阅读说明：本技术 一种基于物联网边缘计算的人工心脏控制系统及运行方法 (Artificial heart control system based on Internet of things edge calculation and operation method ) 是由 高斌 赵大玮 穆振霞 张万松 符珉瑞 于 2020-12-01 设计创作，主要内容包括：一种基于物联网边缘计算的人工心脏控制系统及运行方法,属于生物医学工程领域。包括人工心脏、控制器、边缘计算模块、云服务器,控制器用于控制人工心脏,采集人工心脏的实时数据,并且将此数据传输到边缘计算模块和云服务器；边缘计算模块用于处理控制器传输的人工心脏的数据,然后将数据传输给云服务器,同时反馈给控制器；云端服务器对控制器传输的数据进行处理,对边缘计算模块传输的数据进行保存,结合患者的生理状态信息对数据进行再次优化处理,将最终的处理结果反馈给控制器,控制器反馈给人工心脏。通过对人工心脏采集的原始数据进行分级处理,能够高效率的优化人工心脏的运行状态,使患者的心脏得到更加有效的恢复。(An artificial heart control system based on Internet of things edge calculation and an operation method belong to the field of biomedical engineering. The system comprises an artificial heart, a controller, an edge computing module and a cloud server, wherein the controller is used for controlling the artificial heart, collecting real-time data of the artificial heart and transmitting the data to the edge computing module and the cloud server; the edge computing module is used for processing the data of the artificial heart transmitted by the controller, transmitting the data to the cloud server and simultaneously feeding the data back to the controller; the cloud server processes the data transmitted by the controller, stores the data transmitted by the edge calculation module, optimizes the data again by combining the physiological state information of the patient, feeds back the final processing result to the controller, and feeds back the final processing result to the artificial heart. By carrying out grading processing on the original data acquired by the artificial heart, the running state of the artificial heart can be efficiently optimized, and the heart of the patient can be recovered more effectively.)

1. An artificial heart control system based on Internet of things edge computing is characterized by comprising an artificial heart, a controller, an edge computing module and a cloud server; the artificial heart is in circuit or signal connection with the controller, the controller is in circuit or signal connection with the edge computing module and the cloud server respectively, and the edge computing module is in circuit or signal connection with the cloud server;

the controller is used for controlling the artificial heart, collecting real-time data of the artificial heart and transmitting the data to the edge computing module and the cloud server; the edge computing module is used for processing the data of the artificial heart transmitted by the controller, storing the original data and the processed data, transmitting the data to the cloud server, and feeding the data back to the controller; the cloud server processes the data transmitted by the controller, stores the data transmitted by the edge calculation module, optimizes the data again by combining the physiological state information of the patient, feeds back the final processing result to the controller, and feeds back the final processing result to the artificial heart.

2. The artificial heart control system based on the internet of things edge computing is characterized in that the artificial heart is a split type artificial heart and comprises an artificial heart pump and an in-vitro magnetic driving system;

the controller is used for controlling the artificial heart, collecting data generated by the artificial heart and transmitting the data to the edge computing module and the cloud server; the edge computing module is used for storing and processing data, transmitting network and converting communication protocols and is connected with other terminal equipment; the cloud server is used for receiving data transmitted by the controller and the edge computing module, processing the data, optimizing the data by combining physiological information of a patient, feeding the data back to the controller, and optimally controlling the artificial heart by the controller according to the optimized data;

the controller is used for controlling the in-vitro magnetic driving system, further controlling the artificial heart pump, acquiring data generated by the artificial heart, including the rotating speed and the output flow of the artificial heart pump, transmitting the data to the edge computing module and the cloud server, and then correcting the running state of the artificial heart pump for the first time according to a PID algorithm;

the edge computing module is embedded with a real-time operating system, can process data in real time, comprises the steps of cleaning, integrating and storing the data, and transmits the optimized data to the cloud server;

the edge computing module can receive data transmitted by the cloud server and can distinguish whether the data is processed by the controller locally or in the cloud.

3. The internet of things edge computing based artificial heart control system of claim 1, wherein the edge computing module is embedded with a real-time operating system selected from the group consisting of RT-Thread, FREERTOS, LINUX operating systems;

the data processed by the edge calculation module comprises original data acquired by the controller, including original data such as the rotating speed and the output flow of the artificial heart pump;

the edge calculation module processes data, including data cleaning, integration and storage, wherein the data cleaning refers to cleaning original data, including removing missing data, removing data with format and content errors, removing data with logic errors and removing unnecessary data, the data integration refers to integrating the cleaned data, and the data storage refers to storing the cleaned and integrated data.

4. The system of claim 1, wherein the edge computing module comprises a built-in port, and substantially comprises two ports: COM1, COM2 and COM1 ports are connected with a controller, and data transmission is carried out by using IIC, SPI, UART and other transmission protocols; the COM2 port is connected with a cloud server, a TCP \ IP data transmission protocol is used, Socket application programming interfaces under the TCP \ IP protocol are used for communication, and whether the data are transmitted locally by the controller or processed by the cloud side is identified according to the difference of the interfaces and the difference of the communication protocols.

5. The artificial heart control system based on the internet of things edge calculation is characterized in that the edge calculation module is connected with other terminal equipment, mainly the terminal equipment for acquiring electrocardiosignals;

the terminal equipment for acquiring the electrocardiosignals is twelve-lead electrocardio acquisition equipment or portable electrocardio acquisition equipment.

6. The artificial heart control system based on the internet of things edge computing is characterized in that when the cloud server receives data transmitted by the controller and the edge computing module at the same time, the cloud server firstly stores the data transmitted by the edge computing module and secondly processes the data transmitted by the controller;

the cloud server processes the original data transmitted by the controller, the processing process of the cloud server is consistent with that of the edge computing module for the original data, and the data cleaning, integration and storage are also included;

a large amount of data stored by the cloud server comprises original data transmitted by the controller, data transmitted by the edge computing module and physiological state information of a patient, machine learning is used for modeling training, so that the operation state of the artificial heart at the next moment is predicted, if a risk is generated, early warning is timely generated, early warning information is timely transmitted to the controller, and the operation state of the artificial heart is adjusted.

7. The method for operating the artificial heart control system based on the Internet of things edge computing according to any one of claims 1 to 6 is characterized by comprising the following steps:

firstly, starting an artificial heart for the first time, and inputting initial parameters; after the artificial heart system is started, the artificial heart pump stably operates, and the controller acquires main parameters during the operation of the artificial heart pump: the rotating speed of the artificial heart pump and the output flow of the artificial heart pump are adjusted through a PID algorithm according to the two main parameters, and the adjusted rotating speed of the artificial heart pump is fed back to the artificial heart pump, so that the first correction of the artificial heart pump is realized; meanwhile, the controller transmits the acquired original data to the edge computing module through a wired network and transmits the acquired original data to the cloud server through a wireless network;

through the first correction, the artificial heart pump can stably operate;

secondly, after the artificial heart pump is subjected to first correction and stable operation, the controller sends a signal 'the artificial heart pump is subjected to first stable operation' to the edge calculation module, and after the edge calculation module receives the signal, the edge calculation module starts to acquire electrocardiosignals; the edge computing module processes the electrocardiosignals acquired in real time by using an electrocardio algorithm, the electrocardio data processing result is fed back to the controller, meanwhile, the electrocardio data processing result is uploaded to the cloud server, and the controller performs secondary optimization control on the running state of the artificial heart according to the electrocardiosignals fed back by the edge computing module;

thirdly, after the artificial heart pump is optimized and adjusted for the second time and operates stably, the controller sends a signal 'the artificial heart pump operates stably for the second time' to the edge calculation module, after the edge computing module receives the signal, the edge computing module sends a signal that the artificial heart pump has stably operated for the second time and the corresponding rotating speed to the cloud server, after the cloud server receives the signal sent by the edge computing module, the cloud server sends a signal of receiving to the edge computing module, and then the cloud server starts to receive the rotating speed data of the artificial heart pump, the output flow data of the artificial heart pump and the electrocardiosignal data transmitted by the edge computing module, meanwhile, the cloud server comprehensively integrates the physiological state information of the patient and the received data, at the moment, the data result is directly fed back to the controller, and the controller performs third-time optimization control on the running state of the artificial heart according to the data;

fourthly, the cloud server keeps various data of different heart failure patients, the data of each patient comprises data transmitted by the edge computing module and physiological state information of the patient, and an information database about the heart failure patients with different degrees is established by taking the age stage and the heart failure degree of the patient as important data classification indexes;

the cloud server receives a first batch of data uploaded by the edge computing module as training data, trains the training data by using a related machine learning algorithm to further establish a corresponding model, and then sends the model to the edge computing module;

when the edge calculation module judges that a result generated by the model in the using process does not accord with the expectation of the rotating speed of the corresponding artificial heart pump, the model is sent to the cloud server for correction, then the retrained model is sent to the edge calculation module, the operation is repeated for multiple times until the requirement of the edge calculation module is met, and the final model can be used on the edge calculation module;

and fifthly, predicting the operation state of the artificial heart at the next moment according to the stable model, if a risk is generated, generating early warning in time, transmitting early warning information to the controller in time, and adjusting the operation state of the artificial heart.

Technical Field

The invention relates to an artificial heart control system based on Internet of things edge calculation, and belongs to the field of biomedical engineering.

Background

Heart failure is a disease that seriously affects human health. Patients with heart failure are in large numbers and have high mortality rates, and the most effective treatment modalities are heart transplantation and artificial heart assist. Since heart transplantation cannot be widely performed due to limited heart donors, artificial hearts have been gradually developed. With the rapid development of the technology, the artificial heart becomes an important clinical treatment means as a treatment mode of heart failure. The existing artificial heart control system has the problems that a large amount of data generated by the artificial heart cannot be processed in time, the control precision is not high, and the sudden problem cannot be responded in time.

Disclosure of Invention

In order to solve the problems, the invention provides an artificial heart control system based on the edge calculation of the internet of things, and particularly aims at the problems in a split type artificial heart control system.

In order to achieve the purpose, the invention adopts the following technical scheme:

an artificial heart control system based on Internet of things edge computing comprises an artificial heart, a controller, an edge computing module and a cloud server; the artificial heart is in circuit or signal connection with the controller, the controller is in circuit or signal connection with the edge computing module and the cloud server respectively, and the edge computing module is in circuit or signal connection with the cloud server;

the controller is used for controlling the artificial heart, collecting real-time data of the artificial heart and transmitting the data to the edge computing module and the cloud server; the edge computing module is used for processing the data of the artificial heart transmitted by the controller, storing the original data and the processed data, transmitting the data to the cloud server, and feeding the data back to the controller; the cloud server processes the data transmitted by the controller, stores the data transmitted by the edge calculation module, optimizes the data again by combining the physiological state information of the patient, feeds back the final processing result to the controller, and feeds back the final processing result to the artificial heart.

The artificial heart is a split type artificial heart and comprises an artificial heart pump and an in-vitro magnetic driving system.

The controller is used for controlling the artificial heart, collecting data generated by the artificial heart and transmitting the data to the edge computing module and the cloud server; the edge computing module is used for storing and processing data, transmitting network and converting communication protocols, and can be connected with other terminal equipment; the cloud server is used for receiving the data transmitted by the controller and the edge computing module, processing the data, optimizing the data by combining physiological information of the patient, feeding the data back to the controller, and optimally controlling the artificial heart by the controller according to the optimized data.

The controller is used for controlling the in-vitro magnetic driving system, further controlling the artificial heart pump, acquiring data generated by the artificial heart, including the rotating speed, the output flow and the like of the artificial heart pump, transmitting the data to the edge computing module and the cloud server, and then correcting the running state of the artificial heart pump for the first time according to a PID algorithm;

the edge computing module is embedded with a real-time operating system, can process data in real time, comprises the steps of cleaning, integrating and storing the data, and transmits the optimized data to the cloud server.

Further, the real-time operating system embedded in the edge computing module may be an operating system such as RT-Thread, FREERTOS, LINUX, etc.

Further, the data processed by the edge calculation module comprises original data collected by the controller, including original data such as the rotating speed and output flow of the artificial heart pump;

further, the edge calculation module processes the data, including data cleaning, integration and storage, wherein the data cleaning refers to cleaning the original data, including removing missing data, removing data with format and content errors, removing data with logic errors and removing unnecessary data, the data integration refers to integrating the cleaned data, and the data storage includes storing the cleaned and integrated data.

The edge computing module can receive data transmitted by the cloud server and can distinguish whether the data is processed by the controller locally or in the cloud.

Further, the edge calculation module has built-in ports, and basically comprises two ports: COM1, COM2 and COM1 ports are connected with a controller, and data transmission is carried out by using IIC, SPI, UART and other transmission protocols; the COM2 port is connected with a cloud server, a TCP \ IP data transmission protocol is used, Socket application programming interfaces under the TCP \ IP protocol are used for communication, and whether the data are transmitted locally by the controller or processed by the cloud side is identified according to the difference of the interfaces and the difference of the communication protocols.

The edge calculation module is connected with other terminal equipment which is mainly used for acquiring electrocardiosignals, the artificial heart acquires electrocardio data and uses an electrocardio algorithm to process after being corrected for the first time and stably operated, the data processing result is fed back to the controller, and the controller performs the second optimization control on the operation state of the artificial heart;

the terminal equipment for collecting the electrocardiosignals can be common twelve-lead electrocardio collecting equipment and also can be portable electrocardio collecting equipment, such as an intelligent bracelet.

The cloud server is used for receiving data transmitted by the controller and the edge computing module, comprehensively processing physiological state information of the patient and the received data, feeding back a data result to the controller, and performing third-time optimization control on the running state of the artificial heart by the controller according to the data.

Further, when the cloud server receives data transmitted by the controller and the edge computing module at the same time, the cloud server firstly stores the data transmitted by the edge computing module, and secondly processes the data transmitted by the controller.

Further, the cloud server processes the raw data transmitted by the controller, and the processing process of the raw data is consistent with that of the raw data processed by the edge computing module, and the processing process also includes data cleaning, integration and storage.

The physiological state information of the patient comprises conventional physiological information such as heart failure degree, blood oxygen saturation, blood pressure and the like, and also comprises whether the patient is subjected to drug treatment and the type of the used drug.

A large amount of data stored by the cloud server comprises original data transmitted by the controller, data transmitted by the edge computing module and physiological state information of a patient, machine learning is used for modeling training, so that the operation state of the artificial heart at the next moment is predicted, if a risk is generated, early warning is timely generated, early warning information is timely transmitted to the controller, and the operation state of the artificial heart is adjusted.

Further, the cloud server receives the first batch of data uploaded by the edge computing module as training data, trains the training data by using a relevant machine learning algorithm to further establish a corresponding model, and then sends the model to the edge computing module.

Further, when the edge computing module judges that a result generated in the using process of the model is not in accordance with the expectation, the model is sent to the cloud server for correction, then the retrained model is sent to the edge computing module, and the operation is repeated for multiple times until the requirement of the edge module is met, so that the final model can be used on the edge computing module.

The invention relates to an operation method of an artificial heart control system based on Internet of things edge calculation, which is characterized by comprising the following steps of:

firstly, starting an artificial heart for the first time, and inputting initial parameters; after the artificial heart system is started, the artificial heart pump stably operates, and the controller acquires main parameters during the operation of the artificial heart pump: the rotating speed of the artificial heart pump and the output flow of the artificial heart pump are adjusted through a PID algorithm according to the two main parameters, and the adjusted rotating speed of the artificial heart pump is fed back to the artificial heart pump, so that the first correction of the artificial heart pump is realized; meanwhile, the controller transmits the acquired original data to the edge computing module through a wired network and transmits the acquired original data to the cloud server through a wireless network;

through the first correction, the artificial heart pump can stably operate;

secondly, after the artificial heart pump is subjected to first correction and stable operation, the controller sends a signal 'the artificial heart pump is subjected to first stable operation' to the edge calculation module, and after the edge calculation module receives the signal, the edge calculation module starts to acquire electrocardiosignals; the edge computing module processes the electrocardiosignals acquired in real time by using an electrocardio algorithm, the electrocardio data processing result is fed back to the controller, meanwhile, the electrocardio data processing result is uploaded to the cloud server, and the controller performs secondary optimization control on the running state of the artificial heart according to the electrocardiosignals fed back by the edge computing module;

thirdly, after the artificial heart pump is optimized and adjusted for the second time and operates stably, the controller sends a signal 'the artificial heart pump operates stably for the second time' to the edge calculation module, after the edge computing module receives the signal, the edge computing module sends a signal that the artificial heart pump has stably operated for the second time and the corresponding rotating speed to the cloud server, after the cloud server receives the signal sent by the edge computing module, the cloud server sends a signal of receiving to the edge computing module, and then the cloud server starts to receive the rotating speed data of the artificial heart pump, the output flow data of the artificial heart pump and the electrocardiosignal data transmitted by the edge computing module, meanwhile, the cloud server comprehensively integrates the physiological state information of the patient and the received data, at the moment, the data result is directly fed back to the controller, and the controller performs third-time optimization control on the running state of the artificial heart according to the data;

fourthly, the cloud server keeps various data of different heart failure patients, the data of each patient comprises data (the rotating speed of the artificial heart pump, the output flow of the artificial heart pump and electrocardio signals) transmitted by the edge computing module and physiological state information of the patient, and the data are used as important data classification indexes according to the age stage and the heart failure degree of the patient, so that a heart failure patient information database with different degrees is established;

the cloud server receives a first batch of data uploaded by the edge computing module as training data, trains the training data by using a related machine learning algorithm to further establish a corresponding model, and then sends the model to the edge computing module;

when the edge calculation module judges that a result generated by the model in the using process does not accord with the expectation of the rotating speed of the corresponding artificial heart pump, the model is sent to the cloud server for correction, then the retrained model is sent to the edge calculation module, the operation is repeated for multiple times until the requirement of the edge calculation module is met, and the final model can be used on the edge calculation module;

and fifthly, predicting the operation state of the artificial heart at the next moment according to the stable model, if risks are generated (for example, the rotating speed given by the model continuously exceeds the rotating speed of the pump in stable operation for multiple times, namely the pump is considered to be risky), timely generating early warning, timely transmitting early warning information to the controller, and adjusting the operation state of the artificial heart.

Compared with the prior art, the invention has the beneficial effects that:

by applying the edge calculation module, the original data can be processed locally in time, more terminal equipment for measuring physiological signals can be accessed, the multitasking of the body state is realized, the adverse reaction can be processed in time, the response speed of the system is improved, and the method has the characteristics of real-time performance, high bandwidth, low time delay and multitasking;

by applying the cloud server, the physiological state data of the patient can be comprehensively processed, and the physiological state data of different patients can be stored, so that a database of heart failure patients can be established, a large amount of data can be modeled and trained by machine learning, the prediction of the next moment of the operation state of the artificial heart can be realized, and the processing efficiency can be faster under the support of the 5G technology;

by three feedbacks: the controller collects original data to perform first feedback control, the edge calculation module performs second feedback control after the heart rate data of the patient is integrated, and the cloud server performs third feedback control after the comprehensive data of the patient is integrated, so that fine control over the running state of the artificial heart is realized, the running efficiency and the service life of the artificial heart are improved, and the speed and the effect of recovering the heart of the patient are improved.

Drawings

FIG. 1 is an overall system logic block diagram of the present invention.

Fig. 2 is a block diagram of an algorithm embodying the present invention.

Fig. 3 is a connection diagram of the edge computing module with the controller and cloud server of the present invention.

Fig. 4 is a data transfer protocol used by two COM ports of the edge computing module of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Referring to fig. 1, fig. 2, fig. 3 and fig. 4, the present invention provides a technical solution: an artificial heart control system based on internet of things edge computing, the system comprising: the system comprises an artificial heart, a controller, an edge computing module and a cloud server.

The artificial heart is a split artificial heart designed in the laboratory and comprises an artificial heart pump and an in-vitro magnetic driving system.

If the patient is in a hospital:

in a first step, the physician initially turns on the artificial heart control system based on the clinical performance of the patient, and initial parameters are input by the physician empirically, for example, the physician gives the artificial heart pump 500 rpm for activation based on the clinical characteristics of the patient.

After the artificial heart system is started, the artificial heart pump stably operates, and the controller acquires main parameters during the operation of the artificial heart pump: the rotating speed of the artificial heart pump and the output flow of the artificial heart pump are adjusted through a PID algorithm according to the two main parameters, and the adjusted rotating speed of the artificial heart pump is fed back to the artificial heart pump, so that the first correction of the artificial heart pump is realized. Meanwhile, the controller transmits the acquired original data to the edge computing module through a wired network and transmits the acquired original data to the cloud server through a wireless network.

After the first correction, the artificial heart pump can stably operate, for example, the rotation speed of the artificial heart pump can be stabilized at 5500 rotations per minute 5000-.

Furthermore, the raw data collected by the controller mainly comprises the rotating speed of the artificial heart pump and the output flow of the artificial heart pump.

Further, the wireless network may be WIFI, bluetooth, etc., and the wired network may be ethernet, etc.

The edge computing module is embedded with a real-time operating system, can process data in real time, comprises the steps of cleaning, integrating and storing the data, and transmits the optimized data to the cloud server.

Further, the real-time operating system may be an operating system such as RT-Thread, FREERTOS, LINUX, etc.

Further, the edge calculation module processes the data, including data cleaning, integration and storage, where the data cleaning refers to cleaning the original data (the rotation speed of the artificial heart pump and the output flow rate of the artificial heart pump), including removing missing data, removing data with format and content errors, removing data with logic errors and removing unnecessary data, the data integration refers to integrating the cleaned data, and the data storage refers to storing the cleaned and integrated data.

The edge computing module can receive data transmitted by the cloud server and can distinguish whether the data is controller local data or cloud-processed data.

Further, the edge calculation module has built-in ports, and basically comprises two ports: COM1, COM2 and COM1 ports are connected with a controller, and data transmission is carried out by using IIC, SPI, UART and other transmission protocols; the COM2 port is connected with a cloud server, a TCP \ IP data transmission protocol is used, Socket application programming interfaces under the TCP \ IP protocol are used for communication, and whether the data are transmitted locally by the controller or processed by the cloud side is identified according to the difference of the interfaces and the difference of the communication protocols.

And secondly, after the artificial heart pump is subjected to the first correction stable operation, for example, the rotating speed of the artificial heart pump can be stabilized at 5500 revolutions per minute within one minute, the controller sends a signal that the artificial heart pump is stably operated to the edge calculation module, and the edge calculation module starts to acquire the electrocardiosignals after receiving the signal.

Further, the edge computing module processes the electrocardiosignals acquired in real time by using an electrocardio algorithm, the electrocardio data processing result is fed back to the controller, the electrocardio data processing result is uploaded to the cloud server, the controller performs secondary optimization control on the operation state of the artificial heart according to the electrocardiosignals fed back by the edge computing module, and for example, the artificial heart pump at the time can be stabilized at 5200-.

Preferably, in a hospital, the terminal device for collecting the electrocardiosignals can be a twelve-lead electrocardiosignal collecting system, and in daily life, the terminal device can be an intelligent bracelet or other portable devices capable of collecting the electrocardiosignals.

Preferably, the devices have a data transmission function, can perform data transmission through serial port communication, and can also perform data transmission through WIFI or Bluetooth.

Thirdly, after the artificial heart pump is optimized and adjusted for the second time, for example, the artificial heart pump can be stabilized at 5200 + 5300 revolutions per minute at the time after stable operation, the controller sends a signal to the edge computing module to ensure that the artificial heart pump is stably operated for the second time, the edge computing module sends a signal to the cloud server to ensure that the artificial heart pump is stably operated for the second time and rotates at 5200 + 5300 revolutions per minute after receiving the signal, the cloud server sends a signal to the edge computing module to ensure that the cloud server receives the signal after receiving the signal sent by the edge computing module, and then the cloud server starts to receive the artificial heart pump rotating speed data, the artificial heart pump output flow data and the electrocardiosignal data transmitted by the edge computing module, and simultaneously the cloud server comprehensively integrates the physiological state information of the patient and the received data, at this time, the data result is directly fed back to the controller, and the controller performs third optimized control on the operation state of the artificial heart according to the data, for example, the rotation speed of the artificial heart pump at this time can be stabilized at 5250 and 5260 revolutions per minute.

Further, the physiological status information of the patient includes the degree of heart failure, age, sex, whether a medication is performed and the type of medication used, and other data of measurement used during the visit (such as blood pressure, blood oxygen saturation, etc.).

And fourthly, the cloud server stores various data of different heart failure patients, wherein the data (the rotating speed of the artificial heart pump, the output flow of the artificial heart pump and the electrocardio signals) transmitted by the edge computing module and the physiological state information of the patients serve as important data classification indexes according to the age stages and the heart failure degrees of the patients, so that a heart failure patient database with different degrees is established.

Further, the cloud server receives the first batch of data uploaded by the edge computing module as training data (for example, when the hospital receives data of 1000 patients, the data of the 1000 patients is used as training data), and the data is trained by using a relevant machine learning algorithm to establish a corresponding model, and then the model is sent to the edge computing module.

Further, when the edge calculation module itself determines that the result generated by the model in the using process is not in accordance with the expectation (for example, the artificial heart pump is stabilized at 5250 revolutions per minute and 5260 revolutions per minute, the rotation speed given when the model is used is 6000 revolutions per minute, that is, the result is not in accordance with the expectation, and the difference between the rotation speed given by the model and the rotation speed after the artificial heart pump is stably operated is considered to be in accordance with the expectation within 200 revolutions per minute), the model is sent to the cloud server for correction, then the model after retraining is sent to the edge calculation module, and the operation is repeated for multiple times until the requirement of the edge calculation module is met, and the final model can be used on the edge calculation module.

And fifthly, predicting the operation state of the artificial heart at the next moment according to the stable model, if risks are generated (for example, the rotating speed given by the model continuously exceeds the rotating speed of the pump in stable operation for multiple times, namely the pump is considered to be risky), timely generating early warning, timely transmitting early warning information to the controller, and adjusting the operation state of the artificial heart.

Further, the early warning module can be a buzzer module and can give an alarm to give an alarm in case of risk.

Further, the early warning information can be transmitted to a terminal of the patient, the doctor or the family member of the patient through a wireless network, and the terminal can be a mobile phone or a tablet computer.

And sixthly, the doctor thinks that the heart of the patient can meet basic life requirements under the assistance of the artificial heart pump, and the patient can be discharged.

Further, if a new heart failure patient is hospitalized, the doctor inputs the data of the new patient for physical examination in the hospital into the model established before, and at the moment, each item of data of the new patient can be used as a test set for model training, so that a reasonable suggestion is given to the doctor, and the doctor can treat the new patient more conveniently.

After patient discharge, if active outside:

when a patient is discharged, for example, the rotating speed of the artificial heart pump carried on the patient is stabilized at 5250-5260 revolutions per minute, if the rotating speed difference between the rotating speed continuously given by the model stored in the edge calculation module for multiple times and the rotating speed when the pump is stably operated is 200 revolutions per minute, the edge calculation module timely sends out early warning information to the controller, the buzzer sounds, the patient immediately stops all activities when hearing the alarm of the buzzer, takes a rest in place, and then the activities are performed after the early warning is eliminated.

The patient does not need to interact with the cloud server while the patient is in the field.

When the patient ends the external activities and returns home:

when a patient is at home, the patient can be connected with a wireless network at home, and the edge computing module can transmit the rotating speed of the artificial heart pump, the output flow of the artificial heart pump and the data of the electrocardiosignals to the cloud server through the wireless network.

The cloud server stores the data transmitted by the edge computing module.

Having thus described the general principles of the invention, it will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit of the invention, and therefore, the present embodiments are considered in all respects to be illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein and are therefore not to be considered limited to the claims appended hereto.

Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.