Intelligent wearable device management system and method based on modular design

Abstract

The present invention discloses a smart wearable device management system and method based on modular design, which belongs to the field of wearable device management technology, wherein the system includes: a wearable device module; a user management module, which is used to manage wearable devices according to user accounts; a function management module, which is used to determine the callable algorithm by matching the parameter type with the input parameter type of each algorithm in the AI ​​algorithm library; a data analysis module, which is used to analyze the collected sensor data through the callable algorithm to obtain the analysis result; a correlation analysis module, which is used to perform correlation analysis on the historical data of the user account, obtain the associated parameter type, obtain the relevant parameter set and the corresponding prediction model; a function extension module, which is used to determine the extended parameter type according to the relevant parameter set, match the parameter type and the extended parameter type with the input parameter type of each algorithm, and determine the extensible function. The present invention can manage the functions of various wearable devices.

Description

Technical Field

[0001] The present invention relates to the technical field of wearable device management, and in particular to a smart wearable device management system and method based on modular design. Background Art

[0002] With the development of information technology, based on the miniaturization of sensor units and integrated circuits, electronic products can provide a variety of applications and functions within a wearable size. Wearable devices are electronic devices that are miniaturized and made into product shapes that people can wear with them (for example: headbands, smart glasses, watches, bracelets, rings, etc.). They record, collect, and analyze the wearer's relevant information by wearing them, and provide the wearer with the information content needed by the wearer after the information processing results. Wearable devices can be worn directly on the body and can be in the form of wearable cameras, smart glasses, smart watches, wearable medical and health devices, activity trackers, 3D motion trackers, and smart clothing.

[0003] In the prior art, wearable devices are responsible for collecting user health data, and then interacting and synchronizing data with PC software through data cables, processing, statistics and storing data on the PC side, and presenting statistical results of different dimensions to users for reference or social sharing.

[0004] In the prior art, wearable devices collect user health data and other data (such as sports data, etc.) through various types of sensors, and analyze the collected user data through algorithms in the AI ​​algorithm library. However, since different types of sensors can be set on different wearable devices, when one of the wearable devices is low on power or damaged, it may not be possible to collect all parameter types required by the AI ​​algorithm library, resulting in some functions being unable to be implemented. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a smart wearable device management system and method based on modular design, which can intelligently manage multiple wearable devices according to user account information.

[0006] On the one hand, an embodiment of the present invention provides an intelligent wearable device management system based on modular design, including: a wearable device module, including several types of wearable devices, wherein the wearable devices include several sensor devices for collecting different types of sensor data; a user management module, for managing wearable devices according to user accounts, and obtaining wearable device data, including wearable device types, wearable device status information, and sensor types corresponding to the wearable device types; a function management module, for obtaining the wearable device type of the current user account, determining the parameter type of the collectable data according to the sensor type of the wearable device type, matching the parameter type of each algorithm in the AI ​​algorithm library with the input parameter type to determine the callable algorithm, and generating a function list; a data analysis module, for obtaining sensor data of the wearable device in current operation, and determining the callable algorithm according to the parameter type corresponding to the sensor data, and analyzing the collected sensor data by the callable algorithm to obtain an analysis result; a correlation analysis module, for performing correlation analysis on the historical data of the user account, obtaining the associated parameter type, and obtaining one or more related parameter sets and corresponding prediction models; a function extension module, for obtaining the parameter type corresponding to one or more wearable devices in current operation, determining the extended parameter type according to the related parameter set, matching the parameter type and the extended parameter type with the input parameter type of each algorithm in the AI ​​algorithm library, and determining the extensible function.

[0007] According to some embodiments of the present invention, the system includes: a power saving management module, which is used to obtain the sensor types of multiple wearable devices currently in operation. If there are multiple sensors of the same type, the remaining working time of each wearable device is determined based on the current remaining power of the wearable device equipped with the sensor and the operating frequency of the sensor. The wearable device with a longer remaining working time turns on the sensor, and the wearable device with a shorter remaining working time turns off the sensor.

[0008] According to some embodiments of the present invention, the association analysis module includes: a correlation analysis unit, used to arbitrarily obtain data of two parameter types in historical data, determine whether the two parameter types are correlated through the Pearson correlation coefficient, and if so, generate a related parameter set based on the two parameter types; a first prediction model unit, used to use the historical data of the parameter type corresponding to the related parameter set as a sample, and train a prediction model with one parameter type as input and another parameter type as output.

[0009] According to some embodiments of the present invention, the association analysis module includes: a related parameter set merging unit, used to traverse all related parameter sets, determine whether there is a parameter type in the current related parameter set that is the same as a parameter type in other related parameter sets, and if so, merge the related parameter sets corresponding to the one parameter type to obtain a merged related parameter set, and mark the one parameter type; a second prediction model unit, used to use the historical data of the parameter type corresponding to the merged related parameter set as a sample, and train a prediction model with the marked parameter type as input and the unmarked parameter type as output.

[0010] According to some embodiments of the present invention, the function extension module includes: an extended parameter type unit, which is used to traverse all parameter types corresponding to one or more wearable devices currently in operation, obtain a related parameter set containing the current parameter type from all related parameter sets, traverse all parameter types in the related parameter sets, and determine whether there is a parameter type that is different from all the parameter types. If so, determine that the one parameter type is an extended parameter type; an extended function display unit, which is used to match the input parameter type of each algorithm in the AI ​​algorithm library according to all current parameter types and extended parameter types, determine the extensible function and display it on the interactive interface; a predicted extended parameter unit, which is used to determine the usable prediction model according to all parameter types and the extended parameter type when the user determines to use the extensible function through the interactive interface, and obtain the predicted value of the extended parameter type based on the prediction model and the data corresponding to the parameter type; an extended function calling unit, which is used to call the corresponding AI algorithm based on the input parameter type of the extensible function and the predicted value of the extended parameter type to obtain an analysis result.

[0011] According to some embodiments of the present invention, the power saving management module includes: a preset basic function unit, which is used to determine the preset basic functions of the function list based on user interaction operations; a low-battery adjustment unit, which is used to issue a low-battery warning for the power of one or more wearable devices currently in operation. When a low-battery warning is issued, the parameter type corresponding to the sensor type required for the current preset basic function is obtained, and the parameter type that can be used as an extended parameter type is determined according to the parameter type and the relevant parameter set to obtain a sensor that can be turned off; a sensor control unit, which is used to obtain all sensor information in the current operation when the battery is low, turn off other sensors except the sensors required for the preset basic functions, and determine whether to turn off the turnable sensor based on user interaction operations.

[0012] According to some embodiments of the present invention, the system includes: a data merging module, which is used to obtain sensor information of all wearable devices currently working under the same user account, and determine whether there are sensors of the same type working at the same time. If so, when obtaining the data of all sensors currently working, the data obtained by sensors of the same type in the same time period are merged and stored; the merging process includes: comparing the start working time points of multiple sensors of the same type, using the data of sensors with earlier start working time points as merged data, and deleting the data of sensors with later start working time points.

[0013] According to some embodiments of the present invention, the system includes: a non-wearable device module, which is used to manage non-wearable devices according to user accounts, send or receive information through user account information, and interact with wearable devices based on user account information.

[0014] According to some embodiments of the present invention, the system includes: a second functional module, used to obtain the wearable device type and non-wearable device type of the current user account, determine the parameter type of collectible data based on the type of the non-wearable device and the sensor type of the wearable device, match the input parameter type of each algorithm in the AI ​​algorithm library to determine the callable algorithm, and generate a second function list.

[0015] The embodiments of the present invention achieve at least the following beneficial effects: the embodiments of the present invention use the historical data corresponding to the parameters required by the AI ​​algorithm as samples, perform correlation analysis on the historical data of the user account, and obtain whether there is a correlation between different parameter types. If there is a correlation, the corresponding prediction model can be trained through the historical data, so that when some sensors are not working, the prediction model can be used to predict the predicted values ​​of the corresponding parameters, thereby supplementing the parameters required for using the AI ​​algorithm and ensuring the realization of the algorithm function.

[0016] On the other hand, an embodiment of the present invention provides a smart wearable device management method based on modular design, including: S100, collecting different types of sensor data based on several types of wearable devices, the wearable devices including several sensor devices; S200, managing wearable devices according to user accounts, and obtaining wearable device data, including wearable device types, wearable device status information, and sensor types corresponding to the wearable device types; S300, obtaining the wearable device type of the current user account, determining the parameter type of the collectable data according to the sensor type of the wearable device type, matching the parameter type of each algorithm in the AI ​​algorithm library to determine the callable algorithm, and generating a function list; S400, obtaining the sensor data of the wearable device in the current work, and determining the callable algorithm according to the parameter type corresponding to the sensor data, and analyzing the collected sensor data by the callable algorithm to obtain an analysis result; S500, performing correlation analysis on the historical data of the user account to obtain the associated parameter type, and obtaining one or more related parameter sets and corresponding prediction models; S600, obtaining the parameter type corresponding to one or more wearable devices in the current work, determining the extended parameter type according to the related parameter set, matching the parameter type and the extended parameter type with the input parameter type of each algorithm in the AI ​​algorithm library, and determining the extensible function.

[0017] The embodiments of the present invention achieve at least the following beneficial effects: the embodiments of the present invention use the historical data corresponding to the parameters required by the AI ​​algorithm as samples, perform correlation analysis on the historical data of the user account, and obtain whether there is a correlation between different parameter types. If there is a correlation, the corresponding prediction model can be trained through the historical data, so that when some sensors are not working, the prediction model can be used to predict the predicted values ​​of the corresponding parameters, thereby supplementing the parameters required for using the AI ​​algorithm and ensuring the realization of the algorithm function.

[0018] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0020] Figure 1 A schematic block diagram of a module of an apparatus according to an embodiment of the present invention;

[0021] Figure 2 The figure is a flowchart of a method according to an embodiment of the present invention.

[0022] Reference numerals:

[0023] Wearable device module 100, user management module 200, function management module 300, data analysis module 400, association analysis module 500, function expansion module 600. DETAILED DESCRIPTION

[0024] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0025] In the description of the present invention, "several" means one or more, "more" means two or more, "greater than", "less than", "exceed" etc. are understood as not including the number itself, and "above", "below", "within" etc. are understood as including the number itself. If there is a description of "first" or "second", it is only used for the purpose of distinguishing the technical features, and cannot be understood as indicating or implying the relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0026] Wearable devices, such as glasses, gloves, watches, bracelets, Bluetooth scales, heart rate monitors, clothing and shoes, are equipped with one or more sensors, such as accelerometers, optical heart rate detectors, gyroscopes, GPS, barometers, geomagnetic sensors, etc. Accelerometers can measure direction and acceleration, and can determine whether the device is in a horizontal or vertical position to determine whether the device is moving, thereby achieving step counting. Optical heart rate detectors use LEDs to illuminate the skin and the fluctuations generated by blood absorbing light to determine heart rate levels. Different types of smart wearable products serve different fields, and the similarity is that they will make full use of their own sensitive sensor systems to capture data in the field of concern. Professional health data analysis models and algorithms can be used to classify and statistically process the original health data collected by wearable devices to obtain characteristic quantities that can indicate certain health indicators of users, including heart rate, pulse, sleep quality, calories consumed, etc.

[0027] The AI ​​algorithm library involved in the embodiments of the present invention includes: PPG, ECG, GSR, body temperature signal preprocessing; heart rate algorithm: eIoT + ADI, etc.; motion algorithm: G-sensor, gyroscope, geomagnetism, air pressure signal preprocessing; blood oxygen saturation algorithm eIoT + ADI, etc.; heart rate variability HRV detection algorithm, etc.; sleep monitoring algorithm (motion parameters + PPG + blood oxygen saturation + environmental sounds, etc.), emotion monitoring algorithm (motion mode + GSR + heart rate + body temperature), intelligent human health status recognition algorithm (heart rate + HPV + body temperature + blood oxygen + sleep quality + blood pressure + motion parameters), etc.

[0028] The embodiment of the present invention can use the historical data corresponding to the parameters required by the above-mentioned AI algorithm as samples to perform correlation analysis on the historical data of the user account. For example: the sleep monitoring algorithm requires input parameter types including: motion parameters, PPG, blood oxygen saturation, ambient sound, etc. Through the analysis of historical data, the relationship between ambient sound and time can be analyzed, and it is found that there is a correlation between the size of the ambient sound and time, and then a relevant parameter set is established. In this way, when the battery of a wearable device is low, the sensor for collecting ambient sound can be turned off, and the predicted ambient sound can be obtained through a pre-trained prediction model, thereby not affecting the functional use of the sleep monitoring algorithm.

[0029] Reference Figure 1 The embodiment of the present invention provides a smart wearable device management system based on modular design, including:

[0030] The wearable device module 100 includes several types of wearable devices, and the wearable devices include several sensor devices for collecting different types of sensor data. The sensor types of this embodiment can be glasses, gloves, watches, bracelets, Bluetooth scales, heart rate meters, clothing and shoes, etc. The sensor of this embodiment can be an acceleration sensor, an optical heart rate detector, a gyroscope, a GPS, a barometer, a geomagnetic sensor, etc.

[0031] The user management module 200 is used to manage wearable devices according to user accounts and obtain wearable device data, including wearable device types, wearable device status information, and sensor types corresponding to wearable device types. This embodiment manages the wearable device data of the same user account by registering and logging in to an account on the Internet platform, and realizes data sharing between different wearable devices.

[0032] The function management module 300 is used to obtain the wearable device type of the current user account, determine the parameter type of the data that can be collected according to the sensor type of the wearable device type, match the input parameter type of each algorithm in the AI ​​algorithm library to determine the callable algorithm, and generate a function list. For example, the sensor type included in the wearable device type of this embodiment includes an optical heart rate detector, etc. By comparing the parameter type of the optical heart rate detector with the parameter type in the AI ​​algorithm library, the algorithm that can be called is obtained.

[0033] The data analysis module 400 is used to obtain the sensor data of the currently working wearable device, and determine the callable algorithm according to the parameter type corresponding to the sensor data, and analyze the collected sensor data through the callable algorithm to obtain the analysis result. This embodiment determines the currently available algorithm by determining the working wearable device and its sensor data, and calls the available algorithm to analyze the sensor data to obtain the analysis result.

[0034] The correlation analysis module 500 is used to perform correlation analysis on the historical data of the user account, obtain the associated parameter type, and obtain one or more related parameter sets and corresponding prediction models. This embodiment performs correlation analysis on the historical data of the user account, where the historical data can be the historical data of the sensor, or other historical data such as exercise time, etc. By performing correlation analysis on the historical data, it can be obtained whether there is a correlation between different parameter types. If there is a correlation, the corresponding prediction model can be trained through the historical data, so that when some sensors are not working, the prediction model can be used to predict the predicted value of the corresponding parameter, thereby supplementing the parameters required for using the AI ​​algorithm and ensuring the realization of the algorithm function.

[0035] The function extension module 600 is used to obtain the parameter type corresponding to one or more wearable devices currently in operation, determine the extended parameter type according to the relevant parameter set, match the parameter type and the extended parameter type with the input parameter type of each algorithm in the AI ​​algorithm library, and determine the expandable function.

[0036] In some embodiments, the system of an embodiment of the present invention includes: a power saving management module, which is used to obtain the sensor types of multiple wearable devices currently in operation. If there are multiple sensors of the same type, the remaining working time of each wearable device is determined based on the current remaining power of the wearable device equipped with the sensor and the operating frequency of the sensor, and the wearable device with a longer remaining working time turns on the sensor, and the wearable device with a shorter remaining working time turns off the sensor.

[0037] In some embodiments, the association analysis module 500 of the embodiment of the present invention includes:

[0038] The correlation analysis unit is used to arbitrarily obtain data of two parameter types in the historical data, and determine whether the two parameter types are correlated through the Pearson correlation coefficient. If so, a related parameter set is generated according to the two parameter types.

[0039] The first prediction model unit is used to use historical data of parameter types corresponding to the relevant parameter set as samples to train a prediction model with one parameter type as input and another parameter type as output.

[0040] In some embodiments, the association analysis module 500 of the embodiment of the present invention includes:

[0041] The related parameter set merging unit is used to traverse all related parameter sets to determine whether there is a parameter type in the current related parameter set that is the same as a parameter type in other related parameter sets. If so, the related parameter sets corresponding to a parameter type are merged to obtain a merged related parameter set, and a parameter type is marked.

[0042] The second prediction model unit is used to use the historical data of the parameter type corresponding to the merged related parameter set as samples, and train a prediction model with the marked parameter type as input and the unmarked parameter type as output.

[0043] In some embodiments, the function expansion module 600 of the embodiment of the present invention includes:

[0044] The extended parameter type unit is used to traverse all parameter types corresponding to one or more wearable devices currently in operation, obtain the relevant parameter set containing the current parameter type from all relevant parameter sets, traverse all parameter types in the relevant parameter set, and determine whether there is a parameter type that is different from all parameter types. If so, determine that a parameter type is an extended parameter type.

[0045] The extended function display unit is used to match the input parameter types of each algorithm in the AI ​​algorithm library according to all current parameter types and extended parameter types, determine the extensible functions and display them on the interactive interface.

[0046] The prediction extended parameter unit is used to determine the available prediction model based on all parameter types and extended parameter types when the user determines to use the extensible function through the interactive interface, and obtain the prediction value of the extended parameter type based on the data corresponding to the prediction model and the parameter type.

[0047] The extended function calling unit is used to call the corresponding AI algorithm based on the input parameter type of the extensible function and the predicted value of the extended parameter type to obtain the analysis result.

[0048] In some embodiments, the power saving management module of the embodiment of the present invention includes:

[0049] The preset basic function unit is used to determine the preset basic functions of the function list based on user interaction operations.

[0050] The low-battery adjustment unit is used to issue a low-battery warning for one or more wearable devices currently in operation. When a low-battery warning is issued, the parameter type corresponding to the sensor type required by the currently preset basic function is obtained, and the parameter type that can be used as an extended parameter type is determined based on the parameter type and the relevant parameter set to obtain a sensor that can be turned off.

[0051] The sensor control unit is used to obtain all sensor information currently working when the battery is low, turn off all sensors except those required for preset basic functions, and determine whether to turn off the disabling sensors based on user interaction operations.

[0052] In some embodiments, the system of the embodiment of the present invention includes: a data merging module, which is used to obtain sensor information of all wearable devices currently working under the same user account, determine whether there are sensors of the same type working at the same time, and if so, when obtaining the data of all sensors currently working, merge and store the data obtained by sensors of the same type in the same time period; the merging process includes: comparing the start working time points of multiple sensors of the same type, using the data of sensors with earlier start working time points as the merged data, and deleting the data of sensors with later start working time points.

[0053] In some embodiments, the system of the embodiment of the present invention includes: a non-wearable device module, which is used to manage the non-wearable device according to the user account, send or receive information through the user account information, and interact with the wearable device based on the user account information. The non-wearable device module of the embodiment of the present invention can be a car, and by registering and logging in to the user account on the car system platform and uploading corresponding data, data sharing between the car and other wearable devices can be achieved.

[0054] In some embodiments, the system of the embodiment of the present invention includes: a second functional module, which is used to obtain the wearable device type and non-wearable device type of the current user account, determine the parameter type of the collectable data based on the type of the non-wearable device and the sensor type of the wearable device, match the input parameter type of each algorithm in the AI ​​algorithm library to determine the callable algorithm, and generate a second function list. In a specific embodiment, the non-wearable device is a car, and the wearable device is a watch containing GPS. According to the data that can be collected by the car, including car positioning data, and the data that can be collected by the watch, including user personal positioning data, the parking positioning and navigation function can be obtained by matching the car positioning data and the user's personal positioning data with the algorithm parameter type in the AI ​​algorithm library. Through the parking positioning and navigation function, the user can collect the car positioning data and the user's personal positioning data to obtain parking navigation information.

[0055] Reference Figure 2 Another aspect of the present invention provides a method for managing a smart wearable device based on modular design, comprising the following steps:

[0056] S100: Collect different types of sensor data based on several types of wearable devices, where the wearable devices include several sensor devices.

[0057] S200: Manage the wearable device according to the user account and obtain the wearable device data, including the wearable device type, the wearable device status information and the sensor type corresponding to the wearable device type.

[0058] S300. Obtain the wearable device type of the current user account, determine the parameter type of the collectable data according to the sensor type of the wearable device type, match it with the input parameter type of each algorithm in the AI ​​algorithm library to determine the callable algorithm, and generate a function list.

[0059] S400: Obtain sensor data of the currently working wearable device, determine a callable algorithm according to a parameter type corresponding to the sensor data, and analyze the collected sensor data through the callable algorithm to obtain an analysis result.

[0060] S500: Perform correlation analysis on historical data of the user account to obtain associated parameter types, and obtain one or more related parameter sets and corresponding prediction models.

[0061] S600, obtaining parameter types corresponding to one or more wearable devices currently in operation, determining extended parameter types according to relevant parameter sets, matching parameter types and extended parameter types with input parameter types of each algorithm in the AI ​​algorithm library, and determining extensible functions.

[0062] Although specific embodiments are described herein, those of ordinary skill in the art will recognize that many other modifications or alternative embodiments are also within the scope of the present disclosure. For example, any of the functions and / or processing capabilities described in conjunction with a particular device or component may be performed by any other device or component. In addition, although various exemplary implementations and architectures have been described according to embodiments of the present disclosure, those of ordinary skill in the art will recognize that many other modifications to the exemplary implementations and architectures described herein are also within the scope of the present disclosure.

[0063] Some aspects of the present disclosure are described above with reference to the block diagram and flow chart of the system, method, system and / or computer program product according to the exemplary embodiments.It should be understood that the combination of one or more blocks in the block diagram and the flow chart and the blocks in the block diagram and the flow chart can be realized by executing computer executable program instructions respectively.Equally, according to some embodiments, some blocks in the block diagram and the flow chart may not need to be executed in the order shown, or may not need to be executed in full.In addition, additional components and / or operations beyond those components and / or operations shown in the blocks in the block diagram and the flow chart may be present in certain embodiments.

[0064] Therefore, the blocks in the block diagrams and flow charts support the combination of devices for performing the specified functions, the combination of elements or steps for performing the specified functions, and the program instruction devices for performing the specified functions. It should also be understood that each block in the block diagrams and flow charts and the combination of blocks in the block diagrams and flow charts can be implemented by a special-purpose hardware computer system or a combination of special-purpose hardware and computer instructions that performs a specific function, element or step.

[0065] The program modules, applications, etc. described herein may include one or more software components, including, for example, software objects, methods, data structures, etc. Each such software component may include computer-executable instructions that, in response to execution, cause at least a portion of the functionality described herein (e.g., one or more operations of the illustrative methods described herein) to be performed.

[0066] Software components can be encoded with any of various programming languages. An exemplary programming language can be a low-level programming language, such as an assembly language associated with a specific hardware architecture and / or an operating system platform. The software component comprising assembly language instructions may need to be converted to executable machine code by an assembler before being executed by hardware architecture and / or platform. Another exemplary programming language can be a higher-level programming language, which can be transplanted across multiple architectures. The software component comprising a higher-level programming language may need to be converted to an intermediate representation by an interpreter or a compiler before execution. Other examples of programming languages ​​include but are not limited to macro languages, shells or command languages, job control languages, scripting languages, database queries or search languages ​​or report writing languages. In one or more exemplary embodiments, the software component comprising the instruction of one of the above-mentioned programming language examples can be directly executed by an operating system or other software components, without first being converted into another form.

[0067] Software components may be stored as files or other data storage structures. Software components of similar type or related functions may be stored together, such as in a specific directory, folder, or library. Software components may be static (e.g., preset or fixed) or dynamic (e.g., created or modified at execution time).

[0068] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge scope of ordinary technicians in the relevant technical field without departing from the purpose of the present invention.

Claims

1. A smart wearable device management system based on modular design, characterized in that: include: The wearable device module includes several types of wearable devices, wherein the wearable devices include several sensor devices for collecting different types of sensor data; The user management module is used to manage wearable devices according to user accounts and obtain wearable device data, including wearable device type, wearable device status information, and sensor type corresponding to the wearable device type; Function management module, used to obtain the wearable device type of the current user account, determine the parameter type of the data that can be collected according to the sensor type of the wearable device type, match it with the input parameter type of each algorithm in the AI ​​algorithm library to determine the callable algorithm, and generate a function list; The data analysis module is used to obtain the sensor data of the wearable device currently in operation, and determine the callable algorithm according to the parameter type corresponding to the sensor data, and analyze the collected sensor data through the callable algorithm to obtain the analysis result; The correlation analysis module is used to perform correlation analysis on the historical data of the user account to obtain the associated parameter type, and obtain one or more related parameter sets and corresponding prediction models; by performing correlation analysis on the historical data, it is determined whether there is a correlation between different parameter types. If there is a correlation, the corresponding prediction model is trained through the historical data. When some sensors are not working, the prediction model is used to predict the predicted values ​​of the parameters corresponding to the said part of the sensors, so as to supplement the parameters required for using the AI ​​algorithm; A function extension module, used to obtain parameter types corresponding to one or more wearable devices currently in operation, determine an extended parameter type according to the relevant parameter set, match the parameter type and the extended parameter type with the input parameter type of each algorithm in the AI ​​algorithm library, and determine the extensible function; A power saving management module is used to obtain the sensor types of multiple wearable devices currently in operation. If there are multiple sensors of the same type, the remaining working time of each wearable device is determined according to the current remaining power of the wearable device equipped with the sensor and the working frequency of the sensor, and the wearable device with a longer remaining working time turns on the sensor, and the wearable device with a shorter remaining working time turns off the sensor; The power saving management module includes: A preset basic function unit, used to determine the preset basic functions of the function list based on user interaction operations; A low-battery adjustment unit is used to issue a low-battery warning for one or more wearable devices currently in operation. When a low-battery warning is issued, the parameter type corresponding to the sensor type required by the currently preset basic function is obtained, and the parameter type that can be used as the extended parameter type is determined according to the parameter type and the related parameter set, so as to obtain a sensor that can be turned off; The sensor control unit is used to obtain all sensor information currently working when the battery is low, turn off other sensors except the sensors required for the preset basic functions, and determine whether to turn off the turnable sensors based on user interaction operations.

2. The intelligent wearable device management system based on modular design according to claim 1 is characterized in that: The association analysis module comprises: A correlation analysis unit, used for arbitrarily acquiring data of two parameter types in the historical data, determining whether the two parameter types are correlated by using the Pearson correlation coefficient, and if so, generating a correlated parameter set according to the two parameter types; The first prediction model unit is used to use the historical data of the parameter type corresponding to the relevant parameter set as samples to train a prediction model with one parameter type as input and another parameter type as output.

3. The intelligent wearable device management system based on modular design according to claim 2 is characterized in that: The association analysis module comprises: A related parameter set merging unit, used to traverse all related parameter sets, determine whether a parameter type in the current related parameter set is the same as a parameter type in other related parameter sets, and if so, merge the related parameter sets corresponding to the one parameter type to obtain a merged related parameter set, and mark the one parameter type; The second prediction model unit is used to use the historical data of the parameter type corresponding to the merged related parameter set as samples, and train a prediction model with the marked parameter type as input and the unmarked parameter type as output.

4. The intelligent wearable device management system based on modular design according to claim 1 is characterized in that: The function extension module includes: An extended parameter type unit, used to traverse all parameter types corresponding to one or more wearable devices currently in operation, obtain a relevant parameter set containing the current parameter type from all relevant parameter sets, traverse all parameter types in the relevant parameter set, and determine whether there is a parameter type that is different from all the parameter types. If so, determine that the parameter type is an extended parameter type; The extended function display unit is used to match the input parameter types of each algorithm in the AI ​​algorithm library according to all current parameter types and extended parameter types, determine the extendable functions and display them on the interactive interface; A prediction extended parameter unit, used for determining an available prediction model according to all parameter types and the extended parameter type when the user determines to use the extendable function through the interactive interface, and obtaining a prediction value of the extended parameter type based on the prediction model and data corresponding to the parameter type; The extended function calling unit is used to call the corresponding AI algorithm based on the input parameter type of the extensible function and the predicted value of the extended parameter type to obtain the analysis result.

5. The intelligent wearable device management system based on modular design according to claim 1 is characterized in that: The system comprises: The data merging module is used to obtain the sensor information of all wearable devices currently working under the same user account, determine whether there are sensors of the same type working at the same time, and if so, when obtaining the data of all sensors currently working, merge and store the data obtained by sensors of the same type in the same time period; the merging process includes: comparing the start working time points of multiple sensors of the same type, using the data of sensors with earlier start working time points as the merged data, and deleting the data of sensors with later start working time points.

6. The intelligent wearable device management system based on modular design according to claim 1 is characterized in that: The system comprises: The non-wearable device module is used to manage non-wearable devices according to user accounts, send or receive information through user account information, and interact with wearable devices based on user account information.

7. The intelligent wearable device management system based on modular design according to claim 6 is characterized in that: The system comprises: The second functional module is used to obtain the wearable device type and non-wearable device type of the current user account, determine the parameter type of the collectable data based on the type of the non-wearable device and the sensor type of the wearable device, match the input parameter type of each algorithm in the AI ​​algorithm library to determine the callable algorithm, and generate a second function list.

8. A method for managing smart wearable devices based on modular design, used in the system according to any one of claims 1 to 7, characterized in that: The following steps are involved: S100, collecting different types of sensor data based on several types of wearable devices, where the wearable devices include several sensor devices; S200, managing the wearable device according to the user account, and obtaining the wearable device data, including the wearable device type, the wearable device status information, and the sensor type corresponding to the wearable device type; S300, obtaining the wearable device type of the current user account, determining the parameter type of the data that can be collected according to the sensor type of the wearable device type, matching it with the input parameter type of each algorithm in the AI ​​algorithm library to determine the callable algorithm, and generating a function list; S400, obtaining sensor data of the currently working wearable device, and determining a callable algorithm according to a parameter type corresponding to the sensor data, and analyzing the collected sensor data by the callable algorithm to obtain an analysis result; S500, performing correlation analysis on historical data of the user account to obtain associated parameter types, and obtaining one or more related parameter sets and corresponding prediction models; S600, obtaining parameter types corresponding to one or more wearable devices currently in operation, determining an extended parameter type according to the relevant parameter set, matching the parameter type and the extended parameter type with the input parameter type of each algorithm in the AI ​​algorithm library, and determining an extensible function.

Images