CN116889684A

CN116889684A - Parameter configuration method and system of blood supply driving device and related device

Info

Publication number: CN116889684A
Application number: CN202310980558.XA
Authority: CN
Inventors: 乔元风; 曾凡; 孙德佳; 阎昶安; 王明刚; 朱江烽
Original assignee: Shanghai Xuanwei Medical Technology Co ltd; Xuanwei Beijing Biotechnology Co ltd
Current assignee: Shanghai Xuanwei Medical Technology Co ltd; Xuanwei Beijing Biotechnology Co ltd
Priority date: 2023-08-04
Filing date: 2023-08-04
Publication date: 2023-10-17
Anticipated expiration: 2043-08-04
Also published as: CN116889684B

Abstract

The application provides a parameter configuration method, a parameter configuration system and a related device of a blood supply driving device. The method comprises the following steps: acquiring user individual data corresponding to a target device; the target device is a blood supply driving device used by a user; acquiring target equipment parameters matched with the physical state of the user based on the individual data of the user; the physical state of the user is associated with the blood supply requirement of the blood supply driving system of the user; the physical state of the user at least comprises a behavior state and/or a muscle strength degree; the target equipment parameters comprise driving component operation parameters matched with the blood supply driving system in the physical state; the target apparatus is configured based on the target device parameters. The application can enable the blood supply driving device to be more matched with the individual situation of the user under the automatic configuration of the parameters of the target equipment, and reduce the customization cost of the blood supply driving device.

Description

Parameter configuration method and system of blood supply driving device and related device

Technical Field

Embodiments of the present application relate to the field of driving devices, and more particularly, to a method, a system, and a related apparatus for configuring parameters of a blood supply driving device.

Background

Cardiovascular disease is one of the major killers threatening human health. Most cardiovascular diseases ultimately affect left ventricular function, resulting in reduced cardiac function. The heart pump, also called as target device, can partially or completely replace the pumping function of heart, lighten the burden of left ventricle, meet the blood perfusion requirement of whole body tissues and organs, and improve the life quality of users.

In the related art, a heart pump is generally in a constant speed operation mode, i.e., the rotational speed and flow rate of the pump are kept constant. Although the heart pump can relieve the heart burden of a user and restore certain heart functions, the non-pulsating blood flow generated by the constant speed pump can influence the self-regulation of micro arteries in a blood circulation system, so that the blood is excessively diluted, the oxygen carrying capacity of the blood is reduced, and the hemodynamic characteristics of the whole cardiac cycle are unstable.

At present, the cost for custom research and development, production and use of medical products such as medical instruments, consumables, medicaments and the like is high and is not low. In the related art, it is common to assemble and use related equipment for a user, and actively adapt the user to the equipment through rehabilitation training for the user. Thus, existing heart pumps, arterial pumps, and other devices lack the flexibility of adjustment for users and the user experience is poor.

Therefore, a new technical solution is needed to overcome the technical problems in the related art.

Disclosure of Invention

In this context, it is desirable for embodiments of the present application to provide a method, a system, and a related apparatus for configuring parameters of a blood supply driving device, so as to assist in personalized configuration of parameters of the blood supply driving device, so that the blood supply driving device can be more matched with individual situations of a user under automatic configuration of parameters of a target device, reduce customization cost of the blood supply driving device, and facilitate popularization and application of the blood supply driving device.

In a first aspect of the embodiments of the present application, there is provided a parameter configuration method of a blood supply driving device, including:

acquiring user individual data corresponding to a target device; the target device is a blood supply driving device used by a user; the user individual data comprise at least one of physiological index data, diagnosis and treatment information and target device attributes of the user;

acquiring target equipment parameters matched with the physical state of the user based on the individual data of the user; the physical state of the user is associated with the blood supply requirement of the user blood supply driving system; the physical state of the user at least comprises a behavior state and/or a muscle strength degree; the target equipment parameters comprise driving component operation parameters matched with the blood supply driving system in the physical state;

The target device is configured based on the target device parameters.

In a second aspect of the embodiment of the application, a parameter configuration system of a blood supply driving device is provided, and the system comprises the blood supply driving device, monitoring end equipment and the parameter configuration device; wherein the method comprises the steps of

The monitoring end equipment is configured to collect user individual data corresponding to the blood supply driving device; the user individual data comprise at least one of physiological index data, diagnosis and treatment information and target device attributes of the user;

the parameter configuration device is configured to acquire the user individual data from the monitoring end equipment; acquiring target equipment parameters matched with the physical state of the user based on the individual data of the user; the physical state of the user is associated with the blood supply requirement of the user blood supply driving system; the physical state of the user at least comprises a behavior state and/or a muscle strength degree; the target equipment parameters comprise driving component operation parameters matched with the blood supply driving system in the physical state; configuring the target device based on the target device parameters;

the blood supply driving device is configured to operate with the target device parameters so that the blood supply driving system is matched with the physical state of the user.

In an example of this embodiment, the monitoring end device includes at least: one of a heartbeat sensor, a blood oxygen detection sensor, a gyroscope, an acceleration sensor and a muscle electric sensor.

It should be noted that the parameter configuration system is configured to perform the parameter configuration method of the blood supply driving device according to any one of the first aspects.

In a third aspect of the embodiments of the present application, there is provided a parameter configuration apparatus of a blood supply driving apparatus, applied to implement the parameter configuration method of a blood supply driving apparatus as set forth in any one of the first aspects, the apparatus including:

the acquisition unit is used for acquiring the user individual data corresponding to the target device; the target device is a blood supply driving device used by a user; the user individual data comprise at least one of physiological index data, diagnosis and treatment information and target device attributes of the user;

the prediction unit is used for acquiring target equipment parameters matched with the physical state of the user based on the individual data of the user; the physical state of the user is associated with the blood supply requirement of the user blood supply driving system; the physical state of the user at least comprises a behavior state and/or a muscle strength degree; the target equipment parameters comprise driving component operation parameters matched with the blood supply driving system in the physical state;

And the configuration unit is used for configuring the target device based on the target equipment parameters.

In a fourth aspect of embodiments of the present application, there is provided a computer-readable storage medium comprising instructions that, when run on a computer, cause the computer to perform the parameter configuration method of the blood supply driving device of any one of the first aspects.

In a fifth aspect of embodiments of the present application, there is provided a computing device comprising: at least one processor, memory, and input output unit; wherein the memory is configured to store a computer program and the processor is configured to invoke the computer program stored in the memory to perform the method of configuring parameters of the blood supply drive device of any of the first aspects.

The embodiment of the application provides a parameter configuration method and system of a blood supply driving device and a related device. In the embodiment of the application, the user individual data corresponding to the blood supply driving device (namely the target device) used by the user is obtained, and the user individual data comprises at least one of physiological index information, diagnosis and treatment information and target device attributes of the user. Here, the user individual data can provide a data basis for the subsequent individual customized configuration mode of the blood supply driving device based on the current physical state of the user and the configuration requirement of the device. Specifically, after acquiring the user individual data, target device parameters matching the physical state of the user are acquired based on the user individual data. Because the physical state of the user is associated with the blood supply requirement of the blood supply driving system of the user, the physical state of the user, such as the behavior state and/or muscle exertion degree of the user, can be analyzed by combining the individual data of the user, and further, the individual condition of the user is further analyzed by referring to the physical state of the user so as to obtain the individual parameter configuration of the blood supply driving device matched with the physical state of the user. In particular, the target device parameters include drive component operating parameters that are matched to the state of the body in which the blood supply drive system is located. Finally, configuring the target device based on the target device parameters to achieve automated device parameter configuration of the target device.

In the embodiment of the application, the physical state used for reflecting the running condition of the blood supply driving system is analyzed based on the user individual data, and the target equipment parameters matched with the user individual condition are customized for the blood supply driving device by combining the physical state of the user, so that the target device can be more suitable for the requirement of the user on the blood supply driving system under the automatic configuration of the target equipment parameters. Meanwhile, the customized parameter configuration of the blood supply driving device is realized by identifying individual conditions of the user, the customized cost of the blood supply driving device is greatly reduced, and the popularization and the application of the blood supply driving device are facilitated.

Drawings

The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present application will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. Several embodiments of the present application are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which:

FIG. 1 is a flow chart of a method for configuring parameters of a blood supply driving device according to an embodiment of the present application;

fig. 2 is a flowchart of a method for obtaining parameters of a target device according to an embodiment of the present application;

FIG. 3 is a flowchart illustrating a behavior state recognition method according to an embodiment of the present application;

FIG. 4 is a schematic diagram of raw data of an acceleration sensor and a gyroscope according to an embodiment of the present application;

FIG. 5 is a schematic diagram showing a filtering effect of an acceleration sensor and a gyroscope according to an embodiment of the present application;

FIG. 6 is a schematic diagram showing the effect of constant integration of an acceleration sensor and a gyroscope according to an embodiment of the present application;

FIG. 7 is a schematic diagram of a process flow of data of a muscular sensor according to an embodiment of the present application;

FIG. 8 is a diagram of raw data of a muscular sensor according to an embodiment of the present application;

FIG. 9 is a schematic diagram showing the effect of the constant integration of a muscular sensor according to an embodiment of the present application;

FIG. 10 is a schematic diagram of a frequency domain characteristic energy density according to an embodiment of the present application;

FIG. 11 is a schematic diagram showing the effect of constant integration of the energy density of the frequency domain feature according to an embodiment of the present application;

FIG. 12 is a schematic diagram of a blood oxygen balance mode according to an embodiment of the present application;

FIG. 13 is a schematic diagram of a parameter configuration apparatus of a blood supply driving apparatus according to an embodiment of the present application;

FIG. 14 is a schematic diagram of a medium according to an embodiment of the present application;

Fig. 15 is a schematic structural diagram of a computing device according to an embodiment of the present application.

In the drawings, the same or corresponding reference numerals indicate the same or corresponding parts.

Detailed Description

The principles and spirit of the present application will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are presented merely to enable those skilled in the art to better understand and practice the application and are not intended to limit the scope of the application in any way. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

Those skilled in the art will appreciate that embodiments of the application may be implemented as a system, apparatus, device, method, or computer program product. Accordingly, the present disclosure may be embodied in the following forms, namely: complete hardware, complete software (including firmware, resident software, micro-code, etc.), or a combination of hardware and software.

Applicant has found that in the related art, the heart pump is typically in a constant speed mode of operation, i.e., the rotational speed and flow rate of the pump remain constant. Although the heart pump can relieve the heart burden of a user and restore certain heart functions, the non-pulsating blood flow generated by the constant speed pump can influence the self-regulation of micro arteries in a blood circulation system, so that the blood is excessively diluted, the oxygen carrying capacity of the blood is reduced, and the hemodynamic characteristics of the whole cardiac cycle are unstable.

In the related art, in addition to the above-described heart pump, recovery of heart function can be achieved with the assistance of an arterial pump. However, the arterial pump is usually an auxiliary device used in heart surgery, and the device main body is arranged outside the user body, so that the arterial pump cannot be implanted into the user body or carried by the user, and the daily life requirements of the user are difficult to meet. In addition, the arterial pump is also used in a constant-speed operation mode, and the rotating speed and the flow rate are kept at constant values. Obviously, the arterial pump also cannot solve the technical problems of the heart pump in the related art.

The applicant also finds that the cost of custom research, development, production and use of medical products such as medical instruments, consumables, medicaments and the like is high at present. In the related art, it is common to assemble and use related equipment for a user, and actively adapt the user to the equipment through rehabilitation training for the user. Thus, existing heart pumps, arterial pumps, and other devices lack the flexibility of adjustment for users and the user experience is poor.

Therefore, a new technical solution is needed to overcome the technical problems of the blood supply driving device in the related art.

The embodiment of the application provides a parameter configuration method, a parameter configuration system and a related device of a blood supply driving device. In the embodiment of the application, the user individual data corresponding to the blood supply driving device (namely the target device) used by the user is obtained, and the user individual data comprises at least one of physiological index information, diagnosis and treatment information and target device attributes of the user. The physiological index information and the diagnosis and treatment information in the individual data of the user are mainly used for representing the current physical state of the user from each dimension, and the target device attribute reflects the configuration requirement of the blood supply driving device. Therefore, the user individual data can provide a data basis for the subsequent individual customization configuration mode of the blood supply driving device according to the current physical state of the user and the configuration requirement of the device. Specifically, after acquiring the user individual data, target device parameters matching the physical state of the user are acquired based on the user individual data. Because the physical state of the user is associated with the blood supply requirement of the blood supply driving system of the user, the physical state of the user, such as the behavior state and/or muscle exertion degree of the user, can be analyzed by combining the individual data of the user, and further, the individual condition of the user is further analyzed by referring to the physical state of the user so as to obtain the individual parameter configuration of the blood supply driving device matched with the physical state of the user. In particular, the target device parameters include drive component operating parameters that are matched to the state of the body in which the blood supply drive system is located. Finally, configuring the target device based on the target device parameters to achieve automated device parameter configuration of the target device.

In the embodiment of the application, the physical state used for reflecting the running condition of the blood supply driving system is analyzed based on the user individual data, and the target equipment parameters matched with the individual condition of the user are customized for the blood supply driving device by combining the physical state of the user, so that the target device can be more suitable for the individual condition of the user under the automatic configuration of the target equipment parameters. Meanwhile, the customized parameter configuration of the blood supply driving device is realized by identifying individual situations of users, so that the customized cost of the blood supply driving device is greatly reduced, and the popularization and the application of the blood supply driving device are facilitated.

In some embodiments, the parameter configuration device of the blood supply driving device is one or a plurality of parameter configuration devices. The parameter configuration devices of the blood supply driving devices can be distributed or centralized. In the practical application scene, the blood supply driving device is matched with the parameter configuration device. For example, the parameter configuration means may be implemented as a module deployed in a blood supply driving device, including a software module and/or a hardware module, or other forms of component modules. The blood supply driving device can also be realized as a separate device connected with the blood supply driving device, and the connection mode can be a wired mode or a wireless mode. The embodiment of the application is not limited, and the embodiment can also be realized as a software service for accessing the blood supply driving device, such as a cloud service, an external model service and the like.

It should be noted that, the server according to the embodiment of the present application may be an independent physical server, or may be a server cluster or a distributed system formed by a plurality of physical servers, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, big data, and basic cloud computing services such as an artificial intelligent platform.

The terminal device according to the embodiment of the present application may be a device that provides voice and/or data connectivity to a user, a handheld device with a wireless connection function, or other processing device connected to a wireless modem. Such as mobile telephones (or "cellular" telephones) and computers with mobile terminals, which can be portable, pocket, hand-held, computer-built-in or car-mounted mobile devices, for example, which exchange voice and/or data with radio access networks. Such as personal communication services (Personal Communication Service, PCS) phones, cordless phones, session initiation protocol (Session initialization Protocol, SIP) phones, wireless local loop (Wireless Local Loop, WLL) stations, personal digital assistants (Personal Digital Assistant, PDAs), and the like.

It should be noted that any number of elements in the figures are for illustration and not limitation, and that any naming is used for distinction only and not for limitation.

The principles and spirit of the present application are explained in detail below with reference to several representative embodiments thereof.

Referring to fig. 1, fig. 1 is a flowchart illustrating a parameter configuration method of a blood supply driving device according to an embodiment of the present application. It should be noted that embodiments of the present application may be applied to any scenario of a blood supply driving device. In particular, the scenario is configured for the personalized parameters of the blood supply drive held by the user.

Fig. 1 shows a flow chart of a parameter configuration method of a blood supply driving device according to an embodiment of the present application.

In the related art, the heart pump and the arterial pump are generally in a constant speed operation mode, i.e., the rotational speed and flow rate of the pump are kept constant. However, the non-pulsatile flow produced by the constant velocity pump affects the self-regulation of the arterioles in the blood circulation system, resulting in excessive dilution of the blood, a decrease in the oxygen carrying capacity of the blood, and an unstable hemodynamic characteristic of the whole cardiac cycle. Aiming at the problems brought by the constant-speed working mode, the working modes of the blood supply driving device such as the heart pump, the arterial pump and the like need to be dynamically adjusted so that the blood supply driving device meets the individual condition of the user in the physical state, and the customization difficulty of the blood supply driving device is reduced.

Firstly, in order to adjust the operation mode of the blood supply drive device, individual situations of the user need to be acquired first. This individual condition may be determined based on the current operating state of the blood circulation system of the user.

Step S101, obtaining user individual data corresponding to a target device.

Step S102, acquiring target device parameters matched with the physical state of the user based on the individual data of the user.

In the embodiment of the application, the target device is a blood supply driving device used by a user. The blood supply driving device is used for continuously pumping blood for a user, providing dynamic compensation of a blood circulation system and assisting the blood circulation system to maintain whole body blood perfusion. In practice, blood supply driving means include, but are not limited to: heart pump, implantable arterial pump.

The heart pump is a device capable of simulating the heart function of a human being, can be implanted into the body of a user and used for a long time, and is mostly applied to scenes such as medical research and treatment. The heart pump can partially or completely replace the blood pumping function of the heart, lighten the burden of the left ventricle, meet the blood perfusion requirements of whole body tissues and organs and improve the life quality of users. An implantable arterial pump is a device that can be implanted in a user and used for a long period of time to continuously provide an auxiliary blood supply driving function to the heart. Implantable arterial pumps are commonly used in heart disease users and can serve as a bridge prior to heart transplantation when other treatments are ineffective. In particular, implantable arterial pumps are surgically implanted in the chest or abdomen and connected to the heart or aorta to provide a continuous blood pumping function. Such a device may help the user's heart to continue to pump blood effectively, maintaining systemic blood circulation.

As an alternative embodiment, in an embodiment of the present application, a blood supply driving device includes: the device comprises a pump body, a driving module, a control module, an energy supply module and a sensor.

The pump body of the blood supply driving device can be made of flexible materials such as silica gel or polyurethane so as to simulate the softness of human myocardial tissues. The pump body has a chamber therein for containing a blood simulation fluid or other fluid, and a fluid inlet and outlet tube is typically provided on the housing of the pump body. In order to be able to regularly contract and relax the pump body as the actual heart, a motor or pneumatic drive module is usually used in the blood supply drive.

Further alternatively, the external part surface of the target device or the mobile implanted arterial pump is marked with the newly added number of the equipment by using a wear-resistant material silk screen printing or laser engraving mode. The number may be presented in the form of a character, one-dimensional code, two-dimensional code, or other pattern made up of an ASCII/UTF-8 character set. In practice, the professional medical institution maintains a database of target device equipment numbers and networking passwords.

And the driving module is used for controlling the motion of the pump body to realize different heart rates and cardiac output. The control module is the core of the blood supply driving device, and different heart rates and cardiac output can be realized by controlling the output of the driving module.

The control module consists of a microprocessor and a program control unit. Specifically, the control module is configured to configure target device parameters of the driver module. It is worth to say that, the target equipment parameters set to the driving module need to be checked and confirmed by related personnel, and checking records are generated and stored in the history adaptation database. Or by a machine learning model validated by an audit of the relevant person. As an alternative embodiment, control and monitoring of the pumps (including heart pumps and arterial pumps) is achieved by means of a user interface or wireless communication, etc.

The energy supply module of the blood supply driving device can use a battery or an interface power supply, wherein the battery can keep the pump continuously working when the equipment moves, and the interface power supply can provide stable energy supply when the equipment is used for a long time.

In practice, the control module may be implemented as a low-power and networking-capable computing device or module. Here, the module may be a hardware module or a software module. Alternatively, the control module may include, but is not limited to, the following: a single board computer, portable equipment, a low power consumption micro controller unit (Micro Controller Unit, MCU), an internet of things gateway. The single board computer is a complete computing platform, integrates a processor, a memory, a storage interface and an input/output interface, and has relatively low power consumption. Portable devices, such as smartphones, tablets, PDAs, etc., are often of smaller size and lower power consumption design to extend battery life. An MCU, for example, a microcontroller with low power consumption and small volume, is used to control and monitor the sensors, perform simple tasks, and connect external devices. The internet of things gateway, for example, is used for connecting and managing internet of things devices, and generally has low power consumption and smaller size, and is used for processing functions such as data transmission, edge calculation, connectivity management and the like.

And the sensor is used for collecting the physiological index data of the user and the equipment parameters. Specifically, the device information detection device is used for detecting device information such as pump rotation speed and electric quantity, and physiological index information such as heart rate, blood oxygen saturation, posture data (for example, acceleration data, gyroscope data and the like), muscle electrical data and the like. In an embodiment of the present application, the sensor includes, but is not limited to: heartbeat sensor, blood oxygen detection sensor, acceleration sensor, gyroscope, muscle electrical sensor. In practical applications, the sensors are classified according to the sensor types, for example, the following sensors are implemented:

myoelectric sensor: also known as myoelectric sensors, are used to measure and record electrical signals as muscles produce activity. The electrical signals as the muscles contract and relax can be monitored to provide information about the muscle activity and state. Myoelectric sensors typically use electrodes attached to the surface of the muscle to capture the pattern of activity and intensity of muscle contraction by detecting changes in the muscle potential.

Acceleration sensor: the acceleration sensor may measure the acceleration of the object, i.e. the rate of change of the object in speed and direction. It can detect linear and gravitational acceleration of an object, providing information about the object's motion, vibration and tilt. In wearable devices and mobile devices, acceleration sensors are commonly used for pedometers, gesture recognition, motion tracking, gesture control, and other applications.

A gyro sensor: gyroscopic sensors are used to measure and sense the rotation and angular velocity of an object. It can detect the turning, steering and rotational speed of an object and provide information about direction, angle and attitude. The gyro sensor has wide application in the fields of aerospace, navigation systems, virtual reality, game control and the like.

Blood oxygen saturation sensor: blood oxygen saturation sensors (also known as pulse oxygen saturation sensors) are used to non-invasively measure oxygen saturation levels in blood. It typically detects the oxygen content of blood by infrared light and light scattering principles, providing information about blood oxygen levels and heart pulses. Blood oxygen saturation sensor is widely used in medical field, especially in the aspects of monitoring, diagnosis and sleep monitoring.

Heartbeat sensor: the heartbeat sensor is used for detecting and recording the beating frequency of the heart. It can acquire heartbeat data by measuring electrocardiographic activity, pulse or heart shock, etc. The heartbeat sensor provides information concerning the activity of the heart, heart rate variability, and heart health. Heartbeat sensors are widely used in the fields of health monitoring, athletic training, medical monitoring, and the like.

The above-described sensor is merely an example, and the embodiment of the present application is not limited thereto.

In step S101, after the sensor collects the physiological index data and the device parameters, the physiological index data and the device parameters are transmitted to the control module. Alternatively, the physiological index data and the device parameters may be transmitted to the host computer. Wherein the sensor comprises at least: one of a heartbeat sensor, a blood oxygen detection sensor, an acceleration sensor, a gyroscope and a muscle electric sensor. Further alternatively, the physiological index data and the device parameters can be transmitted to an upper computer, and the upper computer trains an individuation parameter configuration model corresponding to various working modes, so that the device parameters are predicted through the individuation parameter configuration model to assist the blood supply driving device to adapt to individual situations of users. For example, by automatically realizing the customized parameter configuration of the blood supply driving device, the parameter adjustment process of the blood supply driving device is more efficient, so that the configuration parameters of the blood supply driving device can be timely adjusted, and the auxiliary blood supply driving device can meet the individual conditions of users in different behavior states. Optionally, the individualized parameter configuration model and related parameters obtained by the upper computer training can be downloaded and updated to the blood supply driving device carried by the user. For example, after the professional medical institution reviews, the personalized parameter configuration model and related parameters passing the review are downloaded to the control module of the blood supply driving device according to a preset updating period or updating condition.

Further alternatively, different types of sensors are provided according to different acquisition requirements. In practical application, in order to further reduce the power consumption of the implantable device, part or all of the sensors are arranged in the extracorporeal device, and are realized as independent modules or devices separated from the blood supply driving device, and control signals and data are transmitted and collected between the sensors and the control module of the blood supply driving device in a wireless or wired communication mode.

In the embodiment of the application, the individual data of the user can comprehensively feed back the individual condition of the user from multiple aspects of physiology, psychology, adaptation condition of equipment and the like of the user, thereby providing data support for the customized parameter setting scheme of the blood supply driving device used by the user.

User individual data includes, but is not limited to: at least one of physiological index information, diagnosis and treatment information and target device attribute of the user. It can be understood that the physiological index information and the diagnosis and treatment information in the individual data of the user are mainly used for representing the physical state of the user from each dimension, and the target device attribute reflects the configuration requirement of the blood supply driving device. Therefore, the user individual data can provide a data basis for the subsequent individual customization configuration mode of the blood supply driving device according to the current physical state of the user and the configuration requirement of the device. The specific types and the number of the user individual data are related to specific application scenarios, and the embodiment of the application is not limited to this.

Specifically, as an alternative embodiment, the physiological index information of the user itself includes, but is not limited to: heart rate, blood oxygen saturation, posture data, muscle electrical data, and underlying physiological information. For example, the underlying physiological information includes, but is not limited to: height, weight, age, sex, basic medical history. As an alternative embodiment, the medical information includes, but is not limited to: current cardiac index, blood circulation parameters, case records, treatment protocol. The diagnosis and treatment information and the basic physiological information are relatively fixed, can be obtained from the individual data of the historical user, can be obtained from diagnosis and treatment records, cases, registration information or other information, and can also be obtained in other modes. Compared with partial physiological index information needing frequent monitoring, the diagnosis and treatment information and the basic physiological information are relatively fixed, and can be directly stored in a user side and a server side carried by a user. The server side can be an upper computer, a cloud server or other service equipment.

Heart rate, blood oxygen saturation, posture data, muscle electrical data, which change as the user's behavioral state, physical state, or other personalized conditions change. Therefore, the physiological change condition of the user needs to be acquired in real time or periodically through monitoring end equipment such as various sensors. In practice, the sensors include, but are not limited to: heartbeat sensor, blood oxygen detection sensor, acceleration sensor, gyroscope, muscle electrical sensor. The detailed description is presented above with respect to various sensors and is not expanded herein.

For a user, the individual needs of the blood supply drive system may also vary with time, physical state, psychological, pathological conditions, etc., and therefore, some of the widely varying data may need to be monitored. In practical application, the monitoring period and the time of the individual data of the user can be set according to the data change characteristics. Further optionally, the user individual data further comprises collecting physiological index information of the user with a sensor. For example, the sensor detects various physiological indicators of the user such as blood oxygen saturation, heart beat, acceleration data, gyroscope data, muscle electrical signals, and the like. The gesture data such as acceleration data and gyroscope data can be used for representing the activity state of a user. The physiological indexes can calculate the heartbeat frequency, blood oxygen level, activity state, muscle force and direction of the user in real time, so that the equipment parameters and the running state of the blood supply driving device can be regulated in real time through the calculation results. The physiological index information acquired by the sensor or other module equipment is read in real time through the data interface of the blood supply driving device, so that the blood supply driving device can be regulated in time, and the real-time performance of the running state of the blood supply driving device is ensured. The data interface may be, for example, a bluetooth interface, a WiFi interface, a dedicated data interface, a USB interface, etc.

After the user individual data are acquired, the individual demands of the user on the blood supply driving system are further mined from the user individual data, so that a data basis is provided for the subsequent individual parameter configuration of the blood supply driving device. For a user, the individual requirements of the blood supply driving system also change with time, physical state, psychological condition, disease condition and other factors, so that the individual data of most users often change in real time, and the individual data needs to be analyzed, identified and processed in time.

Specifically, in step S102, a target device parameter matching the physical state of the user is acquired based on the user individual data.

Since the blood supply state is associated with the operation of the blood supply driving system of the user, for example, the user is in a blood supply state of the blood supply driving system in a movement state, the user is in a blood supply state of the blood supply driving system in a sleep state, and the user is in a blood supply state of the blood supply driving system in a household labor state. Thus, the individual situation of the user is further analyzed in combination with the individual patient data, so that in a subsequent step an individual parameter configuration of the blood supply drive can be realized on the basis of the above situation. How the individual situation of the user is analyzed is described in connection with the following.

In the embodiment of the application, the individual data of the user have various forms. Such as text, pictures, video, waveform information, etc. In practical applications, in an example, the information of the height, weight, age, sex, basic medical history, case record, treatment plan, etc. of the user may be stored in text form in the electronic case, so that the basic physiological information and the diagnosis and treatment information can be obtained by collecting the electronic case. In another example, the basic physiological information such as height, weight, age, sex, basic medical history, case records, and treatment plan of the user may be stored in a picture form in a scan of the handwritten case, so that the basic physiological information and the diagnosis and treatment information contained in the picture need to be acquired through an image recognition technology. Of course, other examples may also be that in the remote diagnosis scene, the user's height, weight, age, gender, basic medical history, case records, treatment plan and other basic physiological information may also be stored in the form of video, audio and other forms in the cloud service end or local equipment during the inquiry process, and further, the video, audio and other files need to be further subjected to natural language analysis to obtain the basic physiological information and the diagnosis and treatment information contained therein.

In still other examples, the current cardiac marker, blood circulation parameters, may also be stored in an examination simplex form. The examination sheets are typically in a rich text form, and thus require further analysis of the diagnostic information contained therein using image recognition techniques. For example, the change curve of the indexes such as blood oxygen content, blood circulation quantity, pulse rate, nutrition and material energy exchange efficiency and the like or related indexes.

In other examples, diagnosis and treatment information such as CT examination results and PCT examination results may also be stored in a database in a special picture form, so that the picture features may be further extracted, and the diagnosis and treatment information included in the picture may be identified based on the picture features.

As an alternative embodiment, the user individual data may also be differentiated using whether it is structured. For example, the structured data may be plain text information, rich text information, pictures, video or audio files having a fixed format in the user individual data. Further alternatively, the video or audio file may be processed into a video clip or audio clip having a fixed format by pre-clipping. The unstructured data may be plain text information, rich text information, pictures, video or audio files that do not have a fixed format in the user individual data.

The user individual data also includes target device attributes. Such data may be device base attributes, such as device model number, device identification, initial values, etc., set according to the device's own attributes. Further alternatively, the heart pump or the dynamically implantable arterial pump may be labeled with the device number of the target apparatus. For example, the external part surface of the heart pump or the artery pump implanted by the movement is marked with equipment numbers by using a wear-resistant material silk screen printing or laser engraving mode. The device number may be presented in the form of characters, one-dimensional codes, two-dimensional codes, or other patterns comprised of an ASCII/UTF-8 character set. Alternatively, the target device attributes may be data collected by sensors, such as operating parameters of the target device.

In the related art, research and development of a machine learning model often need to be realized through cooperation among multiple subjects such as medicine, mathematics, computers and the like and across industries, so if a traditional research and development mode of the machine learning model is adopted, the customization time of a single model is longer, the research and development cost is higher, and the machine learning model is difficult to adapt to individual conditions of different users under different physical states.

Aiming at the problem, on the basis of acquiring the physical state of the user, the embodiment of the application provides a customized equipment parameter prediction mode. User physical states include, but are not limited to, user behavioral states, in which individual needs of the user differ. Thus, in step S102, the behavior state of the user is identified based on the user individual data. Specifically, the blood supply requirement of each user is deeply analyzed, and the corresponding individual condition of the user in different physical states (such as the blood perfusion requirement of the user in the current active state) is predicted, so that the target equipment parameters matched with the physical state of the user are obtained. And parameter configuration of the target device is realized through the target equipment parameters, and the target device is assisted to adapt to individual situations of users.

Based on the principle manner, referring to fig. 2, an optional embodiment of acquiring, in the step S102, the target device parameter matched with the physical state of the user based on the user individual data is specifically implemented as the following steps S201 to S203:

step S201, identifying the behavior state of the user based on the individual data of the user;

step S202, a target working mode corresponding to a user behavior state is obtained; the target working mode comprises one of a motion mode, a blood oxygen balance mode, a sleep mode and a constant speed mode of the target device; the target working mode is used for meeting the blood supply requirement of a user in the current behavior state;

step S203, carrying out parameter prediction processing on individual data of a user through an individual parameter configuration model corresponding to a target working mode to obtain target equipment parameters; the individuation parameter configuration model is obtained through pre-training based on historical user individual data.

Through the steps S201 to S203, the behavior state of the user can be identified according to the user individual data, and then, an individual parameter configuration model is selected in combination with the user behavior state, so as to perform parameter prediction processing on the user individual data to obtain the target device parameters, and the auxiliary blood supply driving device adapts to the individual situation of the user in the current behavior state.

Of course, in practical application, the prediction of the real-time behavior state can be performed, and the finally obtained target equipment parameter in this case is the equipment parameter configuration which is helpful for the blood supply driving device to adapt to the current situation of the user, and can be used for the scenes of device configuration, updating, adjustment and the like; the method can also be used for predicting the historical behavior state, and in this case, the finally obtained target equipment parameters are equipment parameter configuration which is helpful for the blood supply driving device to adapt to the historical condition of the user, and can be used for the scenes of personalized analysis, model training, auxiliary diagnosis and treatment of the user and the like.

In step S201, the behavior state of the user is identified based on the user individual data. In the embodiment of the application, the behavior state of the user comprises a plurality of types. Further alternatively, the behavior state of the user may be individually customized according to the age group, daily activity law, daily activity requirement of the user. Alternatively, it may be configured by a professional medical institution for different groups of people in advance, for example, it may be classified into: heart disease population, hypertension population, and diabetes population. Taking heart disease as an example, it can be classified into: heart disease population of children, heart disease population of middle-aged and young people and heart disease population of old people. Taking heart disease as an example, the degree of illness can be categorized as: mild population, moderate population, severe population. Taking user a as an example, the behavior state L of user a may be set as follows: shallow sleep, deep sleep, resting (awake), walking, jogging, holding, daily activities (including office, household).

In the embodiment of the application, each behavior state is provided with a corresponding equipment parameter gear (Threshold). As an alternative embodiment, a plurality of device parameter gears are provided in order to adapt to individual situations of the user in different physical states. It is understood that the device parameter gear is a plurality of rotational speed intervals of the target apparatus. Rotational speeds may overlap between different device parameter gears. In different equipment parameter gears, the rotating speed adjusting trend is determined by the actual application scene corresponding to the interval and the physical state change of the user in the scene.

In the embodiment of the application, each equipment parameter gear is respectively configured with a corresponding driving component operation parameter. Drive component operating parameters corresponding to each device parameter gear include, but are not limited to: at least one of a maximum rotational speed, a minimum rotational speed, a run-time default rotational speed, a maximum heartbeat compensated rotational speed, a minimum heartbeat compensated rotational speed, and a default heartbeat compensated rotational speed of the implantable arterial pump.

Taking a heart pump as an example, N device parameter gears are set, wherein N is an integer greater than 1. Let N be 50. In each equipment parameter gear, the highest rotating speed (marked as V) corresponding to the equipment parameter gear is arranged _Max ) Minimum rotation speed (denoted as V _Min ) Run-time default speed (denoted as V _Nomal ). When the target device is in a certain device parameter gear, the rotation speed of the target device cannot exceed the corresponding maximum rotation speed or the minimum rotation speed, and the target device is usually executed by adopting a default rotation speed in running.

The default rotation speed may be a value between the maximum rotation speed and the minimum rotation speed, and may be plural or one. The default rotational speed may be set statically, for example, to a certain static value, which may be set according to the activity rule of the user. Further alternatively, the static value may be the difference between the maximum rotational speed and the current blood pressure cycle parameter of the user. In another embodiment, the runtime default speed may also be dynamically adjusted based on user experience and/or monitoring metrics. Further alternatively, the physiological index value detected by a device such as a sports watch, a heart monitoring device, etc. is evaluated whether the current physical state of the user is at an optimal value given by a doctor. If yes, maintaining the default rotating speed in the current running process; if not, adjusting the default rotating speed in the running process until the user is monitored to be in the optimal physical state.

The specific implementation manner of acquiring the target device parameters matched with the physical state of the user based on the individual data of the user in step S102 is described below by taking different types of physiological index data as an example.

In an alternative implementation, it is assumed that the physiological index data includes at least acceleration data and/or gyroscope data. Based on the above assumption, the present application provides an alternative embodiment of step S201, as shown in fig. 3, which may be implemented as the following steps:

step S301, extracting physiological index data from individual data of a user;

step S302, determining the quantity of motion of a user in a specified time period based on the physiological index data;

step S303, determining the behavior state of the user in the appointed time period according to the quantity of the user in the appointed time period.

Through the steps S301 to S303, the behavior state of the user in each time period can be determined according to the physiological index data, so that the working mode adapted by the target device can be selected in an auxiliary manner in combination with the individual user condition (such as blood perfusion requirement of each organ) reflected by the behavior state, and an individual data analysis basis is provided for the subsequent acquisition process of the target device parameters. For convenience of description, the operation mode adapted to the target device is also referred to as a target operation mode in the present application.

In step S301, the physiological index data is extracted from the user individual data. Optionally, the physiological index data includes: acceleration data and/or gyroscope data. In the embodiment of the application, the acceleration data and/or the gyroscope data can reflect the behavior state characteristics of the user, such as the quantity of motion, from the gesture of the user, the position and the like. For example, by adopting a pre-established behavior rule fitting function, a fitting array is obtained from the data, so that the quantity of motion of the user is calculated through the fitting array. For another example, by collecting acceleration data and gyroscope data of the user at each time period within 24 hours, the action distance of the user can be determined, and thus the motion amount of the user can be estimated. Therefore, the motion quantity of the user in different time periods can be analyzed through the acceleration data and/or the gyroscope data of the user in different time periods, so that the behavior state of the user in different time periods can be conveniently judged. In the embodiment of the present application, a period of time that needs to be processed is referred to as a specified period of time for convenience of description.

In step S302, the amount of motion of the user in a specified period of time is determined based on the physiological index data. Specifically, further optionally, acceleration data and/or gyroscope data within each specified period of time are obtained from the physiological index data; fitting the acceleration data and/or the gyroscope data by adopting a behavior rule fitting function to obtain a first behavior rule fitting array; and fitting the fixed integral of the array in each appointed time period according to the first behavior rule to serve as the motion quantity of the user in each appointed time period.

From a functional nature, an input generally corresponds to an output. Based on the characteristics of the sensor data, the sensor data is displayed offline, rather than in the form of waves, and the input sensor data is assumed to be all positive values by default. Based on the characteristics, a behavior rule fitting function can be obtained by adopting a fitting algorithm for a result obtained after the default input sensor data takes a positive value, and the motion quantity or the motion strength corresponding to the current behavior state is identified by obtaining a fixed integral of the behavior rule fitting function for a period of time.

For example, the manner in which the behavior rule fitting function is constructed is described below in connection with specific examples.

Let the behavior rule fit function be the function Poly. The input parameters of the hypothetical law of behavior fitting function include: t, xx, n, where n is the order of the fit. Based on the above assumption, according to the length L of the t array, the index list index is constructed and calculated by the following formula, namely:

the time list ts, and the value list xs are constructed by the following formula:

where t is time axis data, xx is the input sensor value, and function max represents the maximum value in the sub-list. Through the formula, the maximum element value in the sub-list can be calculated and then is assigned to x _i . Further, list x _s The maximum value of each sub-list in (a) is assigned to the variable x _i The point set list is constructed as points:

points＝{(t ₀ ，x ₀ )，(t ₁ ，x ₁ )，(t ₂ ，x ₂ )，Λ，(t _n-1 ，x _n-1 )}

further, the array length corresponding to N data in the point set is calculated: n=points.

Further, the counter T is traversed according to the length L of xx, and a loop is started, and 1 is increased every time, and the specific formula is as follows:

t＝T*(1/L)

n＝N–1

notably, n in the formula herein is the maximum index of the point set.

Further, the initialization x and y are set to 0. Traversing N data in the point set, marking a result value corresponding to N obtained by each cycle as i, and calculating a self-defined function B (i), namely:

furthermore, the custom function B (i) is brought in to update x and y, namely:

x＝x+x _i ·B _i

y＝y+y _i ·B _i

then, x will be added to list px and y will be added to list py. If y is greater than 0, in the list

Y is added to py; otherwise, 0 is added in the list py. The above-described loop process is followed until i=n is traversed

T=l, ends. After the loop is over, polynomial interpolation results px and py are returned. Therefore, a function Poly is constructed to assist the subsequent data analysis flow of the physiological index information.

In step S303, the behavior state of the user in the specified time period is determined according to the motion amount of the user in the specified time period. Specifically, in an alternative implementation manner, the behavior state of the user in each specified time period is obtained according to the motion quantity of the user in each specified time period and the mapping relation between the preset motion quantity and the behavior state.

In the embodiment of the present application, the first behavior rule fitting array includes, but is not limited to: fitting arrays in a stationary state (static), an interference NOISE state (NOISE), and a load state (HOLD) are respectively set in each specified period. The fit array here may be constructed using the function Poly described above. Further optionally, the movement amount of the user in each specified period of time includes: the user is respectively in a stationary state, an interference noise state, and a movement amount in a weight-bearing state in each specified period of time.

For example, after receiving the physiological index data collected by the sensor, an information matrix in M time periods may be obtained and denoted as M. Wherein, the row information of the information matrix M can be expressed as:

[T，KV ₀ ，V ₀ ，KV ₁ ，V ₁ ，…，KV _n ，V _n ，L]

in combination with the current behavior state L, the time T and the corresponding sensor data value V, a feature extraction function is defined, and is used for confirming the sensor state corresponding to the current behavior state, so that the processing is convenient, and the data is shown in fig. 4.

Specifically, it is necessary to perform filtering denoising processing on acceleration data and gyroscope data. Alternatively, the triaxial acceleration data (AX, AY, AZ) are averaged, and the resulting average is noted as: (AX+AY+AZ)/3. Further, the average result is clipped by a function clip (filtered, a_min=0, a_max=none), and the acceleration filter result ACC is output. Similarly, the three-axis gyroscope data (GX, GY, GZ) is subjected to filtering processing by adopting the flow, and a gyroscope filtering result GYRO is obtained. Further, the acceleration filtering result ACC and the GYRO filtering result GYRO are subjected to MEAN processing, and a final overall filtering result MEAN is output, and the overall filtering effect is shown in fig. 5.

After the filtering processing, according to the start-stop time corresponding to the behavior state L, the time T in each start-stop time range, the MEAN value MEAN of the filtering result MEAN, and the fitting order n are respectively input into the behavior rule fitting function Poly to obtain a first fitting array (i.e., a first behavior rule fitting array), which is respectively marked as a static (corresponding to a static state), a NOISE (corresponding to an interference NOISE state), and a HOLD (corresponding to a load state). Wherein the interference noise is mainly from the sensor.

Next, a mapping function of the form f (x) =y is established, and the first fitting arrays STILL, NOISE, HOLD are substituted into the mapping function, respectively. Data in the length range from 0 to n-1 in each array are taken, and integral is calculated on the data to obtain three corresponding fixed integral results P _STILL ，P _NOISE ，P _HOLD . Wherein a specific image of the three definite integral results is seen in fig. 6. In fig. 6, raw is original data of MEAN, and a hatched area represents a constant integration result.

Finally, the result P is integrated _STILL ，P _NOISE ，P _HOLD As the amount of motion P in the current period m. Thus, from the movement amount P of the period m, the behavior state of the current user is analyzed. Specifically, a mapping relationship Pmap between the numerical range of the motion amount P and the behavior state L is established, so that the behavior state L corresponding to the motion amount P can be obtained through the mapping relationship Pmap of n to 1.

After the physiological index data is acquired, in another alternative implementation, it is assumed that the physiological index data includes at least muscle electrical data. Based on the above assumption, referring to fig. 7, in the above step S201, an alternative embodiment of identifying the behavior state of the user based on the user individual data is specifically implemented as the following steps:

step S701, fitting the muscle electricity data in each appointed time period in the physiological index data by adopting a behavior rule fitting function to obtain a second behavior rule fitting array;

step S702, fitting the fixed points of the array in each appointed time period by using a second behavior rule as the motion intensity of the user in each appointed time period;

step 703, fitting an array based on a second behavior rule, marking the muscle movement condition of the user by adopting a force generation identifier, and obtaining the muscle force generation intensity in the marked designated time period; the exertion indicator is used for indicating that the user uses muscles to perform the exercise reaching the set intensity in the current time period.

Through the steps S701 to S703, the exercise intensity and the muscle strength in the corresponding time period can be extracted from the muscle electrical data, thereby being beneficial to further acquiring the blood supply requirement of the user and assisting in improving the adaptability of the blood supply driving device.

For example, in step S701, the muscle electrical data first needs to be segmented according to the behavior state L. For ease of illustration, this example is illustrated with both resting and holding behaviors. Specifically, the user completes detection of various physiological indexes under the guidance of professional staff, and the muscle electricity data acquired by various sensors is obtained by automatically collecting various physiological indexes of the user. For example, electromyogram (EMG) data shown in fig. 8 refers to a myobioelectric pattern recorded with an electromyography. The EMG data here is raw data collected by the user with his hand held by the wristband muscular sensor in μv.

And defining a feature extraction function by combining the current behavior state L, the time T and the corresponding sensor data value V, wherein the feature extraction function is used for confirming whether the user performs behaviors such as holding, exerting force and the like in a corresponding time period.

After receiving the myoelectric data, in order to reduce the calculation amount, the myoelectric data is conveniently processed by using a behavior rule fitting function, and the data smaller than 0 in the original myoelectric data can be set to be 0. Then, according to the start-stop time corresponding to the behavior state L, the time T in each start-stop time range, the MEAN value MEAN of the filtering result MEAN, and the fitting order n are respectively input into the behavior rule fitting function Poly to obtain a second fitting array (i.e., a second behavior rule fitting array), which are respectively marked as STILL (corresponding to the static state), NOISE (corresponding to the interference NOISE state), HOLD (corresponding to the load state). Wherein the interference noise is mainly from the sensor.

Further, in step S702, a mapping function of the form f (x) =y is created, and the second fitting arrays STILL, NOISE, HOLD are substituted into the mapping function, respectively. Taking the data in the length range from 0 to n-1 in each second fitting array, and integrating the data to obtain three fixed integration results S _STILL ，S _NOISE ，S _HOLD As a scoring value for the intensity of exercise.

Wherein a specific image of the result of the fixed integration of the second fit array is shown in fig. 9. In fig. 9, the EMG RAW is the original data with a value of 0 or more in the EMG data, and the hatched area indicates the result of the constant integration.

Next, in step S703, the muscular movement condition of the user is marked by using the force identifier based on the second behavior rule fitting array, and the strength of muscular force within the marked designated time period is obtained.

In an optional embodiment, in step S703, the second behavior rule fitting array is subjected to fourier transform, and the square of the absolute value of the fourier transform result is used as the frequency domain characteristic energy density in each specified time period; fitting the frequency domain characteristic energy density in each appointed time period by adopting a behavior rule fitting function to obtain a third behavior rule fitting array; calculating the constant points of the third behavior rule fitting array in each appointed time period; if the fixed integral result of the third behavior rule fitting array is larger than a preset threshold, marking a designated time period of which the fixed integral result is larger than the preset threshold by adopting a force generating identifier; and the result of the definite integral is taken as the muscle strength of the user in the current appointed time period.

For example, in step S703, the second behavior rule fitting array EMG RAW is segmented according to the start-stop time corresponding to the behavior state L, and fourier transformation is performed on the EMG RAW data corresponding to each start-stop time range T, that is:

emg_fft＝FFT(emg_data)

then, the fourier transform result is calculated by using the following formula, to obtain the frequency domain characteristic energy density corresponding to each start-stop time range T, as the frequency domain characteristic energy density power_density corresponding to each behavior state L, see fig. 10. The formula is as follows:

power_density＝|emg_fft| ²

then, the frequency domain characteristic energy density power_density, time T and fitting order n corresponding to each behavior state L are input into a behavior rule fitting function Poly to obtain a third fitting array (i.e., a third behavior rule fitting array), which are respectively marked as a static state, a NOISE state and a HOLD state. Wherein the interference noise is mainly from the sensor.

Further, a mapping function of the form f (x) =y is established, and the third fitting arrays STILL, NOISE, HOLD are substituted into the mapping function, respectively. Taking data in the length range from 0 to n-1 in each third fitting array, and calculating integral of the data to obtain three fixed integral results Spd corresponding to the third fitting array _STILL ，Spd _NOISE ，Spd _HOLD . Wherein, the specific image of the result of the fixed integration of the third fitting array is shown in fig. 11. In fig. 11, the area of the hatched portion represents the constant integral of the frequency energy density fitting function.

Finally, the fixed integral result of the array is fitted according to the third behavior rule, and the stress situation of the user is marked. Specifically, if the Spd is greater than the preset threshold, the corresponding designated time period is marked by adopting the force Flag (i.e. the force identifier), and the Spd is used as the muscle force strength of the user in the current designated time period. In practical applications, the start-stop time corresponding to the negative portion may be directly used as a time period when the user has a force generating phenomenon (such as a holding behavior) from fig. 11.

Through the processing flow in the above example, the behavior state of the user can be identified. The specific processing flow and the related threshold parameters can be set according to the actual application scene.

After identifying the behavior state of the user based on the user individual data, a target working mode corresponding to the behavior state of the user needs to be acquired. Several processing schemes for the target operation mode are described below in connection with specific scenarios.

As an alternative implementation, the operation modes corresponding to the user behavior state include, but are not limited to: a sports mode, a blood oxygen balance mode, a sleep mode and a constant speed mode. It can be stated that the switching between the working modes can be performed manually, can be realized automatically through the detection of the physiological index data and the identification of the behavior state, and can be preset according to the historical activity law.

The motion mode can monitor the motion state, the motion quantity and the force-exerting state in real time, so that the rotation speed of the pump is corresponding to the rotation speed of the pump. The blood oxygen balance mode can dynamically adjust the rotation speed of the pump along with the blood oxygen content in a certain interval. The sleep mode can set the rotation speed of the pump to be reduced on the premise of not reducing the blood oxygen saturation in a period of time, so that the user can quickly sleep. The mode can be set automatically when preset conditions are met, or can be switched manually. The constant speed mode can make the pump run at constant speed in a certain interval and time. Compared with the traditional constant speed mode, the constant speed mode related by the application can be set according to the individualized data of the user, for example, the constant speed in the constant speed mode can be set according to the age, the sex, the diagnosis and treatment record and the historical physiological index data of the user. Of course, in practical application, a constant speed associated with different application scenarios can also be established, so that a constant speed required by the operation of the corresponding target device is determined by identifying the current application scenario.

In an alternative embodiment, the target operating mode is assumed to be a motion mode. Based on this assumption, the above step S202 may be implemented as: and setting the target working mode of the designated time period marked with the force application mark as a movement mode.

Continuing to base on the assumption, in the step S203, the parameter prediction process is performed on the user individual data through the personalized parameter configuration model corresponding to the target working mode, so as to obtain the target device parameter, which may be implemented as:

calling a motion mode parameter configuration model corresponding to a motion mode from a plurality of models obtained through pre-training; inputting the physiological index data into a motion mode parameter configuration model in the current behavior state to obtain a predicted value of the running parameters of the driving part in a motion mode; and carrying out smoothing treatment on the predicted value to obtain an adjustment value of the operation parameter of the driving part in unit time in the motion mode.

In the embodiment of the application, the motion mode parameter configuration model is obtained by training the historical motion quantity and the historical motion strength of the user in each behavior state. Further optionally, the predicted value of the driving part operating parameter in the motion mode comprises at least one of the following parameter values: a target rotational speed value of the heart pump and a target heartbeat compensation rotational speed value of the implanted arterial pump. Accordingly, the unit adjustment value includes at least one of the following parameter values: a rotational speed adjustment value of the heart pump and a heartbeat compensation rotational speed adjustment value of the implanted arterial pump.

It is understood that, further optionally, the heart rate, blood oxygen content, blood oxygen saturation and other physiological index data may also be used as feedback parameters for adjusting the personalized parameter configuration model. Therefore, the predicted value output by the individuation parameter configuration model can assist the blood supply driving device to be more and more adapted to the blood supply requirement of a user. In practical application, besides the motion mode parameter configuration model, the configuration parameters in the motion mode parameter configuration model can be optimized according to the load characteristics of the blood supply driving system of the user in the motion mode.

In practical application, in a movement mode, the amount of movement and the degree of muscle exertion influence blood supply, so that the final operation parameters of the driving component need to be regulated and controlled through the two parameters, and a movement mode parameter configuration model corresponding to the movement mode can be expressed as:

V _max >V _tar >V _min

wherein V is _max Maximum device parameter corresponding to behavior state L, V _min From the state of behaviorL corresponds to the minimum equipment parameter, V _tar Is the predicted value of the target equipment parameter of the target device, P _max For the historic maximum movement amount S _max For the historic maximum exercise intensity, w ₂ And w ₃ Is a custom weight. Specifically V _max And V _min Obtained by bringing the behavior state L into DicVG (L), V _tar Is the speed of the driving part when the target device reaches the physiological and psychological health index, P _max Maximum amount of motion in data acquisition phase, S _max Maximum intensity of motion, w, in the data acquisition phase ₂ And w ₃ And weights are obtained for the collected man-machine running-in data through an automatic mathematical modeling mode. w (w) ₂ And w ₃ Can be obtained by calculating the data acquired by the upper computer.

Taking a motion mode as an example, the control module obtains sensor data (i.e. physiological index data) through wireless communication modes such as Wi-Fi, bluetooth and ZigBee, obtains Dicv (KV) =v and Dict (KV) =t after analysis, and inputs the sensor data into a motion mode parameter configuration model corresponding to the motion mode for parameter prediction after processing by adopting a filtering denoising mode in the previous example.

Then, obtaining the target speed V of the heart pump or the arterial pump in the motion mode through a motion mode parameter configuration model corresponding to the motion mode _tar (i.e., predicted values). The target rate V is calculated by the following formula _tar Smoothing to obtain rate regulating value V of heart pump or arterial pump in unit time _tmp . Let the adjustment period be T, let it be assumed from the current rate V _cur To a target rate V _tar Based on which the number of rate adjustments per time is gol/T. The specific formula is as follows:

the driving component operation parameters under the motion mode can be configured for the user through the motion mode parameter configuration model, so that the driving component operation parameters which are more in line with the current blood supply requirements of the user can be predicted through the motion mode matched with the current behavior state of the user and the motion mode parameter configuration model.

In general, resting heart rate is the heart rate in resting or resting state. Resting heart rate is relatively slow, while recovery heart rate when transitioning from exercise to other states, or maximum heart rate in exercise, is relatively fast. In order to improve the comfort of the user, for the operation parameters of the driving component of the target device, the blood oxygen saturation cannot be adjusted by adopting the heart rate in a certain state as a standard all the time, so that the blood oxygen saturation of the user can be always maintained to be 99% or even 100%, and the physical and mental health of the user is affected.

Therefore, in various testing activities, the operation parameters of the driving part of the target device (such as the target rotating speed value of the heart pump and the target heartbeat compensation rotating speed value of the implanted arterial pump) can be dynamically adjusted, so that the blood oxygen content can reach the use requirements of various organs of a human body. This mode is called blood oxygen balance mode.

As another optional implementation manner, in the step S202, an optional embodiment of obtaining the target working mode corresponding to the user behavior state is specifically implemented as the following steps: and setting the target working mode which is not marked with the exertion mark and is not in the sleep state for a specified time period as an oxygen blood balance mode.

In the blood oxygen balance mode, in step S203, the blood oxygen balance mode parameter configuration model corresponding to the blood oxygen balance mode is called from among the plurality of models obtained by training in advance. The blood oxygen balance mode parameter configuration model is obtained by training reference blood oxygen parameters which are required to be achieved under each behavior state. The reference blood oxygen parameter is linearly related to the drive component operating parameter value. Further optionally, the reference blood oxygen parameter is obtained based on historical blood oxygen parameters under each behavior state and somatosensory information fed back by the user. The reference blood oxygen parameters include, but are not limited to: blood oxygen content and blood oxygen saturation. Further, the driving component operating parameters of the target device can be further adjusted in combination with feedback evaluations of the user and the professional medical institution for each test activity.

In step S203, the blood oxygen parameter in the physiological index data is input into the blood oxygen balance mode parameter configuration model in the current behavior state, so as to obtain a predicted value of the driving component operation parameter in the blood oxygen balance mode. And finally, carrying out smoothing treatment on the predicted value to obtain a unit adjustment value of the operating parameter of the driving part in the blood oxygen balance mode.

It should be noted that, the method for obtaining the operation parameters of each driving component in the blood oxygen balance mode is similar to the method for obtaining the operation parameters of the driving component in the previous motion mode, and the description is omitted for the sake of brevity.

For example, assume that the blood oxygen saturation threshold that needs to be reached in behavior state L is Os. Based on this, in the data acquisition phase, the various behavior states manually adjusted and the real-time values of the driving component operating parameters are brought to the blood oxygen saturation threshold Os by observing the real-time blood oxygen and the user activity performance. Thus, threshold ranges [ V ] of driving part operation parameters corresponding to various behavior states L are recorded _min ，V _max ]And a corresponding adjustment time gol. The adjustment time gol is the time required for the current driving part operation parameter to reach the target driving part operation parameter attribute. The corresponding relation records are as follows: dicVG (L) = [ V ] _min ，V _max ，Goal]The specific relationship can be expressed as an effect shown in fig. 12.

From the above, it follows that the blood oxygen saturation is linearly related to the driving member operating parameters, so that a polynomial fit can be used to derive the following function:

V _max >V _tar >V _min

wherein V is _max Maximum device parameter corresponding to behavior state L, V _min Minimum device parameter corresponding to behavior state L, V _tar Is the predicted value of the target equipment parameter of the target device, os is the blood oxygen saturation, w ₁ To w _n Is a custom weight. Specifically V _max And V _min Obtained by bringing the behavior state L into DicVG (L), V _tar Is the speed of the driving component when the target device reaches the physiological and psychological health index, os is the blood oxygen saturation, and w ₁ To w _n The weight of the man-machine running-in data acquired by the upper computer is obtained through an automatic mathematical modeling mode.

In the blood oxygen balance mode parameter configuration model, the operation parameters of the driving part of the target device can be dynamically adjusted according to parameters such as blood oxygen content, blood oxygen saturation and the like, so that the target device is assisted to enable each organ of a user to reach the target blood oxygen saturation.

As another alternative implementation manner, in the step S202, the obtaining the target working mode corresponding to the user behavior state may be implemented as: the target operation mode for the specified period of time in the sleep state is set to the sleep mode.

Based on this, in step S203, a sleep mode parameter configuration model corresponding to the sleep mode is called from among the models obtained by training in advance. And inputting the blood oxygen parameters in the physiological index data into a sleep mode parameter configuration model to obtain a predicted value of the running parameters of the driving part in the sleep mode, wherein the sleep mode parameter configuration model is used for reducing the value of the parameters of the driving part under the condition of keeping the current blood oxygen saturation. For example, in the sleep mode, the running parameters of the driving component can be adjusted down to the minimum value defined by the gear of the device parameters, the value corresponding to the comfort of the user feedback body can be adjusted down, and the decreasing value can be dynamically adjusted according to the physiological index monitoring condition in the sleep state. And finally, carrying out smoothing treatment on the predicted value to obtain a unit adjustment value of the operation parameter of the driving part in the sleep mode.

It should be noted that, the method for obtaining the operation parameters of each driving component in the sleep mode is similar to the method for obtaining the operation parameters of the driving component in the motion mode and the blood oxygen balance mode, and the description is omitted.

In an optional embodiment, the pre-warning condition corresponding to the user may be determined according to the diagnosis and treatment information. If the physiological index data meets the early warning condition, early warning information corresponding to the physiological index data is generated to assist related personnel (such as medical staff or guardianship personnel) to timely check the health condition of the user. For example, assuming that the pre-warning condition includes a minimum level of blood oxygen saturation, if the blood oxygen saturation is below the minimum level, a low blood oxygen warning is generated and sent to the pre-bound medical facility or associated personnel.

Step S103, configuring the target apparatus based on the target device parameter.

Through the steps, the target equipment parameters can be configured into the target device, so that the individuation parameter configuration process of the target device is realized, the adaptability of the target device to the individual situation of the user is improved, and the user experience is improved.

Further optionally, before S103, an availability decision is also required for the target device parameter to determine whether the target device parameter can be applied to the individual situation of the user itself. Availability discrimination, including but not limited to the following:

The first mode of discrimination: judging whether the data acquired by various sensors exceeds a threshold value or not so as to eliminate abnormal measured values, and avoiding potential risks and interfering the life of a user. For example, whether an abnormality exists in the sensor is detected. For example, whether an acceleration exceeding a threshold value, a gyroscope or a myoelectric sensor value exists is detected to judge an abnormal situation.

The second mode of discrimination: and judging whether the monitoring device is worn by the monitored object. For example, whether the monitoring object is in a wearing state is determined based on blood oxygen and acceleration sensor data.

The third mode of discrimination: judging whether the monitoring object wears by himself. Further, the display screen of the control module and the monitoring switch are used for carrying out equipment state association, so that whether the wearer is himself or herself is judged. Or, manually connected to indicate to the wearer as himself.

After one or more of the above determinations are made, the target device parameters may be configured into the target apparatus to control the drive components of the target apparatus to meet the blood supply requirements.

As an alternative embodiment, according to the use state of the monitoring device and the working condition of the sensor, if an abnormal condition occurs, such as an abnormality occurs in the control module or a detection abnormality occurs in the physiological index data, the control module automatically enters the adjustment working state or resumes the default constant speed state.

As an optional embodiment, after step S101, after obtaining the user individual data corresponding to the target device, the user individual data may also be used to train the personalized parameter configuration model of the user; setting the device parameter gear matched with the user behavior state based on the user individual data; uploading the user individual data, the trained individualized parameter configuration model and the updated equipment parameter gear to a history adaptation database for an auditing end to audit the individualized parameter configuration model and/or the equipment parameter gear in the history adaptation database; and if the personalized parameter configuration model and/or the equipment parameter gear pass the auditing, issuing the personalized parameter configuration model and/or the equipment parameter gear to the target device from the history adaptation database.

Further optionally, after the personalized parameter configuration model and/or the device parameter range audit is passed, personalized audit information for the personalized parameter configuration model and/or the device parameter range is generated. And further, storing the individuation parameter configuration model, the equipment parameter gear, the target equipment parameter and corresponding individuation audit information into the history adaptation database. Therefore, a data basis is provided for subsequent auditing evaluation, and the accuracy of the parameters of the target equipment is further improved.

In an alternative embodiment, a method for establishing a history adaptation database is also provided. Specifically, a medical data sample is obtained. In the embodiment of the application, the medical data sample comprises a history device used by a user, history equipment parameters and history user individual data corresponding to the history equipment parameters. The historical equipment parameters comprise a plurality of equipment parameter gears and driving component operation parameters corresponding to the equipment parameter gears. The type of history device includes a heart pump and/or an implantable arterial pump. Further, privacy data is extracted from the historical user individual data. In an embodiment of the present application, the privacy data includes at least one of heart rate, blood oxygen saturation, muscle electrical data, physiological gender, age, weight, height, underlying medical history, cardiac index, blood circulation parameters, case records, and treatment regimen of the user. And then, desensitizing the privacy data to obtain the individual data of the history user after the desensitization. Finally, storing the historical device, the historical equipment parameters and the historical user individual data corresponding to the historical equipment parameters into the historical adaptation database, and establishing a corresponding relation between the historical device and the used equipment parameter gear and a corresponding relation between the historical device and the historical user individual data.

Through the steps, the history adaptation database can be constructed, so that history data which is required to be referred when a professional medical institution inquires, retrieves and audits equipment parameters are adjusted is convenient, an evaluation basis is provided for evaluating the equipment parameters, an individuation parameter configuration process of a target device is assisted, and the accuracy of the target equipment parameters is improved. Meanwhile, the time cost consumed by the historical data retrieval during the equipment parameter evaluation is reduced, and the configuration efficiency of the device individuation parameters is improved.

In the above or the following embodiments, further optionally, a monitoring end may be further provided, where the monitoring end is configured to collect individual data of the user, including, but not limited to, physiological index information, diagnosis and treatment information, and target device attributes. Specifically, as an alternative embodiment, a monitoring end for acquiring the physiological index data is provided; and establishing communication connection between the monitoring end and various sensors so as to acquire the physiological index data through the various sensors and feed back the physiological index data to the monitoring end through the communication connection. Wherein the plurality of sensors comprises at least: one of a heartbeat sensor, a blood oxygen detection sensor, a gyroscope, an acceleration sensor and a muscle electric sensor.

Optionally, the monitoring end mainly comprises a sensor, an MCU, a power supply and a micro display screen. In this embodiment, further, the MCU is used as a basic calculation unit for processing the user individual data collected by the various sensors, and a communication unit for establishing communication with the control module and transmitting the user individual data. The MCU can establish a communication channel with the control module through Wi-Fi, bluetooth, zigBee, NFC and the like.

In some examples, the various sensors may be co-mounted in a device, which may be implemented in wearable form, such as a wristband, foot ring, or the like. More specifically, the various sensors described in the foregoing embodiments may be disposed in the same device, and the physiological index information and/or device information collected by the sensors may be transmitted to the control module through the device. Alternatively, in another example, the device may be provided in a plurality of different devices, where the plurality of devices respectively transmit the respective collected physiological index information or device information to the control module. As an alternative implementation manner, for the sensors in the multiple different devices, the control module may be accessed after physical networking through a wireless communication manner.

In practical applications, taking the control module in the blood supply driving device described above as an example, it is assumed that the control module limits, by means of a logic circuit, the signal threshold values required for the maximum pump speed and the minimum pump speed that the energy supply module can supply to the driving module. That is, the maximum pump speed and the minimum pump speed of the drive module are limited, thereby ensuring that the pump speed is within a safe range. Specifically, the pump speed control signal value issued by the control module cannot exceed the maximum speed of the pump nor be lower than the minimum speed. Likewise, there are corresponding arrangements in the energy supply module and the drive module to ensure that each system operates relatively independently. Thus, through the triple insurance mechanism, the stability of each module is ensured, and the stability of other modules or devices in the system is not depended on, so that the risk of out-of-control of the blood supply driving device is reduced, and the life safety of a user is assisted to be protected.

Further alternatively, the control module initial setting may be a default mode, i.e. a station mode, allowing other network devices to discover and connect. In the default mode, one-to-many connections are supported, and connection restriction is performed according to the computing power of the network device. In practical application, the networking mode can adopt Wi-Fi, bluetooth, zigBee and the like, and when the connection handshake is performed, the monitoring end needs to send the equipment number of the blood supply driving device and the internal networking communication password. When the connection between the monitoring end equipment and the control module is disconnected, the control module operates according to a default mode. Alternatively, in the case of a network outage, the default mode of operation may be the constant speed mode described above.

It should be noted that, in practical application, to ensure safety, the addition and initial configuration of the devices at the monitoring end need to be performed in a professional medical institution, including but not limited to the following basic settings: connection of MCU and control module, pump speed limit and sensor calibration. Further, each update adjustment also needs to be performed in the professional medical institution or performed with the remote assistance of the professional medical institution.

Further alternatively, the heart pump or the dynamically implantable arterial pump may be labeled with the device number of the target apparatus. For example, the external part surface of the heart pump or the artery pump implanted by the movement is marked with equipment numbers by using a wear-resistant material silk screen printing or laser engraving mode. The device number may be presented in the form of characters, one-dimensional codes, two-dimensional codes, or other patterns comprised of an ASCII/UTF-8 character set. In practice, the professional medical institution maintains a database of device numbers and networking passwords for each target device. When a device is added, the networking password is acquired by scanning or inputting the device number. And various devices or sensor modules are connected with the MCU by using Wi-Fi, bluetooth, zigBee, UART, SPI and other wireless communication modes or establishing a communication link between the devices or the sensor modules and the MCU by using UART, I2C, SPI, ADC, PWM, CAN and other wired communication modes, writing the network connection mode, the device number and the networking password of the connectable control module, and then manually restarting the monitoring end device. After restarting, the monitoring end device automatically establishes connection with the control module, but if the device number or the password is wrong, the control module automatically disconnects.

If the digital signal value of the sensor is transmitted through a UART, I2C, SPI or other transmission mode, the digital signal value can be directly transmitted as the value of the sensor. If the analog signal of the sensor is transmitted through an interface such as an ADC, analog-to-digital conversion is required to convert it into a sensor value of a digital signal.

Specifically, an infinite loop is established in the MCU, and the sensor values are read at a high speed according to a preset sensor reading sequence. To identify the different sensors, each sensor may be assigned a number according to a sensor type code table. For example, the model of the acceleration sensor is set to 0x01, the gyroscope is set to 0x02, and the muscular sensor is set to 0x03. Because wearable devices are small in size and do not require multiple sensors of the same type to be installed in a small area, the device can be assigned numbers using naming rules for the device type to avoid duplicate and redundant communication codes.

At the end of each cycle, this thread counts up a count value indicating the time that the cycle has elapsed. In this way, the time value corresponding to each sensor data, namely the time from the start of the MCU to the current moment, can be obtained through the counter arranged in the MCU in the monitoring end, and the time stamp is used for recording and processing the sensor data so as to facilitate the subsequent data analysis and processing. Further alternatively, all sensor values are output in a 16-bit floating point format after parsing, with a transmission time value in 16 integer units, starting from 0 after exceeding the value range.

For example, sensor data may be transmitted from the MCU to the control module via USB, serial communication, wi-Fi, zigBee, bluetooth, or the like. The sensor terminal MCU uses a custom reduced communication protocol including a frame header, a frame length, a protocol type, a terminal ID, a sensor number, a sensor value, a frame checksum end. When the control module receives the sensor information sent by the monitoring end MCU, the control module generates a unique key according to the networking equipment number I and the sensor number S:

KV＝(I<<16)|S

the KV is obtained by shifting the networking equipment number by 16 bits leftwards and then carrying out bit-wise OR operation with the sensor number. The key value design can store the networking equipment number and the sensor number in an integer at the same time, and is convenient to index and search quickly.

Then, to facilitate finding the sensor value and the time of receipt, two mapping structures will be generated:

DicV(KV)＝V

DickT(KV)＝T

wherein KV is a key value, and represents a combination of a networking equipment number and a sensor number, and V represents a corresponding sensor value in a mapping structure DicV. In the mapping structure Dickt, T represents the time when the current control module receives the sensor value, and the current MCU starts and then performs accumulation counting.

Furthermore, an infinite loop is established in the MCU, and the two mapping structures DicV and Dickt are traversed respectively to obtain key value pairs KV and V and key value pairs KV and T, and all or part of information of all key value pairs KV and V and T is sent in the instruction. The transmission instruction frame structure needs to include the corresponding relation of KV, V and T, for example, V and T corresponding to different KV may be transmitted using a HEX array or a special symbol interval of a specific format of a character string. For example, at [ { KV: KV1, V: KV1, T: T1}; { KV: KV2, V: KV2, T: T2}; …; { KV: KVn, V: KVn, T: T3} ] is represented using an array of JSONs and a dictionary format string.

Specifically, in KV1, V1, T1; KV2, V2, T2; …; KVn, vn, tn "," split KV, V and T, use "; "dividing the value and time of each terminal sensor, wherein", "sum"; "may be referred to by any symbol.

Wherein, [0x02,0x0101,0x00AA,0x0001,0x0102,0x00AB,0x0002] indicates that the HEX array is used for transmission, 0x02 represents that there are two groups of sensor data currently, 0x010001 represents that the sensor transmission value of the No. 0x01 networking terminal is 0x00AA, the time for recording the value by the sensor is 0x0002, the sensor transmission value of the No. 0x02 of the No. 0x01 networking terminal is 0x00AA, and the time for recording the value by the sensor is 0x0002.

Before the cycle of the round is completed, after the frame content assembly is completed, traversing all communication links currently established by the MCU, and sending the message frame to all links.

In this embodiment, a monitoring terminal is configured to collect individual data of a user, including physiological index information, diagnosis and treatment information, and target device attributes. The monitoring end can provide a data basis for individual condition analysis and the customizing flow of the individual parameter configuration model, is beneficial to further reducing the cost of model individuation customization and is beneficial to providing parameter configuration models which are more suitable for individual conditions of different users for professional medical institutions or related personnel.

In the above or below embodiments, the following method is also proposed for cases where the custom cost is high and the blood supply driving device is not sufficiently adaptable to the individual.

Further alternatively, the user individual data can be transmitted to the upper computer, and the data acquisition of the user individual condition and the training of the individuation parameter configuration model can be completed through the upper computer. Specifically, as an alternative embodiment, after step S101, the physiological index data may also be transmitted from the sensor to the host computer. The upper computer is used for training the individualized parameter configuration model, and communication connection is established between the sensor and the upper computer. Further, in the upper computer, filtering the physiological index data; and taking the sensor identification and the equipment identification of the sensor as indexes, and storing the physiological index data after the filtering treatment into a corresponding mapping structure according to the acquisition time. The sensor identification comprises a sensor number, and the equipment identification comprises an equipment number with the sensor built in. Further, according to the acquisition time of the sensor, adding the behavior state matched with the physiological index data into the mapping structure to construct and obtain an information matrix corresponding to each time period; and storing the information matrix into a hard disk in a lasting way.

Thus, the user individual data is processed by the upper computer to complete the targeted analysis of the user individual condition. On the basis of analyzing individual user conditions, individual parameter configuration models which are suitable for each behavior state in the individual user conditions are further constructed by adopting individual user data in a mathematical modeling mode, so that an automatic training process of a prediction model of driving component parameters in the blood supply driving device is realized, parameter configuration models which are more suitable for different individual user conditions are provided for professional medical institutions or related personnel, and the parameter setting difficulty is reduced.

As an alternative embodiment, the control module in the blood supply driving device also has the functions of internal/external message communication, behavior state recognition, and issuing the operation parameters of the driving component. The control module is mainly applied to control the target device, but in the training stage (such as scientific research, engineering research and development, testing and feedback stage), the sensor data can be transferred to a data acquisition system at an upper computer so as to process the sensor data and other related data, and the upper computer is used for realizing customized analysis of individual conditions of users and engineering research and development flow of a parameter configuration model. The specific flow is as follows:

a) And manually switching the working mode of the control module into a research and development mode, and setting the network communication address of the upper computer. The specific setting method is as follows:

the control module interface is connected in a wired mode, a special instruction is sent to set the current working state as a research and development mode, and meanwhile, the network communication address of the upper computer is set. After the setting is finished, after a connection instruction is sent, the control module is connected with a network address interface of the upper computer, and the connection can still be carried out after the control module is restarted next time (the restarting of the control module does not influence the action of a driving and energy system on a pump).

b) And setting a data acquisition program in another computer system (computing equipment except the monitoring end and the control module) as an upper computer, and receiving sensor data from the control module.

And writing a data acquisition program in the upper computer, wherein the data acquisition program is used for receiving the sensor data transmitted from the target device control module. The upper computer receives the sensor information character string or the HEX array through the network connection established with the control module, and the DicV (KV) =V and DickT (KV) =T are obtained after analysis.

c) The sensor data is preprocessed, including filtering and denoising.

Further alternatively, the muscle electrical data is filtered using a butterworth filter. For example, when the muscle contraction electrical signal (i.e., one of the above-mentioned muscle electrical data) is preprocessed, the muscle contraction electrical signal is subjected to filtering processing using a butterworth filter to improve data quality and reduce noise.

H(z)＝(b ₀ +b ₁ z ^-1 +b ₂ z ^-2 +…+b _m z ^-m )/(a ₀ +a ₁ z ^-1 +a ₂ z ^-2 +…+a _m z ^-m )

Where H (z) is the transfer function of the filter, z is the unit delay operation, b ₀ To b _m A) ₀ To a _m Is a coefficient of the filter.

Further alternatively, when the output value of the acceleration sensor (i.e. the acceleration data mentioned above) is processed, the x-axis, y-axis and z-axis data thereof are combined and then divided by 3 to perform a dimension reduction operation, so as to obtain a value a _i The process is as follows:

a _i ＝(ax _i +ay _i +az _i )/3

when the output value of the acceleration gyroscope sensor is processed, the data of the x axis, the y axis and the z axis are combined and then divided by 3 to perform dimension reduction operation, and the data is divided by lambda to obtain the valueg _i The process is as follows:

g _i ＝((gx _i +gy _i +gz _i )/3)/λ

wherein λ is an empirical parameter, and is mainly used to convert g into a value less than 1, so as to facilitate calculation.

d) Semi-automatically recording the behavior data of the wearer for the complete day.

For example, by means of the sleep monitoring function built in the intelligent bracelet, the starting and ending time point t of the sleep of the wearer can be automatically identified _L0 ，1，t _L0 N, and marks the sensor indicator for this period as sleep state L0.

For example, with weight-setting training consumables (e.g., weight-setting dumbbell), the wearer's force applied to the muscles during the training process is measured, and the myoelectric signal acquisition device is used to collect the myoelectric information P. By recording start and end times t _p ，1，t _p N, the muscle usage can be calculated for training effect assessment and further analysis.

For example, different activity states, such as sitting L1, lying L2, walking L3, running L4, jumping L5, etc., are identified by sensor data acquired by a motion sensor (such as an acceleration sensor, a gyroscope, etc.). By quantitatively recording the time t of each activity _li ，1，t _li N, the daily activity mode and the movement quantity of the wearer can be known, and the behavior set L= { L0, ll, L2, …, ln }

e) The sensor data is stored.

The upper computer receives the sensor data through the network interface and stores the sensor data. Simultaneously recording the data of DicV (KV) =V and DicT (KV) =T, obtaining the behavior state L (sleep, running, jumping, lying and the like) corresponding to the sensor time through the steps, and recording the behavior state L as Dickt (T) =L, thereby realizing the complete correlation of the sensor value, type, time and behavior.

Through KV correlation T and V and T correlation L, an array [ T, KV, V and L ] can be formed, a plurality of groups of sensors can be transmitted at the same time, the formats can be [ T, KV0, V0, KV1, V1, …, KVn, vn and L ], the time T is set at the first position, the current behavior state is set at the last position, each time T forms a row of data, each row stores the state of one time, and the storage formats of m time ends are as follows:

M＝[T0，KV0，V0，KV1，V1，...，KVn，Vn，L

T1，KV0，V0，KV1，V1，...，KVn，Vn，L

...

Tm，KV0，V0，KV1，V1，...，KVn，Vn，L]

And the sensor data is stored in the hard disk in a lasting manner, so that the storage of different terminals, different sensors, different behaviors and different times can be realized.

Through the optimization steps, the sensor data of the target device control module can be collected, preprocessed and stored in the upper computer so as to support analysis engineering research and development work in stages of scientific research, engineering research and development, testing, feedback and the like.

In this embodiment, the research and development mode is used to process the individual user data (including the sensor data) in the upper computer to complete the targeted analysis of the individual user condition. On the basis of analyzing individual situations of users, individual parameter configuration models which are suitable for each behavior state in the individual situations of the users are further constructed by adopting a mathematical modeling mode by adopting individual data of the users, so that an automatic training process of a prediction model of driving component parameters in a blood supply driving device is realized, individual customization cost of the models is greatly reduced, parameter configuration models which are more suitable for individual situations of different users are provided for professional medical institutions or related personnel, and parameter setting difficulty is reduced.

Having described the method of an exemplary embodiment of the present application, a parameter configuration system of an blood supply driving device of an exemplary embodiment of the present application, which includes the blood supply driving device, a monitoring end device, and a parameter configuration device, will be described. See the following for specific functions:

As an optional implementation manner, the monitoring end device at least includes: one of a heartbeat sensor, a blood oxygen detection sensor, a gyroscope, an acceleration sensor and a muscle electric sensor.

It should be noted that, the parameter configuration device is used for implementing the parameter configuration function in the parameter configuration method of the blood supply driving device, and in this embodiment, a detailed description is not required.

According to the embodiment of the application, through the parameter configuration system of the blood supply driving device, the physical state used for reflecting the running condition of the blood supply driving system is analyzed based on the individual data of the user, and then the target equipment parameters matched with the individual condition of the user are customized for the blood supply driving device by combining the physical state of the user, so that the target device can be more suitable for the requirement of the user on the blood supply driving system under the automatic configuration of the target equipment parameters. Meanwhile, the customized parameter configuration of the blood supply driving device is realized by identifying individual conditions of the user, the customized cost of the blood supply driving device is greatly reduced, and the popularization and the application of the blood supply driving device are facilitated.

Having described the method and system of an exemplary embodiment of the present application, a parameter configuration apparatus of a blood supply driving apparatus of an exemplary embodiment of the present application will be described with reference to fig. 13, the apparatus including:

an acquiring unit 1301, configured to acquire user individual data corresponding to a target device; the target device is a blood supply driving device used by a user; the user individual data comprise at least one of physiological index data, diagnosis and treatment information and target device attributes of the user;

A prediction unit 1302, configured to obtain, based on the user individual data, a target device parameter that matches a physical state of the user; the physical state of the user is associated with the blood supply requirement of the user blood supply driving system; the physical state of the user at least comprises a behavior state and/or a muscle strength degree; the target equipment parameters comprise driving component operation parameters matched with the blood supply driving system in the physical state;

a configuration unit 1302, configured to configure the target apparatus based on the target device parameter.

As an alternative embodiment, the prediction unit 1302 is configured to, when acquiring the target device parameter matching the physical state of the user based on the user individual data:

identifying a behavioral state of a user based on the user individual data; acquiring a target working mode corresponding to a user behavior state; the target working mode comprises one of a motion mode, a blood oxygen balance mode, a sleep mode and a constant speed mode of the target device; the target working mode is used for meeting the blood supply requirement of a user in the current behavior state; carrying out parameter prediction processing on the user individual data through an individual parameter configuration model corresponding to the target working mode to obtain the target equipment parameters; the individuation parameter configuration model is obtained through pre-training based on historical user individual data.

As an alternative embodiment, the prediction unit 1302 is configured to, when identifying the behavior state of the user based on the user individual data:

extracting the physiological index data from the user individual data; the physiological index data at least comprises acceleration data and/or gyroscope data; determining a quantity of motion of a user within a specified time period based on the physiological index data; and determining the behavior state of the user in the appointed time period according to the quantity of the user in the appointed time period.

As an alternative embodiment, when the prediction unit 1302 determines the amount of motion within a specified period of time based on the physiological index data, it is configured to:

acquiring acceleration data and/or gyroscope data in each appointed time period from the physiological index data; fitting the acceleration data and/or the gyroscope data by adopting a behavior rule fitting function to obtain a first behavior rule fitting array; and fitting the fixed integral of the array in each appointed time period according to the first behavior rule to serve as the motion quantity of the user in each appointed time period.

Accordingly, the prediction unit 1302, when determining the behavior state of the user in the specified period according to the amount of motion of the user in the specified period, is configured to:

And acquiring the behavior state of the user in each appointed time period according to the motion quantity of the user in each appointed time period and the mapping relation between the preset motion quantity and the behavior state.

As an alternative embodiment, the first behavior rule fitting array includes: fitting arrays in a stationary state, an interference noise state and a loading state are respectively arranged in each specified time period. The amount of motion of the user within each specified time period includes: the user is respectively in a stationary state, an interference noise state, and a movement amount in a weight-bearing state in each specified period of time.

fitting the muscle electricity data in each appointed time period in the physiological index data by adopting a behavior rule fitting function to obtain a second behavior rule fitting array; fitting the fixed points of the array in each appointed time period by using the second behavior rule to serve as the motion intensity of the user in each appointed time period; marking the muscle movement condition of the user by adopting a force generation identifier based on the second behavior rule fitting array, and acquiring the muscle force generation intensity in the marked designated time period; the exertion indicator is used for indicating that the user uses muscles to perform the exercise reaching the set intensity in the current time period.

As an optional implementation manner, when the prediction unit 1302 marks the muscle movement situation of the user with the strength identifier based on the second behavior rule fitting array and obtains the strength of the muscle strength within the marked specified period of time, the prediction unit is configured to:

performing Fourier transform on the second behavior rule fitting array, and taking the square of the absolute value of the Fourier transform result as the frequency domain characteristic energy density in each appointed time period; fitting the frequency domain characteristic energy density in each appointed time period by adopting a behavior rule fitting function to obtain a third behavior rule fitting array; calculating the constant points of the third behavior rule fitting array in each appointed time period; if the fixed integral result of the third behavior rule fitting array is larger than a preset threshold, marking a designated time period of which the fixed integral result is larger than the preset threshold by adopting the force generating identifier; and taking the result of the definite integral as the muscle strength of the user in the current appointed time period.

As an optional implementation manner, when the prediction unit 1302 obtains the target operation mode corresponding to the user behavior state, the prediction unit is configured to: and setting the target working mode of the designated time period marked with the force application mark as a movement mode.

Accordingly, the prediction unit 1302 performs parameter prediction processing on the user individual data through the personalized parameter configuration model corresponding to the target working mode, and when obtaining the target device parameter, is configured to:

calling a motion mode parameter configuration model corresponding to a motion mode from a plurality of models obtained through pre-training; the motion mode parameter configuration model is obtained by training the historical motion quantity and the historical motion strength of the user in each behavior state; inputting the physiological index data into a motion mode parameter configuration model in the current behavior state to obtain a predicted value of the running parameters of the driving part in a motion mode; the predicted value includes at least one of the following parameter values: a target rotational speed value of the heart pump and a target heartbeat compensation rotational speed value of the implanted arterial pump; smoothing the predicted value to obtain an adjustment value of the operation parameter of the driving part in unit time in a motion mode; the unit adjustment value includes at least one of the following parameter values: a rotational speed adjustment value of the heart pump and a heartbeat compensation rotational speed adjustment value of the implanted arterial pump.

As an alternative embodiment, the motion mode parameter configuration model is represented by the following function:

V _max >V _tar >V _min

Wherein V is _max Maximum device parameter corresponding to behavior state L, V _min Minimum device parameter corresponding to behavior state L, V _tar Is the predicted value of the target equipment parameter of the target device, P _max For the historic maximum movement amount S _max For the historic maximum exercise intensity, w ₂ And w ₃ Is a custom weight.

As an optional implementation manner, when the prediction unit 1302 obtains the target operation mode corresponding to the user behavior state, the prediction unit is configured to: and setting the target working mode which is not marked with the exertion mark and is not in the sleep state for a specified time period as an oxygen blood balance mode.

calling an oxygen balance mode parameter configuration model corresponding to an oxygen balance mode from a plurality of models obtained through pre-training; the blood oxygen balance mode parameter configuration model is obtained by training reference blood oxygen parameters which are required to be achieved in each behavior state; the reference blood oxygen parameter is linearly related to the driving component operation parameter value; inputting the blood oxygen parameters in the physiological index data into a blood oxygen balance mode parameter configuration model in the current behavior state to obtain a predicted value of the running parameters of the driving component in the blood oxygen balance mode; and carrying out smoothing treatment on the predicted value to obtain a unit adjustment value of the operating parameter of the driving part in the blood oxygen balance mode.

As an alternative embodiment, the blood oxygen balance mode parameter configuration model uses polynomial fitting as the following function:

V _max >V _tar >V _min

wherein V is _max Maximum device parameter corresponding to behavior state L, V _min Minimum device parameter corresponding to behavior state L, V _tar Is the predicted value of the target equipment parameter of the target device, os is the blood oxygen saturation, w ₁ To w _n Is a custom weight.

As an optional implementation manner, when the prediction unit 1302 obtains the target operation mode corresponding to the user behavior state, the prediction unit is configured to: the target operation mode for the specified period of time in the sleep state is set to the sleep mode.

calling a sleep mode parameter configuration model corresponding to a sleep mode from a plurality of models obtained through pre-training; inputting blood oxygen parameters in the physiological index data into a sleep mode parameter configuration model to obtain a predicted value of the running parameters of the driving part in the sleep mode; the sleep mode parameter configuration model is used for reducing the value of the driving component parameter under the condition of keeping the current blood oxygen saturation; and carrying out smoothing treatment on the predicted value to obtain a unit adjustment value of the operation parameter of the driving part in the sleep mode.

As an optional implementation manner, the system further includes an auditing unit, configured to transmit, after the obtaining unit 1301 obtains the user individual data corresponding to the target device, the physiological index data from the sensor to the upper computer; the upper computer is used for training the individuation parameter configuration model; the sensor is connected with the upper computer in a communication way; in the upper computer, filtering the physiological index data; taking a sensor identifier and a device identifier of the sensor as indexes, and storing the physiological index data after filtering treatment into a corresponding mapping structure according to the acquisition time of the sensor; the sensor identification comprises a sensor number; the equipment identifier comprises an equipment number with the sensor built in; adding behavior states matched with the physiological index data into the mapping structure according to the acquisition time of the sensor to construct and obtain an information matrix corresponding to each time period; and storing the information matrix into a hard disk in a lasting way.

As an optional implementation manner, the system further includes an auditing unit, configured to train an individualized parameter configuration model of a user by using the user individual data after the obtaining unit 1301 obtains the user individual data corresponding to the target device; setting the device parameter gear matched with the user behavior state based on the user individual data; uploading the user individual data, the trained individualized parameter configuration model and the updated equipment parameter gear to a history adaptation database for an auditing end to audit the individualized parameter configuration model and/or the equipment parameter gear in the history adaptation database; and if the personalized parameter configuration model and/or the equipment parameter gear pass the auditing, issuing the personalized parameter configuration model and/or the equipment parameter gear to the target device from the history adaptation database.

According to the embodiment of the application, the parameter configuration device of the blood supply driving device is used for analyzing the physical state used for reflecting the running condition of the blood supply driving system based on the individual data of the user, and the target equipment parameters matched with the individual condition of the user are customized for the blood supply driving device by combining the physical state of the user, so that the target device can be more suitable for the requirement of the user on the blood supply driving system under the automatic configuration of the target equipment parameters. Meanwhile, the customized parameter configuration of the blood supply driving device is realized by identifying individual conditions of the user, the customized cost of the blood supply driving device is greatly reduced, and the popularization and the application of the blood supply driving device are facilitated.

Having described the method, system and apparatus of the exemplary embodiments of the present application, reference is next made to fig. 14 for describing a computer readable storage medium of the exemplary embodiments of the present application, and reference is made to fig. 14 for showing a computer readable storage medium that is an optical disc or other form of storage medium, on which a computer program (i.e., program product 100) is stored, which when executed by a processor, implements the steps described in the above method embodiments, for example, obtaining user individual data corresponding to a target apparatus; the target device is a blood supply driving device used by a user; the user individual data comprise at least one of physiological index data, diagnosis and treatment information and target device attributes of the user; acquiring target equipment parameters matched with the physical state of the user based on the individual data of the user; the physical state of the user is associated with the blood supply requirement of the blood supply driving system of the user; the physical state of the user at least comprises a behavior state and/or a muscle strength degree; the target equipment parameters comprise driving component operation parameters matched with the blood supply driving system in the physical state; configuring a target device based on the target device parameters; the specific implementation of each step is not repeated here.

It should be noted that examples of the computer readable storage medium may also include, but are not limited to, a phase change memory (PRAM), a Static Random Access Memory (SRAM), a Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a flash memory, or other optical or magnetic storage medium, which will not be described in detail herein.

Having described the methods, systems, media, and apparatus of exemplary embodiments of the present application, reference is next made to FIG. 15 for a computing device for parameter configuration of blood supply drive apparatus of exemplary embodiments of the present application.

FIG. 15 illustrates a block diagram of an exemplary computing device 110 suitable for use in implementing embodiments of the application, the computing device 110 may be a computer system or a server. The computing device 110 shown in fig. 15 is only one example and should not be taken as limiting the functionality and scope of use of embodiments of the application.

As shown in fig. 15, components of computing device 110 may include, but are not limited to: one or more processors or processing units 1101, a system memory 1102, and a bus 1103 that connects the various system components (including the system memory 1102 and processing units 1101).

Computing device 110 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by computing device 110 and includes both volatile and nonvolatile media, removable and non-removable media.

The system memory 1102 may include computer-system-readable media in the form of volatile memory, such as Random Access Memory (RAM) 11021 and/or cache memory 11022. Computing device 110 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, ROM11023 may be used to read from or write to non-removable, nonvolatile magnetic media (not shown in FIG. 15 and commonly referred to as a "hard disk drive"). Although not shown in fig. 15, a magnetic disk drive for reading from and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media), may be provided. In such cases, each drive may be coupled to bus 1103 by one or more data media interfaces. The system memory 1102 may include at least one program product having a set (e.g., at least one) of program modules configured to carry out the functions of the embodiments of the application.

A program/utility 11025 having a set (at least one) of program modules 11024 may be stored, for example, in system memory 1102, and such program modules 11024 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment. Program modules 11024 generally perform the functions and/or methodologies of the embodiments described herein.

Computing device 110 may also communicate with one or more external devices 1104 (e.g., keyboard, pointing device, display, etc.). Such communication may occur through an input/output (I/O) interface 1105. Moreover, computing device 110 may also communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the Internet via network adapter 1106. As shown in fig. 15, network adapter 1106 communicates with other modules of computing device 110 (e.g., processing unit 1101, etc.) over bus 1103. It should be appreciated that although not shown in fig. 15, other hardware and/or software modules may be used in connection with computing device 110.

The processing unit 1101 executes various functional applications and data processing by executing programs stored in the system memory 1102, for example, acquires user individual data corresponding to a target device; the target device is a blood supply driving device used by a user; the user individual data comprise at least one of physiological index data, diagnosis and treatment information and target device attributes of the user; acquiring target equipment parameters matched with the physical state of the user based on the individual data of the user; the physical state of the user is associated with the blood supply requirement of the blood supply driving system of the user; the physical state of the user at least comprises a behavior state and/or a muscle strength degree; the target equipment parameters comprise driving component operation parameters matched with the blood supply driving system in the physical state; the target apparatus is configured based on the target device parameters. The specific implementation of each step is not repeated here. It should be noted that although in the above detailed description several units/modules or sub-units/sub-modules of a parameter configuration device of a blood supply driving device are mentioned, such a division is only exemplary and not mandatory. Indeed, the features and functionality of two or more units/modules described above may be embodied in one unit/module in accordance with embodiments of the present application. Conversely, the features and functions of one unit/module described above may be further divided into ones that are embodied by a plurality of units/modules.

In the description of the present application, it should be noted that the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.

In the several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. The above-described apparatus embodiments are merely illustrative, for example, the division of the units is merely a logical function division, and there may be other manners of division in actual implementation, and for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some communication interface, device or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer readable storage medium executable by a processor. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

Finally, it should be noted that: the above examples are only specific embodiments of the present application, and are not intended to limit the scope of the present application, but it should be understood by those skilled in the art that the present application is not limited thereto, and that the present application is described in detail with reference to the foregoing examples: any person skilled in the art may modify or easily conceive of the technical solution described in the foregoing embodiments, or perform equivalent substitution of some of the technical features, while remaining within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Furthermore, although the operations of the methods of the present application are depicted in the drawings in a particular order, this is not required to either imply that the operations must be performed in that particular order or that all of the illustrated operations be performed to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step to perform, and/or one step decomposed into multiple steps to perform.

Claims

1. A method for configuring parameters of a blood supply driving device, comprising:

the target device is configured based on the target device parameters.

2. The method of claim 1, wherein the obtaining target device parameters matching the user's physical state based on the user's individual data comprises:

identifying a behavioral state of a user based on the user individual data;

acquiring a target working mode corresponding to a user behavior state; the target working mode comprises one of a motion mode, a blood oxygen balance mode, a sleep mode and a constant speed mode of the target device; the target working mode is used for meeting the blood supply requirement of a user in the current behavior state;

Carrying out parameter prediction processing on the user individual data through an individual parameter configuration model corresponding to the target working mode to obtain the target equipment parameters; the individuation parameter configuration model is obtained through pre-training based on historical user individual data.

3. The method of claim 2, wherein the identifying the behavioral state of the user based on the user individual data comprises:

extracting the physiological index data from the user individual data; the physiological index data at least comprises acceleration data and/or gyroscope data;

determining a quantity of motion of a user within a specified time period based on the physiological index data;

and determining the behavior state of the user in the appointed time period according to the quantity of the user in the appointed time period.

4. The method of claim 3, wherein the determining the amount of motion over a specified period of time based on the physiological index data comprises:

acquiring acceleration data and/or gyroscope data in each appointed time period from the physiological index data;

fitting the acceleration data and/or the gyroscope data by adopting a behavior rule fitting function to obtain a first behavior rule fitting array;

Fitting the fixed points of the array in each appointed time period according to the first behavior rule to serve as the motion quantity of a user in each appointed time period;

the method for determining the behavior state of the user in the appointed time period according to the quantity of the user in the appointed time period comprises the following steps:

5. The method according to claim 2, wherein the obtaining the target working mode corresponding to the user behavior state includes:

setting a target working mode of a designated time period marked with a force application mark as a movement mode;

the parameter prediction processing is performed on the user individual data through the individuation parameter configuration model corresponding to the target working mode to obtain the target equipment parameters, and the method comprises the following steps:

calling a motion mode parameter configuration model corresponding to a motion mode from a plurality of models obtained through pre-training; the motion mode parameter configuration model is obtained by training the historical motion quantity and the historical motion strength of the user in each behavior state;

Inputting the physiological index data into a motion mode parameter configuration model in the current behavior state to obtain a predicted value of the running parameters of the driving part in a motion mode; the predicted value includes at least one of the following parameter values: a target rotational speed value of the heart pump and a target heartbeat compensation rotational speed value of the implanted arterial pump;

smoothing the predicted value to obtain an adjustment value of the operation parameter of the driving part in unit time in a motion mode; the unit adjustment value includes at least one of the following parameter values: a rotational speed adjustment value of the heart pump and a heartbeat compensation rotational speed adjustment value of the implanted arterial pump.

6. The method of claim 5, wherein the motion mode parameter configuration model is represented by the following function:

wherein V is _max Maximum device parameter corresponding to behavior state L, V _min Minimum device parameter corresponding to behavior state L, V _tar Is the predicted value, P _max For the historic maximum movement amount S _max For the historic maximum exercise intensity, w ₂ And w ₃ Is a custom weight.

7. The method according to claim 2, wherein the obtaining the target working mode corresponding to the user behavior state includes:

setting a target working mode which is not marked with a force identifier and is not in a sleep state for a specified time period as a blood oxygen balance mode;

calling an oxygen balance mode parameter configuration model corresponding to an oxygen balance mode from a plurality of models obtained through pre-training; the blood oxygen balance mode parameter configuration model is obtained by training reference blood oxygen parameters which are required to be achieved in each behavior state; the reference blood oxygen parameter is linearly related to the driving component operation parameter value;

inputting the blood oxygen parameters in the physiological index data into a blood oxygen balance mode parameter configuration model in the current behavior state to obtain a predicted value of the running parameters of the driving component in the blood oxygen balance mode;

and carrying out smoothing treatment on the predicted value to obtain a unit adjustment value of the operating parameter of the driving part in the blood oxygen balance mode.

8. The method of claim 7, wherein the blood oxygen balance pattern parameter configuration model is fitted using a polynomial as a function of:

wherein V is _max Maximum device parameter corresponding to behavior state L, V _min Minimum device parameter corresponding to behavior state L, V _tar Is the predicted value, os is the blood oxygen saturation, w ₁ To w _n Is a custom weight.

9. The parameter configuration system of the blood supply driving device is characterized by comprising the blood supply driving device, monitoring end equipment and a parameter configuration device; wherein the method comprises the steps of

10. A parameter configuration apparatus for a blood supply driving apparatus, comprising: