CN116019429B - Health monitoring method, device, equipment and storage medium based on physiological index - Google Patents
Health monitoring method, device, equipment and storage medium based on physiological index Download PDFInfo
- Publication number
- CN116019429B CN116019429B CN202111257038.3A CN202111257038A CN116019429B CN 116019429 B CN116019429 B CN 116019429B CN 202111257038 A CN202111257038 A CN 202111257038A CN 116019429 B CN116019429 B CN 116019429B
- Authority
- CN
- China
- Prior art keywords
- health
- index
- user
- data
- period
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000036541 health Effects 0.000 title claims abstract description 481
- 238000000034 method Methods 0.000 title claims abstract description 78
- 238000012544 monitoring process Methods 0.000 title claims abstract description 49
- 230000008859 change Effects 0.000 claims abstract description 41
- 238000011156 evaluation Methods 0.000 claims abstract description 12
- 238000012806 monitoring device Methods 0.000 claims abstract description 11
- 238000012549 training Methods 0.000 claims description 76
- 239000008280 blood Substances 0.000 claims description 19
- 210000004369 blood Anatomy 0.000 claims description 19
- 230000002159 abnormal effect Effects 0.000 claims description 12
- 230000005856 abnormality Effects 0.000 claims description 11
- 230000036772 blood pressure Effects 0.000 claims description 9
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 claims description 8
- 239000008103 glucose Substances 0.000 claims description 8
- 238000013178 mathematical model Methods 0.000 claims description 8
- 230000037396 body weight Effects 0.000 claims description 7
- 238000005457 optimization Methods 0.000 claims description 7
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 6
- 229910052760 oxygen Inorganic materials 0.000 claims description 6
- 239000001301 oxygen Substances 0.000 claims description 6
- 230000036760 body temperature Effects 0.000 claims description 5
- 150000002632 lipids Chemical class 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims 1
- 201000010099 disease Diseases 0.000 abstract description 14
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 abstract description 14
- 230000009286 beneficial effect Effects 0.000 abstract description 9
- 230000000474 nursing effect Effects 0.000 abstract description 8
- 230000000875 corresponding effect Effects 0.000 description 20
- 230000003862 health status Effects 0.000 description 15
- 230000008569 process Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 8
- 230000001419 dependent effect Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 230000035790 physiological processes and functions Effects 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 235000005118 dietary health Nutrition 0.000 description 2
- 239000002243 precursor Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 208000024891 symptom Diseases 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 210000002249 digestive system Anatomy 0.000 description 1
- 210000000750 endocrine system Anatomy 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 210000000653 nervous system Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 238000010238 partial least squares regression Methods 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 230000001766 physiological effect Effects 0.000 description 1
- 210000002345 respiratory system Anatomy 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000004753 textile Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- -1 watches Substances 0.000 description 1
Landscapes
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention relates to the technical field of physiological monitoring and discloses a physiological index-based health monitoring method, a physiological index-based health monitoring device, a physiological index-based health monitoring equipment and a physiological index-based storage medium. The method reads the current physiological index data of the user acquired in the current time period; inputting the current physiological index data of the user into a preset health index model for index evaluation; and predicting the next period health index of the user and the change tendency of the next period health index based on the physiological index data and the health index of each period of the user, and generating the health guidance suggestion of the user. The invention realizes the function of monitoring the health state of the user in time, helps the user to find hidden diseases, and is beneficial to developing real-time medical assistance and rehabilitation nursing. The problems that the artificial physiological health analysis is time-consuming and labor-consuming, difficult to popularize and free of real-time performance are solved.
Description
Technical Field
The present invention relates to the field of physiological monitoring, and in particular, to a method, apparatus, device, and storage medium for health monitoring based on physiological indicators.
Background
The physiological index is an important index for measuring physiological health of a person, and can help doctors to judge health conditions of the patient through detection of the physiological index, and health levels of various organs, joints and muscles of a circulatory system, a respiratory system, a digestive system, a nervous system, an endocrine system and the like are collective, so that the physiological index of the person can be detected rapidly at present through portable physiological index acquisition equipment such as wearable equipment and the like.
In the prior art, the analysis of the physiological indexes still stays in the manual analysis stage, no mature and perfect intelligent analysis model exists yet, the manual analysis is time-consuming and labor-consuming, the self health state can not be monitored in time, the hidden diseases are found, and the development of real-time medical assistance and rehabilitation nursing is not facilitated.
Disclosure of Invention
The invention mainly aims to provide a physiological index-based health monitoring method, a physiological index-based health monitoring device, physiological index-based health monitoring equipment and a physiological index-based health monitoring storage medium, and aims to solve the problems that how to analyze artificial physiological health is time-consuming and labor-consuming, difficult to popularize and free of real-time performance.
The first aspect of the invention provides a health monitoring method based on physiological indexes, which comprises the following steps:
reading current physiological index data of a user acquired in a current time period;
inputting the current physiological index data of the user into a preset health index model for index evaluation, and outputting the current health index of the user;
predicting a next period health index of the user based on the physiological index data and the health indexes of each period of the user, and determining the change tendency of the next period health index;
And generating health guidance suggestions of the user based on the change tendency of the next period health index of the user and the current period physiological index data.
Optionally, in a first implementation manner of the first aspect of the present invention, before the reading the current physiological index data of the user acquired in the current time period, the method includes:
Acquiring physiological index data of each period of a plurality of sample users and taking the physiological index data as first training sample data;
after the training sample data are cleaned, marking the health index of the first training sample data according to the health state of the sample user to obtain second training sample data with labels;
inputting the second training sample data into a preset mathematical model for training to obtain a health index model, and judging whether the health index model is converged or not;
And if the health index model is converged, stopping training, otherwise, performing iterative optimization on parameters of the health index model by using a back propagation algorithm until the health index model is converged.
Optionally, in a second implementation manner of the first aspect of the present invention, the physiological index data includes:
body temperature data, heart rate data, blood pressure data, blood glucose data, blood lipid data, body weight data, perspiration data, blood oxygen saturation data, and pulse data.
