State monitoring terminal

Abstract

The invention relates to the technical field of health monitoring, and particularly discloses a state monitoring terminal which comprises a wearing sensing module used for collecting physiological data of a user in real time; the mattress sensing module is used for collecting sleep data; the equipment sensing module is used for collecting intelligent equipment use data of a user; the preprocessing module is used for performing timestamp alignment on the collected physiological data, sleep data and intelligent equipment use data; the information pre-input module is used for acquiring basic information and disease information of a user; the state recognition module is used for analyzing the preprocessed sleep data, physiological data and intelligent equipment use data and outputting a state analysis result in combination with basic disease information of the user; the state analysis result comprises low risk, medium risk and high risk; and the feedback module is used for generating graded reminding according to the risk grade of the state analysis result. By adopting the technical scheme of the invention, the user can carry out earlier and more accurate identification and early warning on the sub-health state.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of health monitoring, in particular to a state monitoring terminal. BACKGROUND

[0002] The existing health monitoring equipment mainly adopts wearable devices, such as mainstream smart watch products, which focus on basic physiological index monitoring (such as heart rate, blood oxygen saturation, sleep stage, etc.) and regular activity tracking (such as step count, calorie consumption, motion pattern recognition, etc.).

[0003] However, such devices have obvious limitations in evaluating complex sub-health states such as depression tendency and early cognitive impairment. For mental health problems such as depression, the early symptoms often manifest as subtle changes in behavior patterns, such as social avoidance and loss of interest in daily activities. For cognitive impairment, early signs may be manifested in the decline of interaction ability with the surrounding environment. The existing wearable devices are completely unable to capture these key, non-physiological behavior data, thus missing the window of early risk detection

[0004] Therefore, there is an urgent need for a multi-dimensional health monitoring solution to achieve earlier and more accurate identification and early warning of sub-health states. SUMMARY

[0005] The present application provides a state monitoring terminal, which can identify and early warn sub-health states of users more accurately and earlier.

[0006] To solve the above technical problems, the present application provides the following technical solutions:

[0007] A state monitoring terminal, comprising:

[0008] A wearable perception module for real-time collection of physiological data of a user;

[0009] A mattress perception module for collection of sleep data;

[0010] A device perception module for collection of smart device usage data of the user, and analysis of historical usage patterns of the user according to historical smart device usage data;

[0011] A preprocessing module for time stamp alignment of the collected physiological data, sleep data and smart device usage data;

[0012] An information pre-input module for acquisition of basic information and disease information of the user;

[0013] The state recognition module is configured to analyze the preprocessed sleep data, physiological data, and smart device usage data, combine the basic disease information of the user, and output a state analysis result; the state analysis result includes low risk, medium risk, and high risk.

[0014] The feedback module is configured to generate a graded reminder according to the risk level of the state analysis result.

[0015] Further, the physiological data includes heart rate, body temperature, activity data, and blood oxygen saturation.

[0016] The sleep data includes sleep-in time, wake-up time, deep sleep time period, light sleep time period, rapid eye movement time period, and wakeful time period.

[0017] Further, the disease information includes depression and cognitive impairment.

[0018] Further, when the basic disease is depression, the state recognition module is configured to obtain sleep data, and if the user has a partner, analyze the sleep data of the user and the user's partner to determine the reference sleep quality of the user; if the user has no partner, determine the reference sleep quality of the user according to the sleep data of the user.

[0019] The state recognition module is further configured to obtain activity data, determine whether the user is in a stationary state and has been in the stationary state for more than a first preset time, and if so, obtain current smart device usage data, determine whether the user is currently using a smart device, and if not, determine whether the current time is a historical usage time period according to the historical usage rule of the user, and if not, determine whether more than a second preset time has elapsed.

[0020] If it is a historical usage time period or more than a second preset time has elapsed, the weather information of the current time is further obtained, and the depression state analysis result of the user is determined according to the weather information.

[0021] Further, the weather information includes sunny and non-sunny, and if it is sunny, the risk level is medium risk, and if it is non-sunny, the risk level is high risk.

[0022] Further, when the basic disease is cognitive impairment, the state recognition module is configured to calculate a physiological stability score according to the physiological data.

[0023] The state recognition module is further configured to compare the smart device usage data of the user on the current day with the historical usage rule, determine whether the decrease exceeds a preset proportion, and if so, determine that the device interaction behavior of the user is abnormal.

[0024] The state recognition module is further configured to obtain a cognitive impairment state analysis result according to the physiological stability score and the abnormal device interaction behavior.

[0025] Further, when the physiological stability score is low and the device interaction behavior is abnormal, the cognitive impairment risk of the user is determined as high risk; if only the physiological stability score is low or the device interaction behavior is abnormal, it is determined as medium risk.

[0026] Further, the feedback module is configured to send corresponding graded reminder information to the user when the risk is medium, and send corresponding graded reminder information to the emergency contact person when the risk is high.

[0027] The present scheme constructs a multi-dimensional and multi-data source user state monitoring system by integrating the wearable perception module, the mattress perception module and the device perception module, significantly improving the accuracy and reliability of sub-health state monitoring. Compared with the monitoring method relying only on a single device such as a smart bracelet, the present scheme deeply integrates and cross- verifies the user's physiological indicators, sleep quality and daily device usage habits, which can more comprehensively depict the user's real life state and effectively avoid the one-sidedness and misjudgment that may be caused by a single data source.

[0028] In the evaluation of depression risk, the system not only analyzes the user's activity amount and sleep data, but also introduces the comparison with the sleep quality of the partner, the deviation from the historical device usage habits and the environmental factors such as weather as the basis for judgment, so that the system can distinguish between normal rest state and abnormal social withdrawal or loss of interest behavior; for the monitoring of cognitive impairment, the present scheme combines the subtle changes in physiological stability that are not easy to detect with abnormal functional device interaction behavior, capturing early signals of cognitive decline from both physiological and behavioral aspects.

[0029] In summary, the present scheme can monitor users with sub-health states such as depression and cognitive impairment in real time, output graded risk assessment results, and provide timely and accurate health reminders for users and their families, effectively making up for the shortcomings of existing single monitoring devices in complex sub-health state evaluation. BRIEF DESCRIPTION OF DRAWINGS

[0030] Figure 1 Fig. 1 is a logic block diagram of a state monitoring terminal embodiment one. DETAILED DESCRIPTION

[0031] The following will be further described in detail through specific embodiments:

[0032] Embodiment one

[0033] As shown in Figure 1 , a state monitoring terminal of the present embodiment comprises a wearable perception module, a mattress perception module, a device perception module, a preprocessing module, an information pre-input module, a state recognition module and a feedback module.

[0034] The wearable sensing module, in this embodiment, adopts a smart watch, is used for collecting physiological data of a user in real time through a built-in sensor. The physiological data includes heart rate, body surface temperature, activity data, blood oxygen saturation, etc.

[0035] The bed mat sensing module is used for collecting sleep data. The sleep data includes sleep-in time, wake-up time, deep sleep time period, light sleep time period, rapid eye movement time period and wakeful time period. In this embodiment, an existing sleep monitoring bed mat is adopted, which avoids the problem of not wearing when the user sleeps compared with monitoring sleep by using a smart watch, and can realize monitoring of two persons.

[0036] The device sensing module is used for collecting smart device usage data of a user, and also analyzes historical usage rules of the user according to historical smart device usage data. The smart device includes a mobile phone, a tablet computer and a television. In this embodiment, the smart device usage data refers to a screen-on time period, for example, a usage time period after the mobile phone is unlocked, a time period played after the television is turned on, etc.

[0037] In the analysis, the smart device usage data of the user collected for continuous days (for example, 14 days) is segmented in units of hours for 24 hours of each day, the average screen-on time length and the usage frequency of the user in each time period are counted, the device usage habit baseline of the user in different time periods is formed, and the historical usage rules are used as the baseline.

[0038] The preprocessing module is used for time stamp alignment of the collected multi-source heterogeneous physiological data, sleep data and smart device usage data.

[0039] The information pre-input module is used for obtaining basic information and disease information of a user. The basic information includes name, age, gender, marital status, emergency contact information, etc. The disease information includes depression and cognitive impairment, etc.

[0040] The state recognition module is used for analyzing the preprocessed sleep data, physiological data and smart device usage data, combining the basic disease information of the user, and outputting a state analysis result. The state analysis result includes low risk, medium risk and high risk.

[0041] Specifically, when the underlying disease is depression, the state recognition module is configured to obtain sleep data, and if the user has a partner, the sleep data of the user and the user's partner are analyzed simultaneously to determine the reference sleep quality of the user; if the user has no partner, the reference sleep quality of the user is determined according to the sleep data of the user; the level of the reference sleep quality includes excellent, medium and poor. In this embodiment, when there is no partner, the total sleep time, sleep efficiency (total sleep time / (wake-up time-sleep time), deep sleep time proportion and night wake-up times are calculated by a preset algorithm to obtain the reference sleep quality level; for example, if the total sleep time is greater than 7 hours, the sleep efficiency is higher than 85%, the deep sleep time proportion is more than 20% and the night wake-up times are less than 2, the reference sleep quality is excellent; otherwise, if multiple indicators are lower than the preset health threshold, the reference sleep quality is poor. When there is a partner, the sleep quality levels of the user and the partner are evaluated by the above-mentioned preset algorithm, if the sleep quality level of the user is lower than that of the partner and the sleep quality of the user is poor, the level of the reference sleep quality of the user is poor, if the sleep quality level of the user and the sleep quality level of the partner are both poor, and the sleep efficiency and deep sleep time proportion of the user are significantly lower than the corresponding indicators of the partner (in this embodiment, more than 20% lower than the indicators of the partner), the reference sleep quality of the user is finally determined to be poor. The reference sleep quality of this embodiment is used as a parameter for recognizing the symptoms of depression, and is not the actual sleep quality of the user.

[0042] The state recognition module is configured to obtain activity data, and determine whether the user is in a stationary state and exceeds a first preset time according to the activity data; if yes, obtain the current smart device usage data, and determine whether the smart device is currently being used; if not, determine whether it is a historical use period according to the historical use rule of the user; if not, determine whether the second preset time is exceeded; the first preset time is 5-10 minutes, and the second preset time is 15-30 minutes.

[0043] If it is a historical use period or exceeds the second preset time, the current weather information is also obtained, and the current depression state analysis result of the user is determined according to the weather information; the weather information includes sunny and non-sunny. If it is sunny, the risk level is medium risk, and if it is non-sunny, the risk level is high risk; the sleep quality is high or medium, the activity data is normal, and the smart device usage data is normal, which is low risk.

[0044] When the underlying disease is cognitive impairment, the state recognition module is configured to analyze the heart rate variability (HRV), body surface temperature fluctuation amplitude, daytime activity and blood oxygen saturation of the user according to the physiological data, and calculate a physiological stability score; for example, when the heart rate variability is lower than a preset threshold, the blood oxygen saturation is lower than 94% for two consecutive days, and the body surface temperature diurnal fluctuation is less than 0.5℃, the physiological stability score is low;

[0045] Also used to compare the user's daily smart device usage data with the historical usage patterns to determine if the decrease exceeds the preset proportion. If it exceeds the preset proportion, it is determined that the user's device interaction behavior is abnormal, for example, the screen-on time period from 9:00 to 12:00 decreases by more than 30% compared to the historical screen-on time period.

[0046] The state recognition module is also used to obtain a cognitive impairment state analysis result according to the physiological stability score and the device interaction behavior abnormality. In this embodiment, when the physiological stability score is low and the device interaction behavior is abnormal, it is determined that the user's cognitive impairment risk is high risk; if only the physiological stability score is low or the device interaction behavior is abnormal, it is determined to be medium risk; if all indicators are within the healthy threshold, it is determined to be low risk.

[0047] The feedback module is used to generate a graded reminder according to the risk level of the state analysis result; in the medium risk, the corresponding graded reminder information is sent to the user's mobile phone, and in the high risk, the corresponding graded reminder information is sent to the emergency contact person.

[0048] For example, when the underlying disease is depression, the graded reminder information of medium risk is: the system monitors that you may have emotional fluctuations recently, and suggests that you take appropriate outdoor activities or communicate with friends and family.

[0049] The graded reminder information of high risk is: the system monitors that the user [name] has a high risk of depression, please contact him in time and give him care.

[0050] When the underlying disease is cognitive impairment, the graded reminder information of medium risk is: the system monitors that your physiological indicators fluctuate, and suggests that you pay attention to your physical condition.

[0051] The graded reminder information of high risk is: the system monitors that the user [name] has a high risk of cognitive impairment, and suggests that you contact the user as soon as possible and pay attention to his recent state, and if necessary, consult a professional doctor.

[0052] This scheme integrates wearable sensing module, mattress sensing module and device sensing module to build a multi-dimensional, multi-data source user state monitoring system, which significantly improves the accuracy and reliability of sub-health state monitoring. Compared with the monitoring method relying only on a single device such as a smart bracelet, this scheme deeply integrates and cross- verifies the user's physiological indicators, sleep quality and daily device usage habits, which can more comprehensively depict the user's real life state, and effectively avoid the one-sidedness and misjudgment that may be caused by a single data source.

[0053] Specifically, instead of simply superimposing data, the present scheme realizes accurate recognition of complex health states through comprehensive analysis by establishing multiple judgment conditions. For example, in assessing the risk of depression, by investigating the actual situation of a large number of families with depression, the designed system not only analyzes the user's own activity and sleep data, but also introduces the comparison with the sleep quality of the partner, the deviation from the historical device usage rule, and the environmental factors such as weather as the basis for judgment, so that the system can distinguish between normal rest state and abnormal social withdrawal or loss of interest behavior, thereby improving the pertinence and accuracy of the warning.

[0054] For monitoring cognitive impairment, the present scheme combines subtle changes in physiological stability (such as heart rate variability, body temperature fluctuations) that are not easily detected with abnormal functional device interaction behavior (such as a significant decrease in usage time), capturing early signals of cognitive decline from both physiological and behavioral aspects, enabling more sensitive and earlier risk identification than traditional single monitoring means.

[0055] In summary, the present scheme can monitor users with sub-health states such as depression and cognitive impairment in real time, output graded risk assessment results, and provide timely and accurate health reminders for users and their families, effectively addressing the shortcomings of existing single monitoring devices in complex sub-health state assessment.

[0056] The above is only an embodiment of the present application, which is not limited to this embodiment. The present application is not limited to the field involved in this embodiment, and common knowledge of specific structures and properties in the scheme is not described in detail. The ordinary skilled person in the art knows all the ordinary technical knowledge in the field of the present application before the filing date or the priority date, can know all the prior art in this field, and has the ability to apply conventional experimental means before that date. The ordinary skilled person in the art can perfect and implement the present scheme based on their own ability under the guidance of this application, and some typical known structures or known methods should not be an obstacle for the ordinary skilled person in the art to implement the present application. It should be noted that, for those skilled in the art, without departing from the structure of the present application, a number of modifications and improvements can be made, which should also be considered within the scope of protection of the present application. These will not affect the effectiveness and practicality of the present application. The scope of protection claimed in this application should be based on the content of its claims, and the specific implementation in the specification can be used to explain the content of the claims.

Claims

1. A status monitoring terminal, characterized in that, include: Wearable sensing module is used to collect users' physiological data in real time; Mattress sensing module, used to collect sleep data; The device sensing module is used to collect data on the user's smart device usage and to analyze the user's historical usage patterns based on historical smart device usage data. The preprocessing module is used to align the collected physiological data, sleep data, and smart device usage data with timestamps. The information pre-input module is used to obtain the user's basic information and disease information; The status recognition module is used to analyze preprocessed sleep data, physiological data, and smart device usage data, and combine them with the user's basic medical information to output status analysis results; the status analysis results include low risk, medium risk, and high risk; The feedback module is used to generate tiered alerts based on the risk level of the status analysis results.

2. The status monitoring terminal according to claim 1, characterized in that: The physiological data include heart rate, body surface temperature, activity data, and blood oxygen saturation. Sleep data includes sleep onset time, wake-up time, deep sleep period, light sleep period, REM sleep period, and wakefulness period.

3. The status monitoring terminal according to claim 1, characterized in that: The disease information includes depression and cognitive impairment.

4. The status monitoring terminal according to claim 3, characterized in that: When the underlying disease is depression, the state recognition module is used to acquire sleep data. If the user has a partner, the sleep data of both the user and the user's partner are analyzed to determine the user's reference sleep quality. If the user does not have a partner, the user's reference sleep quality is determined based on the user's sleep data. The status recognition module is also used to acquire activity data and determine whether the user is in a stationary state for more than a first preset time based on the activity data. If so, obtain the current smart device usage data to determine whether the smart device is currently in use. If not, determine whether the current period is a historical usage period based on the user's historical usage patterns. If not, then determine whether the second preset time has been exceeded. If it is a historical usage period, or if it exceeds the second preset time, the system also obtains the current weather information and determines the user's current depression status analysis result based on the weather information.

5. The status monitoring terminal according to claim 4, characterized in that: The weather information includes sunny and cloudy days. If it is sunny, the risk level is medium risk; if it is cloudy, the risk level is high risk.

6. The status monitoring terminal according to claim 5, characterized in that: When the underlying disease is cognitive impairment, the state recognition module is used to calculate a physiological stability score based on physiological data; It is also used to compare the user's daily smart device usage data with historical usage patterns to determine whether the decline exceeds a preset percentage. If it exceeds the preset percentage, the user's device interaction behavior is determined to be abnormal. The state recognition module is also used to obtain the results of cognitive impairment state analysis based on physiological stability scores and abnormal device interaction behavior.

7. The status monitoring terminal according to claim 6, characterized in that: When the physiological stability score is low and the device interaction behavior is abnormal, the user's cognitive impairment risk is determined to be high; if only the physiological stability score is low or the device interaction behavior is abnormal, it is determined to be medium risk.

8. The status monitoring terminal according to claim 7, characterized in that: The feedback module is used to send corresponding graded reminder information to the user when the risk level is medium, and to send corresponding graded reminder information to the emergency contact when the risk level is high.

Images