CN109602410A - A kind of wearable device and its monitoring of pulse method - Google Patents
A kind of wearable device and its monitoring of pulse method Download PDFInfo
- Publication number
- CN109602410A CN109602410A CN201811366462.XA CN201811366462A CN109602410A CN 109602410 A CN109602410 A CN 109602410A CN 201811366462 A CN201811366462 A CN 201811366462A CN 109602410 A CN109602410 A CN 109602410A
- Authority
- CN
- China
- Prior art keywords
- pulse
- health status
- data
- neural network
- monitoring
- 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.)
- Pending
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/021—Measuring pressure in heart or blood vessels
- A61B5/02141—Details of apparatus construction, e.g. pump units or housings therefor, cuff pressurising systems, arrangements of fluid conduits or circuits
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7246—Details of waveform analysis using correlation, e.g. template matching or determination of similarity
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Cardiology (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Animal Behavior & Ethology (AREA)
- Pathology (AREA)
- Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Physiology (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Vascular Medicine (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses wearable device and its monitoring of pulse method, method includes: the pulse data using the sensor acquisition user on the wearable device and stores into caching；The pulse data is handled, by treated, pulse data is input to progress health status prediction in the neural network model that training is completed in advance, obtains health status prediction result；The health status prediction result is shown on the monitoring of pulse interface of wearable device.On the basis of collecting user's pulse data, it is further processed and is analyzed by machine learning, show health status prediction result, people is helped easily and timely to understand the physical condition of oneself, and suggest that user sees a doctor diagnosing and treating in time in body abnormality, ensures the health of people.It is also possible to which doctor is assisted to diagnose, clinical reference is provided.
Description
Technical field
The present invention relates to wearable device technical field, a kind of wearable device and its monitoring of pulse method.
Background technique
In modern society, with the quickening pace of modern life, the people with sub-health state is more and more, and people are for health
Physical condition also increasingly pay attention to.Traditional Chinese Medicine is by practice by diagnosing and treating inferior health and the Other diseases of feeling the pulse
The effective way of proof, for improving, people's constitution, improving health is played an important role and meaning.In life and work,
People can in time and easily obtain diagnosis for physical condition and suggest thering is huge demand.
The wearable devices such as current smartwatch, majority is only to provide the functions such as basic movement and health, using the heart
The physical signs such as the heart rate of rate sensor senses user, lack it is accurate, analyse in depth user's pulse and holistic health
Scheme and product.
Summary of the invention
The present invention provides a kind of wearable device and its monitoring of pulse method, realizes and user is predicted based on pulse data
Health status helps people conveniently, in time to understand the beneficial effect of the physical condition of oneself.
According to an aspect of an embodiment of the present invention, a kind of monitoring of pulse method is provided, wearable device, packet are applied to
It includes:
Using the pulse data and storage of the sensor acquisition user on the wearable device into caching；
The pulse data is handled, by treated, pulse data is input to the neural network that training is completed in advance
Health status prediction is carried out in model, obtains health status prediction result；
The health status prediction result is shown on the monitoring of pulse interface of wearable device.
Other side according to an embodiment of the present invention provides a kind of wearable device, comprising: multiple sensors, with
The processor of sensor connection and the display device being connected to the processor；
Sensor, for acquiring the pulse data of user and storing into caching；
Processor will treated that pulse data is input to has trained in advance for handling the pulse data
At neural network model in carry out health status prediction, obtain health status prediction result；
Display device, for showing the monitoring of pulse interface comprising the health status prediction result.
Using the technical solution of the embodiment of the present invention, the pulse data of the sensor acquisition user on wearable device is simultaneously deposited
It stores up in caching, pulse data is handled, pulse data is input to the neural network that training is completed in advance by treated
Health status prediction is carried out in model, obtains health status prediction result, shows health status prediction result, is thus collecting use
It on the basis of the pulse data of family, is further processed and is analyzed by deep learning, show health status prediction result, help people
Easily and timely understand the physical condition of oneself, and diagnosing and treating of seeing a doctor in time in body abnormality, ensures the body of people
Health.It is also possible to which doctor is assisted to diagnose, clinical reference is provided.
