CN120743096A - Multifunctional wearable equipment and vehicle control and health data processing method and device - Google Patents

Abstract

The disclosed embodiment discloses a multifunctional wearable device and a vehicle control and health data processing method and apparatus, the method comprising: obtaining sensor data currently collected by a wearable device worn by a human body, then analyzing the motion data to determine whether the motion data is a non-accidental touch gesture, and then, if the motion data is a non-accidental touch gesture, analyzing the device to be controlled and the control operation associated with the motion data to generate a control instruction, and finally, based on the control instruction, controlling the device to be controlled to perform the corresponding control operation. This provides users with a more natural and convenient way of interaction, improving the user experience. Analyzing the motion data to determine whether it is a non-accidental touch gesture can effectively reduce erroneous instructions caused by erroneous operations, and can analyze the associated devices to be controlled and control operations according to different gestures, thereby achieving diversified control of multiple devices.

Description

Multifunctional wearable equipment and vehicle control and health data processing method and device

Technical Field

The embodiment of the disclosure relates to the technical field of artificial intelligence, in particular to a multifunctional wearable device and a vehicle control and health data processing method and device.

Background

At the moment of the vigorous development of the intelligent wearable equipment and the Internet of things technology, the functional expansion of the intelligent wearable equipment and the fusion of the intelligent wearable equipment and the multi-scene application become research hotspots. Currently, most of intelligent wearable devices on the market, such as intelligent bracelets and intelligent watches, can only integrate a single function or a few functions, for example, simple motion data recording, or simple device control functions such as incoming call reminding, message viewing and the like. These devices have limitations in functional applications that cannot meet the ever-increasing diversity of demands of users.

Disclosure of Invention

The embodiment of the disclosure provides a multifunctional wearable device, a vehicle control and health data processing method, a device, an electronic device and a computer readable storage medium, and aims to solve one of the technical problems in the related art at least to a certain extent.

In a first aspect, an embodiment of the present disclosure provides a multifunctional wearable device and a vehicle manipulation and health data processing method, the method including:

Acquiring sensor data currently acquired by wearable equipment worn by a human body, wherein the sensor data at least comprises action data;

analyzing the action data to judge whether the action data is a gesture action without false touch;

Analyzing equipment to be controlled and control operation associated with the action data to generate a control instruction under the condition that the action data is a gesture action without false touch;

And controlling the equipment to be controlled to execute the corresponding control operation based on the control instruction.

In a second aspect, embodiments of the present disclosure further provide a multifunctional wearable device and a vehicle handling and health data processing apparatus, the apparatus including:

The wearable device comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring sensor data currently acquired by wearable equipment worn by a human body, and the sensor data at least comprises action data;

The first analysis module is used for analyzing the action data to judge whether the action data is a gesture action without false touch;

The second analysis module is used for analyzing equipment to be controlled and control operation associated with the action data to generate a control instruction under the condition that the action data is a gesture action without false touch;

And the control module is used for controlling the equipment to be controlled to execute the corresponding control operation based on the control instruction.

In a third aspect, an embodiment of the present disclosure further provides an electronic device, where the electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program when executed by the processor implements the steps in the multifunctional wearable device and the vehicle handling and health data processing method described above.

In a fourth aspect, an embodiment of the present disclosure further provides a computer readable storage medium, where a computer program is stored, where the computer program when executed by a processor implements the steps in the multifunctional wearable device and the vehicle handling and health data processing method described above.

In a fifth aspect, the disclosed embodiments also provide a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The computer instructions are read from the computer-readable storage medium by a processor of a computer device, and executed by the processor, cause the computer device to perform the methods provided in the various alternative implementations of the disclosed embodiments.

In summary, by acquiring the sensor data acquired by the wearable device to identify the gesture action, the user can control the device only by making a corresponding gesture without using a traditional input device (such as a mobile phone screen, a remote controller, etc.). Under the scene that some hands are busy or inconvenient to operate the traditional equipment (such as driving and sports), a more natural and convenient interaction mode is provided for the user, and the user experience is improved. The gesture operation method has the advantages that the action data are analyzed to judge whether the gesture operation is a gesture operation without false touch, false instructions generated by false operations (such as false touch caused by clothes friction, natural body shaking and the like) can be effectively reduced, the accuracy and the reliability of equipment control are improved, unnecessary equipment false actions are avoided, and the trust degree of a user on equipment control is improved. The associated equipment to be controlled and control operation can be analyzed according to different gesture actions, so that diversified control of various equipment is realized. The user can conveniently control various intelligent devices through different gestures, such as intelligent household devices, intelligent watches, intelligent glasses and the like, different control modes are not required to be provided for different devices, flexibility and convenience of device control are improved, and the intelligent and integrated living and working environments are constructed. The whole process realizes an automatic process from sensor data acquisition, action analysis to control instruction generation and execution, and embodies a higher degree of intellectualization. The intelligent control mode can better meet the requirements of modern people on convenient and efficient life, promotes the development and application of intelligent equipment and the Internet of things technology, and provides technical support for realizing more intelligent man-machine interaction and intelligent environment.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

In order to more clearly illustrate the technical solutions of the present disclosure, the drawings that are needed in the description of the embodiments will be briefly introduced below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a schematic flow chart of a multifunctional wearable device and a vehicle control and health data processing method according to an embodiment of the disclosure;

fig. 2 is a schematic structural diagram of a multifunctional wearable device and a vehicle control and health data processing apparatus provided in an embodiment of the present disclosure;

fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.

Detailed Description

Reference will now be made in detail to some embodiments of the present disclosure, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated.

The implementations described below in some examples of the disclosure are not representative of all implementations consistent with the disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as detailed in the accompanying claims.

It should be noted that, the execution subject of the multifunctional wearable device and the vehicle control and health data processing method of the present embodiment may be a multifunctional wearable device and a vehicle control and health data processing apparatus, and the apparatus may be configured in any type of wearable device, for example:

The intelligent ring is used as a convenient personal assistant, helps users manage time, receive notification, carry out mobile payment and the like, and enables life to be more convenient and efficient. For example, the user can receive the message notification through the intelligent ring without carrying the mobile phone during exercise and not miss important information, and pay by using the intelligent ring during shopping without taking out the wallet or the mobile phone.

The intelligent watch has a time display function, integrates various sensors such as an accelerometer, a gyroscope and a heart rate sensor, can monitor health indexes such as exercise data, heart rate and sleep quality, and also supports the functions of receiving notification, making a call, sending a short message, mobile payment, navigating, running various application programs and the like.

The intelligent wrist strap is usually worn on the wrist, and has the main playing sports and health monitoring functions such as step number recording, sports distance recording, calories consumed, sleep state recording and the like, and part of the intelligent wrist strap also has the functions of heart rate monitoring, blood pressure monitoring and the like, can also receive mobile phone notification, control mobile phone photographing and the like, and has the characteristics of portability and long endurance time.

Smart glasses-integrating display technology, sensors, and computing functionality into a glasses frame, such as smart glasses with Augmented Reality (AR) or Virtual Reality (VR) functionality, can provide navigation information, display notifications, take pictures or videos, conduct voice calls, etc., and can also operate through gestures or voice commands.

Besides the audio playing function of the common earphone, the intelligent earphone integrates a sensor and an intelligent function, such as heart rate and motion state monitoring, has a voice assistant function, can control music playing, call answering, information inquiring and the like through voice instructions, and also supports the environment noise monitoring and active noise reduction functions.

