through an acceleration sensor.

[0074] The data collection module 1 obtains the real-time heart rate value F, the real-time blood oxygen value G, and the real-time breathing frequency value H through a physiological sensor group.

[0075] In this embodiment: The data acquisition module 1 collects multi-source data by integrating various sensor technologies. This comprehensive data acquisition method solves the problem in traditional technologies where the data acquisition source is single and the health status of the elderly cannot be comprehensively monitored. By integrating data from different sources, the system can more comprehensively capture the physiological state of the elderly, providing rich information support for subsequent data analysis, and thus improving the accuracy and reliability of health monitoring.

[0076] The data acquisition module 1 obtains the skin contact signal index A, the environmental light interference intensity B, and the noise intensity C through a quality detector, and can monitor the impact of external interference on the health monitoring signal in real time. This improvement effectively avoids false alarms or missed alarms caused by signal quality problems, ensuring the stability and accuracy of the data. By real-time monitoring and correcting signal interference, the system can maintain high-precision health monitoring data, providing a reliable guarantee for subsequent analysis and health assessment.

[0077] The data acquisition module 1 obtains the movement amplitude value D and the movement time value E through an acceleration sensor, enabling the system to accurately track the daily activity status of the elderly, especially their movement behavior at night. This function effectively avoids misjudgment caused by failure to monitor the movement state, and can more accurately distinguish normal behavior from abnormal behavior. By real-time monitoring the movement status of the elderly, the system can better identify potential health risks, improving the system's dynamic adaptability and health risk prediction ability.

[0078] The data acquisition module 1 obtains the heart rate value F, the blood oxygen value G, and the respiratory rate value H in real time through a physiological sensor group. These physiological data are crucial for the health assessment of the system. By comprehensively and real-time monitoring key physiological indicators, the system can quickly identify health abnormalities in the elderly, issue early warnings in a timely manner, and initiate intervention measures. This function greatly improves the sensitivity and response speed of the system to health risks, ensuring that alarms can be provided and effective measures can be taken in a timely manner when the elderly show abnormalities.

[0079] By setting up the data acquisition module 1, this system realizes accurate data input and comprehensive health tracking. The integration of multi-source data and the application of high-precision sensors not only improve the efficiency and accuracy of data acquisition, but also enhance the system's adaptability in complex environments, providing a solid foundation for subsequent data processing, analysis, and alarm.

[0080] Embodiment Three: Please refer to Figure 1 , the first data set, the second data set, and the third data set generated by the data processing module 2 are as follows:

[0081] The first data set includes the skin contact signal index A, the environmental light interference intensity B, and the noise intensity C;

[0082] The second data set includes the movement amplitude value D and the movement time value E;

[0083] The third data set includes the real-time heart rate value F, the real-time blood oxygen value G, and the real-time respiratory rate value H.

[0084] In this embodiment: The data processing module 2 preprocesses and classifies the collected multi-source data, and divides the data into three categories: the first data set, the second data set, and the third data set. This classification method can effectively classify different types of data and perform optimization processing, thereby improving the usability and processing efficiency of the data. The structured processing of the data makes the subsequent analysis process more efficient, and at the same time provides more accurate data input for each analysis module, significantly improving the processing accuracy and response speed of the system.

[0085] The data processing module 2 significantly reduces the interference of noise and irregular data on the system through data cleaning, denoising, and formatting. The optimized processing of the data makes the data of each data set more in line with the analysis requirements, thereby improving the efficiency and accuracy of data processing. Through efficient data classification and preprocessing, the system can quickly complete the processing of large-scale data, improving the response speed and accuracy of health monitoring.

[0086] The first data set includes the skin contact signal index A, the ambient light interference intensity B, and the noise intensity C, which are mainly used for signal quality assessment. By processing these data, the system can quickly identify and correct signal problems caused by improper use or external interference, thereby ensuring the stability and accuracy of subsequent health monitoring data. The second data set includes the movement amplitude value D and the movement time value E, focusing on the monitoring of the movement behavior of the elderly. By analyzing these data, the system can accurately track the status of the daily activities of the elderly and timely identify abnormal behaviors, significantly improving the recognition accuracy of abnormal behaviors. The third data set covers key physiological parameters such as the real-time heart rate value F, the blood oxygen value G, and the respiratory rate value H. By analyzing these physiological data, the system can comprehensively evaluate the health status of the elderly and trigger an early warning mechanism in a timely manner when potential health abnormalities are found.

[0087] By classifying the data into three dedicated data sets, the data processing module 2 provides a more detailed and accurate analysis basis for the system. Each data set corresponds to specific health monitoring requirements, thus avoiding data mixing and analysis errors. This modular design improves the adaptability and flexibility of the system, supports the rapid integration of new technologies and new sensors, and provides a good foundation for the future expansion and upgrade of the system.

[0088] The data processing module 2 classifies and refines the collected data, providing more accurate data input for the system, ensuring the efficiency and accuracy of subsequent analysis. The optimization of this module makes the health monitoring process more precise and provides solid data support for subsequent alarms through a clear data structure. Through this series of improvements, the system can achieve a more efficient and accurate health status assessment, greatly enhancing the reliability and response speed of the elderly health monitoring.

[0089] Embodiment 4: Please refer to Figure 1 , the signal data analysis module 3 includes a signal feature calculation unit 31 and a signal feature comparison unit 32;

[0090] The signal feature calculation unit 31 is used to calculate the first data set, thereby generating a signal analysis reference coefficient XHF and a data correction coefficient SQI;

[0091] The signal feature comparison unit 32 is used to compare the signal analysis reference coefficient XHF with a preset signal analysis threshold Y1, and based on the comparison result, determine whether the data correction coefficient SQI needs to be used in subsequent calculations. The comparison results are as follows:

[0092] When XHF < Y1, it means that the data correction coefficient SQI does not need to be used in subsequent calculations;

[0093] When XHF ≥ Y1, it means that the data correction coefficient SQI needs to be used in subsequent calculations.

[0094] The signal analysis reference coefficient XHF and the data correction coefficient SQI are respectively calculated and obtained through the following formulas:

[0095]

[0096] In the formula: a1 and a2 are weight values, A is the skin contact signal index, B is the environmental light interference intensity, C is the noise intensity, J, K, and L are respectively the correction smoothing values, and the values of a1, a2, J, K, and L are adjusted and set by the user.

[0097] In this embodiment: The signal data analysis module 3 is composed of a signal feature calculation unit 31 and a signal feature comparison unit 32, effectively improving the accuracy of signal data analysis.

[0098] The signal feature calculation unit 31 performs detailed calculations on the first data set to generate a signal analysis reference coefficient XHF and a data correction coefficient SQI, thus achieving a precise assessment of signal quality. Through this module, the system can promptly identify and correct signal anomalies, avoiding false alarms or missed alarms caused by improper use or external interference. The signal correction process is optimized through reasonable formulas and adjusted weights, ensuring the flexibility and efficiency of data correction, further enhancing the data reliability of the system. In the calculation formulas of the signal analysis reference coefficient XHF and the data correction coefficient SQI, data can be effectively corrected through weighted calculation to improve signal quality. The correction formula uses multiple adjustable weight parameters and correction smoothing values, allowing users to adjust these parameters according to the actual environment and requirements to achieve the best signal correction effect. This flexible correction mechanism enables the system to adapt to different usage scenarios, thereby improving the accuracy of health monitoring and the customization ability of the system.

[0099] The signal feature comparison unit 32 compares the generated signal analysis reference coefficient XHF with a preset signal analysis threshold Y1 to automatically determine whether to use the data correction coefficient SQI. This mechanism decides whether to perform data correction based on the comparison result of signal quality, avoiding overprocessing or ignoring correction. When the signal analysis reference coefficient XHF is lower than the preset threshold Y1, the system determines that the signal quality is good and does not perform correction; when XHF reaches or exceeds Y1, the system then enables the correction coefficient to perform data correction to ensure the accuracy of subsequent analysis. This mechanism significantly improves the adaptability of the system to signal quality changes and enhances the real-time performance and accuracy of health monitoring.

[0100] The signal data analysis module 3 significantly improves the system's ability to handle signal interference through precise signal quality analysis and an automatic correction mechanism. The flexible calculation formula and intelligent decision-making mechanism in the module not only improve the system's adaptability but also reduce false alarms and missed alarms caused by signal problems. This improvement greatly enhances the real-time performance and accuracy of the elderly health monitoring, provides more reliable data support for the alarm mechanism, and thus improves the response speed and accuracy of the overall system.

[0101] Example Five: Please refer to Figure 1 , the behavior feature analysis module 4 includes a behavior feature calculation unit 41 and a behavior feature comparison unit 42;

[0102] The behavior feature calculation unit 41 is used to integrate and calculate the second data set to generate a physiological behavior determination coefficient XWF;

[0103] The behavior feature comparison unit 42 is used to compare the physiological behavior determination coefficient XWF with a preset physiological behavior determination threshold Y2, and based on the comparison result, determine whether the user's physiological behavior is normal. The specific comparison results are as follows:

[0104] When XWF ≤ Y2 × 60% or XWF ≥ Y2, it represents that the user has a special physiological phenomenon, generates a response information prompt, and generates a response interval value XYS according to the response closing time and intervenes in subsequent calculations with the physiological intervention coefficient SLJ;

[0105] When Y2 × 60 < XWF < Y2, it represents that the user does not have a special physiological phenomenon and does not need to use the physiological intervention coefficient SLJ.

[0106] The physiological behavior determination coefficient XWF and the physiological intervention coefficient SLJ are respectively calculated and obtained through the following formulas:

[0107]

[0108] In the formulas: c1 and c2 are weight values, D is the movement amplitude value, E is the movement time value, M and N are correction smoothing values, and the values of c1, c2, M, and N are adjusted and set by the user.

[0109] In this embodiment: The behavior feature analysis module 4 works in cooperation with the behavior feature calculation unit 41 and the behavior feature comparison unit 42, further improving the accurate analysis of the health status of the elderly. The behavior feature calculation unit 41 integrates and calculates the second data set to generate the physiological behavior determination coefficient XWF, thereby helping the system accurately evaluate the physiological behavior characteristics of the elderly based on key indicators such as movement amplitude and movement time. This module can effectively identify whether the user has a special physiological phenomenon, overcoming the limitation that traditional health monitoring systems are difficult to detect abnormal physiological behaviors in a timely manner.

[0110] The behavior feature comparison unit 42 compares the physiological behavior determination coefficient XWF with the preset physiological behavior determination threshold Y2 to intelligently determine whether the user has a special physiological phenomenon. Based on the comparison result, when the user's behavior exceeds the predetermined range, it automatically generates a response information prompt, and generates a response interval value XYS by calculating the closing time, further triggering the physiological intervention coefficient SLJ for subsequent calculations, so as to ensure that abnormal behaviors are intervened in a timely manner. When the signal quality is within the normal range, the system avoids over-intervention, improving the overall monitoring accuracy and intelligence level.

[0111] The calculation formulas for the physiological behavior determination coefficient XWF and the physiological intervention coefficient SLJ include the movement amplitude value D, the movement time value E, and the correction smoothing value. The formulas accurately determine the movement behavior characteristics of the elderly through weighted calculation. This flexible calculation formula allows users to adjust the weights and correction parameters according to different environmental requirements to optimize the results of physiological behavior analysis. This mechanism enhances the customization ability of the system, enabling it to accurately evaluate the physiological behavior of the elderly in different scenarios and improving the accuracy of monitoring.

[0112] The behavior characteristic analysis module 4 supports flexible parameter adjustment and dynamic monitoring, enabling it to provide personalized health assessments for the elderly in different environments, ensuring that the system can still accurately reflect their physiological behavior characteristics in various usage scenarios, thereby enhancing the adaptability of the system and enabling it to adjust the monitoring strategy in real time to maximize the health management needs of the elderly.

[0113] The system intelligently determines whether to use the physiological intervention coefficient SLJ, avoiding misjudgment and over-intervention. When the movement amplitude and movement time parameters are normal, the system will not intervene, thus avoiding unnecessary data processing. When the behavior is abnormal, the application of the physiological intervention coefficient SLJ can quickly adjust the data to ensure the accuracy of subsequent analysis. This intelligent judgment mechanism greatly improves the response efficiency and accuracy of the alarm system, ensuring that abnormal physiological behaviors of the elderly are promptly responded to, thereby enhancing the stability of health monitoring.

[0114] Example Six: Please refer to Figure 1 , the physiological characteristic analysis module 5 includes a physiological characteristic calculation unit 51 and a physiological characteristic comparison unit 52;

[0115] The physiological characteristic calculation unit 51 is used to integrate the third data set, the data correction coefficient SQI, the response interval value XYS, and the physiological intervention coefficient SLJ to calculate and obtain the alarm reference coefficient. The alarm reference coefficient is divided into the first alarm reference coefficient TAR1, the second alarm reference coefficient TAR2, and the third alarm reference coefficient TAR3;

[0116] The physiological characteristic comparison unit 52 is used to compare the first alarm reference coefficient TAR1, the second alarm reference coefficient TAR2, and the third alarm reference coefficient TAR3 with the preset alarm threshold Y3 respectively to generate a comparison result, and determine whether to give an alarm according to the comparison result. The specific comparison results are as follows:

[0117] When TAR1 ≤ Y3, TAR2 ≤ Y3, and TAR3 ≤ Y3, it means that no alarm is required at present;

[0118] When TAR1 > Y3, TAR2 > Y3, and TAR3 > Y3, it indicates that an alarm needs to be triggered currently.

[0119] The first alarm reference coefficient TAR1, the second alarm reference coefficient TAR2, and the third alarm reference coefficient TAR3 are respectively obtained by calculating through the following formulas:

[0120] TAR1 = d1 × F + d2 × G + d3 × H;

[0121]

[0122]

[0123] In the formulas: d1, d2, and d3 are weight values, and the values of d1, d2, and d3 are adjusted and set by the user. log is the logarithmic function, e is the base function, XYS is the response interval value, SLJ is the physiological intervention coefficient, SQI is the data correction coefficient, F is the real-time heart rate value, G is the real-time blood oxygen value, and H is the real-time respiratory rate value.

[0124] In this embodiment: Through the collaborative action of the physiological feature calculation unit 51 and the physiological feature comparison unit 52 in the physiological feature analysis module 5, the accuracy of the alarm system is significantly improved. The physiological feature calculation unit 51 calculates the alarm reference coefficient by integrating the third data set, the data correction coefficient SQI, the response interval value XYS, and the physiological intervention coefficient SLJ. Through the meticulous calculation of these coefficients, the system can comprehensively evaluate the physiological condition of the elderly, thereby generating multiple alarm reference coefficients. This module can comprehensively consider key physiological parameters such as heart rate, blood oxygen, and respiratory rate and influencing factors to ensure the accuracy and timeliness of the alarm mechanism.

[0125] The physiological feature comparison unit 52 automatically determines whether to send an alarm signal by comparing the calculated alarm reference coefficient with the preset alarm threshold Y3. This mechanism determines whether to trigger the alarm based on the comparison result, ensuring that the alarm is only triggered when the physiological state is abnormal and exceeds the preset threshold. By comprehensively considering the first, second, and third alarm reference coefficients TAR3, the system can more meticulously evaluate the health status, avoid false alarms caused by minor fluctuations, and effectively capture real health risks. This intelligent judgment mechanism improves the reliability and real-time performance of the alarm system.

[0126] The calculation formula of the alarm reference coefficient forms three alarm reference coefficients through the weighted combination of key physiological parameters such as the real-time heart rate value F, blood oxygen value G, and respiratory rate value H, combined with variables such as the data correction coefficient SQI, physiological intervention coefficient SLJ, and response interval value XYS. By adjusting the weight values, users can adjust these coefficients according to actual needs and the environment, making the alarm system more flexible and accurate. This flexible parameter setting enhances the customization and adaptability of the system and can provide more accurate alarm judgments according to different usage scenarios and individual differences of the elderly.

[0127] By introducing multiple alarm reference coefficients and combining the physiological intervention coefficient SLJ and the data correction coefficient SQI, the system can comprehensively evaluate the physiological health status of the elderly from multiple dimensions. This multi-dimensional evaluation method effectively reduces misjudgments caused by single factors and can more comprehensively reflect health risks. In addition, by correcting and smoothing the physiological data, the accuracy of data analysis is improved, ensuring that the alarm judgment is more in line with the actual physiological state.

[0128] Embodiment Seven: Please refer to Figure 1 , the specific alarm method of the alarm module 6 is as follows:

[0129] Adjust the color of the LED screen of the smart device to red, and at the same time send an alarm prompt sound, and perform sound prompts at a frequency of once per second, and call the emergency contact number. At the same time, through the GPS function, send the location to the emergency contact. If it is not closed within three seconds, upgrade the alarm prompt, increase the color of the LED screen by 15%, increase the volume of the alarm prompt sound by 25%, and perform alarms at a frequency of twice per second, and call the emergency contact number. At the same time, through the GPS function of the smart device, send the location to the emergency contact. If it is not closed within three seconds, upgrade the alarm prompt again, increase the color of the LED screen by 35%, increase the volume of the alarm prompt sound by 50%, and perform alarms at a frequency of five times per second, and call the emergency contact number. At the same time, through the GPS function, send the location to the emergency contact;

[0130] By collecting the user's voice, when the smart device detects that the user triggers a pre-set keyword, increase the color of the LED screen by 35%, increase the volume of the alarm prompt sound by 50%, and perform alarms at a frequency of five times per second, and call the emergency contact number. At the same time, through the GPS function, send the location to the emergency contact;

[0131] By detecting the user's set personal schedule, when the user shows abnormal behavior against the time, call the emergency contact number. At the same time, through the GPS function, send the location to the emergency contact.

[0132] In this embodiment: The alarm module 6 adopts a hierarchical alarm mechanism. According to the duration of the alarm and the situation of not being turned off, the intensity of the alarm prompt is gradually increased. This multi-level alarm design can adjust the alarm intensity in a timely manner according to the reaction of the elderly, ensuring that a more obvious reminder can be obtained when the elderly fail to respond in time. Through this design, the alarm system has higher intelligence and adaptability, ensuring that the alarm effect can be maximized in different situations, and avoiding missing the opportunity for emergency response due to the elderly failing to notice the initial alarm in time.

[0133] The alarm module 6 realizes the gradual enhancement of the alarm prompt by gradually adjusting the brightness of the LED screen and the intensity of the alarm volume by 15%, 25%, and 50% respectively. This mechanism can gradually increase the alarm intensity according to the duration of the alarm and the situation of not being turned off, so as to attract the attention of the elderly to the greatest extent and provide clear and easy-to-perceive alarm prompts. Especially considering that the elderly may have reduced vision or hearing, this adjustable alarm prompt scheme effectively makes up for these sensory deficiencies, thus improving the response rate of the alarm.

[0134] The alarm module 6 makes the alarm prompt more flexible and coercive by adjusting the alarm frequency to adapt to the reaction ability of the elderly. When the elderly do not turn off the alarm within a short period of time, the system will automatically increase the alarm frequency to make the alarm prompt more urgent and attract attention. Through this real-time adjustment of the frequency, the system can promptly arouse the alertness of the elderly in the face of the elderly's slow reaction or environmental noise, preventing the alarm information from being missed.

[0135] The multi-level alarm mechanism ensures that the alarm intensity gradually increases in the case where the alarm fails to be turned off in time, ensuring that the elderly can notice the alarm prompt in time. This design is especially suitable for the situation of the elderly with poor physical conditions or slow reactions, significantly improving the response speed in case of emergency, thereby enhancing the overall system's ability to respond to emergencies.

[0136] The alarm module 6 significantly improves the adaptability and accuracy of the system through its hierarchical alarm mechanism and dynamic adjustment of the alarm prompt. Whether it is the elderly with reduced vision or hearing, or those with slow reactions, the multi-level alarm scheme of this system can ensure that attention is attracted in time and the reaction efficiency is improved by enhancing the alarm prompt. This intelligent alarm design not only optimizes the health monitoring experience of the elderly, but also improves the response efficiency of the system to emergencies, provides strong support for the emergency health monitoring of the elderly, and further enhances the stability and reliability of the alarm system.

[0137] The content not described in detail in this specification belongs to the prior art well-known to those skilled in the art.

[0138] Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An emergency alarm system for physiological information of the elderly based on big data, characterized by: It includes a data acquisition module (1), a data processing module (2), a signal data analysis module (3), a behavioral feature analysis module (4), a physiological feature analysis module (5), and an alarm module (6); The data acquisition module (1) is used to collect multi-source information data and input it into the data processing module (2). At the same time, it collects and sets the user's voice and schedule, and sets alarm keywords; The data processing module (2) is used to preprocess the multi-source information data collected by the data acquisition module (1) and classify it into a first data set, a second data set, and a third data set; The signal data analysis module (3) is set in the mobile client and is used to analyze the first data set to generate a data correction coefficient SQI; The behavioral feature analysis module (4) is set in the mobile client and is used to analyze the second data set to generate a physiological behavior determination coefficient XWF, a physiological intervention coefficient SLJ, and a response interval value XYS; The physiological feature analysis module (5) is set in the mobile client and is used to generate an alarm reference coefficient according to the data correction coefficient SQI, the physiological intervention coefficient SLJ, the response interval value XYS, and the third data set; The alarm module (6) performs real-time alarm according to the alarm reference coefficient.

2. According to claim 1, the physiological information emergency alarm system for the elderly based on big data is characterized by: The multi-source data collected by the data acquisition module (1) includes: skin contact signal index and ambient light interference intensity, real-time heart rate value, real-time blood oxygen value, and real-time breathing frequency value of skin contact signal index and ambient light interference intensity; The data acquisition module (1) obtains the skin contact signal index A, the ambient light interference intensity B, and the noise intensity C through a quality detector; The data acquisition module (1) obtains the motion amplitude value D and the motion time value E through an acceleration sensor; The data acquisition module (1) obtains the real-time heart rate value F, the real-time blood oxygen value G, and the real-time breathing frequency value H through a physiological sensor group.

3. According to claim 1, the physiological information emergency alarm system for the elderly based on big data is characterized by: The first data set, the second data set, and the third data set generated by the data processing module (2) are as follows: The first data set includes the skin contact signal index A, the ambient light interference intensity B, and the noise intensity C; The second data set includes the motion amplitude value D and the motion time value E; The third data set includes the real-time heart rate value F, the real-time blood oxygen value G, and the real-time breathing frequency value H.

4. According to the big data-based emergency alarm system for physiological information of the elderly according to claim 1, it is characterized by: The signal data analysis module (3) includes a signal feature calculation unit (31) and a signal feature comparison unit (32); The signal feature calculation unit (31) is used to calculate the first data set to generate a signal analysis reference coefficient XHF and a data correction coefficient SQI; The signal feature comparison unit (32) is used to compare the signal analysis reference coefficient XHF with a preset signal analysis threshold Y1, and according to the comparison result, judge whether the data correction coefficient SQI needs to be used in subsequent calculations. The comparison results are as follows: When XHF < Y1, it means that the data correction coefficient SQI does not need to be used in subsequent calculations; When XHF ≥ Y1, it means that the data correction coefficient SQI needs to be used in subsequent calculations.

5. The big data-based emergency alarm system for physiological information of the elderly according to claim 4 is characterized by: The signal analysis reference coefficient XHF and the data correction coefficient SQI are respectively calculated and obtained through the following formulas: Where: a1 and a2 are weight values, A is the skin contact signal index, B is the ambient light interference intensity, C is the noise intensity, J, K, and L are respectively the correction smoothing values, and the values of a1, a2, J, K, and L are adjusted and set by the user.

6. The big data-based emergency alarm system for physiological information of the elderly according to claim 1 is characterized by: The behavior feature analysis module (4) includes a behavior feature calculation unit (41) and a behavior feature comparison unit (42); The behavior feature calculation unit (41) is used to integrate and calculate the second data set, so as to generate a physiological behavior determination coefficient XWF; The behavior feature comparison unit (42) is used to compare the physiological behavior determination coefficient XWF with a preset physiological behavior determination threshold Y2, and based on the comparison result, determine whether the user has normal physiological behavior. The specific comparison results are as follows: When XWF ≤ Y2 × 60% or XWF ≥ Y2, it represents that the user has a special physiological phenomenon, generates a response information prompt, and generates a response interval value XYS according to the response closing time and intervenes in subsequent calculations with the physiological intervention coefficient SLJ; When Y2 × 60 < XWF < Y2, it represents that the user does not have a special physiological phenomenon and does not need to use the physiological intervention coefficient SLJ.

7. The big data-based emergency alarm system for physiological information of the elderly according to claim 6 is characterized by: The physiological behavior determination coefficient XWF and the physiological intervention coefficient SLJ are respectively calculated and obtained through the following formulas: In the formula: c1 and c2 are weight values, D is the movement amplitude value, E is the movement time value, M and N are the correction smoothing values, and the values of c1, c2, M, and N are adjusted and set by the user.

8. The big data-based emergency alarm system for physiological information of the elderly according to claim 1 is characterized by: The physiological feature analysis module (5) includes a physiological feature calculation unit (51) and a physiological feature comparison unit (52); The physiological feature calculation unit (51) is used to integrate the third data set, the data correction coefficient SQI, the response interval value XYS, and the physiological intervention coefficient SLJ, so as to calculate and obtain an alarm reference coefficient. The alarm reference coefficient is divided into a first alarm reference coefficient TAR1, a second alarm reference coefficient TAR2, and a third alarm reference coefficient TAR3; The physiological feature comparison unit (52) is used to compare the first alarm reference coefficient TAR1, the second alarm reference coefficient TAR2, and the third alarm reference coefficient TAR3 with a preset alarm threshold Y3 respectively, so as to generate a comparison result, and determine whether an alarm needs to be made according to the comparison result. The specific comparison results are as follows: When TAR1 ≤ Y3, TAR2 ≤ Y3, and TAR3 ≤ Y3, it represents that no alarm needs to be made currently; When TAR1 > Y3, TAR2 > Y3, and TAR3 > Y3, it represents that an alarm needs to be made currently.

9. The big data-based emergency alarm system for physiological information of the elderly according to claim 8 is characterized by: The first alarm reference coefficient TAR1, the second alarm reference coefficient TAR2, and the third alarm reference coefficient TAR3 are respectively calculated and obtained through the following formulas: TAR1 = d1 × F + d2 × G + d3 × H; In the formula: d1, d2 and d3 are weight values, and the values ​​of d1, d2 and d3 are adjusted and set by the user, log is the logarithmic function, e is the base function, XYS is the response interval value, SLJ is the physiological intervention coefficient, SQI is the data correction coefficient, F is the real-time heart rate value, G is the real-time blood oxygen value, and H is the real-time respiratory rate value.

10. The big data-based emergency alarm system for physiological information of the elderly according to claim 1 is characterized by: The specific alarm mode of the alarm module (6) is as follows: Adjust the color of the smart device LED screen to red, and the smart device sends an alarm tone, and sounds a sound prompt at a frequency of once per second, and dials the emergency contact number, and sends the location to the emergency contact through the GPS function. If it is not closed within three seconds, the alarm prompt will be upgraded, the color of the LED screen will be increased by 15%, the volume of the alarm prompt tone will be increased by 25%, and the alarm will be sounded at a frequency of twice per second, and the emergency contact number will be dialed. At the same time, the location will be sent to the emergency contact through the GPS function on the smart device. If it is not closed within three seconds, the alarm prompt will be upgraded again, the color of the LED screen will be increased by 35%, the volume of the alarm prompt tone will be increased by 50%, and the alarm will be sounded at a frequency of five times per second, and the emergency contact number will be dialed, and the location will be sent to the emergency contact through the GPS function; By collecting the user's voice, when the smart device detects that the user triggers the pre-set keyword, the LED screen color will be increased by 35%, the volume of the alarm tone will be increased by 50%, and the alarm will be sounded at a frequency of five times per second, and the emergency contact will be dialed. At the same time, the location will be sent to the emergency contact through the GPS function; By detecting the personal schedule set by the user, when the user exhibits abnormal behavior that violates the schedule, the emergency contact number will be dialed and the location will be sent to the emergency contact through the GPS function.

Images