Optionally, in a third implementation manner of the first aspect of the present invention, the predicting the next-period health index of the user based on the physiological index data of each period and the health index of each period of the user, and determining the tendency of the next-period health index to change includes:
establishing a health index prediction model based on the physiological index data of each period and the health index of each period of the user;
predicting a next period health index of the user based on the health index prediction model;
and determining the change tendency of the health index of the user in the next period according to the health index of the user in the current period and the health index of the user in the next period.
Optionally, in a fourth implementation manner of the first aspect of the present invention, the establishing a health index prediction model based on the physiological index data of each period and the health index of each period of the user includes:
Performing multiple regression fitting on the physiological index data of each period and the health index of each period of the user by using a partial least square method so as to establish a preliminary health prediction model;
Selecting physiological index data of each period of the user and health indexes of each period of the user, training the health prediction model, and measuring fitting accuracy of the health prediction model by utilizing relative errors and average relative errors of training results of the health index model and health indexes of each period;
and adjusting parameters of the health prediction model until the fitting precision is smaller than a preset precision threshold value, and stopping training to obtain the final health prediction model.
Optionally, in a fifth implementation manner of the first aspect of the present invention, the generating the health guidance advice of the user based on the change tendency of the next period health index of the user and the current period physiological index data includes:
taking the average value of the health indexes of each period of the user as a baseline index, and adopting a preset formula to calculate half of the deviation range of the health indexes of each period and the baseline index and taking the deviation range as a trend early warning threshold;
If the absolute value of the difference value between the next period health index and the current period health index of the user exceeds the tendency early warning threshold value, the current period health condition of the user is marked as health dynamic abnormality;
Acquiring physiological index data corresponding to the health dynamic abnormality, and screening abnormal physiological index data lower than a normal range from the physiological index data;
and generating the health guidance suggestion corresponding to the user currently according to the screened abnormal index data. Optionally, in a sixth implementation manner of the first aspect of the present invention, before the reading the current physiological index data of the user acquired in the current time period, the method further includes:
Acquiring personal information data of the user, and creating a blank personal health file of the user according to the personal information data of the user, wherein the personal health file is used for storing health data of the user, and the health data comprises: current physiological index data, current health index, next health index change trend, and health guidance advice.
The second aspect of the present invention provides a health monitoring device based on physiological indicators, comprising:
The reading module is used for reading the current physiological index data of the user acquired and uploaded in the current time period;
The health index module is used for inputting the current physiological index data of the user into a preset health index model for index evaluation and outputting the current health index of the user;
The health prediction module is used for predicting the next period health index of the user based on the physiological index data of each period and the health index of each period of the user, and determining the change tendency of the next period health index;
and the guidance suggestion module is used for generating a health guidance suggestion of the user based on the change tendency of the next period health index of the user and the current period physiological index data.
Optionally, in a first implementation manner of the second aspect of the present invention, before the reading module, the health index model building module is further included, specifically configured to:
Acquiring physiological index data of each period of a plurality of sample users and taking the physiological index data as first training sample data;
after the training sample data are cleaned, marking the health index of the first training sample data according to the health state of the sample user to obtain second training sample data with labels;
inputting the second training sample data into a preset mathematical model for training to obtain a health index model, and judging whether the health index model is converged or not;
And if the health index model is converged, stopping training, otherwise, performing iterative optimization on parameters of the health index model by using a back propagation algorithm until the health index model is converged.
Optionally, in a second implementation manner of the second aspect of the present invention, the reading module is specifically configured to:
Body temperature data, heart rate data, blood pressure data, blood glucose data, blood lipid data, body weight data, perspiration data, blood oxygen saturation data, and pulse data are read.
Optionally, in a third implementation manner of the second aspect of the present invention, the health prediction module further includes:
Model building unit: the method comprises the steps of establishing a health index prediction model based on physiological index data of each period and health indexes of each period of a user;
an index prediction unit: for predicting a next period health index of the user based on the health index prediction model;
trend prediction unit: and the method is used for determining the change tendency of the next period health index of the user according to the current period health index and the next period health index of the user.
Optionally, in a fourth implementation manner of the second aspect of the present invention, the health prediction model building unit is configured to:
Performing multiple regression fitting on the physiological index data of each period and the health index of each period of the user by using a partial least square method so as to establish a preliminary health prediction model;
Selecting physiological index data of each period of the user and health indexes of each period of the user, training the health prediction model, and measuring fitting accuracy of the health prediction model by utilizing relative errors and average relative errors of training results of the health index model and health indexes of each period;
and adjusting parameters of the health prediction model until the fitting precision is smaller than a preset precision threshold value, and stopping training to obtain the final health prediction model.
Optionally, in a fifth implementation manner of the second aspect of the present invention, the instruction suggestion module is configured to calculate, using a preset formula, a half of a deviation range between the health index of each period and the baseline index by using a mean value of the health index of each period of the user as a baseline index, and use the calculated value as a trend early warning threshold;
If the absolute value of the difference value between the next period health index and the current period health index of the user exceeds the tendency early warning threshold value, the current period health condition of the user is marked as health dynamic abnormality;
Acquiring physiological index data corresponding to the health dynamic abnormality, and screening abnormal physiological index data lower than a normal range from the physiological index data;
and generating the health guidance suggestion corresponding to the user currently according to the screened abnormal index data.
Optionally, in a sixth implementation manner of the second aspect of the present invention, the archiving module is configured to obtain a personal information profile of the user, and create a blank personal health profile of the user according to the personal information profile of the user, where the personal health profile is used to store health data of the user, and the health data includes: current physiological index data, current health index, next health index change trend, and health guidance advice.
A third aspect of the present invention provides an electronic device based on a physiological index, including: a memory and at least one processor, the memory having instructions stored therein; the at least one processor invokes the instructions in the memory to cause the physiological-index-based electronic device to perform the physiological-index-based health monitoring method described above.
A fourth aspect of the present invention provides a computer readable storage medium having instructions stored therein which, when run on a computer, cause the computer to perform the above-described physiological index based health monitoring method.
According to the technical scheme provided by the invention, the health monitoring method based on the physiological index is provided, and the physiological index data of the user is read, and the health index model and the health prediction model are utilized for analysis and prediction, so that corresponding guiding suggestions are provided. The health monitoring and analyzing method can monitor the health state of the user in time, find out hidden diseases and is beneficial to developing real-time medical assistance and rehabilitation nursing. The problems that the artificial physiological health analysis is time-consuming and labor-consuming, difficult to popularize and free of real-time performance are solved.
Drawings
FIG. 1 is a diagram illustrating a first embodiment of a physiological index-based health monitoring method according to an embodiment of the present invention;
FIG. 2 is a diagram illustrating a second embodiment of a physiological index-based health monitoring method according to an embodiment of the present invention;
FIG. 3 is a diagram illustrating a third embodiment of a physiological index-based health monitoring method according to an embodiment of the present invention;
FIG. 4 is a diagram illustrating a fourth embodiment of a physiological index based health monitoring method according to an embodiment of the present invention;
FIG. 5 is a diagram of a health monitoring device based on physiological indicators according to an embodiment of the present invention;
FIG. 6 is a diagram of a health monitoring device based on physiological indicators according to another embodiment of the present invention;
fig. 7 is a schematic diagram of an embodiment of an electronic device based on a physiological index according to an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a health monitoring method, a device, equipment and a storage medium based on physiological indexes, wherein physiological index data are read through a physiological index acquisition device such as a wearable electronic device, and are analyzed through a health index model and a health prediction model, and the result is stored in a personal health file. The real-time health monitoring method can monitor the health state of the patient in time, find out hidden diseases and is beneficial to medical aid and rehabilitation nursing.
The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, 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 described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.
For ease of understanding, a specific flow of an embodiment of the present invention is described below, referring to fig. 1, and an embodiment of a health monitoring method based on physiological indexes in an embodiment of the present invention includes:
101. Reading current physiological index data of a user acquired in a current time period;
It can be understood that the execution subject of the present invention may be a health monitoring device based on a physiological index, and may also be a terminal or a server, which is not limited herein. The embodiment of the invention is described by taking a server as an execution main body as an example.
In this embodiment, the time period refers to an interval time for collecting the physiological index data, including, but not limited to, for example, the time period is fixed to be collected at 8 a day and the time period is 24 hours, the current time period is collected at 8 a day and the physiological index data collected in the current time period is the current physiological index data.
In this embodiment, the collected devices include, but are not limited to, wearable electronic devices and other physiological index data collection devices, where the wearable electronic devices refer to electronic devices with integrated electronic technology or other intelligent functions, and have human physiological index sensing measurement modules, including but not limited to, hats, shirts, clothing, other textiles, watches, glasses, and the like. The wearable electronic device utilizes the sensor to monitor human body actions and various physiological indexes and provides own body data for a user.
In this embodiment, various kinds of physiological index data refer to digital performance of the intensity of each physiological function of a person, each physiological index has a normal range, and physiological index data exceeding the normal range is poor performance of the physiological function. Various physiological indicators include, but are not limited to, pulse rate, blood pressure, blood glucose level, body weight, etc. The physiological index data is a digitized signal after the physiological index is subjected to analog-to-digital conversion.
102. Inputting the current physiological index data of the user into a preset health index model for index evaluation, and outputting the current health index of the user;
In this embodiment, the health index model refers to a model capable of performing index evaluation on the health status of a user: health index 85-100, user health status: the health state is good; health index 70-85, user health status: health; health index 50-70, user health status: sub-health; health index 30-50, user health status: a disease precursor state; health index 0-30, user health status: disease state.
In this embodiment, the health index model is obtained by machine learning, using an algorithm to instruct a computer to obtain a proper model by using known data, and using the model to make a judgment on a new situation, including but not limited to training and learning by using various physiological index data of a large number of users to obtain a health index model, and using the health index model to make a judgment on the collected physiological index data.
103. Predicting a next period health index of the user based on the physiological index data and the health indexes of each period of the user, and determining the change tendency of the next period health index;
In this embodiment, the physiological index data of each period refers to a series of physiological index data collected in history and physiological index data of the current period, including but not limited to physiological index data of the first three months collected when the month is taken as a period and physiological index data of the current month. The health index of each period refers to a series of historical health indexes obtained by analysis of a health index model.
In this embodiment, the next-period health index includes, but is not limited to, a period one, and may be a future health index of a plurality of periods.
In this alternative embodiment, the prediction means that the health prediction model is trained by using the read physiological index data and the health index analyzed by the model, so as to achieve the function of predicting the health state.
In this embodiment, the change trend refers to the direction of the change of the next period health index relative to the current period health index, and reveals the direction of the change of the health status of the user, including but not limited to the trend of the next period health index to decrease, i.e. the health status becomes worse; the next phase health index tends to rise, indicating a better state of health.
104. And generating health guidance suggestions of the user based on the change tendency of the next period health index of the user and the current period physiological index data.
In this embodiment, the health instruction advice includes, but is not limited to advice on providing dietary health, exercise instruction, rehabilitation care instruction, instruction for regular life.
In this embodiment, the health guidance advice generation manner includes, but is not limited to: corresponding guidance suggestion databases are correspondingly generated when different physiological indexes are different from normal people; guiding advice is given by professionals.
According to the technical scheme provided by the invention, the health monitoring method based on the physiological index is provided, and the physiological index data of the user is read, and the health index model and the health prediction model are utilized for analysis and prediction, so that corresponding guiding suggestions are provided. The health monitoring and analyzing method can monitor the health state of the user in time, find out hidden diseases and is beneficial to developing real-time medical assistance and rehabilitation nursing. The problems that the artificial physiological health analysis is time-consuming and labor-consuming, difficult to popularize and free of real-time performance are solved.
Referring to fig. 2, another embodiment of a health monitoring method based on physiological indexes according to an embodiment of the present invention includes:
201. Reading current physiological index data of a user acquired in a current time period;
In this embodiment, collecting refers to sensing human motion and various physiological indexes by sensors of the device, including but not limited to collecting temperature, blood pressure, blood glucose, blood oxygen and blood glucose, body weight, pulse, perspiration.
In this embodiment, before health monitoring of the user is performed, a health index model is established, and when health monitoring is performed subsequently, the model is not required to be established again.
Optionally, in an embodiment, the step 201 further includes:
Acquiring physiological index data of each period of a plurality of sample users and taking the physiological index data as first training sample data;
after the training sample data are cleaned, marking the health index of the first training sample data according to the health state of the sample user to obtain second training sample data with labels;
inputting the second training sample data into a preset mathematical model for training to obtain a health index model, and judging whether the health index model is converged or not;
And if the health index model is converged, stopping training, otherwise, performing iterative optimization on parameters of the health index model by using a back propagation algorithm until the health index model is converged.
In this alternative embodiment, the physiological index data acquisition sources of each period of the plurality of sample users include, but are not limited to, acquiring various physiological indexes of the users from the medical care system, and converting the physiological index data into physiological index data through analog-to-digital conversion. The physiological index data has properties including, but not limited to: the method has the advantages of time sequence, fixed time period acquisition and sequential arrangement.
In this alternative embodiment, training refers to a process of determining perfect parameters of a model, and adjusting parameters of a constructed model with a large number of data samples, so that accuracy of an output result reaches a target range.
In this alternative embodiment, the cleaning includes, but is not limited to, the process of re-examining and checking the data, deleting duplicate data, correcting missing values, misspellings and invalid values, reconciling, normalizing and normalizing the data, and making the data comparable and convertible.
In this alternative embodiment, marking according to the health status of the user includes, but is not limited to, identifying health indices 85-100, user health status: the health state is good; health index 70-85, user health status: health; health index 50-70, user health status: sub-health; health index 30-50, user health status: a disease precursor state; health index 0-30, user health status: disease state.
In this optional embodiment, the first training sample refers to the initial physiological index data of each period of the plurality of sample users; the second training sample is a training sample with a label after cleaning and a known true value.
In this alternative embodiment, the preset mathematical model refers to a mathematical relationship of the physiological index data and the health index abstraction, including but not limited to a mapping relationship.
In this alternative embodiment, parameters of the mathematical model are continuously adjusted during the training process, so that the training result of the training sample approaches and converges to the label of the sample infinitely. The training process is a cross-validation process: the second training samples are randomly grouped, after grouping, the test and verification are performed in a crossing manner among groups, the tested samples are also used for verification in a crossing manner, and the verified samples can also be used for testing.
In this alternative embodiment, the gradient of the error function is calculated for all parameters in the network using a back propagation algorithm in combination with a gradient descent method. This gradient will feed back the optimization method to update the parameters to minimize the error function, allowing the model to converge.
Defining an error with an error function:
Wherein a represents an error between the tag health index of the training sample and the output result of the health model, n represents n samples, y p represents a tag health index of a certain period, y p' represents the output result of the corresponding health model, and q is a constant. And solving the partial derivative of the input physiological index data in the reverse output direction of the error function, then adjusting the parameters of the health index model according to the partial derivative and the gradient of the error, iterating again until the gradient of the error approaches 0 infinitely, converging the health index model at the moment, and finishing training.
In this alternative embodiment, the number of iterations is not limited, including but not limited to, the parameters of the health index model after the last adjustment as the parameters of the next training. The iterative process is a process that continuously optimizes the model parameters.
Optionally, in an embodiment, the physiological index data of step 201 includes: body temperature data, heart rate data, blood pressure data, blood glucose data, blood lipid data, body weight data, perspiration data, blood oxygen saturation data, and pulse data.
In this alternative embodiment, the above-mentioned physiological indicators are not limited, and include, but are not limited to, various important physiological indicators affecting physiological health.
202. Inputting the current physiological index data of the user into a preset health index model for index evaluation, and outputting the current health index of the user;
In this embodiment, the preset health index model is established prior to 201, including but not limited to a model trained from physiological index data samples of a plurality of users.
203. Predicting a next period health index of the user based on the physiological index data and the health indexes of each period of the user, and determining the change tendency of the next period health index;
204. And generating health guidance suggestions of the user based on the change tendency of the next period health index of the user and the current period physiological index data.
In the technical scheme provided by the invention, the health monitoring method based on the physiological index is provided, and particularly comprises a method for establishing a health index model, after the health index model is established, the physiological index data of a user is read, and analysis and prediction are performed by using the health index model and a health prediction model, so that corresponding guiding suggestions are given. The health monitoring and analyzing method can timely monitor the self health state of the user, convert the physiological health state into a visual health index, is beneficial to the user to monitor the self health state, find hidden diseases and is beneficial to developing real-time medical assistance and rehabilitation nursing. The problem of manual analysis inefficiency is solved.
Referring to fig. 3, another embodiment of a health monitoring method based on physiological indexes according to an embodiment of the present invention includes:
301. reading current physiological index data of a user acquired in a current time period;
302. inputting the current physiological index data of the user into a preset health index model for index evaluation, and outputting the current health index of the user;
303. establishing a health index prediction model based on the physiological index data of each period and the health index of each period of the user;
optionally, in an embodiment, the step 303 includes:
Performing multiple regression fitting on the physiological index data of each period and the health index of each period of the user by using a partial least square method so as to establish a preliminary health prediction model;
Selecting physiological index data of each period of the user and health indexes of each period of the user, training the health prediction model, and measuring fitting accuracy of the health prediction model by utilizing relative errors and average relative errors of training results of the health index model and health indexes of each period;
and adjusting parameters of the health prediction model until the fitting precision is smaller than a preset precision threshold value, and stopping training to obtain the final health prediction model.
In this alternative embodiment, the partial least square method refers to researching the relationship between the independent variable and the dependent variable by using various types of physiological index data as the independent variable and the health index of each period as the dependent variable. The partial least squares method extracts components a 1 and b 1(a1 from the independent and dependent variables, respectively, as linear combinations of part of the principal dependent independent variables, and b 1 as linear combinations of the dependent variables. ) a 1 represents the physiological index data as much as possible, b 1 represents the health index, and the component a 1 of the independent variable has the strongest interpretation ability on the health index b 1, namely, the covariance of a 1 and b 1 reaches the maximum.
After the first components a 1 and b 1 are extracted, partial least squares regression performs a fit of the independent variable to a 1 and a fit of the dependent variable to b 1, respectively. If the regression equation has reached satisfactory accuracy, the algorithm terminates; otherwise, the component extraction of the second round will be performed using the remaining physiological index after the argument is interpreted by a 1 and the residual information after the argument is interpreted by b 1. This is repeated until a satisfactory accuracy is achieved. If j (j is a constant) components a 1,…,aj are finally extracted from the independent variable, the operation is defined to carry out regression on a 1,…,aj, and finally, the regression equation of the independent variable to the independent variable is converted.