Detailed description of the invention
Fig. 1 is the flow chart of the monitoring of pulse method in the embodiment of the present invention；
Fig. 2 is the flow diagram of the monitoring of pulse method in the embodiment of the present invention；
Fig. 3 is the block diagram of the wearable device in the embodiment of the present invention.
Specific embodiment
The development of the wearable devices such as smartwatch is swift and violent, they have the computing capability and resource of oneself, and generally all can
Be embedded in a variety of MEMS (Micro-Electro-Mechanical System, MEMS) sensor, to the acquisitions of data,
Operation and signal processing provide software and hardware support.In addition, wearable device generally all can long periods of wear with user, if
Monitoring of pulse analytic function is integrated on wearable device, then user can be whenever and wherever possible to the physical condition of oneself
And exception is monitored, it is problematic to find in time, and obtain corresponding help and suggest, user experience is enhanced, together
When can reduce the cost of diagnosing and treating, effectively ensured people's health life.Based on this, the present invention is directed to be to mention
A kind of monitoring of pulse and diagnosis scheme based on wearable devices such as smartwatch out carries out the physiological status such as the pulse of people
Real-time monitoring, and comprehensive analysis and diagnosis are carried out by deep learning, reach and prediction result is prompted to user and correlation is provided
It is recommended that ensureing the purpose of the health of people.
Fig. 1 is the flow chart of the base monitoring of pulse method in the embodiment of the present invention, referring to Fig. 1, the arteries and veins of the embodiment of the present invention
It fights monitoring method, is applied to wearable device, including the following steps:
Step S101 arrives caching using the pulse data and storage of the sensor acquisition user on the wearable device
In；
Step S102 handles the pulse data, and by treated, pulse data is input to training completion in advance
Neural network model in carry out health status prediction, obtain health status prediction result；
Step S103 shows the health status prediction result on the monitoring of pulse interface of wearable device.
As shown in Figure 1 it is found that the monitoring of pulse method of the embodiment of the present invention, monitoring of pulse analytic function, which is integrated into, to be worn
It wears in equipment, since wearable device is often worn on user so that it is convenient to which user pays close attention to the body of oneself whenever and wherever possible
Health status ensure that the accuracy of prediction result moreover, predict according to monitoring of pulse data health status, and
Facilitate timely medical treatment diagnosing and treating when body abnormality, ensures the health of people.It is also possible to which doctor is assisted to examine
It is disconnected, clinical reference is provided.
In practical applications, the realization of the monitoring of pulse method based on wearable device needs to solve following technical problem.
(1) in order to analyze the variation of human pulse, the frequency, power and fluctuation for needing wearable device that can acquire pulse signal become
The data such as change.(2) wearable device computing capability and resource are limited, need to reduce the power consumption of system as far as possible.(3) how accurately
Carry out the analysis and diagnosis of human pulse.Below by taking this wearable device of smartwatch as an example, to the base of the embodiment of the present invention
In the monitoring of pulse method of wearable device solution above-mentioned technical problem and the technological means that uses be illustrated.
The embodiment of the present invention is felt the pulse similar to Traditional Chinese Medicine, is power and changing rule according to pulse, is passed through acquisition
Sensing data analyzes the health status of body using reasonable effective machine learning model, when predicting unusual condition
Corresponding suggestion is provided and is helped, the physical condition for meeting user obtains demand.
It include: pressure sensor on the wearable devices hardware such as smartwatch of the embodiment of the present invention, processor and aobvious
Showing device.It is integrated in the pressure sensor of several impression pulsation on wrist-watch ontology and/or watchband, pressure sensor collects arteries and veins
Frequency, power and the fluctuating change data fought.It should be noted that pressure sensor is when realizing in addition to meeting electrical and property
It can should be also adapted to the structure snd size size of the wearable devices such as smartwatch except index.Processor is then used for data processing
And analysis, the effect of display device are display and interaction.
Fig. 2 is the flow diagram of the monitoring of pulse method in the embodiment of the present invention, referring to fig. 2, a monitoring of pulse mistake
Journey starts, and step S201 is first carried out, and pressure sensor acquires data；
The strong and weak variation of the pulse of user can apply different pressure to sensor, therefore, be obtained by acquisition sensor
To pressure signal be also fluctuations, these data reflect the strong and weak variation of pulse, are also equivalent to obtain in this way
The variation Wave data of pulse.
It should be noted that pressure sensor is only to schematically illustrate in the embodiment of the present invention, sensor is without being limited thereto, can
To replace with any other sensors that can acquire human pulse data according to demand.
Step S202, is saved in caching；
It is suitable with first in first out by the original pulse data of acquisition after collecting original pulse data in the present embodiment
Sequence is stored in the caching of predetermined length, that is, after obtaining original pulse data, is protected in a manner of first in first out (FIFO)
There are in the caching of appropriate length.After data in cache are full of, pre-processed.
Step S203, low-pass filtering；
Since original pulse data inevitably includes noise, to the original pulse data in caching into
Row filtering processing, obtains filtered pulse data.Such as the pulse delta data in caching is passed through into sliding average or other
Low-pass filtering treatment obtains filtered data to remove interference noise.
Step S204, pulse data analysis and prediction；
In this step, the pulse data after filtering processing is input in the neural network model that training is completed in advance and is carried out
Health status prediction, obtains health status prediction result.Referring to fig. 2, when carrying out pulse data analysis and prediction, the present embodiment
In filtered pulse data is predicted by machine learning and using Exception Model.Here Exception Model is according to big
Measure user's sample two-way long short-term memory Recognition with Recurrent Neural Network model that training is completed in advance or bidirectional valve controlled cycling element circulation
Neural network model.
Two-way long short-term memory Recognition with Recurrent Neural Network (Bi-directional Long Short-Term Memory
Recurrent Neural Network, abbreviation BLSTM-RNN) or bidirectional valve controlled cycling element Recognition with Recurrent Neural Network (Bi-
Directional Gated Recurrent Units Recurrent Neural Network BGRU-RNN) even depth
Model is practised, it can be more efficiently compared to classical Recognition with Recurrent Neural Network (Recurrent Neural Network, abbreviation RNN)
To time series signal it is long when context model, more effectively capture its temporal correlation and changing rule, significantly
Ground improves Forecasting recognition performance.
In order to save power consumption and accelerate forecasting efficiency, in present invention implementation, two-way long short-term memory circulation mind is trained in advance
Through network model or bidirectional valve controlled cycling element Recognition with Recurrent Neural Network model and save on the server or smartwatch is local, instruction
Steps are as follows for white silk:
Using wearable device acquisition there is the pulse delta data of the user of different health status to protect as sample data
It deposits, in conjunction with the practical diagnostic result of the sample data, establishes pulse information staqtistical data base, analyze under various health status
Corresponding pulse variation tendency；Two-way long short-term memory is followed using pulse variation tendency data corresponding under various health status
Ring neural network model or bidirectional valve controlled cycling element Recognition with Recurrent Neural Network model are trained, and the difference for obtaining training completion is strong
The variation model of pulse data under health situation.
That is, it is necessary first to acquire a large amount of sample data.For different health status, adopted using smartwatch
It is preserved after collecting the pulse delta data of a large number of users, and (diagnostic result can be done the practical diagnostic result of combination by doctor
Out), pulse information staqtistical data base is established, to analyze the corresponding pulse variation tendency under various physical conditions.Utilize these
Sample data is trained the models such as BLSTM-RNN or BGRU-RNN, trains the pulse data under different health status
Variation model.The health status of user can be analyzed and predicted after obtaining training pattern.
Step S205, judges whether exception；
Filtered pulse data is input to the models such as trained BLSTM-RNN or BGRU-RNN, analyzes Pulse Rate
According to changing rule it is whether consistent with the changing rule of abnormal health status in model, determined if consistent it is abnormal, if
It is inconsistent, determine non-exception.To predict the health status of user, final prediction result is obtained.
Step S206 inquires medical information data library；
In this step, the acquisition of information that user inputs after the health status prediction result for having checked display is obtained to ask
It asks, according to the information acquisition request, sends the inquiry request comprising corresponding health status prediction result information to server；
Receive the Health & Fitness Tip information and related medical resource information for the health status prediction result that the server returns.
Step S207, health status prediction result are shown.
Here display includes the health obtained after inquiry medical information data library when being judged as exception in step S205
Health status prediction knot when being judged as non-abnormal in advisory information and related medical resource information display output and step S205
The display of fruit exports.
Thus in the embodiment of the present invention simultaneously by health index and analysis result etc. information smartwatch pulse
Real-time display is carried out on observation interface.
If it is abnormal that health status prediction result shows that the health status of user occurs, obtained according to the information that user inputs
Request is taken, accesses and inquires the medical information data library on remote server, contain in the medical information data library to difference
The corresponding improvement treatment advice and related medical resource of physical condition and lesion, then return to intelligent hand for query result
Table is shown to user for smartwatch, provided for user reasonably suggest it is for reference.Finally, return step S201 continues to acquire
Pulse data.
In addition, in embodiments of the present invention, method shown in Fig. 2 further comprises: receiving user and open opening for monitoring of pulse
It opens instruction or closes the out code of monitoring of pulse, according to the open command received, control executes monitoring of pulse, and
According to the out code received, monitoring of pulse function is closed in control.
Relevant application programming interface (i.e. API) is provided when practical application, make user to the unlatching of monitoring of pulse and
Closing is controlled and is managed.In this way, the opening and closing of monitoring of pulse function can be freely arranged in user according to actual needs,
To reduce power consumption.
It can be seen from the above, the monitoring of pulse method based on wearable device of the embodiment of the present invention facilitates user whenever and wherever possible
The health status of oneself is detected, is early found when accomplishing problematic, early treatment ensures people's health life.Meanwhile it should
System can also be used as the auxiliary diagnosis means of doctor, provide clinical reference.
A kind of wearable device is additionally provided in the embodiment of the present invention, referring to Fig. 3, wearable device 300 includes: multiple biographies
Sensor 301, the processor 302 being connect with sensor 301 and the display device 303 being connect with the processor 302；
Sensor 301, for acquiring the pulse data of user and storing into caching；
Processor 302, for handling the pulse data, by treated, pulse data is input to preparatory training
Health status prediction is carried out in the neural network model of completion, obtains health status prediction result；
Display device 303, for showing the monitoring of pulse interface comprising the health status prediction result.
It should be noted that Fig. 3 schematically illustrates two sensors, and in other embodiments of the invention, sensing
The quantity of device can be three or more, without being limited thereto.
In one embodiment of the invention, sensor 301 is also used to the original pulse data that will be acquired, with first in first out
It is stored sequentially in the caching of predetermined length；Processor 302 is obtained for being filtered to the original pulse data in caching
To filtered pulse data；
Processor 302 is remembered in short-term specifically for filtered pulse data is input to the two-way length that training is completed in advance
Recall progress health status prediction in Recognition with Recurrent Neural Network model or bidirectional valve controlled cycling element Recognition with Recurrent Neural Network model.
In one embodiment of the invention, two-way long short-term memory Recognition with Recurrent Neural Network model or bidirectional valve controlled circulation are single
Training obtains first Recognition with Recurrent Neural Network model through the following steps: having the use of different health status using wearable device acquisition
The pulse delta data at family is saved as sample data, in conjunction with the practical diagnostic result of the sample data, establishes pulse information
Staqtistical data base, analysis corresponding pulse variation tendency under various health status；Utilize corresponding arteries and veins under various health status
Variation tendency of fighting data are to two-way long short-term memory Recognition with Recurrent Neural Network model or bidirectional valve controlled cycling element Recognition with Recurrent Neural Network
Model is trained, and obtains the variation model of pulse data under the different health status of training completion.
The display device 303 in one embodiment of the invention is also used to obtain user and checks the strong of display
The information acquisition request inputted after health condition predicting result；
The wearable device further include: communication module, for sending comprising corresponding according to the information acquisition request
The inquiry request of health status prediction result information receives the pre- for the health status of the server return to server
The Health & Fitness Tip information and related medical resource information for surveying result, Health & Fitness Tip information and related medical resource information are sent to
The display device carries out display output.
In one embodiment of the invention, the unlatching that display device 303 is also used to receive user's unlatching monitoring of pulse refers to
The out code of monitoring of pulse is enabled or closes, the processor 302 is also used to execute according to the open command received
Monitoring of pulse and according to the out code received, closes monitoring of pulse function.
In conclusion the embodiment of the present invention by traditional theory of traditional Chinese medical science in conjunction with wearable device, artificial intelligence technology,
It on the basis of collecting user's pulse data, is further processed and is analyzed by deep learning, help people convenient and in time
The physical condition for solving oneself can be found in time when there is unusual condition, and provided corresponding suggestion and helped, it is proposed that Yong Huji
When see a doctor diagnosing and treating, ensure the health of people.It is also possible to which doctor is assisted to diagnose, clinical reference is provided.
The electronic equipment of one embodiment of the invention includes memory and processor, by interior between memory and processor
The connection of portion's bus communication, memory is stored with the program instruction that can be executed by processor, when program instruction is executed by processor
It can be realized the above-mentioned monitoring of pulse method based on wearable device.
In addition, the logical order in above-mentioned memory can be realized and as independence by way of SFU software functional unit
Product when selling or using, can store in a computer readable storage medium.Based on this understanding, of the invention
Technical solution substantially the part of the part that contributes to existing technology or the technical solution can be with software in other words
The form of product embodies, which is stored in a storage medium, including some instructions use so that
One computer equipment (can be personal computer, server or the network equipment etc.) executes each embodiment institute of the application
State all or part of the steps of method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read-
Only Memory), random access memory (RAM, Random Access Memory), magnetic or disk etc. are various can be with
Store the medium of program code.
Another embodiment of the present invention provides a kind of computer readable storage medium, computer-readable recording medium storages
Computer instruction, computer instruction make the computer execute above-mentioned method.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The dress for the function of being specified in one box or multiple boxes of one process or multiple processes and/or block diagrams of present flow chart
It sets.
It should be noted that the terms "include", "comprise" or its any other variant are intended to the packet of nonexcludability
Contain, so that the process, method, article or equipment for including a series of elements not only includes those elements, but also including
Other elements that are not explicitly listed, or further include for elements inherent to such a process, method, article, or device.
In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including the element
Process, method, article or equipment in there is also other identical elements.
In specification of the invention, numerous specific details are set forth.Although it is understood that the embodiment of the present invention can
To practice without these specific details.In some instances, well known method, structure and skill is not been shown in detail
Art, so as not to obscure the understanding of this specification.Similarly, it should be understood that disclose in order to simplify the present invention and helps to understand respectively
One or more of a inventive aspect, in the above description of the exemplary embodiment of the present invention, each spy of the invention
Sign is grouped together into a single embodiment, figure, or description thereof sometimes.However, should not be by the method solution of the disclosure
It is interpreted into and reflects an intention that i.e. the claimed invention requires more than feature expressly recited in each claim
More features.More precisely, just as the following claims reflect, inventive aspect is single less than disclosed above
All features of embodiment.Therefore, it then follows thus claims of specific embodiment are expressly incorporated in the specific embodiment party
Formula, wherein each, the claims themselves are regarded as separate embodiments of the invention.
The above description is merely a specific embodiment, under above-mentioned introduction of the invention, those skilled in the art
Other improvement or deformation can be carried out on the basis of the above embodiments.It will be understood by those skilled in the art that above-mentioned tool
Body description only preferably explains that the purpose of the present invention, protection scope of the present invention are subject to the protection scope in claims.
Claims (10)
1. a kind of monitoring of pulse method, which is characterized in that be applied to wearable device, comprising:
Using the pulse data and storage of the sensor acquisition user on the wearable device into caching；
The pulse data is handled, by treated, pulse data is input to the neural network model that training is completed in advance
Middle progress health status prediction, obtains health status prediction result；
The health status prediction result is shown on the monitoring of pulse interface of wearable device.
2. the method according to claim 1, wherein acquisition user pulse data and store include into caching
By the original pulse data of acquisition, it is stored sequentially in the caching of predetermined length with first in first out；The pulse data is carried out
Processing, comprising: the original pulse data in caching is filtered, filtered pulse data is obtained.
3. according to the method described in claim 2, it is characterized in that, pulse data is input to training completion in advance by treated
Neural network model in carry out health status prediction, obtaining health status prediction result includes:
Filtered pulse data is input to and trains the two-way long short-term memory Recognition with Recurrent Neural Network model completed or double in advance
Health status prediction is carried out into gating cycle unit Recognition with Recurrent Neural Network model.
4. according to the method described in claim 3, it is characterized in that, the two-way long short-term memory Recognition with Recurrent Neural Network model or
Training obtains bidirectional valve controlled cycling element Recognition with Recurrent Neural Network model through the following steps:
Using wearable device acquisition there is the pulse delta data of the user of different health status to save as sample data, knot
The practical diagnostic result for closing the sample data, establishes pulse information staqtistical data base, and analysis is corresponding under various health status
Pulse variation tendency；
Using pulse variation tendency data corresponding under various health status to two-way long short-term memory Recognition with Recurrent Neural Network model
Or bidirectional valve controlled cycling element Recognition with Recurrent Neural Network model is trained, and obtains Pulse Rate under the different health status of training completion
According to variation model.
5. the method according to claim 1, wherein this method further comprises:
The information acquisition request that user inputs after the health status prediction result for having checked display is obtained, is obtained according to the information
Request is taken, sends the inquiry request comprising corresponding health status prediction result information to server；
Receive the Health & Fitness Tip information and related medical resource for the health status prediction result that the server returns
Information, by Health & Fitness Tip information and the display output of related medical resource information.
6. the method according to claim 1, wherein this method further comprises:
User is received to open the open command of monitoring of pulse or close the out code of monitoring of pulse,
According to the open command received, control executes monitoring of pulse, and according to the out code received, control
System closes monitoring of pulse function.
7. a kind of wearable device characterized by comprising multiple sensors, the processor being connect with sensor and with institute
State the display device of processor connection；
Sensor, for acquiring the pulse data of user and storing into caching；
Processor, for handling the pulse data, by treated, pulse data is input to what training in advance was completed
Health status prediction is carried out in neural network model, obtains health status prediction result；
Display device, for showing the monitoring of pulse interface comprising the health status prediction result.
8. wearable device according to claim 7, which is characterized in that the sensor is also used to the original arteries and veins that will be acquired
It fights data, is stored sequentially in the caching of predetermined length with first in first out；
The processor obtains filtered pulse data for being filtered to the original pulse data in caching；
The processor is followed specifically for filtered pulse data is input to the two-way long short-term memory that training is completed in advance
Health status prediction is carried out in ring neural network model or bidirectional valve controlled cycling element Recognition with Recurrent Neural Network model.
9. wearable device according to claim 8, which is characterized in that the two-way long short-term memory Recognition with Recurrent Neural Network
Training obtains through the following steps for model or bidirectional valve controlled cycling element Recognition with Recurrent Neural Network model:
Using wearable device acquisition there is the pulse delta data of the user of different health status to save as sample data, knot
The practical diagnostic result for closing the sample data, establishes pulse information staqtistical data base, and analysis is corresponding under various health status
Pulse variation tendency；
Using pulse variation tendency data corresponding under various health status to two-way long short-term memory Recognition with Recurrent Neural Network model
Or bidirectional valve controlled cycling element Recognition with Recurrent Neural Network model is trained, and obtains Pulse Rate under the different health status of training completion
According to variation model.
10. wearable device according to claim 7, which is characterized in that
The display device is also used to obtain the acquisition of information that user inputs after the health status prediction result for having checked display
Request；
The wearable device further include: communication module, for according to the information acquisition request, sending to include corresponding health
The inquiry request of condition predicting result information receives the health status prediction that is directed to that the server returns and ties to server
Health & Fitness Tip information and related medical resource information are sent to described by the Health & Fitness Tip information and related medical resource information of fruit
Display device carries out display output；
The display device, the open command for being also used to receive user's unlatching monitoring of pulse or the closing for closing monitoring of pulse refer to
It enables,
The processor is also used to execute monitoring of pulse and according to the institute received according to the open command received
Out code is stated, monitoring of pulse function is closed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811366462.XA CN109602410A (en) | 2018-11-16 | 2018-11-16 | A kind of wearable device and its monitoring of pulse method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811366462.XA CN109602410A (en) | 2018-11-16 | 2018-11-16 | A kind of wearable device and its monitoring of pulse method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109602410A true CN109602410A (en) | 2019-04-12 |
Family
ID=66004158
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811366462.XA Pending CN109602410A (en) | 2018-11-16 | 2018-11-16 | A kind of wearable device and its monitoring of pulse method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109602410A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110558652A (en) * | 2019-09-19 | 2019-12-13 | 承德石油高等专科学校 | Antifog haze gauze mask of multilayer structure |
| CN111281360A (en) * | 2020-03-06 | 2020-06-16 | 中国人民解放军陆军军医大学第一附属医院 | Health monitoring system for smart bracelet |
| CN111640502A (en) * | 2020-05-29 | 2020-09-08 | 口碑(上海)信息技术有限公司 | Distribution object health state detection method and device |
| CN111631688A (en) * | 2020-06-24 | 2020-09-08 | 电子科技大学 | Algorithm for automatic sleep staging |
| CN112268983A (en) * | 2020-09-25 | 2021-01-26 | 中国建设银行股份有限公司 | A intelligent glasses for health management |
| CN112633473A (en) * | 2020-12-18 | 2021-04-09 | 展讯通信（上海）有限公司 | Wearable device based on AI and application data processing method thereof |
| CN112656387A (en) * | 2020-06-15 | 2021-04-16 | 杭州星迈科技有限公司 | Wearable device data processing method and device and computer device |
| CN113261924A (en) * | 2021-04-15 | 2021-08-17 | 北京雪扬科技有限公司 | Intelligent stroke early warning system and method |
| CN116130095A (en) * | 2023-04-04 | 2023-05-16 | 深圳市金瑞铭科技有限公司 | State monitoring method and device based on sensing technology and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101378251A (en) * | 2007-08-28 | 2009-03-04 | 深圳迈瑞生物医疗电子股份有限公司 | Method for improving signal display quality under a condition of low sampling rate |
| CN103908259A (en) * | 2014-04-03 | 2014-07-09 | 深圳市德凯瑞科技有限公司 | Intelligent wearable device and human motion monitoring and recognition method |
| WO2017171637A1 (en) * | 2016-03-28 | 2017-10-05 | MATTEUCCI, Gianfranco | System and method for monitoring vascular system health |
| 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 |
| CN107582037A (en) * | 2017-09-30 | 2018-01-16 | 深圳前海全民健康科技有限公司 | Method based on pulse wave design medical product |
| CN107595243A (en) * | 2017-07-28 | 2018-01-19 | 深圳和而泰智能控制股份有限公司 | A kind of illness appraisal procedure and terminal device |
| CN107970027A (en) * | 2017-11-23 | 2018-05-01 | 安徽大学 | A kind of radial artery detection and human body constitution identifying system and method |
| CN108095730A (en) * | 2018-01-31 | 2018-06-01 | 成都四海万联科技有限公司 | A kind of hanging equipment of multi-functional chest for monitoring health |
-
2018
- 2018-11-16 CN CN201811366462.XA patent/CN109602410A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101378251A (en) * | 2007-08-28 | 2009-03-04 | 深圳迈瑞生物医疗电子股份有限公司 | Method for improving signal display quality under a condition of low sampling rate |
| CN103908259A (en) * | 2014-04-03 | 2014-07-09 | 深圳市德凯瑞科技有限公司 | Intelligent wearable device and human motion monitoring and recognition method |
| WO2017171637A1 (en) * | 2016-03-28 | 2017-10-05 | MATTEUCCI, Gianfranco | System and method for monitoring vascular system health |
| CN107595243A (en) * | 2017-07-28 | 2018-01-19 | 深圳和而泰智能控制股份有限公司 | A kind of illness appraisal procedure and terminal device |
| 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 |
| CN107582037A (en) * | 2017-09-30 | 2018-01-16 | 深圳前海全民健康科技有限公司 | Method based on pulse wave design medical product |
| CN107970027A (en) * | 2017-11-23 | 2018-05-01 | 安徽大学 | A kind of radial artery detection and human body constitution identifying system and method |
| CN108095730A (en) * | 2018-01-31 | 2018-06-01 | 成都四海万联科技有限公司 | A kind of hanging equipment of multi-functional chest for monitoring health |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110558652A (en) * | 2019-09-19 | 2019-12-13 | 承德石油高等专科学校 | Antifog haze gauze mask of multilayer structure |
| CN111281360A (en) * | 2020-03-06 | 2020-06-16 | 中国人民解放军陆军军医大学第一附属医院 | Health monitoring system for smart bracelet |
| CN111640502A (en) * | 2020-05-29 | 2020-09-08 | 口碑(上海)信息技术有限公司 | Distribution object health state detection method and device |
| CN111640502B (en) * | 2020-05-29 | 2023-08-22 | 口碑(上海)信息技术有限公司 | Method and device for detecting health state of delivery object |
| CN112656387A (en) * | 2020-06-15 | 2021-04-16 | 杭州星迈科技有限公司 | Wearable device data processing method and device and computer device |
| CN111631688A (en) * | 2020-06-24 | 2020-09-08 | 电子科技大学 | Algorithm for automatic sleep staging |
| CN111631688B (en) * | 2020-06-24 | 2021-10-29 | 电子科技大学 | Algorithm for automatic sleep staging |
| CN112268983A (en) * | 2020-09-25 | 2021-01-26 | 中国建设银行股份有限公司 | A intelligent glasses for health management |
| CN112633473A (en) * | 2020-12-18 | 2021-04-09 | 展讯通信（上海）有限公司 | Wearable device based on AI and application data processing method thereof |
| WO2022127497A1 (en) * | 2020-12-18 | 2022-06-23 | 展讯通信（上海）有限公司 | Ai-based wearable device, and application data processing method therefor |
| CN113261924A (en) * | 2021-04-15 | 2021-08-17 | 北京雪扬科技有限公司 | Intelligent stroke early warning system and method |
| CN116130095A (en) * | 2023-04-04 | 2023-05-16 | 深圳市金瑞铭科技有限公司 | State monitoring method and device based on sensing technology and storage medium |
| CN116130095B (en) * | 2023-04-04 | 2023-07-11 | 深圳市金瑞铭科技有限公司 | State monitoring method and device based on sensing technology and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109602410A (en) | A kind of wearable device and its monitoring of pulse method | |
| US10950047B2 (en) | Techniques for anonymizing neuromuscular signal data | |
| Yang et al. | Using PPG signals and wearable devices for atrial fibrillation screening | |
| CN109804331B (en) | Detecting and using body tissue electrical signals | |
| US11672727B2 (en) | Data acquisition and analysis of human sexual response using a personal massaging device | |
| CN109480858B (en) | Wearable intelligent system and method for quantitatively detecting motor retardation symptoms of Parkinson patients | |
| US9161705B2 (en) | Method and device for early detection of heart attack | |
| CN107714024A (en) | For monitoring the method, system and device of cardiomotility | |
| Tazarv et al. | A deep learning approach to predict blood pressure from ppg signals | |
| CN104200120A (en) | System and method for health status monitoring based on traditional Chinese medicine diagnosis information | |
| WO2015200750A1 (en) | Early detection of hemodynamic decompensation using taut-string transformation | |
| KR20170045099A (en) | System, method and program for analyzing blood flow by deep neural network | |
| CN110037668A (en) | The system that pulse signal time-space domain binding model judges age, health status and malignant arrhythmia identification | |
| Scrugli et al. | An adaptive cognitive sensor node for ECG monitoring in the Internet of Medical Things | |
| CN108323158A (en) | Heart sound identification method and cloud system | |
| CN107361753A (en) | Health state monitoring method based on pulse wave characteristic point | |
| Diab et al. | Embedded machine learning using microcontrollers in wearable and ambulatory systems for health and care applications: A review | |
| CN109065163A (en) | Tcm diagnosis service platform | |
| Chen et al. | Edge2Analysis: a novel AIoT platform for atrial fibrillation recognition and detection | |
| RU2657966C2 (en) | Device and method for remote wireless diagnostics of the functional state of the cardiovascular system of human on the basis of motor activity and photoplethysmography | |
| CN112370057A (en) | Pressure evaluation method and device, computer equipment and storage medium | |
| Vanmechelen et al. | Assessment of movement disorders using wearable sensors during upper limb tasks: A scoping review | |
| US20220000426A1 (en) | Multi-modal brain-computer interface based system and method | |
| CN110200642A (en) | A kind of measurement method and terminal of cognitive load and psychological pressure | |
| Aggelides et al. | A gesture recognition approach to classifying allergic rhinitis gestures using wrist-worn devices: a multidisciplinary case study |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20191115 Address after: 266104 Laoshan Qingdao District North House Street investment service center room, Room 308, Shandong Applicant after: GOERTEK TECHNOLOGY Co.,Ltd. Address before: 266061, No. 3, building 18, Qinling Mountains Road, Laoshan District, Shandong, Qingdao 401 Applicant before: QINGDAO ZHENSHI TECHNOLOGY CO.,LTD. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190412 |