In the embodiments of the present disclosure, the "multifunctional wearable device and vehicle manipulation and health data processing apparatus" as an execution subject to execute the "multifunctional wearable device and vehicle manipulation and health data processing method" will be described, and is not limited herein.

The following description of the embodiments is not intended to limit the priority of the embodiments.

Fig. 1 is a flow chart of a multifunctional wearable device and a vehicle handling and health data processing method according to a first embodiment of the present disclosure.

As shown in fig. 1, the method includes:

Step 101, acquiring sensor data currently acquired by a wearable device worn by a human body, wherein the sensor data at least comprises action data.

Optionally, the wearable device is a ring, and the sensor data further includes heart rate data and temperature data.

Wherein, the finger ring needs to integrate a motion sensor (such as an accelerometer and a gyroscope), a heart rate sensor and a temperature sensor. These sensors are capable of sensing motion, heart rate and body temperature information of the human body in real time. A Microcontroller (MCU) may then be used to perform data reading operations on the individual sensors. The sensor usually performs data acquisition according to a certain sampling frequency, for example, the sampling frequency of the motion sensor can be set to be 100Hz, so as to ensure that the rapid motion of a human body can be accurately captured. The MCU performs data interaction with the sensor through a corresponding communication protocol (such as I2C, SPI), and converts the acquired analog signals into digital signals. Simple preprocessing is performed on the collected raw data, such as removing noise, calibrating data, etc. For example, for heart rate data, a moving average filtering algorithm may be used to remove high frequency noise, improving the accuracy of the data.

It should be noted that, the core hardware of the intelligent ring is the type selection and integration of various sensors, and performance, power consumption and volume are required to be considered. For example, an IMU (inertial measurement unit) integrating a three-axis accelerometer and a three-axis gyroscope, such as bosch BMI270, may be employed. The sensor has the characteristics of low power consumption and high resolution, and can accurately capture various motion postures of a human body. Meanwhile, in order to further improve the acquisition precision of the motion data, a geomagnetic sensor, such as AK09918, is innovatively introduced, and through the fusion of geomagnetic data with accelerometer and gyroscope data, more accurate gesture calculation can be realized, and particularly under a complex space motion scene, gesture misjudgment caused by single sensor data errors can be effectively avoided. The heart rate data acquisition can be performed by using a PPG (photoplethysmography) sensor, red light, infrared light LEDs and a photoelectric detector are integrated, and heart rate signals are acquired by detecting the absorption change of blood to light with different wavelengths. In order to improve the accuracy of heart rate data, a multichannel PPG technology is adopted on the design of the sensor, a plurality of detection points are arranged, light signals are collected from different angles, and measurement errors caused by factors such as skin surface states, wearing tightness and the like are reduced. In addition, bioelectrical impedance technology is introduced for auxiliary measurement, and the impedance change of human tissues is detected through tiny current, so that more physiological information is obtained, and the accuracy and reliability of heart rate data are further optimized. Alternatively, a digital temperature sensor DS18B20 may be employed, which has the advantages of high accuracy, programmable resolution (9-12 bits), high tamper resistance, etc. In order to realize accurate measurement of the temperature of different parts of a human body, a plurality of temperature sensors are uniformly distributed on the surface of the ring, and the sensors can quickly and accurately sense the temperature change of the human body by combining with the optimal design of heat conduction materials. Meanwhile, an infrared temperature sensor such as MLX90614 is innovatively introduced, so that non-contact temperature measurement can be realized, the skin surface temperature of a human body can be measured, the ambient temperature can be detected to a certain extent, and more dimensional information is provided for subsequent data analysis.

The hardware circuit design of the intelligent finger ring needs to be developed around the power supply, signal processing and transmission of the sensor. In order to reduce the power consumption, a low-power Microcontroller (MCU), such as NordicnRF52832, is adopted, and an ARMCortex-M4F kernel is built in the MCU, so that the low-power microcontroller has strong processing capacity and low power consumption characteristics and supports various wireless communication protocols.

For the power supply of the sensor, a rechargeable lithium battery is adopted for power supply, and an efficient power management circuit is designed. The power management chip selects TPS62740 of Texas instruments, can realize low quiescent current and high-efficiency power conversion, and provides stable voltage for the sensor and the MCU. Meanwhile, energy harvesting techniques such as piezoelectric energy harvesting and thermoelectric energy harvesting are introduced. The ring is internally integrated with a miniature piezoelectric sheet, mechanical energy generated by human body movement is converted into electric energy, a thermoelectric generation material is adopted at the contact part of the ring and skin, so that the temperature difference between the human body and the environment is converted into electric energy, an additional energy source is provided for the ring, and the endurance time of equipment is prolonged.

In terms of signal processing, for a sensor (such as a PPG sensor) outputting an analog signal, a high-precision Analog Front End (AFE) circuit is designed, which comprises a signal amplifying module, a filtering module and the like. The instrument amplifier INA128 is adopted for signal amplification, has the characteristics of high common mode rejection ratio and low offset voltage, and removes high-frequency noise through a low-pass filter to improve the signal quality. For a sensor (such as DS18B 20) with digital signal output, the sensor is directly connected with a GPIO pin of the MCU, and adopts a single bus protocol for data communication, so that the hardware circuit design is simplified.

In order to realize control and data reading of various sensors, corresponding sensor drivers need to be developed. Based on an MCU operating system (such as ZephyrRTOS), adopting a modularized design idea to respectively write driving programs of the IMU, the PPG and the temperature sensor.

For IMU sensors, parameters such as working mode, measuring range, sampling rate and the like of the sensor are configured through I2C or SPI communication protocol. In the data reading process, an interrupt mode is adopted to trigger data acquisition, when the sensor data is ready, an interrupt signal is generated to inform the MCU to read the data, so that the polling cost of the CPU is reduced, and the power consumption is reduced. Meanwhile, the calibration function of sensor data is realized in a driving program, and the data of the accelerometer, the gyroscope and the geomagnetic sensor are subjected to offset compensation and scale factor calibration according to factory calibration parameters and actual use environments of the sensor, so that the accuracy of the data is improved.

The driving program of the PPG sensor is mainly responsible for controlling the luminous time sequence of the LED, setting the gain of the photoelectric detector and reading PPG signal data. In order to reduce the power consumption, an intermittent acquisition mode is adopted, and the acquisition interval is dynamically adjusted according to the change frequency of the heart rate signal. For example, the acquisition interval is properly prolonged in the resting state, and shortened in the exercise state, ensuring accurate capture of heart rate changes. Meanwhile, a signal preprocessing algorithm such as baseline drift correction and denoising is added into the driver, so that the quality of the original PPG signal is improved.

The driver of the temperature sensor communicates with the DS18B20 through a single bus protocol to read and convert temperature data. In order to improve the real-time performance of temperature measurement, a multithreading technology is adopted, and temperature data acquisition threads are independently operated in the background, so that the temperature change information can be timely acquired. For the infrared temperature sensor, sensor parameters are configured through an I2C protocol, the ambient temperature and target temperature data are read, fusion processing of the temperature data is realized in a driving program, and data of a plurality of temperature sensors are weighted and averaged to obtain a more accurate temperature value.

In the data acquisition process, in order to improve the accuracy and reliability of the data, the acquired original data needs to be preprocessed. And for the motion data, performing data fusion and filtering processing by adopting a Kalman filtering algorithm. The Kalman filtering can optimally estimate the data of the accelerometer, the gyroscope and the geomagnetic sensor according to the state equation and the observation equation of the system, effectively remove noise interference and improve the accuracy of gesture calculation. Meanwhile, an adaptive filtering algorithm is introduced, filtering parameters are automatically adjusted according to the change of a motion scene, for example, the suppression force on noise is increased in a severe motion scene, and the sensitivity on weak signals is improved in a static scene. Preprocessing of heart rate data mainly includes removal of baseline wander, filtering denoising, and peak detection. And a baseline drift correction algorithm based on polynomial fitting is adopted to fit and correct the baseline of the PPG signal, and a band-pass filter (such as a Butterworth band-pass filter) is used for removing high-frequency noise and low-frequency noise, so that the effective frequency band of the heart rate signal is reserved. In the aspect of peak detection, a method of combining threshold detection with morphological analysis is adopted to accurately identify the peak value of the heart rate signal and calculate the heart rate value. Meanwhile, a machine learning algorithm is introduced to detect the abnormality of heart rate data, a model of a normal heart rate mode is established, and when the abnormal heart rate data is detected, an early warning signal is sent out in time. The preprocessing of temperature data mainly comprises data smoothing and outlier processing. And identifying and processing abnormal temperature data by setting a reasonable temperature threshold range, for example, repeatedly measuring or marking as invalid data when the temperature value exceeds a normal range. In addition, the change trend of the temperature data is predicted by combining a time sequence analysis algorithm, so that more valuable temperature information is provided for users.

In order to further improve the data acquisition capability and application value of the intelligent ring, a multi-sensor fusion technology can be introduced, so that more accurate scene perception is realized. The scene recognition model is constructed by combining the motion data, heart rate data and temperature data with other sensor data (such as an air pressure sensor and a humidity sensor) and combining a machine learning algorithm. For example, when a user performs running exercise, by analyzing motion data (acceleration, angular velocity), heart rate data (elevated heart rate), temperature data (elevated body surface temperature), and air pressure data (possible elevation changes), running scenes can be accurately identified, and data acquisition strategies and function applications can be automatically adjusted according to different scenes. In the running scene, the power consumption of the sensor is reduced, the duration of the equipment is prolonged, and meanwhile, the sleep quality is accurately estimated by analyzing the heart rate, the respiratory rate and the body movement data.

In order to realize real-time processing and quick response of data, an edge computing technology is introduced into the intelligent ring. And carrying out preliminary analysis and processing on the acquired data locally by utilizing the computing capability of the MCU, and extracting key information. For example, when abnormal heart rate or strenuous exercise is detected, judgment and early warning are immediately carried out at the ring end, all data are not required to be uploaded to the cloud for processing, and response speed and user experience are improved. Meanwhile, data is compressed and screened through edge calculation, so that data transmission quantity is reduced, dependence on a network is reduced, and power consumption is further reduced. For some simple gesture control instructions, the finger ring end can be directly identified and processed, and quick vehicle control response is realized.

Optionally, the Bluetooth low-power consumption main control main board can send instructions to each sensor and receive sensor data returned by each sensor module, wherein each sensor comprises a gravity sensor, a photoplethysmography sensor and a temperature sensor, after the sensor data currently collected by a ring worn by a human body are obtained, the Bluetooth low-power consumption main control main board further comprises the steps of sending the sensor data to a mobile phone client for storage and recording, analyzing the sensor data to obtain an analysis result, and displaying the analysis result on a designated page in the mobile phone client.

In the practical application of the intelligent ring, the data interaction between the main control main board and each sensor and the data transmission, analysis and display between the main control main board and the mobile phone client are realized based on the Bluetooth low-power consumption (BluetoothLowEnergy, BLE) technology, so that the key links for improving the functionality and user experience of the intelligent ring are realized. The scheme specifically describes a Bluetooth low-power-consumption communication mechanism, a data processing flow and a mobile phone client function implementation.

The Bluetooth low-power consumption technology is a wireless communication technology specially designed for low-power consumption equipment, has the characteristics of low power consumption, low cost, low delay and the like, and is very suitable for small wearable equipment such as intelligent rings. The main control main board is used as a Bluetooth low-power-consumption central device, and each sensor module is used as a peripheral device to conduct data interaction through a GATT (GenericAttributeProfile, general attribute configuration file) protocol. The GATT protocol defines how attribute values are discovered, read, written and notified between devices, in which case the master motherboard communicates with sensor modules through GATT services and features, each of which defines specific services and features for transmitting instructions and data.

And the main control main board sends instructions to the gravity sensor, the photoplethysmography (PPG) sensor and the temperature sensor according to a preset acquisition strategy or the operation requirement of a user. The sending flow of the instruction is as follows, the main control main board scans the peripheral Bluetooth low power consumption equipment, and after the sensor module is found, connection is established through a Bluetooth protocol. In the connection establishment process, the main control main board and the sensor module negotiate communication parameters such as connection interval, slave delay and the like so as to optimize the power consumption and performance of communication. The main control main board constructs corresponding instruction data according to the function requirement of the sensor. For example, an instruction to set parameters such as sampling frequency and measuring range can be sent to the gravity sensor, an instruction to control the luminous intensity and sampling period of the LED can be sent to the PPG sensor, and an instruction to start temperature measurement and set measurement accuracy can be sent to the temperature sensor. The instruction data are packaged according to the GATT characteristic format and are sent to the corresponding sensor module through the Bluetooth low-power-consumption link. After receiving the instruction, the sensor module performs data acquisition according to the instruction requirement and encapsulates the acquired sensor data. And returning the data to the main control main board through the Bluetooth low-power-consumption link according to the GATT characteristic format. After the main control main board receives the data, the data is analyzed and checked, and the accuracy and the integrity of the data are ensured. In order to improve the reliability of data transmission, a check algorithm such as a Cyclic Redundancy Check (CRC) may be used to check the data.

After the main control main board acquires the sensor data, the main control main board sends the data to the mobile phone client through the Bluetooth low power consumption technology. The whole transmission flow is as follows, the main control main board establishes Bluetooth low-power connection with the mobile phone client. The mobile phone client side is used as a central device to scan surrounding Bluetooth low-power consumption devices, and initiates a connection request after finding out an intelligent ring main control main board. In the connection establishment process, both parties negotiate communication parameters, such as connection interval, maximum Transmission Unit (MTU), etc., to ensure efficient transmission of data. The main control main board encapsulates the sensor data according to a certain protocol format, for example, the gravity sensor data, the PPG sensor data and the temperature sensor data are packed into a data frame by adopting a JSON format. And the information such as the time stamp, the equipment identifier and the like is added in the data frame, so that the mobile phone client can conveniently manage and analyze the data. And after the encapsulation is finished, the data frame is sent to the mobile phone client through the Bluetooth low-power-consumption link. After receiving the data frame, the mobile phone client analyzes and checks the data frame. After verification passes, the data is stored in a local database, such as a SQLite database. In the storage process, an index is established according to the information such as the data type, time and the like, so that the subsequent data query and analysis are convenient. Meanwhile, in order to ensure the security of the data, the stored data can be encrypted, and the data can be encrypted and stored by adopting an encryption algorithm such as AES (advanced encryption Standard). The mobile phone client adopts a flexible data storage strategy to adapt to different use scenes and user requirements, and gathers and stores the sensor data according to fixed time intervals, such as every minute or every hour. This approach is suitable for long-term trend analysis of data, such as heart rate trend, body temperature trend, etc. of the user. When a specific event is detected, such as heart rate abnormality, strenuous exercise, etc., the sensor data for the relevant period of time is stored. The method can record the detailed data of the occurrence of the key event and provide basis for subsequent analysis and diagnosis. The user can manually select to store the current sensor data according to the own requirements. For example, when a special exercise is performed or the body is inconvenient, the user manually saves the data, so that the user can conveniently communicate with doctors or professionals later.

The mobile phone client analyzes and processes the stored sensor data to mine information behind the data, and the specific analysis method is that the motion state of a user, such as walking, running, jumping, stillness and the like, is identified through analysis of gravity sensor data. And performing classification training on the gravity sensor data by adopting a machine learning algorithm, such as a Support Vector Machine (SVM) or a random forest algorithm, and establishing a motion state recognition model. Classifying the gravity sensor data acquired in real time according to the model, judging the current motion state of the user, and calculating parameters such as the number of steps, the distance, the speed and the like of the motion. And processing the PPG sensor data, and extracting physiological indexes such as heart rate, blood oxygen saturation and the like. First, the heart rate signal is extracted from the raw PPG signal by digital signal processing algorithms, such as filtering, peak detection, etc. Then, by utilizing the principle of photoelectric volume pulse wave and combining the absorption characteristics of red light and infrared light, the blood oxygen saturation is calculated. Meanwhile, a deep learning algorithm, such as a Recurrent Neural Network (RNN) or a Convolutional Neural Network (CNN), is introduced to analyze the PPG signal and predict cardiovascular health conditions of the user, such as detecting potential diseases such as arrhythmia. The temperature sensor data is analyzed to monitor the change in body temperature of the user. And (3) predicting trend of the body temperature data by adopting a time sequence analysis method, and judging whether the user has health problems such as fever and the like. Meanwhile, the influence of the environment where the user is located on the body temperature is analyzed by combining the environment temperature data, and reasonable health advice is provided for the user, such as reminding the user of heatstroke prevention and temperature reduction under a high-temperature environment.

The mobile phone client displays the analysis result on a designated page in an intuitive and understandable manner, so that a user can conveniently check and understand the physical condition and the exercise condition of the user. Through data visualization, a user can quickly and intuitively know the change and distribution of the data. And regularly generating a health report, gathering physiological indexes and motion data of the user for a period of time, and analyzing and evaluating the physiological indexes and the motion data. The health report comprises heart rate average value, calories consumed by exercise, sleep quality assessment and the like, and gives corresponding health advice and exercise guidance. When abnormal data such as overhigh heart rate and abnormal body temperature are detected, the mobile phone client sends real-time reminding to the user in a popup window, vibration, sound and other modes, timely informs the user of potential health risks and provides corresponding countermeasure suggestions.

Alternatively, it may be detected whether the sensor data is valid, and in the case where the sensor data is invalid, the sensor data is discarded.

Step 102, analyze the motion data to determine whether the motion data is a gesture motion that is not a false touch.

Optionally, the wearable device is equipped with various sensors, such as accelerometers, gyroscopes, magnetometers, and the like. The action situation is fully understood by fusing the data of the sensors. For example, an accelerometer may detect changes in acceleration of the hand, a gyroscope may sense the angle of rotation, and a magnetometer may provide directional information. When the data of the sensors are mutually verified, the information such as the motion track, the speed, the direction and the like of the hand is comprehensively analyzed, and whether the motion is the intentional gesture motion can be accurately judged. If only the data of a single sensor is abnormal, and the data of other sensors are normal, the data is abnormal due to false touch or sensor fault, and the data is not true gesture motion.

Optionally, a pattern library of common gesture actions is established, and the collected action data is matched with standard gestures in the pattern library. A large amount of gesture motion data is trained through a machine learning algorithm, so that the system learns the characteristics of different gestures. For example, an action mode of common gestures such as "waving a hand", "making a fist" and "sliding" is set, and when action data is collected, the similarity between the action and each gesture in the mode library is calculated. If the similarity exceeds a certain threshold, the corresponding gesture action is judged, and if the similarity is lower, the gesture action is possibly a false touch or other non-gesture actions.

It should be noted that, the false touch is generally shorter in duration and lower in frequency, and the intentional gesture generally has a certain duration and regular frequency. For example, when the hand is shaking briefly, it may be a false touch-generated motion, while a continuous, rhythmic hand motion is more likely to be an intentional gesture. By analyzing the characteristics of duration, frequency and the like of the action data, reasonable thresholds are set to distinguish between false touch and non-false touch gesture actions.

Optionally, context information such as the current activity scene of the user and the use state of the device may be considered. For example, some small movements of the hands may be false touches when the user is viewing information using a smart watch, while the same movements may be considered intentional gesture movements when the user is exclusively wearing a wearable device for gesture control operations. In addition, in combination with the state information of the device, such as whether the device is in an awake state, whether a specific application operation is being performed, and the like, the gesture operation of whether the action is a non-false touch is also facilitated to be accurately judged.

Optionally, personalized judgment can be performed according to historical action data and behavior habits of the user. The gesture movement habit of each user may be different, and by learning the habit of the user, the system can more accurately recognize the intention of the user. For example, some users are accustomed to gesture operations in a particular manner, from which the system can determine whether the current action is a false touch. If a certain user normally performs a specific gesture motion at a specific time and under a specific scene, the gesture motion may be a false touch when a motion which does not accord with the habit of the user occurs, otherwise, the gesture motion is more likely to be an intentional gesture motion.

And step 103, analyzing equipment to be controlled and control operation associated with the action data to generate a control instruction under the condition that the action data is a gesture action without false touch.

Specifically, a mapping relation library can be constructed in advance in a system of the wearable device or a matched application program, and the mapping relation library records corresponding relations among different gesture actions, the device to be controlled and the control operation. For example:

Gesture motion	Device to be controlled	Control operation
			One time for making fist	Intelligent bulb	Opening up
Waving hands twice	Intelligent curtain	Closing
			Finger drawing ring	Vehicle with a vehicle body having a vehicle body support	Unlocking the device

And after judging that the action data belongs to the gesture action without false touch, comparing the action data with the gesture action in the mapping relation library. A pattern matching algorithm, such as a Dynamic Time Warping (DTW) algorithm, can be adopted, so that the problems of stretching and deformation of gesture motion data on a time axis can be effectively solved, and gesture motions matched with the gesture motion data can be accurately found. And once the matched gesture is found, the corresponding equipment to be controlled and the control operation information can be acquired from the mapping relation library. For example, if the gesture motion matched is "make a fist once", the device to be controlled is "smart light bulb", and the control operation is "on". And generating a control instruction conforming to the equipment communication protocol according to the determined equipment to be controlled and the control operation. Different devices to be controlled may employ different communication protocols, for example, if the devices to be controlled support bluetooth communication, control instructions conforming to the Bluetooth Low Energy (BLE) protocol may be generated, the instructions typically containing information such as device address, operation code, data, etc. For devices connected through Wi-Fi, the control instructions generated based on TCP/IP or UDP protocols may be in the form of HTTP requests, such as sending a POST request to a specific API interface of the device, the request containing parameters for controlling the operation.

And 104, controlling the equipment to be controlled to execute the corresponding control operation based on the control instruction.

Optionally, a first transmission frequency corresponding to the device to be controlled may be determined first, then the first transmission frequency is processed based on a second transmission frequency of the control instruction, a third transmission frequency is obtained, and according to the third transmission frequency, the heart rate data and the temperature data are uploaded to a cloud server for storage and recording.

