Model construction method, parameter configuration method and related devices

By constructing an individualized parameter configuration model and dynamically adjusting the parameters of the blood supply drive device, the problem of insufficient adaptability of existing equipment to users is solved, reducing customization costs and improving the stability of blood circulation.

CN116803447BActive Publication Date: 2024-11-01XUANWEI (BEIJING) BIOTECHNOLOGY CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310980532.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-08-04
Publication Date
2024-11-01
Estimated Expiration
2043-08-04

AI Technical Summary

Technical Problem

The existing cardiac pump and arterial pump equipment lacks adaptability to individual users, resulting in unstable blood circulation, and the data model is difficult to apply to customized scenarios, which has high R&D costs.

Method used

By obtaining the user's physiological index data, using the behavioral law fitting function to fit the muscle electrical data, calculate the exercise intensity, and constructing an individualized parameter configuration model based on this, dynamically adjusting the parameters of the blood supply drive device to adapt to the user's physical state.

Benefits of technology

It reduces the customization cost of blood supply drive devices, improves the adaptability and user experience of the equipment, and achieves more stable blood circulation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116803447B_ABST
    Figure CN116803447B_ABST
Patent Text Reader

Abstract

The present application provides a model building method, a parameter configuration method and related devices. The method includes: obtaining user individual data corresponding to a target device; the target device is a blood supply drive device used by the user; the user individual data includes the user's physiological index data; the muscle electrical data in each specified time period in the physiological index data is fitted using a behavioral law fitting function to obtain a first behavioral law fitting array; the definite integral of the first behavioral law fitting array in each specified time period is used as the user's exercise intensity in each specified time period; an individualized parameter configuration model is constructed based on the exercise intensity; the individualized parameter configuration model is used to predict the target device parameters that match the user's physical state. The present application can construct an individualized parameter configuration model, so that the blood supply drive device can be more adapted to the user's physical state under the auxiliary configuration of the model, thereby reducing the customization cost of the blood supply drive device.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present application relate to the field of drive equipment. More specifically, the embodiments of the present application relate to a model building method, a parameter configuration method and related devices. Background Art

[0002] Cardiovascular disease is one of the main killers threatening human health. Most cardiovascular diseases will eventually affect the left ventricular function, leading to decreased heart function. Heart pumps, also known as target devices, can partially or completely replace the heart's pumping function, reduce the burden on the left ventricle, meet the blood perfusion needs of body tissues and organs, and improve the user's quality of life.

[0003] In the related art, heart pumps usually work in a constant speed mode, that is, the speed and flow of the pump remain constant. Although this type of heart pump can relieve the user's heart burden and restore a certain degree of heart function, the non-pulsating blood flow generated by the constant speed pump will affect the self-regulation of the micro-arteries in the blood circulation system, resulting in excessive dilution of the blood, decreased blood oxygen carrying capacity, and unstable hemodynamic characteristics of the entire cardiac cycle.

[0004] At present, the costs of customized research and development, production, and use of medical products such as medical devices, consumables, and drugs are all high. In related technologies, users are usually equipped with related equipment and are actively adapted to the equipment through recovery training. Therefore, existing heart pumps, arterial pumps, and other equipment lack adaptive adjustments for users. In addition, in related technologies, data models are often established for large populations, which are difficult to model, have a long cycle, and have high research and development costs, making them difficult to apply to customized product scenarios.

[0005] Therefore, it is urgent to design a new technical solution to overcome the technical problems existing in the relevant technologies. Summary of the invention

[0006] In this context, the embodiments of the present application hope to provide a model building method, a parameter configuration method and related devices to construct an individualized parameter configuration model, so that the blood supply drive device can be more adapted to the user's physical condition with the auxiliary configuration of the individualized parameter configuration model, thereby reducing the customization cost of the blood supply drive device and facilitating the promotion and application of the blood supply drive device.

[0007] In a first aspect of the embodiments of the present application, a model building method is provided, comprising:

[0008] Acquire user individual data corresponding to the target device; the target device is a blood supply drive device used by the user; the user individual data includes the user's physiological index data;

[0009] The muscle electrical data in each specified time period in the physiological index data are fitted using a behavior law fitting function to obtain a first behavior law fitting array;

[0010] The definite integral of the array in each specified time period is fitted according to the first line rule as the exercise intensity of the user in each specified time period;

[0011] An individualized parameter configuration model is constructed based on exercise intensity; wherein the individualized parameter configuration model is used to predict target device parameters that match the user's physical state; the target device parameters include driving component operating parameters that match the target device under the user's physical state.

[0012] In a second aspect of the embodiments of the present application, a model building device is provided, the device comprising:

[0013] An acquisition unit, used to acquire user individual data corresponding to a target device; the target device is a blood supply drive device used by the user; the user individual data includes at least one of the user's own physiological index data, diagnosis and treatment information, and target device attributes;

[0014] A fitting unit, used for fitting the muscle electrical data in each specified time period in the physiological index data using a behavior law fitting function to obtain a first behavior law fitting array;

[0015] A definite integral unit, used to fit the definite integral of the array in each specified time period according to the first behavior rule as the exercise intensity of the user in each specified time period;

[0016] A construction unit is used to construct an individualized parameter configuration model based on exercise intensity; wherein the individualized parameter configuration model is used to predict target device parameters that match the user's physical state; the target device parameters include driving component operating parameters that match the target device under the user's physical state.

[0017] In a third aspect of the implementation manner of the present application, a parameter configuration method is provided, including:

[0018] Acquire user individual data corresponding to the target device; the target device is a blood supply drive device used by the user; the user individual data includes the user's own physiological index data;

[0019] Based on the user's individual data, the target device parameters matching the user's physical state are predicted through the individualized parameter configuration model; wherein the individualized parameter configuration model is constructed based on the exercise intensity; the exercise intensity is obtained by fitting the muscle electrical data in each specified time period in the physiological indicator data using the behavioral law fitting function; the user's physical state at least includes the degree of muscle force; the target device parameters include the driving component operating parameters of the target device matching the user's physical state;

[0020] The target device is configured based on the target device parameters.

[0021] In a fourth aspect of the embodiments of the present application, a computer-readable storage medium is provided, which includes instructions, and when the instructions are executed on a computer, the computer executes the model building method described in any one of the first aspects.

[0022] In a fifth aspect of the implementation of the present application, a computing device is provided, comprising: at least one processor, a memory and an input-output unit; wherein the memory is used to store a computer program, and the processor is used to call the computer program stored in the memory to execute the model building method described in any one of the first aspects.

[0023] In an embodiment of the present application, a model construction method, a parameter configuration method and a related device are provided. In an embodiment of the present application, the user individual data corresponding to the blood supply drive device (i.e., the target device) used by the user is obtained, and the user individual data includes the user's physiological index information. Here, the user individual data can reflect the user's current physical state and provide a data basis for the subsequent individualized model customization method. After obtaining the user individual data, the muscle electrical data in each specified time period in the physiological index data is fitted using a behavioral law fitting function to obtain a first behavioral law fitting array. Then, the definite integral of the first behavioral law fitting array in each specified time period is used as the user's exercise intensity in each specified time period. Finally, an individualized parameter configuration model is constructed based on the exercise intensity, and the individualized parameter configuration model is used to predict the target device parameters that match the user's physical state. The target device parameters include the driving component operating parameters that match the target device under the user's physical state.

[0024] In an embodiment of the present application, the muscle electrical data in the physiological indicator data is fitted into a behavioral law array through a behavioral law fitting function to obtain the user's exercise intensity in each time period, and then the user's exercise intensity change law is analyzed in combination with the exercise intensity in each time period, thereby constructing an individualized parameter configuration model that meets the user's individual situation, so that the blood supply drive device can be more adapted to the user's physical condition under the auxiliary configuration of the individualized parameter configuration model, thereby reducing the customization cost of the blood supply drive device, which is conducive to the promotion and application of the blood supply drive device. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present application will become readily understood. In the accompanying drawings, several embodiments of the present application are shown in an exemplary and non-limiting manner, wherein:

[0026] Figure 1 A flowchart of a model building method provided in one embodiment of the present application;

[0027] Figure 2 A schematic diagram of raw data of a muscle electrical sensor provided in one embodiment of the present application;

[0028] Figure 3 A schematic diagram of a definite integral effect of a muscle electrical sensor provided in one embodiment of the present application;

[0029] Figure 4 A schematic diagram of a frequency domain characteristic energy density provided by an embodiment of the present application;

[0030] Figure 5 A schematic diagram of a definite integral effect of a frequency domain characteristic energy density provided in one embodiment of the present application;

[0031] Figure 6 A schematic diagram of raw data of an acceleration sensor and a gyroscope provided in one embodiment of the present application;

[0032] Figure 7 A schematic diagram of filtering effects of an acceleration sensor and a gyroscope provided in one embodiment of the present application;

[0033] Figure 8 A schematic diagram of a definite integral effect of an acceleration sensor and a gyroscope provided in one embodiment of the present application;

[0034] Fig. 9 A flow chart of a parameter configuration method of a blood supply drive device provided in one embodiment of the present application;

[0035] Fig.10 A flowchart of a method for acquiring target device parameters provided in one embodiment of the present application;

[0036] Fig.11 A flowchart of a behavior state recognition method provided in one embodiment of the present application;

[0037] Fig.12 A schematic diagram of the principle of a blood oxygen balance mode provided in one embodiment of the present application;

[0038] Fig.13 A schematic diagram of the structure of a model building device provided in one embodiment of the present application;

[0039] Fig.14 A schematic diagram of the structure of a medium provided in one embodiment of the present application;

[0040] Fig.15 A schematic diagram of the structure of a computing device provided in one embodiment of the present application.

[0041] In the drawings, the same or corresponding reference numerals represent the same or corresponding parts. DETAILED DESCRIPTION

[0042] 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 provided only to enable those skilled in the art to better understand and implement the present application, and are not intended to limit the scope of the present application in any way. On the contrary, these embodiments are provided to make the present disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0043] Those skilled in the art know that the embodiments of the present application can be implemented as a system, device, equipment, method or computer program product. Therefore, the present disclosure can be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0044] Cardiovascular disease is one of the main killers threatening human health. Most cardiovascular diseases will eventually affect the left ventricular function, leading to decreased heart function. Heart pumps, also known as target devices, can partially or completely replace the heart's pumping function, reduce the burden on the left ventricle, meet the blood perfusion needs of body tissues and organs, and improve the user's quality of life.

[0045] The applicant has found that in the related art, the heart pump is usually in a fixed speed working mode, that is, the speed and flow of the pump remain constant. Although this kind of heart pump can relieve the user's heart burden and restore a certain heart function, the non-pulsating blood flow generated by the fixed speed pump will affect the self-regulation of the micro-arteries in the blood circulation system, resulting in excessive dilution of the blood, decreased blood oxygen carrying capacity, and unstable hemodynamic characteristics of the entire cardiac cycle.

[0046] In the related art, in addition to the above-mentioned heart pump, an arterial pump can also be used to assist in the recovery of heart function. However, an arterial pump is usually an auxiliary device used in heart surgery. The main body of the device is set outside the user's body and cannot be implanted in the user's body or carried by the user, making it difficult to meet the user's daily life needs. In addition, the arterial pump also uses a fixed-speed working mode, and its speed and flow rate are also maintained at constant values. Obviously, the arterial pump is also unable to solve the technical problems existing in the heart pump in the related art.

[0047] The applicant also found that currently, the costs of customized research and development, production, and use of medical products such as medical devices, consumables, and drugs are all high. In the related technology, users are usually equipped with related equipment and equipment, and users are actively adapted to the equipment and equipment through recovery training. Therefore, existing heart pumps, arterial pumps, and other equipment lack adaptability to users, and the user experience is poor.

[0048] In addition, in related technologies, data models are often built for large populations, which makes modeling difficult, time-consuming, and costly, and it is difficult to apply them to customized product scenarios.

[0049] Therefore, it is urgent to design a new technical solution to overcome the technical problems existing in the blood supply drive device in the related technology.