In this alternative embodiment, multiple regression fit refers to fitting multiple independent variables, including but not limited to two independent variables: weight data and blood pressure data; three independent variables: blood pressure data, pulse data, and perspiration data.
In this alternative embodiment, the relative error refers to the error between the model training result and the true health index, and the average relative error is obtained by averaging based on the relative error.
In this alternative embodiment, the fitting accuracy refers to the overall coincidence degree of the health prediction model and the health index true value, and is positively correlated with the relative error and the average relative error.
In this optional embodiment, the preset precision threshold is a value of a set fitting precision range, if the fitting precision value is within the range, it indicates that model training is completed, and if the fitting precision is greater than the preset precision threshold, it indicates that the fitting degree is not good, and continuous training is required.
304. Predicting a next period health index of the user based on the health index prediction model;
305. and determining the change tendency of the health index of the user in the next period according to the health index of the user in the current period and the health index of the user in the next period.
Optionally, in an embodiment, the step 305 includes:
Taking the average value of the health indexes of each period of the user as a baseline index, and adopting a preset formula to calculate the deviation degree of the health indexes of each period and the baseline index and taking the deviation degree as a trend early warning threshold;
If the absolute value of the difference value between the next period health index and the current period health index of the user exceeds the tendency early warning threshold value, the current period health condition of the user is marked as health dynamic abnormality;
Acquiring physiological index data corresponding to the health dynamic abnormality, and screening abnormal physiological index data lower than a normal range from the physiological index data;
and generating the health guidance suggestion corresponding to the user currently according to the screened abnormal index data.
In this alternative embodiment, the baseline index refers to the average health index of the user over each period, and the health index size of the user fluctuates around the baseline index.
In this alternative embodiment, the early warning includes, but is not limited to, that the health index fluctuates due to the fluctuation of the physiological index data of the user, and the state of the user is stable within a certain range. The deviation degree of the health index of each period from the baseline index can be calculated as the fluctuation range of the health index of the user, namely the tendency early warning threshold value. Assuming that the value of the health index in the previous t period is y 1,y2,y3,……,yt as a sample, k is a baseline index, H is the deviation degree of the health index in the next period from the baseline index, t is the period number of the health index, y p represents the tag health index in a certain period, y t+1 represents the health index in the next period, the deviation degree of the health index in the next period from the baseline index can be expressed as:
When the absolute value of y t+1-yt is less than or equal to H and/or y t+1≥yt, the change trend of the health index in the next period is within the range of the trend early warning threshold value or the health index in the next period is increased, and the health dynamic state is normal.
When |y t+1-yt | is not less than H and y t+1≤yt, the change trend of the health index in the next period is out of the trend early warning threshold range, and the health dynamic abnormality is indicated.
In this alternative embodiment, each physiological index has a normal range, and physiological index data exceeding the normal range is a poor representation of the physiological function. Abnormal physiological index data refers to physiological index data exceeding a normal range.
In this embodiment, the health guidance advice generation manner herein includes, but is not limited to: correspondingly generating a guiding suggestion database corresponding to the abnormal physiological index; guiding advice is given by professionals. Advice includes, but is not limited to advice on providing dietary health, exercise instructions, rehabilitation care instructions, instructions for regular life.
In the technical scheme provided by the invention, a health monitoring method based on physiological indexes is provided, a health prediction model is established, and a method for dividing whether dynamics are normal or not is provided, the health prediction model is utilized to predict the future health of a user, and corresponding guiding suggestions are provided. The health monitoring and analyzing method can timely monitor the health state of the user, forecast the future health state of the user, discover the implicit rule in the change of the physiological index data, and is favorable for discovering implicit diseases, and timely develop real-time medical aid and rehabilitation care. The problem of predicting the health state is solved.
Referring to fig. 4, another embodiment of a health monitoring method based on physiological indexes according to an embodiment of the present invention includes:
401. reading current physiological index data of a user acquired in a current time period;
402. Inputting the current physiological index data of the user into a preset health index model for index evaluation, and outputting the current health index of the user;
403. predicting a next period health index of the user based on the physiological index data and the health indexes of each period of the user, and determining the change tendency of the next period health index;
404. And generating health guidance suggestions of the user based on the change tendency of the next period health index of the user and the current period physiological index data.
405. Acquiring personal information data of the user, and creating a blank personal health file of the user according to the personal information data of the user, wherein the personal health file is used for storing health data of the user, and the health data comprises: current physiological index data, current health index, next health index change trend, and health guidance advice.
In this embodiment, the personal information of the user includes, but is not limited to, the name, sex, age, and area of the user.
In this embodiment, the professional healthcare staff can know the health status, symptoms and physiological indexes of the user according to the personal health file, and provide specialized medical assistance measures and suggestions corresponding to the symptoms.
According to the technical scheme provided by the invention, the health monitoring method based on the physiological index is provided, the physiological index data of the user is read, the health index model and the health prediction model are utilized for analysis and prediction, corresponding guiding suggestions are given, and all historical health data are archived and saved. The health monitoring and analyzing method can timely monitor the health state of the user, find out hidden diseases, provide references for daily physiological activities and health states of the user in the medical assistance process, and is beneficial to developing real-time medical assistance and rehabilitation care. The problem of random errors of the physiological index data in the medical rescue process is solved, and the diagnosis errors in the medical rescue process are reduced.
The above description of the health monitoring method based on the physiological index in the embodiment of the present invention, the following description of the health monitoring device based on the physiological index in the embodiment of the present invention refers to fig. 5, and one embodiment of the health monitoring device based on the physiological index in the embodiment of the present invention includes:
The reading module 501 is configured to read current physiological index data of a user acquired and uploaded in a current time period;
the health index module 502 is configured to input the current physiological index data of the user into a preset health index model for index evaluation, and output a current health index of the user;
A health prediction module 503, configured to predict a next-period health index of the user based on the physiological index data of each period and the health index of each period of the user, and determine a tendency of change of the next-period health index;
The guiding suggestion module 504 is configured to generate a guiding suggestion for health of the user based on the trend of change of the next period health index of the user and the current period physiological index data.
According to the technical scheme, the health monitoring equipment based on the physiological index is provided, the physiological index data of the user are read, analysis and prediction are carried out by utilizing the health index module and the health prediction model, and corresponding guiding suggestions are given. The health monitoring and analyzing method can monitor the health state of the user in time, find out hidden diseases and is beneficial to developing real-time medical assistance and rehabilitation nursing. The problems that the artificial physiological health analysis is time-consuming and labor-consuming, difficult to popularize and free of real-time performance are solved.
Referring to fig. 6, another embodiment of a health monitoring device based on physiological indicators according to an embodiment of the present invention includes:
The reading module 501 is configured to read current physiological index data of a user acquired and uploaded in a current time period;
the health index module 502 is configured to input the current physiological index data of the user into a preset health index model for index evaluation, and output a current health index of the user;
A health prediction module 503, configured to predict a next-period health index of the user based on the physiological index data of each period and the health index of each period of the user, and determine a tendency of change of the next-period health index;
The guiding suggestion module 504 is configured to generate a guiding suggestion for health of the user based on the trend of change of the next period health index of the user and the current period physiological index data.
Optionally, the reading module 501 further includes an exponential model building module 500, specifically configured to:
Acquiring physiological index data of each period of a plurality of sample users and taking the physiological index data as first training sample data;
after the training sample data are cleaned, marking the health index of the first training sample data according to the health state of the sample user to obtain second training sample data with labels;
inputting the second training sample data into a preset mathematical model for training to obtain a health index model, and judging whether the health index model is converged or not;
And if the health index model is converged, stopping training, otherwise, performing iterative optimization on parameters of the health index model by using a back propagation algorithm until the health index model is converged.
Optionally, the reading module 501 is further specifically configured to: body temperature data, heart rate data, blood pressure data, blood glucose data, blood lipid data, body weight data, perspiration data, blood oxygen saturation data, and pulse data are read.
Optionally, the health prediction module 503 further includes:
Model creation unit 5031: the method comprises the steps of establishing a health index prediction model based on physiological index data of each period and health indexes of each period of a user;
Index prediction unit 5032: for predicting a next period health index of the user based on the health index prediction model;
Trend prediction unit 5033: the method comprises the steps of determining the change tendency of the next period health index of the user according to the current period health index and the next period health index of the user;
the instruction suggestion unit 5034: the method is used for generating health guidance suggestions of the user based on the change tendency of the next period health index of the user and the current period physiological index data.
Optionally, the model building unit 5031 may be further specifically configured to:
Performing multiple regression fitting on the physiological index data of each period and the health index of each period of the user by using a partial least square method so as to establish a preliminary health prediction model;
Selecting physiological index data of each period of the user and health indexes of each period of the user, training the health prediction model, and measuring fitting accuracy of the health prediction model by utilizing relative errors and average relative errors of training results of the health index model and health indexes of each period;
and adjusting parameters of the health prediction model until the fitting precision is smaller than a preset precision threshold value, and stopping training to obtain the final health prediction model.
Optionally, the instruction suggestion unit 5034 may be further specifically configured to:
taking the average value of the health indexes of each period of the user as a baseline index, and adopting a preset formula to calculate half of the deviation range of the health indexes of each period and the baseline index and taking the deviation range as a trend early warning threshold;
If the absolute value of the difference value between the next period health index and the current period health index of the user exceeds the tendency early warning threshold value, the current period health condition of the user is marked as health dynamic abnormality;
Acquiring physiological index data corresponding to the health dynamic abnormality, and screening abnormal physiological index data lower than a normal range from the physiological index data;
and generating the health guidance suggestion corresponding to the user currently according to the screened abnormal index data.
Optionally, the guidance suggestion module 504 may further include an archiving module 505, specifically configured to:
Acquiring personal information data of the user, and creating a blank personal health file of the user according to the personal information data of the user, wherein the personal health file is used for storing health data of the user, and the health data comprises: current physiological index data, current health index, next health index change trend, and health guidance advice.
According to the technical scheme, the health monitoring equipment based on the physiological index is provided, the physiological index data of a user are read, analysis and prediction are carried out by utilizing the health index module and the health prediction model, and corresponding guiding suggestions are given and archived. The health monitoring and analyzing method can monitor the health state of the user in time, find out hidden diseases and is beneficial to developing real-time medical assistance and rehabilitation nursing. The problem that medical staff does not know the daily physical condition of a patient in the medical assistance process is solved, the diagnosis efficiency is improved, and the misdiagnosis probability is reduced.
The above fig. 5 and fig. 6 describe the health monitoring device based on the physiological index in the embodiment of the present invention in detail from the point of view of the modularized functional entity, and the electronic device in the embodiment of the present invention is described in detail from the point of view of the hardware processing.
Fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, where the electronic device 600 may have a relatively large difference due to different configurations or performances, and may include one or more processors (central processing units, CPU) 610 (e.g., one or more processors) and a memory 620, and one or more storage mediums 630 (e.g., one or more mass storage devices) storing applications 633 or data 632. Wherein the memory 620 and the storage medium 630 may be transitory or persistent storage. The program stored on the storage medium 630 may include one or more modules (not shown), each of which may include a series of instruction operations in the electronic device 600. Still further, the processor 610 may be configured to communicate with the storage medium 630 and execute a series of instruction operations in the storage medium 630 on the electronic device 600.
The electronic device 600 may also include one or more power supplies 640, one or more wired or wireless network interfaces 650, one or more input/output interfaces 660, and/or one or more operating systems 631, such as Windows Serve, mac OS X, unix, linux, freeBSD, and the like. It will be appreciated by those skilled in the art that the electronic device structure shown in fig. 7 is not limiting of the electronic device and may include more or fewer components than shown, or may combine certain components, or may be arranged in a different arrangement of components.
The present invention also provides an electronic device, including a memory and a processor, where the memory stores computer readable instructions that, when executed by the processor, cause the processor to execute the steps of the physiological index based health monitoring method in the above embodiments.
The present invention also provides a computer readable storage medium, which may be a non-volatile computer readable storage medium, and may also be a volatile computer readable storage medium, where instructions are stored in the computer readable storage medium, when the instructions are executed on a computer, cause the computer to perform the steps of the health monitoring method based on the physiological index.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (7)
1. A health monitoring method based on physiological indicators, the health monitoring method comprising:
Acquiring physiological index data of each period of a plurality of sample users and taking the physiological index data as first training sample data;
after the training sample data are cleaned, marking the health index of the first training sample data according to the health state of the sample user to obtain second training sample data with labels;
inputting the second training sample data into a preset mathematical model for training to obtain a health index model, and judging whether the health index model is converged or not;
If the health index model is converged, stopping training, otherwise, performing iterative optimization on parameters of the health index model by using a back propagation algorithm until the health index model is converged;
reading current physiological index data of a user acquired in a current time period;
inputting the current physiological index data of the user into a preset health index model for index evaluation, and outputting the current health index of the user;
predicting a next period health index of the user based on the physiological index data and the health indexes of each period of the user, and determining the change tendency of the next period health index;
Generating health guidance suggestions of the user based on the change tendency of the health index of the user in the next period and the physiological index data of the current period;
Wherein predicting the next period health index of the user based on the physiological index data and the health index of each period of the user, and determining the change trend of the next period health index comprises:
Establishing a health index prediction model based on the physiological index data of each period and the health index of each period of the user; predicting a next period health index of the user based on the health index prediction model; determining the change tendency of the health index of the user in the next period according to the health index of the user in the current period and the health index of the user in the next period;
Wherein, based on the physiological index data of each period and the health index of each period of the user, establishing the health index prediction model includes:
Performing multiple regression fitting on the physiological index data of each period and the health index of each period of the user by using a partial least square method so as to establish a preliminary health index prediction model; selecting physiological index data of each period of the user and health indexes of each period of the user, training the health index prediction model, and measuring fitting accuracy of the health index prediction model by utilizing the relative error and average relative error of the training result of the health index prediction model and the health indexes of each period; and adjusting parameters of the health index prediction model until the fitting precision is smaller than a preset precision threshold value, and stopping training to obtain the final health index prediction model.
2. The physiological index based health monitoring method of claim 1, wherein the physiological index data comprises: body temperature data, heart rate data, blood pressure data, blood glucose data, blood lipid data, body weight data, perspiration data, blood oxygen saturation data, and pulse data.
3. The method of claim 1, wherein generating the user's health guidance advice based on the user's trend of change in the next-period health index and the current-period physiological index data comprises:
Taking the average value of the health indexes of each period of the user as a baseline index, and adopting a preset formula to calculate the deviation degree of the health indexes of each period and the baseline index and taking the deviation degree as a trend early warning threshold;
If the absolute value of the difference value between the next period health index and the current period health index of the user exceeds the tendency early warning threshold value, the current period health condition of the user is marked as health dynamic abnormality;
Acquiring physiological index data corresponding to the health dynamic abnormality, and screening abnormal physiological index data lower than a normal range from the physiological index data;
and generating the health guidance suggestion corresponding to the user currently according to the screened abnormal index data.
4. A method of physiological index based health monitoring according to any of claims 1-3, further comprising, prior to said reading of current physiological index data of the user acquired during the current time period:
Acquiring personal information data of the user, and creating a blank personal health file of the user according to the personal information data of the user, wherein the personal health file is used for storing health data of the user, and the health data comprises: current physiological index data, current health index, next health index change trend, and health guidance advice.
5. A physiological-index-based health monitoring device, comprising:
The health index model construction module is used for acquiring physiological index data of each period of a plurality of sample users and taking the physiological index data as first training sample data; after the training sample data are cleaned, marking the health index of the first training sample data according to the health state of the sample user to obtain second training sample data with labels; inputting the second training sample data into a preset mathematical model for training to obtain a health index model, and judging whether the health index model is converged or not; if the health index model is converged, stopping training, otherwise, performing iterative optimization on parameters of the health index model by using a back propagation algorithm until the health index model is converged;
The reading module is used for reading the current physiological index data of the user acquired and uploaded in the current time period;
The health index module is used for inputting the current physiological index data of the user into a preset health index model for index evaluation and outputting the current health index of the user;
The health prediction module is used for predicting the next period health index of the user based on the physiological index data of each period and the health index of each period of the user, and determining the change tendency of the next period health index;
The guidance suggestion module is used for generating a health guidance suggestion of the user based on the change tendency of the next period health index of the user and the current period physiological index data;
Wherein the health prediction module comprises:
the model building unit is used for performing multiple regression fitting on the physiological index data of each period and the health index of each period of the user by using a partial least square method so as to build a preliminary health index prediction model; selecting physiological index data of each period of the user and health indexes of each period of the user, training the health index prediction model, and measuring fitting accuracy of the health index prediction model by utilizing the relative error and average relative error of the training result of the health index prediction model and the health indexes of each period; adjusting parameters of the health index prediction model until the fitting precision is smaller than a preset precision threshold value, and stopping training to obtain a final health index prediction model;
an index prediction unit for predicting a next period health index of the user based on the health index prediction model;
And the trend prediction unit is used for determining the change trend of the health index of the user in the next period according to the health index of the user in the current period and the health index of the user in the next period.
6. An electronic device, the electronic device comprising: a memory and at least one processor, the memory having instructions stored therein;
the at least one processor invoking the instructions in the memory to cause the electronic device to perform the physiological-index-based health monitoring method of any of claims 1-4.
7. A computer readable storage medium having instructions stored thereon, which when executed by a processor, implement the physiological index based health monitoring method of any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111257038.3A CN116019429B (en) | 2021-10-27 | 2021-10-27 | Health monitoring method, device, equipment and storage medium based on physiological index |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111257038.3A CN116019429B (en) | 2021-10-27 | 2021-10-27 | Health monitoring method, device, equipment and storage medium based on physiological index |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116019429A CN116019429A (en) | 2023-04-28 |
| CN116019429B true CN116019429B (en) | 2024-06-28 |
Family
ID=86078267
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111257038.3A Active CN116019429B (en) | 2021-10-27 | 2021-10-27 | Health monitoring method, device, equipment and storage medium based on physiological index |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116019429B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116741377A (en) * | 2023-06-19 | 2023-09-12 | 联硕智能(深圳)有限公司 | Health target recommendation record tracking method and device based on intelligent watch |
| CN116936104B (en) * | 2023-09-15 | 2023-12-08 | 广东恒腾科技有限公司 | Health detector data analysis system and method based on artificial intelligence |
| CN118379173B (en) * | 2024-06-19 | 2024-09-13 | 江西合一云数据科技股份有限公司 | Comprehensive safety monitoring method based on digital aged care |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102844784A (en) * | 2010-03-29 | 2012-12-26 | 欧姆龙健康医疗事业株式会社 | Health management support device, health management support system, and health management support program |
| CN105205323A (en) * | 2015-09-19 | 2015-12-30 | 深圳市前海安测信息技术有限公司 | User sign data-based healthy diet guide system and method |
Family Cites Families (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW200608938A (en) * | 2004-09-10 | 2006-03-16 | Jang-Min Yang | Cloth system for automatic inspection and analysis feedback of body health condition to provide healthcare guidance and applying method thereof |
| CN1908975A (en) * | 2006-08-10 | 2007-02-07 | 中山大学 | Human feature based healthy intelligent management method and healthy suggestion system |
| US20080126124A1 (en) * | 2006-11-28 | 2008-05-29 | Schechter Alan M | Quantitative assessment, evaluation and triage of the health status of an individual |
| US20190076031A1 (en) * | 2013-12-12 | 2019-03-14 | Alivecor, Inc. | Continuous monitoring of a user's health with a mobile device |
| US20160302671A1 (en) * | 2015-04-16 | 2016-10-20 | Microsoft Technology Licensing, Llc | Prediction of Health Status from Physiological Data |
| CN106021960A (en) * | 2016-06-16 | 2016-10-12 | 山东诺安诺泰信息系统有限公司 | Health management method |
| CN106338596A (en) * | 2016-08-24 | 2017-01-18 | 四川长虹通信科技有限公司 | Health monitoring method, health monitoring apparatus, and electronic equipment |
| FI127893B (en) * | 2017-04-28 | 2019-05-15 | Meru Health Oy | System and method for monitoring personal health and a method for treatment of autonomic nervous system related dysfunctions |
| CN107506602A (en) * | 2017-09-07 | 2017-12-22 | 北京海融兴通信息安全技术有限公司 | A kind of big data health forecast system |
| CN108376561A (en) * | 2018-05-17 | 2018-08-07 | 北京维康恒科技有限公司 | The method and system of rehabilitation suggestion are provided based on real-time sign data |
| CN111785374A (en) * | 2020-06-15 | 2020-10-16 | 山东省玖玖医养健康产业有限公司 | Health condition analysis and prediction method and system based on big data |
| CN111833982A (en) * | 2020-07-09 | 2020-10-27 | 平安科技（深圳）有限公司 | Health report generation method and related equipment based on health data |
| CN112244793B (en) * | 2020-11-02 | 2024-06-04 | 深圳市沃特沃德信息有限公司 | Health monitoring method, device and storage medium |
| CN113160988B (en) * | 2021-04-29 | 2023-09-29 | 深圳市优云健康管理科技有限公司 | Health management system based on big data analysis |
-
2021
- 2021-10-27 CN CN202111257038.3A patent/CN116019429B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102844784A (en) * | 2010-03-29 | 2012-12-26 | 欧姆龙健康医疗事业株式会社 | Health management support device, health management support system, and health management support program |
| CN105205323A (en) * | 2015-09-19 | 2015-12-30 | 深圳市前海安测信息技术有限公司 | User sign data-based healthy diet guide system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116019429A (en) | 2023-04-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116019429B (en) | Health monitoring method, device, equipment and storage medium based on physiological index | |
| Alazzam et al. | [Retracted] A Novel Smart Healthcare Monitoring System Using Machine Learning and the Internet of Things | |
| Pandey | Machine learning and IoT for prediction and detection of stress | |
| CN117438024B (en) | Intelligent acquisition and analysis system and method for acute diagnosis patient sign data | |
| CA2631870C (en) | Residual-based monitoring of human health | |
| CN108366763A (en) | Method and system for assessing the state of mind | |
| JP2018067303A (en) | Diagnosis support method, program and apparatus | |
| CN108135548A (en) | For monitoring the method and system of pressure state | |
| CN117598700B (en) | Intelligent blood oxygen saturation detection system and method | |
| Massaro et al. | Neural networks for automated smart health platforms oriented on heart predictive diagnostic big data systems | |
| KR20220037455A (en) | Systems and methods for automatic detection of clinical outcome measures | |
| WO2022216220A1 (en) | Method and system for personalized prediction of infection and sepsis | |
| CN111048206A (en) | Multi-dimensional health state assessment method and device | |
| CN105593860B (en) | For determining the device and patient health condition determiner of composite score distribution | |
| CN116098595B (en) | System and method for monitoring and preventing sudden cardiac death and sudden cerebral death | |
| CN118553425B (en) | A method and system for constructing a dynamic prediction model for medical health | |
| CN118675741A (en) | Sensor monitoring-based geriatric surgery intelligent nursing system and method | |
| Mendonça et al. | A method for sleep quality analysis based on CNN ensemble with implementation in a portable wireless device | |
| CN117079807A (en) | Intelligent diagnosis support system and method for common diseases of middle-aged and elderly people | |
| Fisher et al. | Monitoring health changes in congestive heart failure patients using wearables and clinical data | |
| Cai et al. | IoT-based gait monitoring system for static and dynamic classification of data | |
| RU129681U1 (en) | SYSTEM FOR DETERMINING THE FUNCTIONAL CONDITION OF A GROUP OF FEEDBACK PEOPLE | |
| Rakshna et al. | Pre-stroke detection using k-nearest neighbour and random forest algorithm | |
| Skubisz et al. | Deep Learning Bio–Signal Analysis from a Wearable Device | |
| Subiramaniyam | Enhanced Real-Time Analysis and Anomaly Detection in Smart Health Monitoring Systems through Integration of Deep Learning Algorithm with IoT-Edge Computing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |