CN107220491A - Cloud Server, the method reminded and computer-readable recording medium - Google Patents
Cloud Server, the method reminded and computer-readable recording medium Download PDFInfo
- Publication number
- CN107220491A CN107220491A CN201710354254.7A CN201710354254A CN107220491A CN 107220491 A CN107220491 A CN 107220491A CN 201710354254 A CN201710354254 A CN 201710354254A CN 107220491 A CN107220491 A CN 107220491A
- Authority
- CN
- China
- Prior art keywords
- user
- hospital
- data
- network system
- probability
- 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
Abstract
The present invention relates to a kind of Cloud Server, the method reminded and computer-readable recording medium, Cloud Server includes：Memory, processor and the processing routine that can be run on the memory and on the processor is stored in, following steps are realized when the processing routine is by the computing device：Obtain time data of the user during non-be in hospital and the treatment data in non-period lung ventilator of being in hospital；The time data and the treatment data are inputted to the nerve network system pre-established, and obtain the abnormity prompt probability of the nerve network system output；If the abnormity prompt probability is more than or equal to default probability threshold value, prompting message is sent to user's lung ventilator.The nerve network system technology that the present invention is handled based on Cloud Server and big data, according to the medical situation of the history of user, can remind user in time when user is likely to occur exception.
Description
Technical field
The present invention relates to communication technical field, more particularly to a kind of Cloud Server, the method reminded and computer-readable deposit
Storage media.
Background technology
At present, it is usually to be gone to a doctor after morbidity for COPD COPD, user returns after taking a turn for the better
Go home middle carry out auxiliary treatment.The characteristics of having recurrent exerbation due to COPD, the time of recurrence can not be advance
It is determined that, therefore how according to the medical situation of the history of user, remind user to turn into urgently in time when user is likely to occur exception
The problem of solution.
The content of the invention
It is an object of the invention to provide a kind of Cloud Server, the method reminded and computer-readable recording medium, it is intended to
The nerve network system technology handled based on Cloud Server and big data, may in user according to the medical situation of the history of user
User can be reminded in time when occurring abnormal.
To achieve the above object, the present invention provides a kind of Cloud Server, it is characterised in that the Cloud Server includes：Deposit
Reservoir, processor and it is stored in the processing routine that can be run on the memory and on the processor, the processing routine
Following steps are realized during by the computing device：
S1, obtains time data of the user during non-be in hospital and the treatment data in non-period lung ventilator of being in hospital；
S2, the time data and the treatment data is inputted to the nerve network system pre-established, and obtain institute
State the abnormity prompt probability of nerve network system output；
S3, if the abnormity prompt probability is more than or equal to default probability threshold value, sends to user's lung ventilator and reminds letter
Breath.
Preferably, before the processing routine realizes the step S2 by the computing device, in addition to：
Obtain the training set of nerve network system, the user of the training set including the first predetermined number in non-hospital stay
Between time data, it is non-be in hospital during lung ventilator treatment data and corresponding abnormity prompt probability；
Obtain the checking collection of nerve network system, the user of the checking collection including the second predetermined number in non-hospital stay
Between time data, it is non-be in hospital during lung ventilator treatment data and corresponding abnormity prompt probability；
The neutral net is trained using the corresponding time data of each user, treatment data and abnormity prompt probability in training set
The pattern function of system；
The god after the corresponding time data of each user, treatment data and the training of abnormity prompt probabilistic verification is concentrated using checking
Pattern function through network system；
If being verified rate more than or equal to predetermined threshold value, training is completed, and institute is used as using the nerve network system after training
State the nerve network system set up in step S2, otherwise increase the quantity of the user of the training set, with re-start training and
Checking.
Preferably, the treatment data include pressure data P, respiratory rate average B, tidal volume average V, blood oxygen average S,
Heart rate data H and number of days D is persistently used, the pattern function is：Abnormity prompt probability Q=P*W1+B*W2+V*W3+S*W4+H*
W5+D*W6, wherein, the W1 is the weights of pressure data, and the W2 is the weights of respiratory rate average, and the W3 is tidal volume
Weights, the W4 be blood oxygen weights, the W5 be heart rate weights, the W6 for persistently use number of days weights.
Preferably, after the processing routine realizes the step S1 by the computing device, in addition to：
Obtain user be in hospital during lung ventilator treatment data, based on user it is non-be in hospital during time data,
It is non-be in hospital during lung ventilator treatment data and during being in hospital lung ventilator treatment data generation using report, and make described
Fed back to report on user's lung ventilator or predetermined user terminal, to be shown.
To achieve the above object, the present invention also provides a kind of method of prompting, and the method for the prompting includes：
S1, obtains time data of the user during non-be in hospital and the treatment data in non-period lung ventilator of being in hospital；
S2, the time data and the treatment data is inputted to the nerve network system pre-established, and obtain institute
State the abnormity prompt probability of nerve network system output；
S3, if the abnormity prompt probability is more than or equal to default probability threshold value, sends to user's lung ventilator and reminds letter
Breath.
Preferably, before the step S2, in addition to：
Obtain the training set of nerve network system, the user of the training set including the first predetermined number in non-hospital stay
Between time data, it is non-be in hospital during lung ventilator treatment data and corresponding abnormity prompt probability；
Obtain the checking collection of nerve network system, the user of the checking collection including the second predetermined number in non-hospital stay
Between time data, it is non-be in hospital during lung ventilator treatment data and corresponding abnormity prompt probability；
The neutral net is trained using the corresponding time data of each user, treatment data and abnormity prompt probability in training set
The pattern function of system；
The god after the corresponding time data of each user, treatment data and the training of abnormity prompt probabilistic verification is concentrated using checking
Pattern function through network system；
If being verified rate more than or equal to predetermined threshold value, training is completed, and institute is used as using the nerve network system after training
State the nerve network system set up in step S2, otherwise increase the quantity of the user of the training set, with re-start training and
Checking.
Preferably, the treatment data include pressure data P, respiratory rate average B, tidal volume average V, blood oxygen average S,
Heart rate data H and number of days D is persistently used, the pattern function is：Abnormity prompt probability Q=P*W1+B*W2+V*W3+S*W4+H*
W5+D*W6, wherein, the W1 is the weights of pressure data, and the W2 is the weights of respiratory rate average, and the W3 is tidal volume
Weights, the W4 be blood oxygen weights, the W5 be heart rate weights, the W6 for persistently use number of days weights.
Preferably, after the step S1, in addition to：
Obtain user be in hospital during lung ventilator treatment data, based on user it is non-be in hospital during time data,
It is non-be in hospital during lung ventilator treatment data and during being in hospital lung ventilator treatment data generation using report, and make described
Fed back to report on user's lung ventilator or predetermined user terminal, to be shown.
The present invention also provides the processing that is stored with a kind of computer-readable recording medium, the computer-readable recording medium
Program, the step of realizing the method reminded described above when the processing routine is executed by processor.
The beneficial effects of the invention are as follows：The lung ventilator of the present invention is in use by network by time data and treatment
Data reach Cloud Server in real time, and Cloud Server is analyzed these data using nerve network system algorithm, draw correspondence
Abnormity prompt probability, when abnormity prompt probability is more than or equal to default probability threshold value, send prompting message to remind user
The recent state of an illness situation of concern.The nerve network system technology that the present invention is handled based on Cloud Server and big data, according to user
History go to a doctor situation, user can be reminded in time when user is likely to occur exception.
Brief description of the drawings
Fig. 1 is the optional application environment schematic diagram of each embodiment one of the invention；
Fig. 2 is the schematic diagram of the hardware structure of the embodiment of Cloud Server one in Fig. 1；
The schematic flow sheet for the embodiment of method one that Fig. 3 reminds for the present invention.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that specific embodiment described herein is only to explain the present invention, not
For limiting the present invention.Based on the embodiment in the present invention, those of ordinary skill in the art are not before creative work is made
The every other embodiment obtained is put, the scope of protection of the invention is belonged to.
It should be noted that the description for being related to " first ", " second " etc. in the present invention is only used for describing purpose, and can not
It is interpreted as indicating or implies its relative importance or the implicit quantity for indicating indicated technical characteristic.Thus, define " the
One ", at least one this feature can be expressed or be implicitly included to the feature of " second ".In addition, the skill between each embodiment
Art scheme can be combined with each other, but must can be implemented as basis with those of ordinary skill in the art, when technical scheme
With reference to occur it is conflicting or when can not realize it will be understood that the combination of this technical scheme is not present, also not in application claims
Protection domain within.
It is the optional application environment schematic diagram of each embodiment one of the invention refering to Fig. 1.In the present embodiment, it is of the invention
It can be applied to include but not limited to, Cloud Server 1, external network 2, the application of Wifi/3G/4G (3) and user's lung ventilator 4
In environment.
Wherein, the Cloud Server 1 can be rack-mount server, blade server, tower server or cabinet-type
The computing devices such as server, the application server 2 can be the clothes that independent server or multiple servers are constituted
Business device cluster.Preferably, Cloud Server 1 is generally set up by related functional department of lung ventilator producer, large hospital or government.
The external network 2 can be intranet (Intranet), internet (Internet), global system for mobile telecommunications
System (Global System of Mobile communication, GSM), WCDMA (Wideband Code
Division Multiple Access, WCDMA), 4G networks, 5G networks, bluetooth (Bluetooth), Wi-Fi etc. is wireless or has
Gauze network.Wherein, the external network 2 and each Wifi/3G/4G (3) and corresponding one or many are passed through in the Cloud Server 1
Individual user's lung ventilator 4 is communicated to connect.