[0050] The embodiment of the present application provides a model construction method, a parameter configuration method and a related device. In the embodiment of the present application, the user individual data corresponding to the blood supply drive device (i.e., the target device) used by the user is obtained, and the user individual data includes the user's physiological index information. Here, the user individual data can reflect the user's current physical state and provide a data basis for the subsequent individualized model customization method. After obtaining the user's individual data, the muscle electrical data in each specified time period in the physiological index data is fitted using a behavioral law fitting function to obtain a first behavioral law fitting array. Then, the definite integral of the first behavioral law fitting array in each specified time period is used as the user's exercise intensity in each specified time period. Finally, an individualized parameter configuration model is constructed based on the exercise intensity, and the individualized parameter configuration model is used to predict the target device parameters that match the user's physical state. The target device parameters include the driving component operating parameters that match the target device in the user's physical state.

[0051] In an embodiment of the present application, the muscle electrical data in the physiological indicator data is fitted into a behavioral law array through a behavioral law fitting function to obtain the user's exercise intensity in each time period, and then the user's exercise intensity change law is analyzed in combination with the exercise intensity in each time period, thereby constructing an individualized parameter configuration model that meets the user's individual situation, so that the blood supply drive device can be more adapted to the user's physical condition under the auxiliary configuration of the individualized parameter configuration model, thereby reducing the customization cost of the blood supply drive device, which is conducive to the promotion and application of the blood supply drive device.

[0052] In some embodiments, the model building device is one or more. Multiple model building devices can be deployed in a distributed manner or in a centralized manner. In actual application scenarios, the blood supply drive device cooperates with the model building device. For example, the model building device is used to generate an individualized parameter configuration model, which can be implemented as a module deployed in the blood supply drive device, including a software module and / or a hardware module, or other forms of component modules. It can also be implemented as an independent device connected to the blood supply drive device, and the connection method can be a wired method or a wireless method. It can also be implemented as a software service connected to the blood supply drive device, such as a cloud service, an external model service, etc., which is not limited by the embodiments of the present application.

[0053] It should be noted that the server involved in the embodiments of the present application can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, big data and artificial intelligence platforms.

[0054] The terminal device involved in the embodiments 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 devices connected to a wireless modem. For example, a mobile phone (or "cellular" phone) and a computer with a mobile terminal, for example, may be a portable, pocket-sized, handheld, computer-built-in or vehicle-mounted mobile device that exchanges voice and / or data with a wireless access network. For example, Personal Communication Service (PCS) phones, cordless phones, Session Initiation Protocol (SIP) phones, Wireless Local Loop (WLL) stations, Personal Digital Assistants (PDAs) and other devices.

[0055] It should be noted that any number of elements in the drawings is for illustration rather than limitation, and any naming is only for distinction and does not have any limiting meaning.

[0056] The principles and spirit of the present application are explained in detail below with reference to several representative implementations of the present application.

[0057] Reference below Figure 1 , Figure 1 A flow chart of a model building method provided in an embodiment of the present application. It should be noted that the implementation of the present application can be applied to any scenario of a blood supply drive device. In particular, it is applicable to a personalized parameter configuration scenario of a blood supply drive device held by a user.

[0058] Figure 1 The process of the model building method provided by one embodiment of the present application is shown.

[0059] In the related art, the heart pump and arterial pump are generally in a constant speed working mode, that is, the speed and flow of the pump remain constant. However, the non-pulsating blood flow generated by the constant speed pump will affect the self-regulation of the micro-arteries in the blood circulation system, resulting in excessive dilution of the blood, decreased blood oxygen carrying capacity, and unstable hemodynamic characteristics of the entire cardiac cycle. In order to address the above-mentioned problems caused by the constant speed working mode, it is necessary to build an individualized parameter configuration model that is adapted to individual conditions for users, and dynamically adjust the equipment parameters of blood supply drive devices such as heart pumps and arterial pumps through the individualized parameter configuration model, so that the blood supply drive device can meet the individual conditions of the user under the current physical state, which helps to reduce the customization difficulty of the blood supply drive device.

[0060] First, in order to build an individualized parameter configuration model, it is necessary to obtain the user's individual situation.

[0061] Step S101, obtaining user individual data corresponding to the target device.

[0062] In the embodiment of the present application, the target device is a blood supply drive device used by the user. The blood supply drive device is used to continuously pump blood for the user, provide power compensation for the blood circulation system, and assist the blood circulation system to maintain blood perfusion throughout the body. In practical applications, the blood supply drive device includes but is not limited to: a heart pump and an implantable arterial pump.

[0063] Among them, the heart pump is a device that can simulate the function of the human heart. It can be implanted in the user's body and used for a long time. It is mostly used in medical research, treatment and other scenarios. The heart pump can partially or completely replace the heart's pumping function, reduce the burden on the left ventricle, meet the blood perfusion needs of tissues and organs throughout the body, and improve the user's quality of life. An implantable arterial pump is a device that can be implanted in the user's body and used for a long time. It is used to continuously provide auxiliary blood supply drive function for the heart. Implantable arterial pumps are often used in users with heart disease. When other treatments are ineffective, they can serve as a bridge before heart transplantation. Specifically, the implantable arterial pump is surgically implanted into the chest or abdomen and connected to the heart or aorta to provide continuous blood pumping function. This device can help the user's heart continue to pump blood effectively and maintain blood circulation throughout the body.

[0064] As an optional embodiment, in the embodiment of the present application, the blood supply drive device includes the following components: a pump body, a drive module, a control module, an energy supply module, and a sensor.

[0065] The pump body of the blood supply drive device can be made of flexible materials, such as silicone or polyurethane, to simulate the softness of human myocardial tissue. There is a chamber inside the pump body for containing blood simulation liquid or other liquids, and the outer shell of the pump body is usually equipped with inlet and outlet pipes. In order to allow the pump body to contract and relax regularly like a real heart, a motor or pneumatic drive module is usually used in the blood supply drive device.

[0066] Optionally, the target device or the external part of the implantable arterial pump is marked with the device's new number by silk-screen printing or laser engraving with wear-resistant materials. The number can be presented in the form of characters composed of ASCII / UTF-8 character sets, one-dimensional codes, two-dimensional codes, or other patterns. In actual applications, professional medical institutions save a database of the target device's device number and networking password.

[0067] The drive module controls the movement of the pump body to achieve different heart rates and cardiac outputs. The control module is the core of the blood supply drive device, and can achieve different heart rates and cardiac outputs by controlling the output of the drive module.

[0068] The control module is composed of a microprocessor and a program control unit. Specifically, the control module is used to configure the target device parameters of the driver module. It is worth noting that the target device parameters set for the driver module need to be reviewed and confirmed by relevant personnel, and an audit record is generated and stored in a historical adaptation database. Alternatively, it is generated by a machine learning model that has been reviewed and confirmed by relevant personnel. As an optional embodiment, the control and monitoring of the pump (including the heart pump and the arterial pump) is achieved through a user interface or wireless communication.

[0069] The energy supply module of the blood supply drive device can use a battery or an interface power supply, wherein the battery can enable the pump to continue working when the device is moving, and the interface power supply can provide a stable energy supply during long-term use.

[0070] In practical applications, the control module can be implemented as a low-power and networkable computing device or module. Here, the module can be a hardware module or a software module. Optionally, the control module can include but is not limited to the following devices: a single-board computer, a portable device, a low-power microcontroller unit (MCU), and an Internet of Things gateway. Among them, a single-board computer is, for example, a complete computing platform that integrates a processor, memory, storage, and input and output interfaces, but has relatively low power consumption. Portable devices, such as smart phones, tablet computers, and PDAs, are usually designed with smaller size and lower power consumption to extend battery life. MCU, for example, is a microcontroller with lower power consumption and smaller size, which is used to control and monitor sensors, perform simple tasks, and connect external devices. The Internet of Things gateway, for example, is used to connect and manage Internet of Things devices, which are usually low-power and small in size, and are used to handle functions such as data transmission, edge computing, and connectivity management.

[0071] Sensors are used to collect the user's physiological indicator data and device parameters. Specifically, they are used to detect device information such as pump speed and power, as well as physiological indicator information such as heart rate, blood oxygen saturation, posture data (for example, acceleration data, gyroscope data, etc.), and muscle electrical data. In the embodiment of the present application, the sensors include but are not limited to: heartbeat sensors, blood oxygen detection sensors, acceleration sensors, gyroscopes, and muscle electrical sensors. In actual applications, they are divided according to the sensor type, for example, they are implemented as the following sensors:

[0072] Myoelectric sensor: Also known as electromyographic sensor, it is used to measure and record the electrical signals generated by muscles when they are active. It can monitor the electrical signals when muscles contract and relax, and provide information about muscle activity and muscle status. Electromyographic sensors usually use electrodes attached to the surface of muscles to capture the activity pattern and intensity of muscle contraction by detecting changes in muscle potential.

[0073] Accelerometer: An accelerometer measures the acceleration of an object, which is the rate of change of its speed and direction. It can detect the linear acceleration and acceleration of gravity of an object, and provide information about the object's motion, vibration, and tilt. In wearable and mobile devices, accelerometers are commonly used in applications such as pedometers, gesture recognition, motion tracking, and gesture control.

[0074] Gyro Sensor: Gyro sensors are used to measure and sense the rotation and angular velocity of an object. They can detect the turn, direction and rotation speed of an object and provide information related to direction, angle and attitude. Gyro sensors are widely used in aerospace, navigation systems, virtual reality and game control.

[0075] Blood oxygen saturation sensor: Blood oxygen saturation sensor (also called pulse oximeter sensor) is used to non-invasively measure the oxygen saturation level in the blood. It usually detects the oxygen content in the blood through infrared light and light scattering principle, providing information about blood oxygen level and heart pulse. Blood oxygen saturation sensor is widely used in the medical field, especially in monitoring, diagnosis and sleep monitoring.

[0076] Heartbeat sensor: Heartbeat sensor is used to detect and record the heartbeat frequency. It can obtain heartbeat data by measuring cardiac electrical activity, pulse or heart vibration. Heartbeat sensor provides information about heart activity, heart rate changes and heart health status. Heartbeat sensors are widely used in health monitoring, sports training and medical monitoring.

[0077] The above sensors are only examples and are not limited in the embodiments of the present application.

[0078] The following is a detailed introduction on how to analyze the individual situation of users.

[0079] In the embodiment of the present application, the individual data of the user has various forms. For example, text, picture, video, waveform information, etc. In practical applications, in one example, the user's height, weight, age, gender, basic medical history, case record, treatment plan and other information can be stored in the electronic medical record in the form of text, so that the above basic physiological information and diagnosis and treatment information can be obtained by collecting the electronic medical record. In another example, the user's height, weight, age, gender, basic medical history, case record, treatment plan and other basic physiological information can also be stored in the form of pictures in the scanned copy of the handwritten case, so that the basic physiological information and diagnosis and treatment information contained in the picture need to be collected by image recognition technology. Of course, other examples can also be that in the remote medical consultation scenario, the user's height, weight, age, gender, basic medical history, case record, treatment plan and other basic physiological information can also be stored in the cloud service end or local device in the form of video, audio, etc. during the consultation process, and then, it is necessary to further perform natural language analysis on the video, audio and other files to obtain the basic physiological information and diagnosis and treatment information contained therein.

[0080] In some other examples, the current heart index and blood circulation parameters can also be stored in the form of a checklist. The checklist is generally in the form of rich text, so it is necessary to further use image recognition technology to parse the diagnosis and treatment information contained in the rich text. For example, blood oxygen content, blood circulation volume, pulse rate, nutrition and material energy exchange efficiency and other indicators or related indicator change curves.

[0081] In other instances, diagnostic information such as CT examination results and PCT examination results can also be stored in the database in the form of special images, so that the image features can be further extracted and the diagnostic information contained in the image can be identified based on the image features.

[0082] As an optional embodiment, the user individual data can also be distinguished by whether it is structured. For example, the structured data can be plain text information, rich text information, pictures, videos or audio files with a fixed format in the user individual data. Further optionally, the video or audio file can be processed into a video clip or audio clip with a fixed format in a pre-cropped form. The unstructured data can be plain text information, rich text information, pictures, videos or audio files without a fixed format in the user individual data.

[0083] The user's individual data also includes the target device attributes. This type of data can be the basic device attributes set according to the device's own attributes, such as device model, device identification, initial value, etc. Further optionally, the heart pump or implantable arterial pump can be marked with the device number of the target device. For example, the device number is marked on the surface of the external part of the heart pump or implantable arterial pump by silk screen printing or laser engraving with wear-resistant materials. The device number can be presented in the form of characters composed of ASCII / UTF-8 character sets, one-dimensional codes, two-dimensional codes, or other patterns. Alternatively, the target device attributes can also be obtained through data collected by sensors, such as operating parameters of the target device.

[0084] In step S101, after the sensor collects the physiological index data and the device parameters, these physiological index data and the device parameters are transmitted to the control module. Alternatively, these physiological index data and the device parameters can also be transmitted to the host computer. Among them, the sensor includes at least one of: a heartbeat sensor, a blood oxygen detection sensor, an acceleration sensor, a gyroscope, and a muscle electrical sensor. Further optionally, these physiological index data and device parameters can be transmitted to the host computer, and the host computer trains the individualized parameter configuration model corresponding to various working modes, so that the device parameters are predicted by the individualized parameter configuration model to assist the blood supply drive device to adapt to the individual situation of the user. For example, by automatically realizing the customized parameter configuration of the blood supply drive device, the parameter adjustment process of the blood supply drive device is made more efficient, so that the configuration parameters of the blood supply drive device can be adjusted in time, and the blood supply drive device can be assisted to meet the individual situation of the user in different behavior states. Optionally, the individualized parameter configuration model and related parameters obtained by the host computer training can be downloaded and updated to the blood supply drive device carried by the user. For example, after review by a professional medical institution, the approved individualized parameter configuration model and related parameters are downloaded to the control module of the blood supply drive device according to a preset update cycle or update condition.

[0085] Further optionally, different types of sensors are provided according to different collection requirements. In practical applications, in order to further reduce the power consumption of the implantable device, some or all of the sensors are provided in an external device, implemented as an independent module or device separated from the blood supply drive device, and transmit control signals and collect data with the control module of the blood supply drive device through wireless or wired communication.

[0086] In the embodiment of the present application, the user's individual data can provide comprehensive feedback on the user's individual situation from multiple aspects such as the user's physiology, psychology, and adaptability to the equipment, thereby providing data support for the subsequent customized parameter setting plan of the blood supply drive device used by the user.

[0087] User individual data includes, but is not limited to: at least one of the user's own physiological indicator information, diagnosis and treatment information, and target device attributes. It is understandable that the physiological indicator information and diagnosis and treatment information in the user's individual data are mainly used to represent the user's physical state from various dimensions, and the target device attributes reflect the configuration requirements of the blood supply drive device. In this way, the user's individual data can provide a data basis for the subsequent personalized customization of the blood supply drive device based on the user's current physical state and the device's own configuration requirements. The specific types and quantities of the above-mentioned user individual data are related to the specific application scenarios, and the embodiments of the present application do not limit this.

[0088] Specifically, as an optional embodiment, the user's own physiological indicator information includes but is not limited to: heart rate, blood oxygen saturation, posture data, muscle electrical data, and basic physiological information. For example, basic physiological information includes but is not limited to: height, weight, age, gender, and basic medical history. As an optional embodiment, diagnosis and treatment information includes but is not limited to: current heart indicators, blood circulation parameters, case records, and treatment plans. Diagnosis and treatment information and basic physiological information are relatively fixed and can be obtained from historical user individual data, or from diagnosis and treatment records, cases, registration information or other information, or in other ways. Compared with some physiological indicator information that needs to be monitored frequently, diagnosis and treatment information and basic physiological information are relatively fixed and can be directly saved in the user end and server end carried by the user. The server end can be a host computer, a cloud server, or other service equipment.

[0089] However, physiological indicators such as heart rate, blood oxygen saturation, posture data, and muscle electrical data change with the user's action state, physical condition, or other individual conditions. Therefore, it is necessary to collect the user's physiological changes in real time or periodically through various sensors and other monitoring devices. In practical applications, sensors include but are not limited to: heart rate sensors, blood oxygen detection sensors, acceleration sensors, gyroscopes, and muscle electrical sensors. For specific instructions, please refer to the above introduction to various sensors, which will not be expanded here.

[0090] For a user, the individualized demand for the blood supply drive system will also change with time, physical condition, psychology, illness and other factors, so it is necessary to monitor some data with large changes. In practical applications, the monitoring cycle and timing of the user's individual data can be set according to the data change characteristics. Further optionally, the user's individual data also includes the user's physiological index information collected by the sensor. For example, the sensor detects the user's blood oxygen saturation, heartbeat, acceleration data, gyroscope data, muscle electrical signals and other physiological indicators. Among them, the acceleration data, gyroscope data and other posture data can be used to reflect the user's activity state. These physiological indicators can calculate the user's heart rate, blood oxygen level, activity state, muscle force size and direction in real time, so that the device parameters and operating state of the blood supply drive device can be adjusted in real time through these calculation results. The physiological index information collected by the sensor or other module equipment is read in real time through the data interface of the blood supply drive device, so as to adjust the blood supply drive device in time and ensure the real-time operation state of the blood supply drive device. The above-mentioned data interface can be, for example, a Bluetooth interface, a WiFi interface, a dedicated data interface, a USB interface, etc.

[0091] After obtaining the user's individual data, it is necessary to further mine the user's individual needs from the user's individual data, so as to provide a data basis for the subsequent construction of a personalized parameter configuration model adapted to the blood supply drive device. For a user, the individual needs for the blood supply drive device will also change with time, physical condition, psychology, disease conditions and other factors. Therefore, most user individual data often changes in real time and needs to be analyzed, identified and subsequently processed in a timely manner.

[0092] Step S102, the muscle electrical data in each specified time period in the physiological index data are fitted using a behavior law fitting function to obtain a first behavior law fitting array.

[0093] Step S103, fitting the definite integral of the array in each specified time period with the first behavior as the rule as the exercise intensity of the user in each specified time period.

[0094] Through the above steps S102 to S103, the exercise intensity in the corresponding time period can be extracted from the muscle electrical data, which helps to further obtain the user's individual situation and assist in building an individualized parameter configuration model to improve the adaptability of the blood supply drive device.

[0095] Generally speaking, according to the properties of the function, one input usually corresponds to one output. Based on the characteristics of sensor data, it can be seen that sensor data is displayed offline, not in the form of waves, and all input sensor data are taken as positive values ​​by default. Based on the above characteristics, for the results obtained after the default input sensor data is taken as positive values, a fitting algorithm can be used to obtain the behavior law fitting function. By calculating the definite integral of the behavior law fitting function over a period of time, the exercise intensity corresponding to the current behavior state can be identified.

[0096] For example, the following describes how to construct a behavior law fitting function with reference to a specific example.

[0097] Assume that the behavior law fitting function involved in the embodiment of the present application is the function Poly. Assume that the input parameters of the behavior law fitting function include: t, xx, n, where n is the order of fitting. Based on the above assumptions, according to the length of the t array being L, the calculation index list index is constructed by the following formula, namely:

[0098]

[0099] The time list ts and the value list xs are constructed by the following formula, namely:

[0100]

[0101]

[0102] Among them, t is the time axis data, xx is the input sensor value, and the function max means taking the maximum value in the sublist. Through the above formula, the maximum element value in the sublist can be calculated, and then the maximum element value is assigned to x i . Then, list x s The maximum value of each sublist in is assigned to the variable x i , construct a list of points and record it as points:

[0103] points={(t0,x0),(t1,x1),(t2,x2),Λ,(t n-1 , x n-1 )}

[0104] Furthermore, the length of the array corresponding to the N data in the point set is calculated: N=points.

[0105] Furthermore, according to the length L of xx, the counter T is traversed and a loop is started, with each loop increasing by 1. The specific formula is as follows:

[0106] t=T*(1 / L)

[0107] n=N–1

[0108] It is worth noting that n in the formula here is the maximum index of the point set.

[0109] Then, initialize x and y to 0. Traverse the N data in the point set, each loop gets the result value corresponding to N, record it as i, and calculate the custom function B(i), that is:

[0110]

[0111] Then, the above custom function B(i) is introduced to update x and y, that is:

[0112] x=x+x i ·B i

[0113] y=y+y i ·B i

[0114] Then, add x to the list px and y to the list py. If y is greater than 0, add

[0115] Add y to list py; otherwise, add 0 to list py. The above loop process continues until i=N and

[0116] The process ends when T=L. After the loop ends, the polynomial interpolation results px and py are returned. Thus, a function Poly is constructed to assist the subsequent data analysis process of the physiological index information.

[0117] After introducing one of the methods for constructing the behavior pattern fitting function, the following introduces a specific method for extracting the user's exercise intensity from the muscle electrical data with a specific example.

[0118] In step S102, the muscle electrical data in each specified time period in the physiological indicator data is fitted using a behavioral law fitting function to obtain a first behavioral law fitting array. In the embodiment of the present application, the first behavioral law fitting array includes but is not limited to: fitting arrays in a static state, an interference noise state, and a weight-bearing state in each specified time period. Further optionally, the exercise intensity of the user in each specified time period includes: the exercise intensity of the user in a static state, an interference noise state, and a weight-bearing state in each specified time period.

[0119] For example, in step S102, the muscle electrical data needs to be segmented according to the behavior state L. For the convenience of explanation, this example uses two behaviors, static and gripping, as examples. Specifically, the user completes various physiological index tests under the guidance of professionals, and the muscle electrical data collected by various sensors are obtained by automatically collecting the user's various physiological indicators. For example, Figure 2 The electromyogram (EMG) data shown here is the raw data collected by the wristband electromyogram sensor when the user is holding and lifting, and the unit is μV.

[0120] Assume that the behavior state is L, the time is T, and the data value output by the sensor is V. Then, combining the current behavior state L, time T, and the corresponding sensor data value V, a feature extraction function is defined to confirm whether the user performs actions such as gripping or exerting force in the corresponding time period.

[0121] After receiving muscle electrical data (such as the sensor data value V in this example), in order to reduce the amount of calculation and facilitate the use of the behavior law fitting function to process the muscle electrical data, the data less than 0 in the original muscle electrical data can be set to 0. Then, according to the start and end time corresponding to the behavior state L, the time T in each start and end time range, the mean Mean of the filtering result MEAN, and the fitting order n are input into the behavior law fitting function Poly to obtain the first fitting array (i.e., the first behavior law fitting array), which are recorded as STILL (corresponding to the static state), NOISE (corresponding to the interference noise state), and HOLD (corresponding to the weight-bearing state). Among them, the interference noise mainly comes from the sensor.

[0122] Then, in step S103, the definite integral of the array in each specified time period is fitted according to the first behavior as a rule, as the exercise intensity of the user in each specified time period.

[0123] For example, in step S103, a mapping function of the form f(x)=y is established, and the first fitting arrays STILL, NOISE, and HOLD are respectively substituted into the mapping function. The data in the length range of 0 to n-1 in each first fitting array are taken, and the definite integral of these data is calculated to obtain three definite integral results S STILL , S NOISE , S HOLD , as the scoring value of exercise intensity.

[0124] The specific image of the definite integral result of the first fitting array can be found in Figure 3 .exist Figure 3 In the figure, EMG RAW refers to the raw data whose values ​​are greater than or equal to 0 in the EMG data, and the shaded area represents the definite integral result.

[0125] Step S104: constructing an individualized parameter configuration model based on exercise intensity.

[0126] In the embodiment of the present application, the individualized parameter configuration model is used to predict the target device parameters that match the user's physical state. The target device parameters include but are not limited to: the driving component operating parameters of the target device that match the user's physical state.

[0127] Specifically, in an optional embodiment, step S104 can be implemented as follows: constructing a motion mode parameter configuration model based on the exercise intensity in each specified time period, the historical maximum exercise intensity, and the first custom weight. In practical applications, when the user is in motion, the blood supply demand is mainly related to factors such as exercise intensity, muscle strength, and amount of exercise. Therefore, the exercise intensity obtained based on muscle electrical data can be used to construct a personalized parameter configuration model adapted to the motion state, that is, a motion mode parameter configuration model. Since the individual situation of the user in the motion state is also related to other factors, various types of motion mode parameter configuration models can be constructed, and this is only one example. For ease of description, the motion mode parameter configuration model in this embodiment is referred to as the first motion mode parameter configuration model in this application. Among them, the motion mode can monitor the motion state, amount of exercise, and force state in real time, so that the pump speed responds quickly.

[0128] The first motion mode parameter configuration model is used to predict the target device parameters. Further optionally, the first motion mode parameter configuration model is expressed as the following formula:

[0129] V max >V tar >V min

[0130] Among them, V maxThe maximum device parameter under the user's current behavior state, V min The minimum device parameters under the user's current behavior state, V tar is the target device parameter, S is the exercise intensity in the current specified time period, and S max is the maximum exercise intensity in history, and w1 is the first custom weight.

[0131] In an embodiment of the present application, the muscle electrical data in the physiological indicator data is fitted into a behavioral law array through a behavioral law fitting function to obtain the user's exercise intensity in each time period, and then the user's exercise intensity change law is analyzed in combination with the exercise intensity in each time period, thereby constructing an individualized parameter configuration model that meets the user's individual situation, so that the blood supply drive device can be more adapted to the user's physical condition under the auxiliary configuration of the individualized parameter configuration model, thereby reducing the customization cost of the blood supply drive device, which is conducive to the promotion and application of the blood supply drive device.

[0132] In the above or following embodiments, after step S102, the muscle movement of the user in each specified time period can be marked based on the first behavior rule fitting array, and the muscle strength in the marked specified time period is obtained. In the marked specified time period, the muscle movement performed by the user reaches the set strength.

[0133] As an optional embodiment, in the above steps, based on the first behavior rule fitting array, the muscle movement of the user in each specified time period is marked, and the muscle strength in the marked specified time period is obtained, which can be implemented as follows:

[0134] The first behavior law fitting array is Fourier transformed, 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; the frequency domain characteristic energy density in each specified time period is fitted using the behavior law fitting function to obtain the second behavior law fitting array; according to the definite integral in each specified time period in the second behavior law fitting array, the specified time period whose definite integral is greater than a preset threshold is marked with a force mark; the corresponding definite integral in the second behavior law fitting array is used as the muscle force intensity of the user in the marked specified time period.

[0135] Continuing with the above example, in the above steps, assume that Figure 3 The first behavior regularity fitting array EMG RAW is segmented according to the start and end time corresponding to the behavior state L, and Fourier transform is performed on the EMG RAW data corresponding to each start and end time range T, that is:

[0136] emg_fft = FFT(emg_data)

[0137] Then, the Fourier transform result is calculated using the following formula to obtain the frequency domain characteristic energy density corresponding to each start and end time range T, which is used as the frequency domain characteristic energy density power_density corresponding to each behavior state L. Figure 4 The formula is as follows:

[0138] power_density=|emg_fft| 2

[0139] Next, the frequency domain characteristic energy density power_density, time T, and fitting order n corresponding to each behavior state L are input into the behavior law fitting function Poly to obtain the second fitting array (i.e., the second behavior law fitting array), which are recorded as STILL (corresponding to the static state), NOISE (corresponding to the interference noise state), and HOLD (corresponding to the load state). Among them, the interference noise mainly comes from the sensor.

[0140] Then, a mapping function of the form f(x)=y is established, and the second fitting arrays STILL, NOISE, and HOLD are respectively substituted into the mapping function. The data in the length range of 0 to n-1 in each second fitting array are taken, and the definite integral of these data is calculated to obtain the three definite integral results Spd corresponding to the second fitting array STILL ,Spd NOISE ,Spd HOLD The specific image of the definite integral result of the second fitting array can be found in Figure 5 .exist Figure 5 In the figure, the shaded area represents the definite integral of the frequency energy density fitting function.

[0141] Finally, the user's force is marked according to the result of the definite integral of the second behavior law fitting array. Specifically, if Spd is greater than the preset threshold, the force Flag (i.e., force mark) is used to mark the corresponding specified time period, and the Spd is used as the user's muscle force intensity in the current specified time period. In practical applications, it can be obtained from Figure 5 The start and end time corresponding to the negative part is directly used as the time period when the user exerts force (such as gripping behavior).

[0142] Through the processing flow in the above example, the user's behavior state can be identified. The specific processing flow and related threshold parameters can be set according to the actual application scenario.

[0143] After obtaining the muscle strength within the marked specified time period, in step S104, an optional implementation method of building an individualized parameter configuration model based on exercise intensity may be:

[0144] Based on the exercise intensity in each designated time period and the muscle strength in the marked designated time period, a second exercise pattern parameter configuration model is constructed. The second exercise pattern parameter configuration model can also be used to predict target device parameters.

[0145] In practical applications, in the exercise mode, the exercise intensity and muscle strength will affect the blood supply. Therefore, the final drive component operating parameters can be regulated by controlling these two parameters at the same time. Further, optionally, the second exercise mode parameter configuration model is expressed as the following formula:

[0146] V max >V tar >V min

[0147] Among them, V max The maximum device parameter under the user's current behavior state, V min The minimum device parameters under the user's current behavior state, V tar is the target device parameter, S is the exercise intensity in the current specified time period, and S max is the maximum exercise intensity in history, w1 is the first custom weight, Spd is the muscle strength in the current specified time period, and Spd max is the historical maximum muscle force intensity, and w2 is the second custom weight.

[0148] In this embodiment, the muscle electrical data in the physiological indicator data is fitted into a behavioral law array through a behavioral law fitting function to obtain the user's exercise intensity and muscle force intensity in each time period, and then the two parameters are combined to comprehensively analyze the user's exercise intensity change law, thereby constructing an individualized parameter configuration model that meets the user's individual situation, so that the configuration parameters of the blood supply drive device can be regulated by these two parameters at the same time, so that the blood supply drive device can be more adapted to the user's physical condition, further reducing the customization cost of the blood supply drive device.

[0149] In the above or following embodiments, after step S101, the acceleration data and / or gyroscope data in each specified time period in the physiological indicator data are fitted using a behavioral law fitting function to obtain a third behavioral law fitting array; the definite integral of the third behavioral law fitting array in each specified time period is used as the user's exercise amount in each specified time period.

[0150] Similar to the above, for the result obtained after the default input sensor data takes a positive value, a fitting algorithm can be used to obtain a behavior law fitting function. By calculating the definite integral of the behavior law fitting function over a period of time, the amount of motion corresponding to the current behavior state can be identified.

[0151] In the embodiment of the present application, the third behavior regularity fitting array includes but is not limited to: fitting arrays in a static state (STILL), an interference noise state (NOISE), and a weight-bearing state (HOLD) in each specified time period. The fitting array here can be constructed using the function Poly introduced above. Further optionally, the amount of exercise of the user in each specified time period includes: the amount of exercise of the user in a static state, an interference noise state, and a weight-bearing state in each specified time period.

[0152] For example, after receiving the physiological index data collected by the sensor, the information matrix within m time periods can be obtained, which is recorded as M. Among them, the row information of the information matrix M can be expressed as:

[0153] [T,KV0,V0,KV1,V1,…,KV n , V n , L]

[0154] Combined with the current behavior state L, time T and the corresponding sensor data value V, a feature extraction function is defined to confirm the sensor state corresponding to the current behavior state for easy processing. Figure 6 shown.

[0155] Specifically, the acceleration data and gyroscope data need to be filtered and denoised. Optionally, the three-axis acceleration data (AX, AY, AZ) is averaged, and the average result is recorded as: (AX+AY+AZ) / 3. Then, the function clip(filtered, a_min=0, a_max=None) is used to clip the average result and output the acceleration filtering result ACC. Similarly, the three-axis gyroscope data (GX, GY, GZ) is filtered using the above process to obtain the gyroscope filtering result GYRO. Then, the acceleration filtering result ACC and the gyroscope filtering result GYRO are averaged to output the final overall filtering result MEAN. The overall filtering effect can be seen. Figure 7 shown.

[0156] After filtering, according to the start and end time corresponding to the behavior state L, the time T within each start and end time range, the mean value Mean of the filtering result MEAN, and the fitting order n are input into the behavior law fitting function Poly to obtain the third fitting array (i.e., the third behavior law fitting array), which are recorded as STILL (corresponding to the static state), NOISE (corresponding to the interference noise state), and HOLD (corresponding to the load state). Among them, the interference noise mainly comes from the sensor.

[0157] Next, a mapping function of the form f(x)=y is established, and the first fitting arrays STILL, NOISE, and HOLD are substituted into the mapping function. The data in the length range of 0 to n-1 in each array are taken, and the definite integral of these data is calculated to obtain the corresponding three definite integral results P STILL , P NOISE , P HOLD . The specific images of the three definite integral results can be found in Figure 8 .exist Figure 8 In the figure, Raw is the original data of MEAN, and the shaded area represents the definite integral result. STILL , P NOISE , P HOLD As the amount of motion P in the current time period m.

[0158] In an optional embodiment, after obtaining the amount of exercise in each specified time period, an individualized parameter configuration model is constructed based on the exercise intensity, which can be implemented as follows:

[0159] Based on the exercise intensity and exercise volume in each specified time period, a third exercise mode parameter configuration model is constructed. The third exercise mode parameter configuration model is used to predict the target device parameters.

[0160] Further optionally, the third motion mode parameter configuration model is expressed as the following formula:

[0161] V max >V tar >V min

[0162] Among them, V max The maximum device parameter under the user's current behavior state, V min The minimum device parameters under the user's current behavior state, V tar is the target device parameter, S is the exercise intensity in the current specified time period, and S max is the maximum exercise intensity in history, w1 is the first custom weight, P is the amount of exercise in the current specified time period, P max is the maximum amount of exercise in history, and w2 is the third custom weight.

[0163] In this embodiment, the acceleration data, gyroscope data, and muscle electrical data in the physiological indicator data are fitted into a behavioral law array through a behavioral law fitting function to obtain the user's exercise volume and exercise intensity in each time period, and then the two parameters are combined to comprehensively analyze the change law of the user's exercise intensity, thereby constructing an individualized parameter configuration model that meets the user's individual situation, so that the configuration parameters of the blood supply drive device can be regulated by these two parameters at the same time, so that the blood supply drive device can be more adapted to the user's physical condition, further reducing the customization cost of the blood supply drive device.

[0164] In practical applications, in addition to the above three sports mode parameter configuration models, it is also possible to comprehensively construct an individualized parameter configuration model that meets the individual situation of the user based on parameters such as exercise volume, exercise intensity, and muscle strength. The construction principle is similar and will not be expanded here.

[0165] After introducing the model building method provided in the embodiment of the present application, a parameter configuration method provided in the embodiment of the present application is introduced below. Fig. 9 A schematic flow chart of a parameter configuration method for a blood supply drive device provided in one embodiment of the present application.

[0166] Step S901, obtaining user individual data corresponding to the target device.

[0167] Step S902: acquiring target device parameters matching the user's physical state based on the user's individual data.

[0168] Specifically, in step S902, target device parameters matching the user's physical state are obtained based on the user's individual data. The individualized parameter configuration model is constructed based on exercise intensity; exercise intensity is obtained by fitting the muscle electrical data in each specified time period in the physiological indicator data using the behavioral law fitting function; the user's physical state at least includes the degree of muscle force; the target device parameters include the operating parameters of the driving components of the target device that match the user's physical state.

[0169] Since the blood supply status is associated with the operation of the user's own blood supply drive system, for example, the blood supply status of the blood supply drive system when the user is in motion, the blood supply status of the blood supply drive system when the user is in sleep, and the blood supply status of the blood supply drive system when the user is doing housework. Therefore, the individual situation of the user is further analyzed in combination with the individual data of the user, so that the personalized parameter configuration of the blood supply drive device can be realized based on the above situation in the subsequent steps.

[0170] In related technologies, the research, development and promotion of machine learning models often require cooperation among multiple disciplines and industries such as medicine, mathematics, and computers. Therefore, if the traditional machine learning model research and development method is adopted, the customization time of a single model is long, the research and development cost is high, and it is difficult to adapt to the individual conditions of different users in different physical conditions.

[0171] To address this issue, based on obtaining the user's physical state, a customized device parameter prediction method is provided in an embodiment of the present application. The user's physical state includes but is not limited to the user's behavioral state, and the individual needs of the user are different under different behavioral states. Therefore, in step S902, the user's behavioral state is identified based on the user's individual data. Specifically, an in-depth analysis is conducted on the blood supply needs of each user, and the corresponding individual conditions of the user under different physical states (such as the blood perfusion needs of the user in the current active state) are predicted, thereby obtaining the target device parameters that match the user's physical state. The parameter configuration of the target device is achieved through the target device parameters, which assists in achieving the adaptation of the target device to the individual conditions of the user.

[0172] Based on the above principle, see Fig.10 As shown, an optional embodiment of acquiring the target device parameters matching the user's physical state based on the user's individual data in the above step S902 is specifically implemented as the following steps S1001 to S1003:

[0173] Step S1001, identifying the user's behavior status based on the user's individual data;

[0174] Step S1002, obtaining a target working mode corresponding to the user's behavior state; the target working mode includes 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 to meet the blood supply demand of the user in the current behavior state;

[0175] Step S1003, performing parameter prediction processing on the user individual data through the individualized parameter configuration model corresponding to the target working mode to obtain the target device parameters; the individualized parameter configuration model is pre-trained based on historical user individual data.

[0176] Through the above steps S1001 to S1003, the user's behavioral state can be identified based on the user's individual data, and then, an individualized parameter configuration model can be selected in combination with the user's behavioral state to perform parameter prediction processing on the user's individual data to obtain target device parameters, thereby assisting the blood supply drive device to adapt to the individual situation of the user in the current behavioral state.

[0177] Of course, in actual applications, it can be a prediction of real-time behavior status. In this case, the target device parameters finally obtained are device parameter configurations that help the blood supply drive device adapt to the user's current situation, and can be used in device configuration, update, adjustment and other scenarios; it can also be a prediction of historical behavior status. In this case, the target device parameters finally obtained are device parameter configurations that help the blood supply drive device adapt to the user's historical situation, and can be used in user individualized analysis, model training, auxiliary diagnosis and treatment and other scenarios.

[0178] In step S1001, the user's behavior state is identified based on the user's individual data. In the embodiment of the present application, the user's behavior state includes multiple types. Further optionally, the user's behavior state can be customized individually according to the user's age group, daily activity pattern, and daily activity needs. Alternatively, it can also be pre-configured for different groups of people by professional medical institutions. For example, according to the type of illness, it can be divided into: heart disease group, hypertension group, and diabetes group. Taking heart disease as an example, according to the age of the patient, it can be divided into: children's heart disease group, young and middle-aged heart disease group, and elderly heart disease group. Taking heart disease as an example, based on the degree of illness, it can be divided into: mild group, moderate group, and severe group. Taking user a as an example, user a's behavior state L can be set to the following: light sleep, deep sleep, stillness (when awake), walking, jogging, holding and lifting, daily activities (including office and housework).

[0179] In the embodiment of the present application, each behavior state is provided with a corresponding device parameter level (Threshold). As an optional embodiment, in order to adapt to the individual conditions of users in different physical states, multiple device parameter levels are provided. It is understandable that the device parameter level is a plurality of speed intervals of the target device. The speeds may overlap between different device parameter levels. In different device parameter levels, the speed adjustment trend is determined by the actual application scenario corresponding to this interval and the changes in the user's physical state in this scenario.

[0180] In the embodiment of the present application, each device parameter gear is respectively configured with a corresponding driving component operating parameter. The driving component operating parameters corresponding to each device parameter gear include, but are not limited to: at least one of the maximum speed, minimum speed, default speed during operation of the heart pump, the maximum heartbeat compensation speed, minimum heartbeat compensation speed, and default heartbeat compensation speed of the implantable arterial pump.

[0181] Taking the heart pump as an example, N equipment parameter gears are set, where N is an integer greater than 1. Assume that N is 50. In each equipment parameter gear, the maximum speed corresponding to the equipment parameter gear is set (denoted as V Max ), minimum speed (denoted as V Min ), the default speed during operation (denoted as V Nomal). When the target device is in a certain equipment parameter gear, its speed cannot exceed the corresponding maximum speed or minimum speed, and is usually executed at the default speed during operation.

[0182] It should be noted that the default speed during operation can be an interval value between the maximum speed and the minimum speed, which can be multiple or one. The default speed during operation can be statically set, for example, set to a static value, which can be set according to the user's own activity pattern. Further optionally, the static value can be the difference between the maximum speed and the user's current blood pressure circulation parameters. In another embodiment, the default speed during operation can also be dynamically adjusted according to user experience and / or monitoring indicators. Further optionally, the physiological indicator values ​​detected by equipment such as sports watches and heart monitoring devices are used to evaluate whether the user's current physical state is at the optimal value given by the doctor. If so, the current default speed during operation is maintained; if not, the default speed during operation is adjusted until the user is monitored to be in the best physical state.

[0183] The following uses different types of physiological indicator data as examples to introduce specific implementation methods of obtaining target device parameters that match the user's physical state based on the user's individual data in the above step S902.

[0184] In an optional implementation, it is assumed that the physiological indicator data at least includes acceleration data and / or gyroscope data. Based on the above assumption, the present application provides an optional embodiment of step S1001, see Fig.11 As shown, it can be implemented as the following steps:

[0185] Step S1101, extracting physiological index data from user individual data;

[0186] Step S1102, determining the amount of exercise of the user in a specified time period based on the physiological indicator data;

[0187] Step S1103, determining the behavior state of the user within the specified time period according to the amount of exercise of the user within the specified time period.

[0188] Through the above steps S1101 to S1103, the user's behavior state in each time period can be determined based on the physiological indicator data, so as to assist in selecting the working mode adapted by the target device in combination with the user's individual situation reflected by the behavior state (such as the blood perfusion requirements of each organ, etc.), and provide an individualized data analysis basis for the subsequent acquisition process of the target device parameters. In this application, for the convenience of description, the working mode adapted by the target device is also referred to as the target working mode.

[0189] In step S1101, physiological index data is extracted from the user's individual data. Optionally, the physiological index data includes: acceleration data and / or gyroscope data. In the embodiment of the present application, since the acceleration data and / or gyroscope data can reflect the user's behavior state characteristics, such as the amount of exercise, from the perspectives of the user's posture, position, etc. For example, by adopting a pre-established behavior law fitting function, a fitting array is obtained from the above data, and the amount of exercise of the user is calculated by the fitting array. For another example, by collecting the acceleration data and gyroscope data of the user in each time period within 24 hours, the user's movement distance can be determined, thereby inferring the user's exercise amount. Therefore, by analyzing the acceleration data and / or gyroscope data of the user in different time periods, the user's exercise amount in different time periods can be analyzed, which is convenient for judging the user's behavior state in different time periods. In the embodiment of the present application, for the convenience of description, the time period to be processed is referred to as a specified time period.

[0190] In step S1102, the amount of exercise of the user in the specified time period is determined based on the physiological indicator data. Specifically, further optionally, the acceleration data and / or gyroscope data in each specified time period are obtained from the physiological indicator data; the acceleration data and / or gyroscope data are fitted using a behavior law fitting function to obtain a third behavior law fitting array; and the definite integral of the third behavior law fitting array in each specified time period is used as the amount of exercise of the user in each specified time period.

[0191] In step S1103, the behavior state of the user in the specified time period is determined according to the amount of exercise of the user in the specified time period. Specifically, in an optional implementation, the behavior state of the user in each specified time period is obtained according to the amount of exercise of the user in each specified time period and a preset mapping relationship between the amount of exercise and the behavior state.

[0192] For example, suppose the definite integral result P STILL , P NOISE , P HOLD As the motion amount P in the current time period m. Here, the method for obtaining the motion amount P refers to the description related to the third fitting array and the motion amount P in the above example, which will not be expanded here.

[0193] Based on this, the current user's behavior state is analyzed from the amount of exercise P in time period m. Specifically, a mapping relationship Pmap between the numerical range of the amount of exercise P and the behavior state L is established, so that the behavior state L corresponding to the amount of exercise P can be obtained through the n-to-1 mapping relationship Pmap.

[0194] It is worth noting that in actual applications, in addition to using the amount of exercise to determine the behavior state, parameters such as exercise intensity, force mark, muscle force intensity, etc. can also be used to determine the behavior state. The specific judgment principle is similar to the above, and will not be elaborated here.

[0195] After identifying the user's behavior status based on the user's individual data, it is necessary to obtain the target working mode corresponding to the user's behavior status. The following introduces several processing solutions for the target working mode in combination with specific scenarios.

[0196] As an optional implementation, the working modes corresponding to the user's behavior state include, but are not limited to: exercise mode, blood oxygen balance mode, sleep mode, and constant speed mode. It can be explained that the switching between working modes can be done manually, or can be automatically realized through the detection of physiological indicator data and the identification of behavior state, or can be pre-set according to historical activity rules.

[0197] Among them, the exercise mode can monitor the exercise state, exercise amount and force state in real time, so that the pump speed can respond quickly. The blood oxygen balance mode can dynamically adjust the pump speed within a certain range with the blood oxygen content. In the sleep mode, the pump speed can be set to be reduced within a period of time without reducing the blood oxygen saturation, so as to quickly enter sleep. This mode can be set automatically when the preset conditions are met, or it can be switched manually. In the fixed speed mode, the pump can run at a constant speed within a certain interval and time. Compared with the traditional fixed speed mode, the fixed speed mode involved in this application can be set according to the user's individualized data. For example, the constant speed in the fixed speed mode is set according to the user's age, gender, medical records and historical physiological indicators. Of course, in actual applications, it is also possible to establish constant speeds associated with different application scenarios, so that the constant speed required for the operation of the corresponding target device can be determined by identifying the current application scenario.

[0198] In an optional embodiment, it is assumed that the target working mode is a sports mode. Based on this assumption, the above step S1002 can be implemented as: setting the target working mode of the specified time period marked with the force mark to the sports mode.

[0199] Continuing on the above assumption, in the above step S1003, the user individual data is subjected to parameter prediction processing through the individualized parameter configuration model corresponding to the target working mode to obtain the target device parameters, which can be implemented as follows:

[0200] From the multiple models obtained in advance, call the motion mode parameter configuration model corresponding to the motion mode; input the physiological indicator data into the motion mode parameter configuration model under the current behavior state to obtain the predicted value of the driving component operating parameter in the motion mode; smooth the predicted value to obtain the adjusted value of the driving component operating parameter per unit time in the motion mode.

[0201] In an embodiment of the present application, the motion mode parameter configuration model is obtained by the user's historical exercise volume and historical exercise intensity training in various behavioral states. Further optionally, the predicted value of the driving component operating parameter in the motion mode includes at least one of the following parameter values: the target speed value of the heart pump, the target heartbeat compensation speed value of the implantable arterial pump. Accordingly, the unit adjustment value includes at least one of the following parameter values: the speed adjustment value of the heart pump, the heartbeat compensation speed adjustment value of the implantable arterial pump.

[0202] It is understandable that, further optionally, physiological index data such as heart rate, blood oxygen content, and blood oxygen saturation can also be used as feedback parameters to adjust the individualized parameter configuration model. Thus, the predicted value output by the individualized parameter configuration model can assist the blood supply drive device to become more and more adapted to the user's blood supply needs. In practical applications, in addition to the motion mode parameter configuration model, the configuration parameters in the motion mode parameter configuration model can also be optimized according to the load characteristics of the user's blood supply drive system in the motion mode.

[0203] In practical applications, similar to the above example, in the exercise mode, the amount of exercise and the degree of muscle force will affect the blood supply. Therefore, the final operating parameters of the driving components can be regulated by these two parameters. The exercise mode parameter configuration model corresponding to the exercise mode (similar to the third exercise mode parameter configuration model above) can be expressed as:

[0204] V max >V tar >V min

[0205] Among them, V max The maximum device parameter corresponding to the behavior state L, V min The minimum device parameter corresponding to the behavior state L, V tar is the predicted value of the target device parameter of the target device, P max is the maximum amount of exercise in history, S max is the maximum exercise intensity in history, w2 and w3 are custom weights. Specifically, V max and V min Substitute the behavior state L into DicVG(L) to obtain V tar is the speed of the driving components when the target device reaches the physiological and psychological health indicators, Pmax is the maximum amount of motion during the data collection phase, S max is the maximum exercise intensity during the data collection phase, and w2 and w3 are the weights obtained by the collected human-machine running-in data through automated mathematical modeling. w2 and w3 can be obtained by calculating the data collected by the host computer.

[0206] Taking the sports mode as an example, the control module obtains sensor data (i.e., physiological indicator data) through wireless communication methods such as Wi-Fi, Bluetooth, ZigBee, etc., and obtains DicV(KV)=V and DicT(KV)=T after analysis. After processing using the filtering and denoising method in the previous example, the sensor data is input into the sports mode parameter configuration model corresponding to the sports mode for parameter prediction.

[0207] Next, the model is configured by the exercise mode parameters corresponding to the exercise mode to obtain the target rate V of the heart pump or arterial pump in the exercise mode. tar (i.e. predicted value). The target rate V is calculated by the following formula tar Smoothing is performed to obtain the rate adjustment value V of the heart pump or arterial pump per unit time. tmp Assume that the adjustment period is T, and assume that the current rate V cur To the target rate V tar The time is Goal, based on this, the number of rate adjustments each time is Goal / T. The specific formula is as follows:

[0208]

[0209] The above-mentioned motion mode parameter configuration model can be used to configure the operating parameters of the driving components under the motion mode for the user. In this way, through the motion mode and the motion mode parameter configuration model that match the user's current behavior state, the operating parameters of the driving components that better meet the user's current blood supply needs can be predicted.

[0210] Generally speaking, the resting heart rate is the heart rate when you are resting or stationary. The resting heart rate is relatively slow, while the recovery heart rate when switching from an exercise state to another state, or the maximum heart rate in an exercise state, is relatively fast. In order to improve user comfort, for the operating parameters of the drive components of the target device, the heart rate of a certain state cannot always be used as a standard to adjust the blood oxygen saturation. This may cause the user's blood oxygen saturation to remain at 99% or even 100%, affecting the user's physical and mental health.

[0211] Therefore, in various test activities, the operating parameters of the target device's drive components (such as the target speed value of the heart pump and the target heart rate compensation speed value of the implantable arterial pump) can be dynamically adjusted to ensure that the blood oxygen content meets the requirements of various organs in the human body. This mode is called the blood oxygen balance mode.

[0212] As another optional implementation, in the above step S1002, an optional implementation scheme for obtaining the target working mode corresponding to the user behavior state is specifically implemented as the following steps: setting the target working mode for a specified time period that is not marked with a force mark and is not in a sleep state to a blood oxygen balance mode.

[0213] In the blood oxygen balance mode, in the above step S1003, the blood oxygen balance mode parameter configuration model corresponding to the blood oxygen balance mode is called from the multiple models obtained by pre-training. Among them, the blood oxygen balance mode parameter configuration model is trained by the reference blood oxygen parameters required to be achieved under various behavioral states. There is a linear correlation between the reference blood oxygen parameters and the driving component operating parameter values. Further optionally, the reference blood oxygen parameters are obtained based on the historical blood oxygen parameters under various behavioral states and the somatosensory information fed back by the user. The reference blood oxygen parameters include but are not limited to: blood oxygen content, blood oxygen saturation. Furthermore, the driving component operating parameters of the target device can be further adjusted in combination with the feedback and evaluation of each test activity by users and professional medical institutions.

[0214] Then, in step S1003, the blood oxygen parameters in the physiological index data are input into the blood oxygen balance mode parameter configuration model under the current behavior state to obtain the predicted value of the driving component operating parameter in the blood oxygen balance mode. Finally, the predicted value is smoothed to obtain the unit adjustment value of the driving component operating parameter in the blood oxygen balance mode.

[0215] It is worth noting that the method for obtaining the operating parameters of each driving component in the blood oxygen balance mode is similar to the method for obtaining the operating parameters of the driving components in the previous sports mode, and the similarities will not be elaborated on.

[0216] 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 collection phase, by observing the real-time blood oxygen and user activity performance, the real-time values ​​of various behavior states and driving component operating parameters are manually adjusted to reach the blood oxygen saturation threshold Os. Thus, the threshold range of the driving component operating parameters corresponding to various behavior states L is recorded [V min , V max ] and the corresponding adjustment time Goal. The adjustment time Goal is the time required for the current drive component operating parameters to reach the target drive component operating parameter attributes. The above corresponding relationship is recorded as: DicVG(L)=[V min , V max , Goal], the specific relationship can be expressed as Fig.12 The effect shown.

[0217] From the above, we can know that the blood oxygen saturation is linearly related to the operating parameters of the driving components, so the following function can be obtained by polynomial fitting:

[0218] V max >V tar >V min

[0219] Among them, V max The maximum device parameter corresponding to the behavior state L, V min The minimum device parameter corresponding to the behavior state L, V tar is the predicted value of the target device parameter of the target device, Os is the blood oxygen saturation, w1 to w n is a custom weight. Specifically, V max and V min Substitute the behavior state L into DicVG(L) to obtain V tar is the speed of the driving components when the target device reaches the physiological and psychological health indicators, Os is the blood oxygen saturation, w1 to w n It is the weight obtained through automated mathematical modeling using the human-machine running-in data collected by the host computer.

[0220] In the above-mentioned blood oxygen balance mode parameter configuration model, the operating parameters of the driving components of the target device can be dynamically adjusted according to parameters such as blood oxygen content and blood oxygen saturation, thereby assisting the target device to enable each organ of the user to reach the target blood oxygen saturation.

[0221] As another optional implementation, in the above step S1002, obtaining the target working mode corresponding to the user behavior state can be implemented as: setting the target working mode for a specified time period in the sleep state to the sleep mode.

[0222] Based on this, in the above step S1003, the sleep mode parameter configuration model corresponding to the sleep mode is called from the multiple models obtained by pre-training. Then, the blood oxygen parameters in the physiological indicator data are input into the sleep mode parameter configuration model to obtain the predicted values ​​of the driving component operating parameters in the sleep mode. The sleep mode parameter configuration model is used to reduce the values ​​of the driving component parameters while maintaining the current blood oxygen saturation. For example, in the sleep mode, the driving component operating parameters can be lowered to the minimum value specified by the device parameter gear, or lowered to the corresponding value when the user feedbacks that the body feels comfortable, and the decrease value can also be dynamically adjusted according to the monitoring of physiological indicators in the sleep state. Finally, the predicted value is smoothed to obtain the unit adjustment value of the driving component operating parameters in the sleep mode.

[0223] It is worth noting that the method for obtaining the operating parameters of each driving component in the sleep mode is similar to the method for obtaining the operating parameters of the driving components in the previous exercise mode and blood oxygen balance mode, and the similarities will not be elaborated on.

[0224] In an optional embodiment, the warning conditions corresponding to the user can also be determined based on the diagnosis and treatment information. If the physiological indicator data meets the warning conditions, warning information corresponding to the physiological indicator data is generated to assist relevant personnel (such as medical staff or guardians) to check the user's health in a timely manner. For example, assuming that the warning conditions include a minimum value of blood oxygen saturation, if the blood oxygen saturation is lower than the minimum value, a low blood oxygen warning is generated and sent to a pre-bound medical institution or relevant personnel.

[0225] Step S903: configuring the target device based on the target device parameters.

[0226] Through the above steps, the target device parameters can be configured into the target device, thereby realizing the personalized parameter configuration process of the target device, improving the adaptability of the target device to the individual situation of the user, and improving the user experience.

[0227] Further, optionally, before S903, it is also necessary to perform usability determination on the target device parameters to determine whether the target device parameters can be applied to the individual situation of the user. The usability determination includes but is not limited to the following:

[0228] The first method of judgment: judging whether the data collected by multiple sensors exceeds the threshold value, so as to eliminate abnormal measurement values, avoid potential risks and interfere with the user's life. For example, detecting whether there is an abnormality in the sensor. For example, detecting whether there is an acceleration, gyroscope or muscle electrical sensor value exceeding the threshold value to judge the abnormal situation.

[0229] The second way of judging is to judge whether the monitored object is wearing the monitoring device. For example, judging whether the monitored object is wearing the monitoring device based on the blood oxygen and acceleration sensor data.

[0230] The third way of judging: judging whether the monitored object is wearing it. Further, the display screen of the control module and the monitoring switch are used to associate the device status to judge whether the wearer is the person himself. Alternatively, a manual connection is made to indicate that the wearer is the person himself.

[0231] After completing one or more of the above determinations, the target device parameters may be configured into the target device to control the driving components of the target device to meet the blood supply demand.

[0232] As an optional embodiment, according to the usage status of the monitoring device and the working condition of the sensor, if an abnormal situation occurs, such as an abnormality in the control module or an abnormality in the detection of physiological indicator data, it automatically enters the adjustment working state or restores the default constant speed state.

[0233] As an optional embodiment, after step S901, after obtaining the user individual data corresponding to the target device, the user individual data can also be used to train the user's individual parameter configuration model; based on the user individual data, the device parameter level matching the user behavior state is set; the user individual data, the trained individual parameter configuration model, and the updated device parameter level are uploaded to the historical adaptation database for the audit end to audit the individual parameter configuration model and / or device parameter level in the historical adaptation database; if the individual parameter configuration model and / or device parameter level passes the audit, the individual parameter configuration model and / or device parameter level are sent from the historical adaptation database to the target device.

[0234] Further optionally, after the individualized parameter configuration model and / or the device parameter gear are audited, individualized audit information for the individualized parameter configuration model and / or the device parameter gear is generated. Then, the individualized parameter configuration model, the device parameter gear, the target device parameters and the corresponding individualized audit information are stored in the historical adaptation database. This helps to provide a data basis for subsequent audit evaluation and further improve the accuracy of the target device parameters.

[0235] In an optional embodiment, a method for establishing a historical adaptation database is also provided. Specifically, a medical data sample is obtained. In the embodiment of the present application, the medical data sample includes the historical device used by the user, the historical device parameters, and the historical user individual data corresponding to the historical device parameters. The historical device parameters include multiple device parameter gears, and the driving component operating parameters corresponding to each device parameter gear. The types of the historical device include heart pumps and / or implantable arterial pumps. Then, privacy data is extracted from the historical user individual data. In the embodiment of the present application, the privacy data includes at least one of the user's heart rate, blood oxygen saturation, muscle electrical data, physiological gender, age, weight, height, basic medical history, heart index, blood circulation parameters, case records, and treatment plans. Then, the privacy data is desensitized to obtain the historical user individual data after desensitization. Finally, the historical device, the historical device parameters, and the historical user individual data corresponding to the historical device parameters are stored in the historical adaptation database, and the corresponding relationship between the historical device and the device parameter gear used, and the corresponding relationship between the historical device and the historical user individual data are established.

[0236] Through the above steps, a historical adaptation database can be constructed, which makes it easier for professional medical institutions to query, retrieve and review the historical data needed for reference when adjusting equipment parameters, provide an evaluation basis for the evaluation of equipment parameters, assist the personalized parameter configuration process of the target device, and improve the accuracy of the target device parameters. At the same time, it also reduces the time cost consumed by historical data retrieval during equipment parameter evaluation and improves the configuration efficiency of personalized device parameters.

[0237] In the embodiment of the present application, the body state used to reflect the operation of the blood supply drive system is analyzed based on the user's individual data, and the target device parameters matching the user's individual situation are customized for the blood supply drive device in combination with the user's physical state, so that the target device can be more adaptable to the user's own needs for the blood supply drive system under the automatic configuration of the target device parameters. At the same time, by identifying the user's individual situation to realize the customized parameter configuration of the blood supply drive device, the customization cost of the blood supply drive device is greatly reduced, which is conducive to the promotion and application of the blood supply drive device.

[0238] At present, the costs of customized research and development, production, and use of medical products such as medical devices, consumables, and drugs are all high. In related technologies, users are usually equipped with related equipment and are actively adapted to the equipment through recovery training. As a result, existing heart pumps, arterial pumps, and other equipment lack user adaptability and have a poor user experience.

[0239] In the above or below embodiments, the following method is also proposed to address the situation where the customization cost is high and the blood supply drive device is not adaptable enough to individuals.

[0240] Further optionally, the user's individual data can also be transmitted to the host computer, and the host computer completes the data collection of the user's individual situation and the training of the individualized parameter configuration model. Specifically, as an optional embodiment, after step S901, the physiological indicator data can also be transmitted from the sensor to the host computer. Among them, the host computer is used to train the individualized parameter configuration model, and a communication connection is established between the sensor and the host computer. Then, in the host computer, the physiological indicator data is filtered; the sensor identification and device identification of the sensor are used as indexes, and the physiological indicator data after filtering is stored in the corresponding mapping structure according to the acquisition time. Among them, the sensor identification includes the sensor number, and the device identification includes the device number of the built-in sensor. Then, according to the sensor acquisition time, the behavior state matching the physiological indicator data is added to the mapping structure to construct the information matrix corresponding to each time period; the information matrix is ​​persistently stored in the hard disk.

[0241] In this way, the upper computer processes the user's individual data to complete the targeted analysis of the user's individual situation. Based on the analysis of the user's individual situation, the user's individual data is further used to construct an individual parameter configuration model adapted to each behavior state in the user's individual situation by mathematical modeling, and the automatic training process of the prediction model of the drive component parameters in the blood supply drive device is realized, which is helpful to provide professional medical institutions or related personnel with a parameter configuration model that is more adapted to different user individual situations and reduces the difficulty of parameter setting.

[0242] As an optional embodiment, the control module in the blood supply drive device also has the functions of internal / external message communication, behavior state recognition, and driving component operation parameter issuance. The control module is mainly used to control the target device, but in the training stage (such as scientific research, engineering development, testing, and feedback), the sensor data can also be transferred to the data acquisition system at the host computer to process the sensor data and other related data, and realize customized analysis of the user's individual situation through the host computer, as well as the engineering development process of the parameter configuration model. The specific process is as follows:

[0243] a) Manually switch the working mode of the control module to the R&D mode, and set the network communication address of the host computer. The specific setting method is as follows:

[0244] Connect the control module interface by wire, send a special command to set the current working state to R&D mode, and set the network communication address of the host computer. After the setting is completed and the connection command is sent, the control module will connect to the network address interface of the host computer, and the connection will still be made after the next control module restart (the restart of the control module will not affect the effect of the drive and energy system on the pump).

[0245] b) Setting up a data acquisition program in another computer system (a computing device other than the monitoring terminal and the control module) as a host computer to receive the sensor data from the control module.

[0246] Write a data acquisition program in the host computer to receive the sensor data transmitted from the target device control module. The host computer receives the sensor information string or HEX array through the network connection established with the control module, and obtains DicV(KV)=V and DickT(KV)=T after parsing.

[0247] c) Preprocess the sensor data, including filtering and denoising.

[0248] Further optionally, a Butterworth filter is used to filter the muscle electrical data. For example, when preprocessing the muscle contraction electrical signal (i.e., one of the muscle electrical data mentioned above), a Butterworth filter is used to filter the muscle contraction electrical signal to improve data quality and reduce noise. The transfer function H(z) of the Butterworth filter is as follows:

[0249] H(z)=(b0+b1z -1 +b2z -2 +…+b m z -m ) / (a0+a1z -1 +a2z -2 +…+a m z -m )

[0250] Where H(z) represents the filter transfer function, z is the unit delay operation, b0 to b m and a0 to a m are the coefficients of the filter.

[0251] Further optionally, when processing the output value of the acceleration sensor (i.e., the acceleration data mentioned above), the x-axis, y-axis, and z-axis data are combined and divided by 3 to perform a dimensionality reduction operation to obtain a value a i , the process is as follows:

[0252] a i =(ax i +ay i +az i ) / 3

[0253] When processing the output value of the accelerometer gyroscope sensor, the x-axis, y-axis and z-axis data are combined and divided by 3 for dimensionality reduction, and then divided by λ to obtain the value g i , the process is as follows:

[0254] g i =((gx i +gy i +gz i ) / 3) / λ

[0255] Among them, λ is an empirical parameter, which is mainly used to convert g into a value less than 1 to facilitate calculation.

[0256] d) Semi-automatically record the wearer's behavioral data for a full day.

[0257] For example, the built-in sleep monitoring function of the smart bracelet can automatically identify the wearer's sleep start and end time points. L0 , 1, t L0, n, and mark the sensor indicators during this period as sleep state L0.

[0258] For example, fixed-weight training consumables (such as fixed-weight dumbbells) are used to measure the force applied to the muscles by the wearer during training, and the muscle electrical information P is collected using an electromyographic signal acquisition device. By recording the start and end time t p , 1, t p ,n, the muscle usage can be calculated for training effect evaluation and further analysis.

[0259] For example, different activity states can be identified through sensor data collected by motion sensors (such as accelerometers, gyroscopes, etc.), such as sitting L1, lying L2, walking L3, running L4, jumping L5, etc. By quantitatively recording the time t of each activity li , 1, t li , n, can understand the wearer's daily activity pattern and exercise volume, behavior set L = {L0, Ll, L2, ..., Ln}

[0260] e) Storing sensor data.

[0261] The host computer receives the sensor data through the network interface and stores it. At the same time, the data of DicV(KV)=V and DicT(KV)=T are recorded. Through the above steps, the behavior state L (sleeping, running, jumping, lying, etc.) corresponding to the sensor time is obtained, which can be recorded as DickT(T)=L, thereby realizing the complete association of sensor value, type, time and behavior.

[0262] By associating T and V through KV and L through T, an array [T, KV, V, L] can be formed. Multiple groups of sensors send at the same time. The format can be [T, KV0, V0, KV1, V1, ..., KVn, Vn, L]. Time T is set in the first position and the current behavior state is set in the last position. Each time T forms a row of data, and each row stores the state of a time. The storage format of m time ends is as follows:

[0263] M=[T0,KV0,V0,KV1,V1,...,KVn,Vn,L

[0264] T1,KV0,V0,KV1,V1,...,KVn,Vn,L ...

[0266] Tm, KV0, V0, KV1, V1, ..., KVn, Vn, L]

[0267] By persistently storing sensor data on a hard disk, storage of different terminals, different sensors, different behaviors, and different times can be achieved.

[0268] Through the above optimization steps, the sensor data of the control module of the target device can be collected, preprocessed and stored in the host computer to support analytical engineering development work in the scientific research, engineering development, testing, usage feedback and other stages.

[0269] In this embodiment, the user's individual data (including sensor data) is processed in the host computer through the research and development mode to complete the targeted analysis of the user's individual situation. Based on the analysis of the user's individual situation, the user's individual data is further used to construct an individual parameter configuration model adapted to each behavior state in the user's individual situation by mathematical modeling, thereby realizing the automated training process of the prediction model of the drive component parameters in the blood supply drive device, greatly reducing the individual customization cost of the model, and helping to provide professional medical institutions or related personnel with a parameter configuration model that is more adapted to different user individual situations, reducing the difficulty of parameter setting.

[0270] After introducing the method of the exemplary embodiment of the present application, next, refer to Fig.13 A model building device according to an exemplary embodiment of the present application is described, and the device comprises:

[0271] The acquisition unit 1301 is used to acquire user individual data corresponding to the target device; the target device is a blood supply drive device used by the user; the user individual data includes at least one of the user's own physiological index data, diagnosis and treatment information, and target device attributes;

[0272] A fitting unit 1302 is used to fit the muscle electrical data in each specified time period in the physiological index data using a behavior law fitting function to obtain a first behavior law fitting array;

[0273] The definite integral unit 1303 is used to fit the definite integral of the array in each specified time period according to the first behavior rule as the exercise intensity of the user in each specified time period;

[0274] The construction unit 1304 is used to construct an individualized parameter configuration model based on the exercise intensity; wherein the individualized parameter configuration model is used to predict the target device parameters that match the user's physical state; the target device parameters include the driving component operating parameters of the target device that match the user's physical state.

[0275] As an optional implementation, the fitting unit 1302 fits the muscle electrical data in each specified time period in the physiological index data using a behavioral law fitting function to obtain a first behavioral law fitting array, and is further used to:

[0276] Based on the first behavior rule fitting array, the muscle movement conditions of the user in each specified time period are marked, and the muscle force intensity in the marked specified time period is obtained.

[0277] The muscle exercise performed by the user reaches a set intensity within the marked specified time period.

[0278] As an optional implementation, the fitting unit 1302 marks the muscle movement of the user in each specified time period based on the first behavior rule fitting array, and obtains the muscle force intensity in the marked specified time period, specifically for:

[0279] Performing Fourier transformation on the regularity fitting array of the first behavior, and taking the square of the absolute value of the Fourier transformation result as the frequency domain characteristic energy density in each specified time period;

[0280] The frequency domain characteristic energy density in each specified time period is fitted using a behavior law fitting function to obtain a second behavior law fitting array;

[0281] According to the second behavior rule, the definite integral in each specified time period in the array is fitted, and the specified time period whose definite integral is greater than a preset threshold is marked with a force mark;

[0282] The corresponding definite integral in the regular fitting array of the second behavior is used as the muscle strength of the user in the marked specified time period.

[0283] As an optional implementation, when the construction unit 1304 constructs the individualized parameter configuration model based on the exercise intensity, it is specifically used to:

[0284] Based on the exercise intensity in each designated time period and the muscle strength in the marked designated time period, a second exercise mode parameter configuration model is constructed;

[0285] The second motion mode parameter configuration model is used to predict the target device parameters; the second motion mode parameter configuration model is expressed as the following formula:

[0286] V max >V tar >V min

[0287] Among them, V max The maximum device parameter under the user's current behavior state, V min The minimum device parameters under the user's current behavior state, V tar is the target device parameter, S is the exercise intensity in the current specified time period, and S maxis the maximum exercise intensity in history, w1 is the first custom weight, Spd is the muscle strength in the current specified time period, and Spd max is the historical maximum muscle force intensity, and w2 is the second custom weight.

[0288] As an optional implementation manner, the fitting unit 1302 is further configured to:

[0289] After the acquisition unit 1301 acquires the user individual data corresponding to the target device, the acceleration data and / or gyroscope data in each specified time period in the physiological indicator data are fitted using a behavior law fitting function to obtain a third behavior law fitting array;

[0290] The definite integral of the array in each specified time period is fitted according to the third behavior rule as the user's exercise amount in each specified time period.

[0291] As an optional implementation, when the construction unit 1304 constructs the individualized parameter configuration model based on the exercise intensity, it is specifically used to:

[0292] Based on the exercise intensity and exercise volume in each specified time period, a third exercise mode parameter configuration model is constructed;

[0293] The third motion mode parameter configuration model is used to predict the target device parameters; the third motion mode parameter configuration model is expressed as the following formula:

[0294] V max >V tar >V min

[0295] Among them, V max The maximum device parameter under the user's current behavior state, V min The minimum device parameters under the user's current behavior state, V tar is the target device parameter, S is the exercise intensity in the current specified time period, and S max is the maximum exercise intensity in history, w1 is the first custom weight, P is the amount of exercise in the current specified time period, P max is the maximum amount of exercise in history, and w2 is the third custom weight.

[0296] As an optional implementation, when the construction unit 1304 constructs the individualized parameter configuration model based on the exercise intensity, it is specifically used to:

[0297] Constructing a first exercise mode parameter configuration model based on the exercise intensity in each specified time period, the historical maximum exercise intensity, and the first custom weight;

[0298] The first motion mode parameter configuration model is used to predict the target device parameters.

[0299] As an optional implementation manner, the first motion mode parameter configuration model is expressed as the following formula:

[0300] V max >V tar >V min

[0301] Among them, V max The maximum device parameter under the user's current behavior state, V min The minimum device parameters under the user's current behavior state, V tar is the target device parameter, S is the exercise intensity in the current specified time period, and S max is the historical maximum exercise intensity, and w1 is the first custom weight.

[0302] As an optional implementation, it further includes a pre-processing unit, which is used to:

[0303] After the acquisition unit 1301 acquires the user individual data corresponding to the target device, the physiological index data is transmitted to the host computer; the physiological index data includes muscle electrical data: the host computer is used to execute the training process of the individualized parameter configuration model;

[0304] The muscle electrical data is filtered using a Butterworth filter; the transfer function H(z) of the Butterworth filter is as follows:

[0305] H(z)=(b0+b1z -1 +b2z -2 +…+b m z -m ) / (a0+a1z -1 +a2z -2 +…+a m z -m )

[0306] Where z is the unit delay, b0 to b m and a0 to a m are the coefficients of the filter.

[0307] As an optional implementation, the first behavior law fitting array includes: fitting arrays in a static state, an interference noise state, and a load state in each specified time period;

[0308] The exercise intensity of the user in each specified time period includes: the exercise intensity of the user in a static state, an interfering noise state, and a weight-bearing state in each specified time period.

[0309] As an optional implementation manner, the preprocessing unit is further used for:

[0310] After the acquisition unit 1301 acquires the user individual data corresponding to the target device, the physiological index data is transmitted from the sensor for collecting the data to the host computer; the host computer is used to execute the training process of the individualized parameter configuration model; a communication connection is established between the sensor and the host computer;

[0311] Performing filtering processing on the physiological indicator data;

[0312] Using the sensor identification and device identification of the sensor as indexes, the filtered physiological index data is stored in a corresponding mapping structure according to the sensor acquisition time; the sensor identification includes the sensor number; the device identification includes the device number of the built-in sensor;

[0313] Adding the behavior state matching the physiological indicator data to the mapping structure according to the sensor acquisition time to construct an information matrix corresponding to each time period;

[0314] The information matrix is ​​persistently stored in the hard disk of the host computer.

[0315] In an embodiment of the present application, through a model building device, the muscle electrical data in the physiological indicator data is fitted into a behavioral law array through a behavioral law fitting function to obtain the user's exercise intensity in each time period, and then the user's exercise intensity change law is analyzed in combination with the exercise intensity in each time period, thereby constructing an individualized parameter configuration model that meets the user's individual situation, so that the blood supply drive device can be more adapted to the user's physical condition under the auxiliary configuration of the individualized parameter configuration model, thereby reducing the customization cost of the blood supply drive device, and facilitating the promotion and application of the blood supply drive device.

[0316] After introducing the method and apparatus of the exemplary embodiment of the present application, next, reference is made to Fig.14 For a description of the computer-readable storage medium of the exemplary embodiment of the present application, please refer to Fig.14, the computer-readable storage medium shown is a CD or other form of storage medium, on which a computer program (i.e., program product 100) is stored. When the computer program is executed by the processor, it will implement the steps recorded in the above method implementation, for example, obtaining the user individual data corresponding to the target device; the target device is a blood supply drive device used by the user; the user individual data includes the user's physiological index data; the muscle electrical data in each specified time period in the physiological index data is fitted using a behavioral law fitting function to obtain a first behavioral law fitting array; the definite integral of the first behavioral law fitting array in each specified time period is used as the user's exercise intensity in each specified time period; an individualized parameter configuration model is constructed based on the exercise intensity; wherein the individualized parameter configuration model is used to predict the target device parameters that match the user's physical state; the target device parameters include the driving component operating parameters that match the target device under the user's physical state.

[0317] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

[0318] After introducing the method, medium and device of the exemplary embodiment of the present application, next, reference is made to Fig.15 A computing device for model building according to an exemplary embodiment of the present application.

[0319] Fig.15 A block diagram of an exemplary computing device 110 suitable for implementing embodiments of the present application is shown. The computing device 110 may be a computer system or a server. Fig.15 The computing device 110 shown is merely an example and should not limit the functionality and scope of use of the embodiments of the present application.

[0320] like Fig.15 As shown, the components of computing device 110 may include, but are not limited to: one or more processors or processing units 1101, system memory 1102, and a bus 1103 connecting different system components (including system memory 1102 and processing unit 1101).

[0321] The computing device 110 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computing device 110, including volatile and nonvolatile media, removable and non-removable media.

[0322] 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 / non-volatile computer system storage media. By way of example only, ROM 11023 may be used to read and write non-removable, non-volatile magnetic media ( Fig.15 is not shown in the Fig.15 As shown in the figure, a disk drive for reading and writing a removable non-volatile disk (such as a "floppy disk") and an optical disk drive for reading and writing a removable non-volatile optical disk (such as a CD-ROM, DVD-ROM or other optical medium) can be provided. In these cases, each drive can be connected to the bus 1103 through one or more data medium interfaces. The system memory 1102 may include at least one program product, which has a set (such as at least one) of program modules, which are configured to perform the functions of each embodiment of the present application.

[0323] 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 of which or some combination may include an implementation of a network environment. Program modules 11024 generally perform the functions and / or methods of the embodiments described herein.

[0324] The computing device 110 may also communicate with one or more external devices 1104 (e.g., a keyboard, a pointing device, a display, etc.). Such communication may be performed via an input / output (I / O) interface 1105. In addition, the computing device 110 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 1106. Fig.15 As shown, the network adapter 1106 communicates with other modules (such as the processing unit 1101, etc.) of the computing device 110 via the bus 1103. It should be understood that although Fig.15 Not shown, other hardware and / or software modules may be used in conjunction with computing device 110 .

[0325] The processing unit 1101 executes various functional applications and data processing by running the program stored in the system memory 1102, for example, obtaining the user individual data corresponding to the target device; the target device is the blood supply drive device used by the user; the user individual data includes the user's physiological index data; the muscle electrical data in each specified time period in the physiological index data is fitted using the behavior law fitting function to obtain the first behavior law fitting array; the definite integral of the first behavior law fitting array in each specified time period is used as the user's exercise intensity in each specified time period; an individualized parameter configuration model is constructed based on the exercise intensity; wherein the individualized parameter configuration model is used to predict the target device parameters that match the user's physical state; the target device parameters include the driving component operating parameters that match the target device in the user's physical state. The specific implementation method of each step is not repeated here. It should be noted that although several units / modules or sub-units / sub-modules of the model building device are mentioned in the above detailed description, this division is only exemplary and not mandatory. In fact, according to the embodiment of the present application, the features and functions of two or more units / modules described above can be concretized in one unit / module. On the contrary, the features and functions of one unit / module described above may be further divided into multiple units / modules to be embodied.

[0326] In the description of the present application, it should be noted that the terms "first", "second" and "third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0327] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0328] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0329] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple 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.

[0330] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can 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 is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.

[0331] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

[0332] In addition, although the operations of the method of the present application are described in a specific order in the drawings, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

Claims

1. A model building device, It is characterized in that include: An acquisition unit, used to acquire user individual data corresponding to a target device; The target device is a blood supply drive device used by a user; The user individual data includes at least one of the user's own physiological index data, diagnosis and treatment information, and target device attributes; A fitting unit, used for fitting the muscle electrical data in each specified time period in the physiological index data using a behavior law fitting function to obtain a first behavior law fitting array; a definite integral unit, used for fitting the definite integral of the array in each specified time period according to the first behavior rule as the exercise intensity of the user in each specified time period; A construction unit, configured to construct an individualized parameter configuration model based on the exercise intensity; wherein the individualized parameter configuration model is used to predict target device parameters that match the user's physical state; the target device parameters include operating parameters of driving components of the target device that match the user's physical state; Wherein, when the construction unit constructs the individualized parameter configuration model based on the exercise intensity, it is specifically used to: Based on the exercise intensity in each designated time period and the muscle strength in the marked designated time period, a second exercise mode parameter configuration model is constructed; The second motion mode parameter configuration model is used to predict the target device parameters; the second motion mode parameter configuration model is expressed as the following formula: Among them, V max The maximum device parameter under the user's current behavior state, V min The minimum device parameters under the user's current behavior state, V tar is the target device parameter, S is the exercise intensity in the current specified time period, and S max is the maximum exercise intensity in history, w 1 is the first custom weight, Spd is the muscle strength in the current specified time period, and Spd max The maximum muscle strength in history, w 2 is the second custom weight.

2. The device according to claim 1, It is characterized in that The fitting unit performs fitting processing on the muscle electrical data in each specified time period in the physiological index data using a behavior law fitting function to obtain a first behavior law fitting array, and is further used to: Based on the first behavior rule fitting array, the muscle movement conditions of the user in each specified time period are marked, and the muscle force intensity in the marked specified time period is obtained; The muscle exercise performed by the user reaches a set intensity within the marked specified time period.

3. The device according to claim 2, It is characterized in that The fitting unit is specifically used to mark the muscle movement of the user in each specified time period based on the first behavior law fitting array, and obtain the muscle force intensity in the marked specified time period: Performing Fourier transformation on the regularity fitting array of the first behavior, and taking the square of the absolute value of the Fourier transformation result as the frequency domain characteristic energy density in each specified time period; The frequency domain characteristic energy density in each specified time period is fitted using a behavior law fitting function to obtain a second behavior law fitting array; According to the second behavior rule, the definite integral in each specified time period in the array is fitted, and the specified time period whose definite integral is greater than a preset threshold is marked with a force mark; The corresponding definite integral in the regular fitting array of the second behavior is used as the muscle strength of the user in the marked specified time period.

4. The device according to claim 1, It is characterized in that The fitting unit is also used for: After the acquisition unit acquires the user individual data corresponding to the target device, the acceleration data and / or gyroscope data in each specified time period in the physiological indicator data are fitted using a behavior law fitting function to obtain a third behavior law fitting array; The definite integral of the array in each specified time period is fitted according to the third behavior rule as the user's exercise amount in each specified time period.

5. The device according to claim 4, It is characterized in that When the construction unit constructs the individualized parameter configuration model based on the exercise intensity, it is specifically used to: Based on the exercise intensity and exercise volume in each specified time period, a third exercise mode parameter configuration model is constructed; The third motion mode parameter configuration model is used to predict the target device parameters; the third motion mode parameter configuration model is expressed as the following formula: Among them, V max The maximum device parameter under the user's current behavior state, V min The minimum device parameters under the user's current behavior state, V tar is the target device parameter, S is the exercise intensity in the current specified time period, and S max is the maximum exercise intensity in history, w 1 is the first custom weight, P is the amount of exercise in the current specified time period, and P max is the largest amount of exercise in history, w 2 Custom weight for the third.

6. The device according to any one of claims 1 to 5, It is characterized in that Also included is a pre-processing unit for: After the acquisition unit acquires the user individual data corresponding to the target device, the physiological index data is transmitted to the host computer; the physiological index data includes muscle electrical data; the host computer is used to execute the training process of the individualized parameter configuration model; The muscle electrical data is filtered using a Butterworth filter; the transfer function H(z) of the Butterworth filter is as follows: 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 z is the unit delay, b 0 To b m and a 0 to a m are the coefficients of the filter.

7. The device according to any one of claims 1 to 5, It is characterized in that The first behavior law fitting array includes: fitting arrays in a static state, an interference noise state, and a load state in each specified time period; The exercise intensity of the user in each specified time period includes: the exercise intensity of the user in a static state, an interfering noise state, and a weight-bearing state in each specified time period.

8. The device according to any one of claims 1 to 5, It is characterized in that The preprocessing unit is also used to: After the acquisition unit acquires the user individual data corresponding to the target device, the physiological index data is transmitted from the sensor that collects the data to the host computer; the host computer is used to execute the training process of the individualized parameter configuration model; A communication connection is established between the sensor and the host computer; Performing filtering processing on the physiological indicator data; Using the sensor identification and device identification of the sensor as indexes, the filtered physiological index data is stored in a corresponding mapping structure according to the sensor acquisition time; the sensor identification includes the sensor number; the device identification includes the device number of the built-in sensor; Adding the behavior state matching the physiological indicator data to the mapping structure according to the sensor acquisition time to construct an information matrix corresponding to each time period; The information matrix is ​​persistently stored in the hard disk of the host computer.