CN116195979B

CN116195979B - Health monitoring method and device based on mattress, mattress and medium

Info

Publication number: CN116195979B
Application number: CN202310223500.0A
Authority: CN
Inventors: 王炳坤
Original assignee: De Rucci Healthy Sleep Co Ltd
Current assignee: De Rucci Healthy Sleep Co Ltd
Priority date: 2023-03-09
Filing date: 2023-03-09
Publication date: 2026-02-03
Anticipated expiration: 2043-03-09
Also published as: CN116195979A

Abstract

This invention discloses a health monitoring method, device, mattress, and medium based on a mattress. The method includes: determining the respiratory signal of a target user on the mattress; inputting the respiratory signal into a preset model to obtain the target user's health confidence level, or the health confidence level and an abnormality level; if, within a preset time period, the preset model outputs multiple abnormality levels and the trend of the abnormality levels conforms to a preset trend, then a health warning message is sent to the target user. The technical solution of this invention utilizes a preset model to uncover the correlation between a user's respiratory signal and health, enabling health monitoring only at the user's home, and solving the problem of the inability to balance economy and accuracy in traditional health monitoring methods.

Description

Health monitoring method and device based on mattress, mattress and medium

Technical Field

The invention relates to the technical field of intelligent mattresses, in particular to a health monitoring method and device based on a mattress, the mattress and a medium.

Background

Regular and adequate sleep plays an important role in combating viral entry and enhancing immunity. One of the standards for measuring health is the quality of sleep, and along with the continuous development of technology, sleep monitoring is becoming more and more common, and people are more and more concerned about the quality of sleep.

Some diseases affect the sleep of the user, some diseases cause abnormal shaking of the patient, some diseases also cause degeneration of the region for controlling breathing in the brain of the patient suffering from the disease, thereby causing weakening of respiratory muscle function, sleep breathing disorder and the like. Health monitoring and health early warning are necessary for special people, such as the elderly. Currently, health monitoring is mainly dependent on some specialized medical instruments or some wearable electronic devices such as watches and the like in hospitals.

However, professional medical devices are expensive, have low popularity, and the accuracy of monitoring the home wearable electronic devices is not high.

Disclosure of Invention

The invention provides a health monitoring method and device based on a mattress, the mattress and a medium, and aims to solve the problem that the economical efficiency and the accuracy of a traditional health monitoring mode cannot be considered.

In a first aspect, the present invention provides a mattress-based health monitoring method, for use in a mattress, the method comprising:

determining a respiration signal of a target user on the mattress;

Inputting the respiratory signal into a preset model to obtain the health confidence coefficient of the target user, or the health confidence coefficient and an abnormality level, wherein the abnormality level is determined based on the respiratory signal and the health confidence coefficient;

And if the preset model outputs a plurality of abnormal grades within the preset time period and the variation trend of the abnormal grades accords with the preset trend, health early warning information is sent to the target user.

In a second aspect, the present invention provides a mattress-based health monitoring device configured in a mattress, the device comprising:

A respiratory signal determination module for determining a respiratory signal of a target user on the mattress;

The signal processing module is used for inputting the respiratory signal into a preset model to obtain the health confidence of the target user, or the health confidence and an abnormality level, wherein the abnormality level is determined based on the respiratory signal and the health confidence;

And the information sending module is used for sending health early warning information to a target user if the preset model outputs a plurality of abnormal grades and the variation trend of the abnormal grades accords with a preset trend in a preset time period.

In a third aspect, the present invention provides a mattress comprising:

the mattress comprises a mattress body, a plurality of flexible piezoelectric sensors and at least one processor, wherein the flexible piezoelectric sensors are in communication connection with the processor;

and a memory communicatively coupled to the at least one processor;

Wherein the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the mattress-based health monitoring method of the first aspect described above.

In a fourth aspect, the present invention provides a computer readable storage medium storing computer instructions for causing a processor to perform the mattress-based health monitoring method of the first aspect described above.

According to the health monitoring scheme based on the mattress, a respiratory signal of a target user on the mattress is determined, the respiratory signal is input into a preset model, and health confidence of the target user or the health confidence and the abnormal level are obtained, wherein the abnormal level is determined based on the respiratory signal and the health confidence, and if a plurality of abnormal levels are output by the preset model in a preset time period and the variation trend of the abnormal level accords with a preset trend, health early warning information is sent to the target user. By adopting the technical scheme, the health confidence coefficient for representing the health of the user (target) and the abnormal level for representing the abnormal degree of the user are obtained by inputting the respiratory signal into the preset model, the association relationship between the respiratory signal and the health of the user is excavated by utilizing the preset model, the health monitoring can be realized only at the home of the user, and the problem that the economical efficiency and the accuracy of the traditional health monitoring mode cannot be considered is solved.

It should be understood that the description in this section is not intended to identify key or critical features of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of a mattress-based health monitoring method according to a first embodiment of the invention;

FIG. 2 is a flow chart of a mattress-based health monitoring method according to a second embodiment of the invention;

fig. 3 is a schematic structural view of a health monitoring device based on a mattress according to a third embodiment of the present invention;

fig. 4 is a schematic structural view of a mattress according to a fourth embodiment of the present invention.

Detailed Description

In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. In the description of the present invention, unless otherwise indicated, "a plurality" means two or more. "and/or" describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate that there are three cases of a alone, a and B together, and B alone. The character "/" generally indicates that the context-dependent object is an "or" relationship. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or mattress that comprises a list of steps or elements is not necessarily limited to those steps or elements that are expressly listed or inherent to such process, method, article, or mattress.

Example 1

Fig. 1 is a flowchart of a mattress-based health monitoring method according to an embodiment of the present invention, where the method is applicable to monitoring health of a user using a mattress, and the method may be performed by a mattress-based health monitoring device, where the mattress-based health monitoring device may be implemented in hardware and/or software, and the mattress-based health monitoring device may be configured in a mattress, where the mattress may be formed by two or more physical entities, or may be formed by one physical entity, and where a flexible piezoelectric sensor is built into the mattress.

As shown in fig. 1, the health monitoring method based on a mattress provided in the first embodiment of the present invention specifically includes the following steps:

s101, determining a respiration signal of a target user on the mattress.

In this embodiment, when a person lies on the mattress, the respiration of the person causes a change, such as slight fluctuation, of the mattress, so that the change information of the mattress can be acquired by using a preset sensor (such as a piezoelectric sensor), and then the respiration signal of the target user can be extracted from the change information by a preset process, such as a signal separation process. Wherein the target user may be understood as a user lying on the mattress, the breathing signal may comprise a breathing frequency, a breathing amplitude, etc., the rolling amplitude of the mattress may be indicative of the breathing amplitude, and the rolling frequency of the mattress may be indicative of the breathing frequency.

S102, inputting the respiratory signal into a preset model to obtain the health confidence of the target user, or the health confidence and an abnormality level, wherein the abnormality level is determined based on the respiratory signal and the health confidence.

In this embodiment, some diseases affect the respiratory health of a person, such as shortness of breath or irregular respiration, so that the health and unhealthy degree of a target user can be monitored by extracting the features of respiratory signals, the health confidence can be used to indicate the predicted probability of the health of the target user, and the abnormal level can be used to indicate the predicted unhealthy degree of the target user. When the health confidence coefficient meets the preset requirement, for example, when the health confidence coefficient is 1, the target user health can be indicated, at this time, the abnormal level can not be output, namely, only the health confidence coefficient is output, and when the health confidence coefficient is not 1, the health confidence coefficient and the abnormal level can be output at the same time.

And S103, if the preset model outputs a plurality of abnormal grades and the variation trend of the abnormal grades accords with the preset trend in a preset time period, health early warning information is sent to a target user.

In this embodiment, if a plurality of abnormal grades are obtained within a preset time period, such as a week, and the variation trend of the abnormal grades accords with the preset trend, such as the rising trend, it may be determined that the health of the target user may be problematic and the problem may be more serious, and at this time, health warning information may be sent to the target user and the preset personnel of the target user, such as the target user himself and his relatives, so as to remind the target user to seek medical advice in time. The health warning information may include information such as frequency, respiration amplitude, health confidence level, abnormality level, etc. of the target user in a preset period of time.

According to the health monitoring method based on the mattress, provided by the embodiment of the invention, the breathing signal of the target user on the mattress is determined, the breathing signal is input into the preset model, and the health confidence of the target user or the health confidence and the abnormality level are obtained, wherein the abnormality level is determined based on the breathing signal and the health confidence, and if a plurality of abnormality levels are output by the preset model in a preset time period and the variation trend of the abnormality level accords with the preset trend, health early warning information is sent to the target user. According to the technical scheme provided by the embodiment of the invention, the health confidence degree representing whether the user is healthy or not and the abnormality level representing the abnormality degree of the user are obtained by inputting the respiratory signal into the preset model, the association relationship between the respiratory signal of the user and the health is excavated by utilizing the preset model, the health monitoring can be realized only at the user's home, and the problem that the economical efficiency and the accuracy of the traditional health monitoring mode cannot be considered is solved.

Example two

Fig. 2 is a flowchart of a health monitoring method based on a mattress according to a second embodiment of the present invention, where the technical solution of the embodiment of the present invention is further optimized based on the above-mentioned alternative technical solutions, and a specific way of monitoring the health of a user by using the mattress is provided.

Optionally, the step of inputting the respiratory signal into a preset model to obtain the health confidence coefficient of the target user, or the health confidence coefficient and the abnormal level includes the step of inputting the respiratory signal into the preset model to obtain the health confidence coefficient of the target user, and the preset model further outputs the abnormal level of the target user if the health confidence coefficient is smaller than a second preset value. The method has the advantages that when the target user is healthy, namely, the health confidence is smaller than the second preset value, the abnormal level of the user does not need to be calculated and output, so that the waste of calculation power is avoided, and the data processing efficiency of the model is improved.

Optionally, if the preset model outputs a plurality of abnormal grades and the variation trend of the abnormal grade accords with a preset trend in a preset time period, health warning information is sent to a target user, wherein if the preset model outputs a plurality of abnormal grades and the number of times that the abnormal grade is larger than a first preset grade exceeds a preset number of times in the preset time period, a health report containing first health warning information is sent to the target user at least once, and if the preset model outputs a plurality of abnormal grades, the abnormal grade is larger than a second preset grade and the variation trend of the abnormal grade accords with an ascending trend in the preset time period, a health report containing second health warning information is sent to the target user at least once, wherein the first preset grade is larger than the second preset grade, and the first health warning information is different from the second health warning information. The method has the advantages that when the health of the target user is abnormal, the information of the health abnormality represented by the abnormality level is comprehensively covered, and the accuracy of health monitoring is improved.

Optionally, the method further comprises the steps that if the accumulated data volume of the respiratory signals is larger than a preset data volume, the preset model outputs a plurality of abnormal grades, the number of times that the abnormal grade is larger than a first preset grade exceeds a preset number of times, a health report containing third health warning information is sent to the target user at least once, and if the accumulated data volume is larger than the preset data volume, the preset model outputs a plurality of abnormal grades, the abnormal grade is larger than a second preset grade and the abnormal grade change trend accords with an ascending trend, a health report containing fourth health warning information is sent to the target user at least once, wherein the first preset grade is larger than the second preset grade, and the third health warning information is different from the fourth health warning information. The advantage of this arrangement is that the condition that the health warning information is missed due to the fact that the target user does not use the mattress for a long time and the data volume of the determinable respiratory signal is too small is avoided.

As shown in fig. 2, a health monitoring method based on a mattress provided in a second embodiment of the present invention specifically includes the following steps:

s201, determining a respiration signal of a target user on the mattress.

Optionally, determining the respiration signal of the target user on the mattress includes obtaining a piezoelectric signal corresponding to the target user on the mattress by using a flexible piezoelectric sensor built in the mattress, and performing filtering processing and signal separation processing on the piezoelectric signal to obtain the respiration signal of the target user. The advantage of setting up like this is that through utilizing the built-in flexible piezoelectric sensor of mattress, has avoided influencing user's sleep when healthy monitoring to through carrying out filtration processing and signal separation processing to the piezoelectric signal, accurate determination target user's respiratory signal.

Specifically, when a target user lies on the mattress, the flexible piezoelectric sensor built in the mattress can be used for collecting piezoelectric signals (electric signals generated by pressure), then the piezoelectric signals can be filtered to filter interference signals in the piezoelectric signals, and then the filtered signals are subjected to signal separation processing to obtain breathing signals of the target user. Wherein the number of flexible piezoelectric sensors is typically a plurality, the flexible piezoelectric sensors may be built into the mattress in the form of a sleep monitoring belt.

S202, inputting the respiratory signal into a preset model to obtain the health confidence coefficient of the target user, and if the health confidence coefficient is smaller than a second preset value, outputting the abnormal grade of the target user by the preset model.

For example, if the second preset value is 0.6, after the respiratory signal is input to the preset model, if the health confidence coefficient output by the preset model is 0.7, the preset model will also output an abnormal level, such as level 1, and if the health confidence coefficient output by the preset model is 0.4, the preset model will not output an abnormal level.

Optionally, the preset model comprises a convolution layer, a coding layer constructed based on a multi-head attention mechanism and a classification layer, wherein the determination mode of the preset model comprises the steps of obtaining a sample breathing signal configured with a sample tag, wherein the sample tag comprises a confidence tag or the confidence tag and an abnormal grade tag, inputting the sample breathing signal into the convolution layer of an initial preset model to obtain a first feature vector, inputting the first feature vector into the coding layer constructed based on causal convolution in the initial preset model to obtain a second feature vector, wherein the causal convolution is used for realizing the multi-head attention mechanism, inputting the second feature vector into the classification layer of the initial preset model to obtain sample health information, and training the initial preset model according to a difference between the sample health information and the sample tag to determine the preset model, wherein the sample health information comprises sample health confidence or the sample health confidence and the abnormal grade. The method has the advantages that the initial preset model is trained by using the sample containing the label, and the preset model with the training completed and accurate output prediction result can be obtained.

Specifically, the convolution layer in the preset model can be used for extracting respiratory characteristics, the coding layer constructed based on the multi-head attention mechanism can be used for extracting the relation between the respiratory characteristics and time, the accuracy of an output result of the preset model is enhanced, and the classification layer is used for processing the characteristic vector output by the coding layer and outputting health confidence after processing or outputting health confidence and abnormal level. Sample respiratory signals may be obtained from published clinical data containing respiratory signals of a plurality of patients whose conditions may be different but whose individual respiratory conditions are abnormal, and respiratory signals of a normative and healthy population. Sample labels of the sample respiratory signal can be preset, such as confidence labels can be 0 and 1, respectively, to indicate unhealthy and healthy, and abnormal grade labels can be 1,2, 3 and 4 grades, with higher grades indicating unhealthy. The sample breath signal with the sample tag may be input into a convolution layer, which may extract a feature vector (first feature vector) from the sample breath signal, where the convolution layer may include a plurality of convolution processing layers and at least one skip connection layer. And then inputting the first eigenvectors into a coding layer constructed based on causal convolution, and extracting the time dependency relationship between the first eigenvectors so as to obtain a second eigenvector. And inputting the second feature vector into a classification layer of the initial preset model to obtain sample health information, wherein the sample health information can comprise sample health confidence and sample abnormality level or only comprises sample health confidence. And carrying out multi-round training on the initial preset model according to the difference between the sample health information and the sample label, and obtaining the preset model after training when the difference is small enough.

Further, the step of inputting the second feature vector into the classification layer of the initial preset model to obtain sample health information comprises the step of inputting the second feature vector into the health classification layer of the initial preset model to obtain sample health confidence, wherein the health classification layer and the abnormal grade prediction layer belong to the classification layer of the initial preset model, the health classification layer comprises a full connection layer and an activation layer, and if the sample health confidence is smaller than a first preset value, the second feature vector is input into the abnormal grade prediction layer to obtain the sample abnormal grade, and the abnormal grade prediction layer comprises the full connection layer. The advantage of setting up like this is that when the probability that the sample respiration signal is healthy respiration signal is great, need not to calculate the unusual grade of this respiration signal, saved the power of calculation, promoted the efficiency of model processing data.

Specifically, the second feature vector is input into a health classification layer of a classification layer in the initial preset model, so that the sample health confidence level can be obtained, the health classification layer can comprise a plurality of full-connection layers and at least one activation layer, and the confidence level can be in a value range of 0 or more and 1 or less. If the sample health confidence is smaller than the first preset value, the probability that the sample respiratory signal is a healthy respiratory signal is smaller, and the second feature vector is required to be input into an abnormal grade prediction layer, so that a sample abnormal grade is obtained, and the abnormal grade prediction layer can comprise a plurality of fully connected layers. The first preset value may be the same as the second preset value, or may be different from the second preset value.

And S203, if the preset model outputs a plurality of abnormal grades and the number of times that the abnormal grade is larger than a first preset grade exceeds the preset number of times in a preset time period, sending a health report containing first health early warning information to the target user at least once.

For example, if the preset time period is a week, the first preset level is 2 levels, and the preset number of times is 3, then the preset model outputs a plurality of abnormal levels in the week, and the number of times that the abnormal level is greater than 2 levels exceeds 3 times, then a health report including the first health warning information may be sent to the target user at least once. The first health warning information is used for prompting that the body of the target user is possibly abnormal, the first health warning information can comprise information such as the frequency, the breathing amplitude, the health confidence coefficient, the abnormal level and the like of the target user in a preset time period, the health report can comprise information such as medical reminding and medical recommendation degree besides the first health warning information, and the higher the abnormal level is, the higher the medical recommendation degree is.

And S204, if the preset model outputs a plurality of abnormal grades, the abnormal grade is larger than a second preset grade and the variation trend of the abnormal grade accords with the upward trend in the preset time period, sending a health report containing second health early warning information to the target user at least once.

The first preset level is greater than the second preset level, and the first health early warning information is different from the second health early warning information.

For example, as described in the above example, if the second preset level is also 2 levels, the preset model outputs a plurality of abnormal levels within a week, where the abnormal levels are all greater than 2 levels, and the abnormal level change trend accords with the upward trend, the health report including the second health warning information may be sent to the target user at least once. The first preset level and the second preset level may be the same or different, and because the first health warning information and the second health warning information may both include information such as an abnormal level, the first health warning information may be the same as the second health warning information or different, and if the first preset level and the second preset level are different, the abnormal level in the first health warning information and the second health warning information may be different.

S205, if the accumulated data volume of the respiratory signals is greater than a preset data volume, the preset model outputs a plurality of abnormal grades, and the number of times that the abnormal grade is greater than a first preset grade exceeds a preset number of times, a health report containing third health early warning information is sent to the target user at least once.

For example, as described above, the preset data amount may be determined based on the cumulative data amount of the breathing signal per hour, such as if the cumulative data amount of the breathing signal per hour is 2 mega-meters when the target user is on the mattress, the preset data amount may be preset to 200 mega-meters, which 200 mega-meters represent that the target user is on bed for approximately 200 hours. If the preset data size is 200 megabytes, when the accumulated data size of the respiratory signal is greater than 200 megabytes, the preset model outputs a plurality of abnormal grades, and the number of times that the abnormal grade is greater than 3 exceeds 3, then a health report containing third health warning information can be sent to the target user at least once. The third health warning information may be the same as the first health warning information and the second health warning information, or may be different from the first health warning information if the preset data size is larger (the duration corresponding to the preset data size is longer than the duration of the preset time period), and the third health warning information may be different from the first health warning information and the second health warning information.

S206, if the accumulated data volume is larger than the preset data volume, the preset model outputs a plurality of abnormal grades, the abnormal grade is larger than a second preset grade, and the abnormal grade change trend accords with the upward trend, a health report containing fourth health early warning information is sent to the target user at least once.

The first preset level is greater than the second preset level, and the third health warning information is different from the fourth health warning information.

For example, as described above, when the cumulative data amount of the respiratory signal is greater than 200 megabytes, the preset model outputs a plurality of abnormal levels, the plurality of abnormal levels are all greater than 2 levels, and the abnormal level change trend accords with the upward trend, the health report including the fourth health warning information may be sent to the target user at least once. The fourth health warning information may be the same as the first health warning information, the second health warning information and the third health warning information, or may be different, if the preset data size is larger and the first preset level and the second preset level are different, the first health warning information, the second health warning information, the third health warning information and the fourth health warning information may be different.

Alternatively, the accumulated data amount of the respiratory signal may be reset every time a health report containing the third health warning information or the fourth health warning information is transmitted to the target user, but the data of the respiratory signal is retained, so that steps 205 and 206 may be performed whenever the accumulated data amount of the respiratory signal is greater than the preset data amount.

According to the health monitoring method based on the mattress, the respiratory signal of the (target) user is determined by using the mattress, the health monitoring method is suitable for daily continuous monitoring of a home environment, is particularly suitable for health monitoring of special people such as old people, the health confidence representing the health of the user is obtained by inputting the respiratory signal into the preset model, the abnormal grade representing the abnormal degree of the user is output by the preset model only when the probability of the health of the user is smaller (when the health confidence is smaller), the waste of calculation force is avoided, the efficiency of data processing of the model is improved, the information of health abnormality represented by the abnormal grade when the health of the target user is abnormal is comprehensively covered by setting the preset time period, the preset times, the preset grade, the preset trend and the preset data quantity, the accuracy of health monitoring is improved, the condition that the data quantity of the determinable respiratory signal is too small for a long time without using the mattress by the target user is avoided, the condition that the health information is missed is caused, the economical efficiency and the early warning of the traditional health monitoring mode can not be realized only at home of the user is solved.

Example III

Fig. 3 is a schematic structural diagram of a health monitoring device based on a mattress according to a third embodiment of the present invention. As shown in fig. 3, the device comprises a respiratory signal determination module 301, a signal processing module 302 and an information transmission module 303, the device can be configured in a mattress, wherein:

According to the health monitoring device based on the mattress, provided by the embodiment of the invention, the health confidence degree representing whether the user is healthy or not and the abnormality level representing the abnormality degree of the user are obtained by inputting the breathing signals into the preset model, the association relation between the breathing signals of the user and the health is excavated by utilizing the preset model, the health monitoring can be realized only in the home of the user, and the problem that the economical efficiency and the accuracy of the traditional health monitoring mode cannot be considered is solved.

Optionally, the preset model comprises a convolution layer, a coding layer constructed based on a multi-head attention mechanism and a classification layer, wherein the determination mode of the preset model comprises the steps of obtaining a sample breathing signal configured with a sample tag, wherein the sample tag comprises a confidence tag or the confidence tag and an abnormal grade tag, inputting the sample breathing signal into the convolution layer of an initial preset model to obtain a first feature vector, inputting the first feature vector into the coding layer constructed based on causal convolution in the initial preset model to obtain a second feature vector, wherein the causal convolution is used for realizing the multi-head attention mechanism, inputting the second feature vector into the classification layer of the initial preset model to obtain sample health information, and training the initial preset model according to a difference between the sample health information and the sample tag to determine the preset model, wherein the sample health information comprises sample health confidence or the sample health confidence and the abnormal grade.

Further, the step of inputting the second feature vector into the classification layer of the initial preset model to obtain sample health information comprises the step of inputting the second feature vector into the health classification layer of the initial preset model to obtain sample health confidence, wherein the health classification layer and the abnormal grade prediction layer belong to the classification layer of the initial preset model, the health classification layer comprises a full connection layer and an activation layer, and if the sample health confidence is smaller than a first preset value, the second feature vector is input into the abnormal grade prediction layer to obtain the sample abnormal grade, and the abnormal grade prediction layer comprises the full connection layer.

Optionally, the signal processing module includes:

the confidence coefficient determining unit is used for inputting the breathing signal into a preset model to obtain the health confidence coefficient of the target user;

And the abnormal grade determining unit is used for outputting the abnormal grade of the target user by the preset model if the health confidence coefficient is smaller than a second preset value.

Optionally, the information sending module includes:

The first sending unit is used for sending a health report containing first health early warning information to the target user at least once if the preset model outputs a plurality of abnormal grades and the number of times that the abnormal grade is larger than a first preset grade exceeds preset times in a preset time period;

And the second sending unit is used for sending a health report containing second health warning information to the target user at least once if the preset model outputs a plurality of abnormal grades, the abnormal grade is larger than a second preset grade and the variation trend of the abnormal grade accords with the ascending trend in the preset time period, wherein the first preset grade is larger than the second preset grade, and the first health warning information is different from the second health warning information.

Optionally, the apparatus further comprises:

the first sending module is configured to send a health report including third health warning information at least once to the target user if the accumulated data volume of the respiratory signal is greater than a preset data volume, the preset model outputs a plurality of abnormal grades, and the number of times that the abnormal grade is greater than a first preset grade exceeds a preset number of times;

And the second sending module is used for sending a health report containing fourth health early warning information to the target user at least once if the accumulated data size is larger than the preset data size, the preset model outputs a plurality of abnormal grades, the abnormal grade is larger than a second preset grade and the variation trend of the abnormal grade accords with the ascending trend, wherein the first preset grade is larger than the second preset grade, and the third health early warning information is different from the fourth health early warning information.

Optionally, the respiratory signal determination module includes:

The piezoelectric signal determining unit is used for acquiring a piezoelectric signal corresponding to a target user on the mattress by utilizing a flexible piezoelectric sensor arranged in the mattress;

and the respiratory signal determining unit is used for filtering and separating the piezoelectric signals to obtain respiratory signals of the target user.

The health monitoring device based on the mattress provided by the embodiment of the invention can execute the health monitoring method based on the mattress provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

Example IV

Fig. 4 shows a schematic structural view of a mattress 40 that may be used to implement an embodiment of the present invention. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 4, the mattress 40 includes a mattress body 41, a plurality of flexible piezoelectric sensors 42, and at least one processor 43, the flexible piezoelectric sensors 42 and the processor 43 being communicatively connected, and a memory 44, such as a Read Only Memory (ROM), a Random Access Memory (RAM), etc., communicatively connected to the at least one processor 43, wherein the memory stores a computer program executable by the at least one processor, and the processor 43 can perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) or the computer program loaded from a storage unit into the Random Access Memory (RAM). In RAM, various programs and data required for the operation of mattress 40 may also be stored. The processor, ROM and RAM are connected to each other by a bus. An input/output (I/O) interface is also connected to the bus.

The various components in mattress 40 are connected to I/O interfaces including input units such as keyboards, mice, etc., output units such as various types of displays, speakers, etc., storage units such as magnetic disks, optical disks, etc., and communication units such as network cards, modems, wireless communication transceivers, etc. The communication unit allows the mattress 40 to exchange information/data with other mattresses through a computer network, such as the internet, and/or various telecommunications networks.

The processor 43 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 43 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 43 performs the various methods and processes described above, such as a mattress-based health monitoring method.

In some embodiments, the mattress-based health monitoring method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as a storage unit. In some embodiments, part or all of the computer program may be loaded and/or installed onto mattress 40 via a ROM and/or communication unit. When the computer program is loaded into RAM and executed by the processor 43, one or more of the steps of the mattress-based health monitoring method described above may be performed. Alternatively, in other embodiments, the processor 43 may be configured to perform the mattress-based health monitoring method in any other suitable manner (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic mattresses (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include being implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be a special or general purpose programmable processor, operable to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

The computer mattress provided by the above can be used for executing the health monitoring method based on the mattress provided by any embodiment, and has corresponding functions and beneficial effects.

Example five

In the context of the present invention, a computer readable storage medium may be a tangible medium, which when executed by a computer processor is used to perform a mattress-based health monitoring method applicable in a mattress, the method comprising:

determining a respiration signal of a target user on the mattress;

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or mattress. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or mattress, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage mattress, a magnetic storage mattress, or any suitable combination of the foregoing.

It should be noted that, in the embodiment of the mattress-based health monitoring device, the units and modules are only divided according to the functional logic, but not limited to the above-mentioned division, so long as the corresponding functions can be implemented, and the specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.

Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.

Claims

1. A health monitoring method based on a mattress, characterized in that it is applied to a mattress, the method comprising:

Identify the target user's breathing signals on the mattress;

The respiratory signal is input into a preset model to obtain the health confidence score of the target user, or the health confidence score and the abnormality level, wherein the abnormality level is determined based on the magnitude of the respiratory signal and the health confidence score;

If the preset model outputs multiple abnormal levels within a preset time period and the trend of the abnormal level changes conforms to a preset trend, then a health warning message is sent to the target user; the health warning message includes the target user's frequency, breathing amplitude, health confidence level, and abnormal level information within the preset time period.

The method further includes:

If the cumulative data volume of the respiratory signal is greater than the preset data volume, and the preset model outputs multiple abnormal levels and the number of times the abnormal level is greater than the first preset level exceeds the preset number, then at least one health report containing third health warning information will be sent to the target user.

If the accumulated data volume is greater than the preset data volume, the preset model outputs multiple abnormal levels, the abnormal level is greater than the second preset level, and the abnormal level change trend conforms to an upward trend, then at least one health report containing fourth health warning information is sent to the target user, wherein the first preset level is greater than the second preset level, and the third health warning information is different from the fourth health warning information.

2. The method according to claim 1, wherein the preset model comprises a convolutional layer, an encoding layer constructed based on a multi-head attention mechanism, and a classification layer, and the preset model is determined by means of:

Acquire a sample respiratory signal configured with a sample label, wherein the sample label includes a confidence label, or the confidence label and an anomaly level label;

The sample respiratory signal is input into the convolutional layer of the initial preset model to obtain the first feature vector;

The first feature vector is input into the encoding layer constructed based on causal convolution in the initial preset model to obtain the second feature vector, wherein the causal convolution is used to implement the multi-head attention mechanism;

The second feature vector is input into the classification layer of the initial preset model to obtain sample health information. Based on the difference between the sample health information and the sample label, the initial preset model is trained to determine the preset model. The sample health information includes sample health confidence, or the sample health confidence and sample anomaly level.

3. The method according to claim 2, wherein inputting the second feature vector into the classification layer of the initial preset model to obtain sample health information includes:

The second feature vector is input into the health classification layer of the initial preset model to obtain the sample health confidence. The health classification layer and the anomaly level prediction layer belong to the classification layer of the initial preset model. The health classification layer includes a fully connected layer and an activation layer.

If the health confidence of the sample is less than a first preset value, the second feature vector is input into the anomaly level prediction layer to obtain the anomaly level of the sample, wherein the anomaly level prediction layer includes a fully connected layer.

4. The method according to claim 1, characterized in that, the step of inputting the respiratory signal into a preset model to obtain the health confidence level of the target user, or, the health confidence level and the abnormality level, includes:

The respiratory signal is input into a preset model to obtain the health confidence level of the target user;

If the health confidence level is less than the second preset value, the preset model also outputs the abnormality level of the target user.

5. The method according to claim 4, characterized in that, if the preset model outputs multiple abnormal levels within a preset time period and the changing trend of the abnormal levels conforms to a preset trend, then sending health warning information to the target user includes:

If, within a preset time period, the preset model outputs multiple abnormal levels and the number of times the abnormal level is greater than the first preset level exceeds a preset number, then at least one health report containing the first health warning information is sent to the target user.

If, within the preset time period, the preset model outputs multiple abnormal levels, the abnormal level is greater than the second preset level, and the abnormal level changes in an upward trend, then at least one health report containing second health warning information is sent to the target user, wherein the first preset level is greater than the second preset level, and the first health warning information is different from the second health warning information.

6. The method according to any one of claims 1-5, characterized in that determining the breathing signal of the target user on the mattress includes:

The flexible piezoelectric sensor built into the mattress is used to acquire the piezoelectric signal corresponding to the target user on the mattress;

The piezoelectric signal is filtered and separated to obtain the respiratory signal of the target user.

7. A health monitoring device based on a mattress, characterized in that it is disposed in the mattress, the device comprising:

A breathing signal determination module is used to determine the breathing signal of a target user on the mattress;

The signal processing module is used to input the respiratory signal into a preset model to obtain the health confidence score of the target user, or the health confidence score and the abnormality level, wherein the abnormality level is determined based on the magnitude of the respiratory signal and the health confidence score;

The information sending module is used to send health warning information to the target user if the preset model outputs multiple abnormal levels within a preset time period and the changing trend of the abnormal levels conforms to a preset trend; the health warning information includes the target user's frequency, breathing amplitude, health confidence level and abnormal level information within the preset time period.

The device further includes:

The first sending module is used to send a health report containing third health warning information to the target user at least once if the cumulative data amount of the respiratory signal is greater than a preset data amount, the preset model outputs multiple abnormal levels and the number of times the abnormal level is greater than the first preset level exceeds a preset number.

The second sending module is used to send a health report containing fourth health warning information to the target user at least once if the accumulated data volume is greater than the preset data volume, the preset model outputs multiple abnormal levels, the abnormal level is greater than the second preset level, and the abnormal level change trend conforms to an upward trend. The first preset level is greater than the second preset level, and the third health warning information is different from the fourth health warning information.

8. A mattress, characterized in that the mattress comprises:

The mattress body, multiple flexible piezoelectric sensors, and at least one processor are included, wherein the flexible piezoelectric sensors and the processor are communicatively connected.

and a memory communicatively connected to the at least one processor;

The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the mattress-based health monitoring method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that the computer-readable storage medium stores computer instructions, the computer instructions being configured to cause a processor to execute and implement the mattress-based health monitoring method according to any one of claims 1-6.