Refering to Fig. 2, in being the schematic diagram of the optional hardware structure of Cloud Server 1 one in Fig. 1, the present embodiment, Cloud Server 1
It may include, but be not limited only to, be in communication with each other the memory 11, processor 12, network interface 13 of connection.It is pointed out that Fig. 2
The Cloud Server 1 with component 10-13 is illustrate only, it should be understood that be not required for implementing all components shown, can
With the more or less component of the implementation of replacement.
Wherein, the memory 11 at least includes a type of readable storage medium storing program for executing, and the readable storage medium storing program for executing includes
Flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memories etc.), random access storage device (RAM), it is static with
Machine access memory (SRAM), read-only storage (ROM), Electrically Erasable Read Only Memory (EEPROM), it is programmable only
Read memory (PROM), magnetic storage, disk, CD etc..In certain embodiments, the memory 11 can be the cloud
The hard disk or internal memory of the internal storage unit of server 1, such as Cloud Server 1.In further embodiments, the memory
11 can also be the External memory equipment of the Cloud Server 1, such as the plug-in type hard disk being equipped with the Cloud Server 1, intelligence
Storage card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, flash card (Flash Card)
Deng.Certainly, the memory 11 can also both including the Cloud Server 1 internal storage unit or set including its external storage
It is standby.In the present embodiment, the memory 11 is generally used for storing the operating system and types of applications for being installed on the Cloud Server 1
Software, such as the program code of the processing routine.In addition, the memory 11 can be also used for temporarily storing defeated
The Various types of data that goes out or will export.
The processor 12 can be in certain embodiments central processing unit (Central Processing Unit,
CPU), controller, microcontroller, microprocessor or other data processing chips.The processor 12 is generally used for controlling the cloud
The overall operation of server 1, for example, perform the control and processing related to the external network 2 progress data interaction or communication
Deng.In the present embodiment, the processor 12 is used to run the program code stored in the memory 11 or processing data, example
The processing routine as described in running.
The network interface 13 may include radio network interface or wired network interface, and the network interface 13 is generally used for
Communication connection is set up between the Cloud Server 1 and other equipment.In the present embodiment, the network interface 13 is used for by described
External network 2 is connected with each Wifi/3G/4G (3), to be connected by Wifi/3G/4G (3) with one or more user's lung ventilators 4
Connect, to set up data transmission channel and communication connection.
Wherein, following steps are realized when above-mentioned processing routine is performed by the processor 12：
Step S1, obtains time data of the user during non-be in hospital and the treatment data in non-period lung ventilator of being in hospital；
In the present embodiment, because user's lung ventilator 4 and Cloud Server 1 are typically employed in the closed system of hospital, therefore,
Preferably, time data of the user in non-period of being in hospital and the treatment data in non-period lung ventilator of being in hospital are by user's lung ventilator 4
It is uploaded in Cloud Server 1.
Wherein, the time data of selection user recent non-hospital stays and the treatment number in the selected non-hospital stays
According to for example, user lives during 2016/12/1-016/12/10,2017/1/3-2017/1/10,2017/2/5-2017/2/10
Institute's (2017/2/10 is not in hospital so far), then choose 2017/1/10-2017/2/5, the time of 201,7/2,/10 twice so far
Data and treatment data.
Wherein, time data includes the start time and the time end point of non-hospital stays of non-hospital stays；Treat number
According to including pressure data P, respiratory rate average B, tidal volume average V, blood oxygen average S, heart rate data H and persistently use number of days D.
Step S2, the time data and the treatment data are inputted to the nerve network system pre-established, and is obtained
Take the abnormity prompt probability of the nerve network system output；
Step S3, if the abnormity prompt probability is more than or equal to default probability threshold value, sends to lung ventilator and reminds letter
Breath.
Wherein, first using substantial amounts of user in the time data during non-be in hospital and the lung ventilator during non-be in hospital
Treatment data carries out the study of predetermined nerve network system, to set up the nerve network system for using, it is preferable that the nerve
Network system is BP neural network system.
After nerve network system is set up, for a certain user, can by its in the recent period the time data of non-hospital stays and
Treatment data in the selected non-hospital stays is counted as the input of the nerve network system by the nerve network system
Calculate, and export corresponding abnormity prompt probability, the abnormity prompt probability is that the exception after the user leaves hospital the last time so far is general
Rate.
Preferably, can be in user's non-hospital stays in the recent period, using the time data of continuous three days and treatment data as god
Once input through network, if the abnormity prompt probability of output is all higher than for continuous three times being equal to default probability threshold value, (this is preset
Probability threshold value be prior probability, for example, 0.7), then user is reminded, such as Cloud Server 1 by external networks 2 to
User's lung ventilator 4 sends prompting message, or Cloud Server 1 by external networks 2 to predetermined user terminal (for example mobile phone or
Tablet personal computer etc.) prompting message is sent, to remind user to pay close attention to recent state of an illness situation.
Compared with prior art, the present embodiment lung ventilator is in use by network by time data and treatment data
Cloud Server is reached in real time, Cloud Server is analyzed these data using nerve network system algorithm, is drawn corresponding different
Probability is often reminded, when abnormity prompt probability is more than or equal to default probability threshold value, sends prompting message to remind user to pay close attention to
Recent state of an illness situation.The nerve network system technology that the present embodiment is handled based on Cloud Server and big data, according to user's
History is gone to a doctor situation, can remind user in time when user is likely to occur exception.
In a preferred embodiment, on the basis of above-mentioned Fig. 2 embodiment, the processing routine is by the processor
12 perform before realizing the step S2, in addition to：
Obtain the training set of nerve network system, the user of the training set including the first predetermined number in non-hospital stay
Between time data, it is non-be in hospital during lung ventilator treatment data and corresponding abnormity prompt probability.Wherein, the first present count
Amount is, for example, 70,000, and each use includes its time data during non-be in hospital, the treatment number in non-period lung ventilator of being in hospital per family
According to and corresponding abnormity prompt probability.
Obtain the checking collection of nerve network system, the user of the checking collection including the second predetermined number in non-hospital stay
Between time data, it is non-be in hospital during lung ventilator treatment data and corresponding abnormity prompt probability.Wherein, the second present count
Amount is, for example, 30,000, and each use includes its time data during non-be in hospital, the treatment number in non-period lung ventilator of being in hospital per family
According to and corresponding abnormity prompt probability.
The neutral net is trained using the corresponding time data of each user, treatment data and abnormity prompt probability in training set
The pattern function of system.
Wherein, the pattern function is：Abnormity prompt probability Q=P*W1+B*W2+V*W3+S*W4+H*W5+D*W6, its
In, the W1 is the weights of pressure data, and the W2 is the weights of respiratory rate average, and the W3 is the weights of tidal volume, institute
The weights that W4 is blood oxygen are stated, the W5 is the weights of heart rate, and the W6 is persistently using the weights of number of days.
Wherein, in addition to lasting use number of days D, remaining pressure data P, respiratory rate average B, tidal volume average V, blood oxygen
Average S, heart rate data H are provided in the form of array, such as in units of day, pressure data P, breathing frequency of the user in one day
Rate average B, tidal volume average V, blood oxygen average S, heart rate data H are respectively an array.
Wherein, after the pattern function of the nerve network system is trained by mass data, pressure data is finally drawn
Weights W1, the weights W2 of respiratory rate average, the weights W3 of tidal volume, the weights W4 of blood oxygen, the weights W5 of heart rate and persistently make
With the weights W6 of number of days optimal value.
The god after the corresponding time data of each user, treatment data and the training of abnormity prompt probabilistic verification is concentrated using checking
Pattern function through network system.
If being verified rate more than or equal to predetermined threshold value (predetermined threshold value is, for example, 0.98), training is completed, after training
Nerve network system as the nerve network system set up in the step S2, otherwise increase the number of the user of the training set
Amount, to re-start training and verify.
In a preferred embodiment, on the basis of above-mentioned Fig. 2 embodiment, the processing routine is by the processor
After 12 perform and realize the step S1, in addition to：
Obtain user be in hospital during lung ventilator treatment data, based on user it is non-be in hospital during time data,
It is non-be in hospital during lung ventilator treatment data and during being in hospital lung ventilator treatment data generation using report, and make described
Fed back to report on user's lung ventilator or predetermined user terminal, to be shown.
In the present embodiment, Cloud Server 1 can exist after the time data and treatment data of user is received with reference to user
The treatment data generation of lung ventilator is corresponding during in hospital includes the pressure of lung ventilator using report using the content of report, uses
The average respiratory rate at family, the average tidal volume of user, the information such as the average blood oxygen and heart rate of user.Further, can be with
Pressure, average respiratory rate, average tidal volume, average blood oxygen and heart rate are generated into corresponding oscillogram, for example, using day as horizontal stroke
Axle, the data cube computation in adjacent day is got up to obtain oscillogram, and the oscillogram is attached to using in report.Report will be finally used to feed back
To on user's lung ventilator or predetermined user terminal, shown, check or refer to for user.
As shown in figure 3, the schematic flow sheet for the embodiment of method one that Fig. 3 reminds for the present invention, the method application of the prompting
In Cloud Server, comprise the following steps：
Step S1, obtains time data of the user during non-be in hospital and the treatment data in non-period lung ventilator of being in hospital；
It is therefore, excellent because user's lung ventilator and Cloud Server are typically employed in the closed system of hospital in the present embodiment
Selection of land, in the time data during non-be in hospital and during non-be in hospital, the treatment data of lung ventilator is uploaded user by user's lung ventilator
Into Cloud Server.
Wherein, the time data of selection user recent non-hospital stays and the treatment number in the selected non-hospital stays
According to for example, user lives during 2016/12/1-016/12/10,2017/1/3-2017/1/10,2017/2/5-2017/2/10
Institute's (2017/2/10 is not in hospital so far), then choose 2017/1/10-2017/2/5, the time of 201,7/2,/10 twice so far
Data and treatment data.
Wherein, time data includes the start time and the time end point of non-hospital stays of non-hospital stays；Treat number
According to including pressure data P, respiratory rate average B, tidal volume average V, blood oxygen average S, heart rate data H and persistently use number of days D.
Step S2, the time data and the treatment data are inputted to the nerve network system pre-established, and is obtained
Take the abnormity prompt probability of the nerve network system output；
Step S3, if the abnormity prompt probability is more than or equal to default probability threshold value, sends to user's lung ventilator and carries
Awake information.
Wherein, first using substantial amounts of user in the time data during non-be in hospital and the lung ventilator during non-be in hospital
Treatment data carries out the study of predetermined nerve network system, to set up the nerve network system for using, it is preferable that the nerve
Network system is BP neural network system.
After nerve network system is set up, for a certain user, can by its in the recent period the time data of non-hospital stays and
Treatment data in the selected non-hospital stays is counted as the input of the nerve network system by the nerve network system
Calculate, and export corresponding abnormity prompt probability, the abnormity prompt probability is that the exception after the user leaves hospital the last time so far is general
Rate.
Preferably, can be in user's non-hospital stays in the recent period, using the time data of continuous three days and treatment data as god
Once input through network, if the abnormity prompt probability of output is all higher than for continuous three times being equal to default probability threshold value, (this is preset
Probability threshold value be prior probability, for example, 0.7), then user is reminded, such as Cloud Server by external networks to
Family lung ventilator sends prompting message, or Cloud Server by external networks to predetermined user terminal (such as mobile phone or flat board
Computer etc.) prompting message is sent, to remind user to pay close attention to recent state of an illness situation.
Compared with prior art, the present embodiment lung ventilator is in use by network by time data and treatment data
Cloud Server is reached in real time, Cloud Server is analyzed these data using nerve network system algorithm, is drawn corresponding different
Probability is often reminded, when abnormity prompt probability is more than or equal to default probability threshold value, sends prompting message to remind user to pay close attention to
Recent state of an illness situation.The nerve network system technology that the present embodiment is handled based on Cloud Server and big data, according to user's
History is gone to a doctor situation, can remind user in time when user is likely to occur exception.
In a preferred embodiment, on the basis of above-mentioned Fig. 3 embodiment, before the step S2, in addition to：
Obtain the training set of nerve network system, the user of the training set including the first predetermined number in non-hospital stay
Between time data, it is non-be in hospital during lung ventilator treatment data and corresponding abnormity prompt probability.Wherein, the first present count
Amount is, for example, 70,000, and each use includes its time data during non-be in hospital, the treatment number in non-period lung ventilator of being in hospital per family
According to and corresponding abnormity prompt probability.
Obtain the checking collection of nerve network system, the user of the checking collection including the second predetermined number in non-hospital stay
Between time data, it is non-be in hospital during lung ventilator treatment data and corresponding abnormity prompt probability.Wherein, the second present count
Amount is, for example, 30,000, and each use includes its time data during non-be in hospital, the treatment number in non-period lung ventilator of being in hospital per family
According to and corresponding abnormity prompt probability.
The neutral net is trained using the corresponding time data of each user, treatment data and abnormity prompt probability in training set
The pattern function of system.
Wherein, the pattern function is：Abnormity prompt probability Q=P*W1+B*W2+V*W3+S*W4+H*W5+D*W6, its
In, the W1 is the weights of pressure data, and the W2 is the weights of respiratory rate average, and the W3 is the weights of tidal volume, institute
The weights that W4 is blood oxygen are stated, the W5 is the weights of heart rate, and the W6 is persistently using the weights of number of days.
Wherein, in addition to lasting use number of days D, remaining pressure data P, respiratory rate average B, tidal volume average V, blood oxygen
Average S, heart rate data H are provided in the form of array, such as in units of day, pressure data P, breathing frequency of the user in one day
Rate average B, tidal volume average V, blood oxygen average S, heart rate data H are respectively an array.
Wherein, after the pattern function of the nerve network system is trained by mass data, pressure data is finally drawn
Weights W1, the weights W2 of respiratory rate average, the weights W3 of tidal volume, the weights W4 of blood oxygen, the weights W5 of heart rate and persistently make
With the weights W6 of number of days optimal value.
The god after the corresponding time data of each user, treatment data and the training of abnormity prompt probabilistic verification is concentrated using checking
Pattern function through network system；
If being verified rate more than or equal to predetermined threshold value (predetermined threshold value is, for example, 0.98), training is completed, after training
Nerve network system as the nerve network system set up in the step S2, otherwise increase the number of the user of the training set
Amount, to re-start training and verify.
In a preferred embodiment, on the basis of above-mentioned Fig. 3 embodiment, after the step S1, in addition to：
Obtain user be in hospital during lung ventilator treatment data, based on user it is non-be in hospital during time data,
It is non-be in hospital during lung ventilator treatment data and during being in hospital lung ventilator treatment data generation using report, and make described
Fed back to report on user's lung ventilator or predetermined user terminal, to be shown.
In the present embodiment, Cloud Server can exist after the time data and treatment data of user is received with reference to user
The treatment data generation of lung ventilator is corresponding during in hospital includes the pressure of lung ventilator using report using the content of report, uses
The average respiratory rate at family, the average tidal volume of user, the information such as the average blood oxygen and heart rate of user.Further, can be with
Pressure, average respiratory rate, average tidal volume, average blood oxygen and heart rate are generated into corresponding oscillogram, for example, using day as horizontal stroke
Axle, the data cube computation in adjacent day is got up to obtain oscillogram, and the oscillogram is attached to using in report.Report will be finally used to feed back
To on user's lung ventilator or predetermined user terminal, shown, check or refer to for user.
The present invention also provides the processing that is stored with a kind of computer-readable recording medium, the computer-readable recording medium
Program, the processing routine realizes the method for above-mentioned prompting when being executed by processor the step of.
The embodiments of the present invention are for illustration only, and the quality of embodiment is not represented.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Understood based on such, technical scheme is substantially done to prior art in other words
Going out the part of contribution can be embodied in the form of software product, and the computer software product is stored in a storage medium
In (such as ROM/RAM, magnetic disc, CD), including some instructions are to cause a station terminal equipment (can be mobile phone, computer, clothes
It is engaged in device, air conditioner, or network equipment etc.) perform method described in each embodiment of the invention.
The preferred embodiments of the present invention are these are only, are not intended to limit the scope of the invention, it is every to utilize this hair
Equivalent structure or equivalent flow conversion that bright specification and accompanying drawing content are made, or directly or indirectly it is used in other related skills
Art field, is included within the scope of the present invention.
Claims (9)
1. a kind of Cloud Server, it is characterised in that the Cloud Server includes：Memory, processor and it is stored in the storage
On device and the processing routine that can run on the processor, the processing routine is realized following step during the computing device
Suddenly：
S1, obtains time data of the user during non-be in hospital and the treatment data in non-period lung ventilator of being in hospital；
S2, the time data and the treatment data is inputted to the nerve network system pre-established, and obtain the god
The abnormity prompt probability exported through network system；
S3, if the abnormity prompt probability is more than or equal to default probability threshold value, prompting message is sent to user's lung ventilator.
2. Cloud Server according to claim 1, it is characterised in that the processing routine is realized by the computing device
Before the step S2, in addition to：
Obtain the training set of nerve network system, the user of the training set including the first predetermined number during non-be in hospital
Time data, treatment data and corresponding abnormity prompt probability in non-period lung ventilator of being in hospital；
Obtain the checking collection of nerve network system, the user of the checking collection including the second predetermined number during non-be in hospital
Time data, treatment data and corresponding abnormity prompt probability in non-period lung ventilator of being in hospital；
The nerve network system is trained using the corresponding time data of each user, treatment data and abnormity prompt probability in training set
Pattern function；
The nerve net after the corresponding time data of each user, treatment data and the training of abnormity prompt probabilistic verification is concentrated using checking
The pattern function of network system；
If being verified rate more than or equal to predetermined threshold value, training is completed, and the step is used as using the nerve network system after training
The nerve network system set up in rapid S2, otherwise increases the quantity of the user of the training set, to re-start training and verify.
3. Cloud Server according to claim 2, it is characterised in that the treatment data includes pressure data P, breathing frequency
Rate average B, tidal volume average V, blood oxygen average S, heart rate data H and number of days D is persistently used, the pattern function is：Exception is carried
Wake up probability Q=P*W1+B*W2+V*W3+S*W4+H*W5+D*W6, wherein, the W1 is the weights of pressure data, and the W2 is to exhale
The weights of mean frequency value are inhaled, the W3 is the weights of tidal volume, and the W4 is the weights of blood oxygen, and the W5 is the weights of heart rate,
The W6 is persistently using the weights of number of days.
4. the Cloud Server according to any one of claims 1 to 3, it is characterised in that the processing routine is by the processing
Device is performed realize the step S1 after, in addition to：
Obtain user be in hospital during lung ventilator treatment data, based on user it is non-be in hospital during time data, it is non-live
The treatment data of lung ventilator and the treatment data generation in period lung ventilator of being in hospital use report during institute, and use report by described
Announcement is fed back on user's lung ventilator or predetermined user terminal, to be shown.
5. a kind of method of prompting, it is characterised in that the method for the prompting includes：
S1, obtains time data of the user during non-be in hospital and the treatment data in non-period lung ventilator of being in hospital；
S2, the time data and the treatment data is inputted to the nerve network system pre-established, and obtain the god
The abnormity prompt probability exported through network system；
S3, if the abnormity prompt probability is more than or equal to default probability threshold value, prompting message is sent to user's lung ventilator.
6. the method for prompting according to claim 5, it is characterised in that before the step S2, in addition to：
Obtain the training set of nerve network system, the user of the training set including the first predetermined number during non-be in hospital
Time data, treatment data and corresponding abnormity prompt probability in non-period lung ventilator of being in hospital；
Obtain the checking collection of nerve network system, the user of the checking collection including the second predetermined number during non-be in hospital
Time data, treatment data and corresponding abnormity prompt probability in non-period lung ventilator of being in hospital；
The nerve network system is trained using the corresponding time data of each user, treatment data and abnormity prompt probability in training set
Pattern function；
The nerve net after the corresponding time data of each user, treatment data and the training of abnormity prompt probabilistic verification is concentrated using checking
The pattern function of network system；
If being verified rate more than or equal to predetermined threshold value, training is completed, and the step is used as using the nerve network system after training
The nerve network system set up in rapid S2, otherwise increases the quantity of the user of the training set, to re-start training and verify.
7. the method for prompting according to claim 6, it is characterised in that the treatment data includes pressure data P, breathing
Mean frequency value B, tidal volume average V, blood oxygen average S, heart rate data H and number of days D is persistently used, the pattern function is：It is abnormal
Probability Q=P*W1+B*W2+V*W3+S*W4+H*W5+D*W6 is reminded, wherein, the W1 is the weights of pressure data, and the W2 is
The weights of respiratory rate average, the W3 is the weights of tidal volume, and the W4 is the weights of blood oxygen, and the W5 is the power of heart rate
Value, the W6 is persistently using the weights of number of days.
8. the method for the prompting according to any one of claim 5 to 7, it is characterised in that after the step S1, also wrap
Include：
Obtain user be in hospital during lung ventilator treatment data, based on user it is non-be in hospital during time data, it is non-live
The treatment data of lung ventilator and the treatment data generation in period lung ventilator of being in hospital use report during institute, and use report by described
Announcement is fed back on user's lung ventilator or predetermined user terminal, to be shown.
9. a kind of computer-readable recording medium, it is characterised in that be stored with processing journey on the computer-readable recording medium
Sequence, the step of the method for prompting of the realization as any one of claim 5 to 8 when the processing routine is executed by processor
Suddenly.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710354254.7A CN107220491A (en) | 2017-05-18 | 2017-05-18 | Cloud Server, the method reminded and computer-readable recording medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710354254.7A CN107220491A (en) | 2017-05-18 | 2017-05-18 | Cloud Server, the method reminded and computer-readable recording medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107220491A true CN107220491A (en) | 2017-09-29 |
Family
ID=59944241
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710354254.7A Pending CN107220491A (en) | 2017-05-18 | 2017-05-18 | Cloud Server, the method reminded and computer-readable recording medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107220491A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110910586A (en) * | 2019-11-28 | 2020-03-24 | 中国银行股份有限公司 | Anti-theft card swiping method and system |
| CN112329812A (en) * | 2020-09-29 | 2021-02-05 | 湖南明康中锦医疗科技发展有限公司 | Slow obstructive pulmonary acute exacerbation automatic early warning method and platform and readable storage medium |
| CN112870504A (en) * | 2019-11-29 | 2021-06-01 | 深圳市大雅医疗技术有限公司 | Respiratory therapy method and device, breathing machine and server |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001000265A1 (en) * | 1999-06-30 | 2001-01-04 | University Of Florida | Medical ventilator and method of controlling same |
| US20090118632A1 (en) * | 2007-11-05 | 2009-05-07 | Goepp Julius G | Effort-Independent, Portable, User-Operated Capnograph Devices And Related Methods |
| CN103201743A (en) * | 2010-11-08 | 2013-07-10 | 皇家飞利浦电子股份有限公司 | Method of continuous prediction of patient severity of illness, mortality, and length of stay |
| CN104135925A (en) * | 2012-02-20 | 2014-11-05 | 佛罗里达大学研究基金会有限公司 | Method and apparatus for predicting work of breathing |
| CN105125215A (en) * | 2015-10-08 | 2015-12-09 | 湖南明康中锦医疗科技发展有限公司 | Neural network based breathing machine state analytic method and device |
| EP3006071A1 (en) * | 2014-10-07 | 2016-04-13 | Hersill, S.L. | Demand oxygen delivery system |
| CN106039510A (en) * | 2016-07-29 | 2016-10-26 | 湖南明康中锦医疗科技发展有限公司 | Breathing machine safety control method, breathing machine and cloud platform |
-
2017
- 2017-05-18 CN CN201710354254.7A patent/CN107220491A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001000265A1 (en) * | 1999-06-30 | 2001-01-04 | University Of Florida | Medical ventilator and method of controlling same |
| US20090118632A1 (en) * | 2007-11-05 | 2009-05-07 | Goepp Julius G | Effort-Independent, Portable, User-Operated Capnograph Devices And Related Methods |
| CN103201743A (en) * | 2010-11-08 | 2013-07-10 | 皇家飞利浦电子股份有限公司 | Method of continuous prediction of patient severity of illness, mortality, and length of stay |
| CN104135925A (en) * | 2012-02-20 | 2014-11-05 | 佛罗里达大学研究基金会有限公司 | Method and apparatus for predicting work of breathing |
| EP3006071A1 (en) * | 2014-10-07 | 2016-04-13 | Hersill, S.L. | Demand oxygen delivery system |
| CN105125215A (en) * | 2015-10-08 | 2015-12-09 | 湖南明康中锦医疗科技发展有限公司 | Neural network based breathing machine state analytic method and device |
| CN106039510A (en) * | 2016-07-29 | 2016-10-26 | 湖南明康中锦医疗科技发展有限公司 | Breathing machine safety control method, breathing machine and cloud platform |
Non-Patent Citations (2)
| Title |
|---|
| HUI ZHU 等: ""Control of Respiratory Mechanics with Artificial Neural Networks"", 《2007 1ST INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICAL ENGINEERING》 * |
| 刘振良: ""呼吸机检测与控制算法的研究与应用"", 《中国优秀硕士学位论文全文数据库-工程科技Ⅱ辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110910586A (en) * | 2019-11-28 | 2020-03-24 | 中国银行股份有限公司 | Anti-theft card swiping method and system |
| CN112870504A (en) * | 2019-11-29 | 2021-06-01 | 深圳市大雅医疗技术有限公司 | Respiratory therapy method and device, breathing machine and server |
| CN112329812A (en) * | 2020-09-29 | 2021-02-05 | 湖南明康中锦医疗科技发展有限公司 | Slow obstructive pulmonary acute exacerbation automatic early warning method and platform and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103532797B (en) | A kind of User logs in method for monitoring abnormality and device | |
| CN107220491A (en) | Cloud Server, the method reminded and computer-readable recording medium | |
| CN107147724A (en) | A kind of information push method, server and computer-readable recording medium | |
| CN113932431B (en) | Method and device for controlling air conditioning equipment and fitness mirror | |
| CN104866602A (en) | Queue processing method and device | |
| CN104753756B (en) | Method, equipment and the system that a kind of group creating is shared with group | |
| CN109186048A (en) | A kind of household electric appliance control method, device and medium | |
| CN107050600A (en) | Compress control method under lung ventilator and continuous positive pressure ventilation CPAP patterns | |
| EP3550798B1 (en) | Information processing method and apparatus | |
| CN108710304A (en) | A kind of client operation management method and client | |
| CN108307243A (en) | Platform game through transport setting method, storage medium, electronic equipment and system is broadcast live | |
| CN108050664A (en) | Acquisition methods, device and the storage medium of conditioner operating parameter | |
| CN107872673A (en) | A kind of method and device of Intelligent Dynamic regulation video encoder | |
| CN104080125B (en) | A kind of triggering method and device based on network load and M2M service priority | |
| CN110874284A (en) | Data processing method and device | |
| Ashraf et al. | Smart energy efficient device-to-multidevice cooperative clustering for multicasting content | |
| CN110400195A (en) | Order data processing method, device, computer equipment and storage medium | |
| CN115111678A (en) | Humidifier control method and device and humidifier | |
| US11904239B2 (en) | Verification of game score | |
| CN114202070A (en) | Power data processing method and device, nonvolatile storage medium and processor | |
| CN109582680B (en) | Business processing method based on new product development, electronic device and readable storage medium | |
| CN103297926B (en) | Group paging method in private network and base station | |
| CN112503731B (en) | Method and device for controlling air conditioning equipment and air conditioning equipment | |
| CN104284420B (en) | Page judgment method and related UE | |
| CN112146246A (en) | Operation control method, operation control device, line control apparatus, and storage medium |
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 | ||
| AD01 | Patent right deemed abandoned | ||
| AD01 | Patent right deemed abandoned |
Effective date of abandoning: 20210730 |