In a first scenario, during a daily commute, a user uses a wearable ring to control the door opening and closing operations of a vehicle. Typically, the transmission of vehicle related data does not need to be too frequent, so the first transmission frequency corresponding to the vehicle is determined to be uploading heart rate data and temperature data every 10 minutes to balance the timeliness of the data with the energy consumption of the device. When a user sends a control command to the vehicle through a gesture (such as unlocking a vehicle door to prepare for getting on), the system processes the first sending frequency according to the second sending frequency of the control command. The second transmission frequency is set to be higher once per 1 minute, considering that the health data of the user may be changed due to emotion, action and other factors before and after operating the vehicle, and has higher monitoring value. And the system carries out fusion processing on the first transmission frequency and the second transmission frequency through an algorithm to obtain a third transmission frequency which is once in 2 minutes. And after the user finishes the vehicle control operation (for example, 10 minutes), the wearable ring packs heart rate data and temperature data acquired in real time according to the third sending frequency, and is connected to the cloud server through Bluetooth or a cellular network. After the cloud server receives the data, the cloud server stores and records according to the time sequence and the user identification, so that the user can conveniently inquire and analyze the health state change of the user in the commuting process.

In the second scenario, in the sports and fitness scenario, the user uses the wearable ring to control parameters such as speed, resistance and the like of intelligent fitness equipment (such as a running machine, a spinning and the like). Since the physical state of the user changes more severely during exercise, in order to monitor the health condition of the user more accurately, the first transmission frequency corresponding to the exercise apparatus is determined to be 5 minutes once. When the user sends control instructions to adjust the parameters of the fitness equipment, the movement state and the physical reaction of the user can be changed along with the operation, and the health data needs to be collected more frequently. Therefore, the second transmission frequency of the control command is set to 30 seconds once. The system performs weighted average and other processing on the first transmission frequency and the second transmission frequency, and obtains that the third transmission frequency is once in 1 minute. In the whole exercise process, as long as a control instruction is sent out, the wearable ring uploads heart rate data and temperature data to the cloud server in time according to the third sending frequency. The cloud server can store the record data, and can also combine exercise data (such as exercise duration, calories consumed and the like) fed back by the exercise equipment to generate a comprehensive exercise health report for the user, so that the user can be helped to scientifically adjust an exercise plan.

In the emergency rescue scene, the user is assumed to use the wearable ring to send control instructions such as distress signals to rescue equipment (such as an emergency caller, a rescue robot and the like). In order to ensure that rescue workers can timely acquire health information of users, the first sending frequency corresponding to rescue equipment is determined to be 3 minutes once. When the user transmits an emergency control instruction, the situation is critical, and the physical condition of the user needs to be grasped in real time, so the second transmission frequency is set to be real-time transmission (i.e. data is collected and attempted to be uploaded every second). And the system adopts a priority strategy, and after the first transmission frequency and the second transmission frequency are fused, the third transmission frequency is obtained to be transmitted in real time. Upon detection of the emergency control instruction, the wearable ring immediately uploads heart rate data and temperature data to the cloud rescue server at a third sending frequency through a network channel with highest priority (such as satellite communication or a special rescue network). After the cloud rescue server receives the data, the data can be pushed to the rescue command center at the first time, and key health data support is provided for rescue personnel to make rescue schemes so as to take more effective rescue measures.

Alternatively, features that can represent different gestures may be extracted from the motion data. For example, for accelerometer data, statistical features such as mean, variance, peak, etc. of the accelerometer data in different axes may be calculated, and for gyroscope data, features such as rotation angle, angular velocity, etc. may be extracted. For example, a gesture classification model may be constructed using machine learning or deep learning algorithms. Common machine learning algorithms include Support Vector Machines (SVMs), decision trees, etc., and deep learning algorithms may employ Convolutional Neural Networks (CNNs) or Recurrent Neural Networks (RNNs). When the model is trained, a large amount of gesture sample data is required to be collected and marked, and different gestures are corresponding to corresponding control instructions. The extracted features are input into a trained gesture classification model, and the model outputs corresponding gesture categories. And determining a gesture control instruction of the user according to a mapping relation between the pre-defined gesture and the control instruction. For example, a "fist-making" gesture is defined to correspond to a vehicle unlocking instruction, and when the model determines that the current gesture is "fist-making", the control instruction is determined to be unlocking the vehicle.

When the data features of the accelerometer and the gyroscope are extracted, more advanced feature extraction methods can be introduced besides basic statistical features such as mean, variance and peak values. For accelerometer data, slope changes over different time periods may be calculated to capture dynamic trends in acceleration, e.g., in a waving motion, the slope changes of acceleration may exhibit a unique pattern. Meanwhile, a frequency domain analysis method, such as Fourier transformation, is utilized to convert the acceleration signal in the time domain into the frequency domain, the energy distribution characteristics of the signal in different frequency bands are extracted, and different gestures often have different energy duty ratios in the frequency domain. For gyroscope data, besides the rotation angle and the angular velocity, the angular acceleration can be calculated, the speed of rotation speed change can be reflected, and more abundant information is provided for gesture recognition. In addition, the gyroscope data is subjected to multi-scale analysis by wavelet transformation, data features can be extracted under different resolutions, the overall outline of the gesture can be captured, local micro-motion changes can be refined, and the similar gestures can be distinguished. In the aspect of multi-sensor fusion feature extraction, data of an accelerometer, a gyroscope and a geomagnetic sensor are processed in a combined mode. By constructing a three-dimensional space coordinate system, data of different sensors are mapped into the same space, space vector features such as the length, the direction and the like of vectors are extracted, the features can describe the motion track and the gesture of the gesture in the space more comprehensively, and the accuracy of gesture recognition is effectively improved.

In the model training stage, in order to improve the generalization capability of the model, a training sample is expanded by adopting a data enhancement technology. For the motion data, various training data are generated through operations such as noise addition, random scaling, time shifting and the like, and various interference and change situations possibly occurring in actual use are simulated. Meanwhile, a migration learning method is adopted, and parameters of a model (such as a CNN model trained on a general gesture recognition data set) which is pre-trained on a large-scale public data set are migrated to a gesture classification task of the system, and fine tuning is performed on a small-scale custom data set, so that training time and data requirements are reduced, and performance of the model is improved. In the aspect of model structure innovation, the advantages of different algorithms are combined to construct a hybrid model. For example, a Convolutional Neural Network (CNN) is combined with a long-short-term memory network (LSTM), the CNN is used for extracting spatial features of gesture data, the LSTM is used for processing time sequence data and capturing time sequence and dynamic change of gesture actions, and the hybrid model can better process complex gesture sequences and improve understanding and classifying ability of gestures. In addition, an active learning mechanism is introduced, and in the model training process, the model actively selects the most valuable sample for labeling and training. By calculating the uncertainty and diversity of the samples, the samples which are difficult to classify or have large information quantity are preferentially selected, so that the manual labeling cost is reduced, and meanwhile, the performance of the model is rapidly improved.

When defining the mapping relation between the gesture and the control instruction, the user-defined function can be provided besides the fixed preset mapping. The user can freely set the corresponding relation between the gestures and the instructions in the mobile phone client according to the use habit and the requirement of the user, so that the individuation and the usability of the system are improved. In an actual application scene, a dynamic instruction mapping adjustment mechanism is established in consideration of influences of different environments and user states on gesture recognition. For example, in a noisy environment, a user may not be convenient to make a large-scale gesture, the system can automatically switch to a simpler and easily-identified gesture instruction set, and when the user is detected to be in a motion state, the sensitivity and fault tolerance range of gesture identification are adjusted, so that false identification caused by body shaking is avoided. Meanwhile, the instruction determination process is optimized in combination with the context information. In addition to the motion data, other sensor data (such as the emotion state of the user reflected by heart rate data and the environmental condition reflected by temperature data) and the historical operating habits of the user are referenced, so that the actual intention of the user is comprehensively judged. For example, when the user heart rate is fast and makes a specific gesture, it may be more prone to triggering emergency help instructions than conventional vehicle control instructions.

Optionally, a stable wireless communication connection needs to be established between the ring and the car key control module. Common communication protocols are Bluetooth (Bluetooth), near Field Communication (NFC), etc. Taking Bluetooth as an example, the ring is used as Bluetooth slave equipment, the automobile key control module is used as Bluetooth master equipment, and the Bluetooth slave equipment and the automobile key control module are paired through Bluetooth to establish a communication channel. And packaging the gesture control instruction into a specific data format, and adding necessary header information and check codes to ensure the integrity and accuracy of the data. For example, the instruction is packaged in JSON format, and includes information such as instruction type, instruction parameters, and the like. The ring sends the encapsulated control instruction to the automobile key control module through Bluetooth. After receiving the instruction, the automobile key control module analyzes and verifies the data and confirms the legitimacy of the instruction. If the command is legal, corresponding vehicle control operations, such as unlocking a vehicle door, starting an engine, etc., are performed according to the type of the command.

In order to ensure that gesture control instructions can be stably and quickly transmitted to an automobile key control module in a vehicle, a Bluetooth Low Energy (BLE) or Ultra Wideband (UWB) technology is selected as a communication protocol. The Bluetooth low-power consumption technology is suitable for instruction transmission under the conventional distance by virtue of low energy consumption and wide equipment compatibility, while the ultra-wideband technology is long in high-precision positioning and anti-interference capability, can realize centimeter-level distance measurement, and can effectively avoid misoperation caused by signal interference. In practical application, a dual-mode communication mode can be adopted, and a communication protocol can be automatically switched according to the distance between the vehicle and the intelligent ring and the environmental signal intensity. When the distance between the vehicle and the intelligent ring is short and the environmental signal is stable, the Bluetooth low-power technology is preferentially used to reduce the energy consumption, and when the distance is long or the intelligent ring is in a complex electromagnetic environment, the intelligent ring is switched to the ultra-wideband technology to ensure the reliability of instruction transmission.

In order to prevent the command from being stolen or tampered in the transmission process, the door opening and closing control command is subjected to high-intensity encryption processing. The instruction data is encrypted by adopting an AES-256 (advanced encryption standard, 256-bit key) symmetrical encryption algorithm, so that only an automobile key control module of the vehicle can decrypt by using the corresponding key. Meanwhile, CRC (cyclic redundancy check) check codes are added in the data frames, and after the automobile key control module receives the instruction, the automobile key control module verifies the integrity of the data by calculating the check codes and comparing the check codes with the received check codes. If the verification is not passed, discarding the command and sending error feedback to the intelligent ring, and requesting to resend the command, thereby avoiding misoperation of the vehicle door caused by the error command.

Optionally, when the control instruction is a door opening control instruction and the device to be controlled is a vehicle, the door opening control instruction is sent to an automobile key control module in the vehicle so that the automobile key control module executes a door opening control action based on the door opening control instruction, or when the control instruction is a door closing control instruction and the device to be controlled is a vehicle, the door closing control instruction is sent to the automobile key control module in the vehicle so that the automobile key control module executes a door closing control action based on the door closing control instruction.

Optionally, after the automobile key control module receives a legal door opening or closing control instruction, the action of the door lock motor is precisely controlled through a Body Control Module (BCM) of the automobile. When the door opening action is executed, an unlocking signal is sent to a door lock motor, the motor drives a lock cylinder to rotate, the locking state of the door is relieved, a door state sensor is triggered, and a signal of successful door unlocking is fed back to an automobile key control module and an intelligent ring. When the door closing action is executed, the door lock motor is controlled to reversely rotate, the door is locked, whether the door is completely closed in place or not is detected through the pressure sensor, and if the door is not closed in place, the door closing action is automatically executed again, so that the safety locking of the door is ensured. In order to improve smoothness and reliability of the door opening and closing, PID (proportion-integration-differentiation) control algorithm is adopted for controlling the door lock motor, driving force of the motor is adjusted in real time according to actual state of the door, and the situation that the door is damaged or cannot be normally closed due to too large or too small driving force of the motor is avoided. In the operation process of opening and closing the vehicle door, the intelligent ring and the vehicle owner mobile phone APP receive state feedback information of the vehicle in real time. When the car door starts to execute the opening or closing action, the intelligent ring prompts the user that the instruction is executed in a vibration mode, an LED light flashing mode and the like, and after the car door is successfully opened or closed, the intelligent ring displays corresponding state icons (such as an unlocking icon displayed in an opening state and a locking icon displayed in a closing state) and informs the user of the current state of the car door in a popup window and message pushing mode on the mobile phone APP. Meanwhile, a user can also view the history record of the opening and closing of the vehicle door on the mobile phone APP in real time, and the history record comprises information such as operation time, operation modes (gesture control or other modes), operation results and the like, so that the user can manage and trace the vehicle state conveniently.

Optionally, the wearable device may monitor a heart rate characteristic of the wearer, compare the heart rate characteristic with a pre-stored heart rate template, determine whether the wearer is a target user, if the wearer is the target user, perform identity verification on the ring and the vehicle through a secret key, and if the identity verification passes, send the control instruction to the vehicle in a preset anti-interference manner, so as to execute the corresponding control operation.

The intelligent ring is internally provided with a photoelectric volume pulse wave (PPG) sensor for heart rate data acquisition, and a multichannel design and self-adaptive sampling frequency are adopted for improving data accuracy. The multichannel sensor collects light signals from different angles, reduces errors caused by wearing position changes, and automatically increases the sampling frequency to more than 200Hz when detecting that a user is in a motion state or heart rate fluctuation is large, so as to ensure complete capture of the heart rate signals. The collected original signals are subjected to digital filtering processing, noise such as baseline drift and motion artifact is removed by using a wavelet transformation algorithm, and a pure heart rate signal is reserved.

When an initial heart rate template is constructed, heart rate data of a user in different states such as rest, exercise and sleep are collected for a week, and statistical characteristics such as average value, standard deviation and variation coefficient of heart rate in each state are calculated. These features are modeled using a Gaussian Mixture Model (GMM) in machine learning to obtain an initial template. In the subsequent use, when new data reach a certain number (such as 100 groups of effective data are newly added every day), the template is updated by a sliding window method, so that the template can adapt to the change of the physical state of a wearer, and higher accuracy is always maintained.

The heart rate data collected in real time will extract the same features as when the template was constructed, and the similarity to the heart rate template is calculated using a Dynamic Time Warping (DTW) algorithm. In order to improve the judgment accuracy, the Heart Rate Variability (HRV) characteristics are combined, and a Support Vector Machine (SVM) model is utilized to carry out comprehensive decision. Setting a similarity threshold and an HRV characteristic threshold, judging that the wearer is a target user when the similarity between the real-time data and the template is higher than a set value and the HRV characteristic accords with an expected range, and rejecting subsequent operation if the wearer is not a non-target user.

The intelligent ring and the vehicle are in an initial pairing stage, and an elliptic curve Encryption (ECC) algorithm is adopted to generate a key pair. The ring generates public key Kr1 and private key Kr2, and the vehicle generates public key Kv1 and private key Kv2. The two parties exchange the public key through a Bluetooth Low Energy (BLE) channel, and a Diffie-Hellman key exchange protocol is used in the exchange process to ensure the security and prevent the public key from being stolen. After pairing is successful, the public key of the other party is stored in a local safe storage area and is used for subsequent identity verification.

And after the wearer is judged to be the target user, starting key identity verification. The vehicle generates a random number R, encrypts E (Kr 1, R) using the ring public key Kr1 and transmits it to the ring. After the ring receives the data, the original random number R is obtained through decryption by using a private key Kr2, H (R) is obtained through hash operation on the R, and the H (R) is sent back to the vehicle. After the vehicle receives H (R), the same hash operation is carried out on the local R, and whether the two hash values are consistent is compared. If the ring identity is consistent, the ring identity verification is passed, otherwise, the ring identity verification fails, and the operation is terminated.

Communication techniques employing Frequency Hopping Spread Spectrum (FHSS) in combination with Orthogonal Frequency Division Multiplexing (OFDM). The FHSS technology rapidly jumps among 80 different frequency points according to a preset pseudo-random sequence, the frequency is hopped 150 times per second, narrow-band interference is avoided, the OFDM technology decomposes gesture control instruction data into 64 sub-carriers for parallel transmission, each sub-carrier adopts QPSK or 16-QAM modulation mode, and the gesture control instruction data is dynamically adjusted according to channel quality. The two technologies work cooperatively to improve the transmission reliability in a complex electromagnetic environment. During transmission, the Received Signal Strength Indication (RSSI) and signal-to-noise ratio (SNR) are monitored in real time. When the RSSI is below-90 dBm or the SNR is below 10dB, it is determined that interference is present. Triggering an adaptive adjustment mechanism, adjusting the frequency hopping sequence and interval of FHSS, and simultaneously reducing the modulation order of OFDM sub-carriers, such as switching from 16-QAM to QPSK, so as to sacrifice part of transmission rate and exchange higher anti-interference capability. If the transmission quality cannot be improved after 3 continuous adjustments, transmission is suspended and the user is prompted to replace the operating environment.

Optionally, the emergency alarm information sent by the vehicle can be received, and according to the emergency alarm information, the wearable device is controlled to vibrate and raise the temperature, so that the user is reminded in an auxiliary manner, the user is warned, and accidents are reduced.

The vehicle establishes a stable connection with the wearable device through bluetooth, cellular network, or a dedicated short-range communication protocol. The vehicle end needs to integrate the communication module, the wearable equipment is also provided with a corresponding communication interface, and the identity authentication and the key exchange are completed by the two parties during initial pairing, so that the data transmission safety is ensured. In a vehicle system, various emergency alert triggering conditions such as occurrence of a collision (detection by an acceleration sensor, a gyroscope, or the like of a vehicle), fuel leakage (monitoring of fuel concentration by a sensor), illegal intrusion (abnormal opening of a door, abnormal movement detection in a vehicle), and the like are preset. When the triggering condition is met, the vehicle immediately generates an emergency alarm information data packet containing key information such as alarm type, vehicle position, time stamp and the like, and sends the emergency alarm information data packet to the bound wearable device through the established communication channel. The wearable device continuously monitors the communication port, and when the data packet of the emergency alarm information is received, the data is subjected to integrity check and decryption processing. After confirming that the data is correct, analyzing information such as alarm types, starting a vibration module according to preset rules, and distinguishing different alarm types through vibration modes with different frequencies and intensities (such as rapid continuous vibration for collision alarm and interval vibration for illegal intrusion alarm). Meanwhile, the heating element is controlled to increase the temperature of the equipment so as to enhance the perception of a user, for example, the temperature is increased to 38-40 ℃ which can be obviously perceived by the human body, and the heating speed is controlled through an algorithm so as to avoid scalding the user due to overhigh temperature.

Optionally, the sensing instruction sent by the cloud server may be received, the sensing instruction is processed, so as to determine an identifier of the target device included in the sensing instruction, determine whether the identifier is a target identifier, and if the identifier is the target identifier, control the wearable device to operate according to a target setting mode.

The cloud server is used as an information interaction center and receives induction instructions from a user operation interface (such as a mobile phone APP and a webpage end) or other related systems. The instructions include information such as the target device identification (e.g., unique ID of the particular wearable ring), the type of operation (the manner in which the shock transfer ring is set), trigger conditions, etc. The cloud server pushes the instruction to the network area where the target wearable device is located through a secure communication protocol (e.g., HTTPS, webSocket). And after the wearable device receives the sensing instruction data packet, extracting key contents such as a target device identifier, an operation type and the like in the instruction by utilizing a built-in analysis program. And comparing the target identifier with the self-stored device identifier to judge whether the target identifier is the target identifier. If the identification is the target identification, the wearable device calls the vibration module to operate according to the target setting mode according to the operation type in the instruction. For example, a slow and continuous vibration mode is set to simulate a gentle touch. Meanwhile, the device packages the self state information and the operation result into a feedback data packet, and sends the feedback data packet back to the cloud server through the communication network. The cloud server transmits the information to the relevant ring of the opposite party, and the vibration function is started after the ring of the opposite party receives the information. In the process, the cloud server needs to encrypt, store and transmit the data, protect the privacy of the user, monitor the execution state of the instruction in real time, and timely retransmit or alarm if abnormal conditions such as transmission failure, equipment unresponsiveness and the like occur.

Optionally, based on a preset detection module, the monitoring parameters corresponding to the sensors can be detected, the monitoring parameters are compared with preset reference parameters according to a preset period to obtain the matching degree, the monitoring parameters are synchronously sent to the mobile phone client under the condition that the matching degree is greater than or equal to a preset threshold, and an early warning prompt is sent under the condition that the matching degree is less than the preset threshold.

Wherein, heart rate sensor and temperature sensor that intelligent ring is built-in continuously gather user's heart rate data and body temperature data. These raw data are first subjected to preliminary processing at the end of the ring, such as noise removal, data alignment, etc. Then, a connection is established with a smart phone of the user through a Bluetooth Low Energy (BLE) technology, and the processed data is transmitted to the mobile phone. After the mobile phone client receives the data, the heart rate data and the temperature data are uploaded to the cloud server through a mobile network or a Wi-Fi network. In the uploading process, in order to ensure the safety and the integrity of the data, an encryption transmission protocol, such as an HTTPS protocol, is adopted to encrypt the data. After receiving the data, the cloud server stores the data in a special database, and the data are classified and stored according to information such as user identification, time stamp and the like, so that the subsequent data query and analysis are convenient.

The preset detection module is integrated in the mobile phone client or the cloud server. The module extracts heart rate data and temperature data stored in the cloud according to a preset period (for example, every 10 minutes) to serve as current monitoring parameters. Meanwhile, the system is preset with reference parameters, and the reference parameters can be customized in a personalized way according to age, gender, physical condition and other factors of different users. For example, the heart rate reference range for a normal adult is typically set to 60-100 beats/min and the body temperature reference range is set to 36.1-37.2 ℃. The detection module compares the extracted monitoring parameters with preset reference parameters, and calculates the matching degree through a specific algorithm. For heart rate data, the matching degree may be determined by calculating the overlapping proportion of the monitored heart rate value and the reference heart rate range. For example, if the monitored heart rate value is 80 beats/min, the reference heart rate range is 60-100 beats/min, the degree of match is 100%. For the temperature data, the ratio of the difference value between the monitored body temperature value and the reference body temperature range to the total width of the reference range can be calculated, and then the ratio is converted into the matching degree through a formula. If the monitored body temperature is 36.8 ℃, the reference range is 36.1-37.2 ℃, and the matching degree is calculated. When the calculated matching degree is greater than or equal to a preset threshold (such as 90%), the current heart rate and temperature data are in a normal or near normal range, and the detection module synchronously sends the monitoring parameters to the mobile phone client. After receiving the data, the mobile phone client displays the data to the user in the form of charts, characters and the like, so that the user can conveniently and intuitively know the health condition of the user. When the matching degree is smaller than a preset threshold value, the abnormal heart rate or temperature data of the user is indicated, and the detection module immediately sends out an early warning prompt. The early warning prompt can be presented to the user in various modes such as popup window, vibration, sound and the like of the mobile phone client. For example, when the heart rate is detected to be too fast (the matching degree is lower than the threshold value), the mobile phone client pops up a red warning frame and sends out a rapid warning sound to remind the user of paying attention to the physical condition, and corresponding measures such as rest, medical treatment and the like are taken in time. Simultaneously, the system can synchronously send the abnormal data and the early warning information to an emergency contact person or a medical service mechanism preset by a user so as to obtain more timely help and support.

In summary, by acquiring the sensor data acquired by the wearable device to identify the gesture action, the user can control the device only by making a corresponding gesture without using a traditional input device (such as a mobile phone screen, a remote controller, etc.). Under the scene that some hands are busy or inconvenient to operate the traditional equipment (such as driving and sports), a more natural and convenient interaction mode is provided for the user, and the user experience is improved. The gesture operation method has the advantages that the action data are analyzed to judge whether the gesture operation is a gesture operation without false touch, false instructions generated by false operations (such as false touch caused by clothes friction, natural body shaking and the like) can be effectively reduced, the accuracy and the reliability of equipment control are improved, unnecessary equipment false actions are avoided, and the trust degree of a user on equipment control is improved. The associated equipment to be controlled and control operation can be analyzed according to different gesture actions, so that diversified control of various equipment is realized. The user can conveniently control various intelligent devices through different gestures, such as intelligent household devices, intelligent watches, intelligent glasses and the like, different control modes are not required to be provided for different devices, flexibility and convenience of device control are improved, and the intelligent and integrated living and working environments are constructed. The whole process realizes an automatic process from sensor data acquisition, action analysis to control instruction generation and execution, and embodies a higher degree of intellectualization. The intelligent control mode can better meet the requirements of modern people on convenient and efficient life, promotes the development and application of intelligent equipment and the Internet of things technology, and provides technical support for realizing more intelligent man-machine interaction and intelligent environment.

When approaching the vehicle, the user gently swings hands against the direction of the vehicle, sensors such as an accelerometer and a gyroscope arranged in a ring rapidly acquire hand motion data, analyze the motion data, and judge that the motion is not mistakenly touched but is a specific gesture instruction for unlocking the vehicle door through comparison with a preset gesture motion model. The finger ring determines the equipment to be controlled as a vehicle according to a preset mapping relation, generates a corresponding control instruction, sends the control instruction to a control system of the vehicle through Bluetooth or a special short-distance communication protocol, and automatically unlocks a vehicle door after the vehicle receives the instruction. After entering the car, the user makes a fist-making and then releases action, after the finger ring recognizes the action, a control instruction for starting the car is generated, the car is started, and the user can easily start commute travel without manually inserting a key or pressing a starting button.

And 2, driving the vehicle to the market for shopping by the user, and stopping the vehicle after the user arrives at the parking lot. When the user leaves the vehicle, the user makes a gesture of rotating the finger, and the intelligent ring collects action data and analyzes and judges an effective gesture instruction of locking the vehicle and starting an anti-theft mode. The ring generates a control instruction and sends the control instruction to the vehicle, and the vehicle not only locks the vehicle door automatically, but also starts the anti-theft system, such as monitoring abnormal sound and illegal intrusion detection around the vehicle. When shopping is finished, the user returns to the parking lot, possibly forgets the parking position of the vehicle, makes the action of lifting the arm to draw circles at the moment, generates an instruction after the finger ring is identified and sends the instruction to the vehicle, and the vehicle flashes a lamp and sounds a loudspeaker after receiving the instruction to help the user to quickly find the position of the vehicle.

Scene 3, when the vehicle suddenly breaks down (such as tire burst and engine abnormality) during driving, a user rapidly makes continuous and rapid palm beating actions, the intelligent ring collects the action data, and the intelligent ring analyzes and judges the action data to be a gesture instruction of emergency call rescue. The ring determines that the equipment to be controlled is a vehicle rescue service system according to a preset rescue service connection relation, generates a control instruction containing information such as the position of the vehicle, the fault type (the auxiliary judgment of sensor data of the vehicle can be realized, such as tire pressure monitoring data and an engine fault code) and the like, and sends the control instruction to a professional road rescue center through a cellular network. Meanwhile, the ring can also generate instructions to control the vehicle to start the hazard warning lamp and automatically lower a part of the vehicle window, so that ventilation in the vehicle and observation conditions of rescue workers are guaranteed, and timely and effective safety guarantee is provided for users in emergency.

And 4, in loving scene application, intelligent wearable equipment (such as lover rings) worn by both lovers and a cloud server are connected in real time. When one party wants to transmit specific information to the opposite party or trigger interaction, the sensing instruction is sent through the cloud server. After the communication module of the wearable device receives the sensing instruction sent by the cloud server, the instruction processing module immediately analyzes the instruction. In the analysis process, the identification information of the target device is extracted from the instruction data, and the identification is compared with the device identification preset by the wearable device. The system judges whether the extracted identification is a preset target identification (namely, the exclusive identification of lover equipment) through built-in judgment logic. If the judgment result is that the marks are matched, namely, the marks are target marks, the control module executes the operation according to a preset target setting mode. The target setting modes can be expressed in loving scenes as equipment vibration reminding, playing exclusive voice messages of both parties, releasing favorite flavor of the other parties, displaying prerecorded images and the like, so that interaction and emotion transfer between lovers based on wearable equipment are realized.

In order to facilitate better implementation of the multifunctional wearable device and the vehicle control and health data processing method, the present disclosure further provides a multifunctional wearable device and a vehicle control and health data processing device based on the multifunctional wearable device and the vehicle control and health data processing method. The meaning of the noun is the same as that in the multifunctional wearable device and the vehicle control and health data processing method, and specific implementation details can be referred to the description in the method embodiment.

Referring to fig. 2, fig. 2 is a schematic structural diagram of a multifunctional wearable device and a vehicle control and health data processing apparatus 200 according to an embodiment of the disclosure, where the multifunctional wearable device and the vehicle control and health data processing apparatus 200 includes:

An obtaining module 210, configured to obtain sensor data currently collected by a wearable device worn by a human body, where the sensor data at least includes action data;

The first analysis module 220 is configured to analyze the motion data to determine whether the motion data is a gesture motion that is not a false touch;

The second analysis module 230 is configured to analyze, in a case where the motion data is a gesture motion that is not a false touch, a device to be controlled and a control operation associated with the motion data to generate a control instruction;

and the control module 240 is configured to control the device to be controlled to execute the corresponding control operation based on the control instruction.

In summary, by acquiring the sensor data acquired by the wearable device to identify the gesture action, the user does not need to use a traditional input device (such as a mobile phone screen, a remote controller, etc.), and only needs to make a corresponding gesture to control the device. Under the scene that some hands are busy or inconvenient to operate the traditional equipment (such as driving and sports), a more natural and convenient interaction mode is provided for the user, and the user experience is improved. The gesture operation method has the advantages that the action data are analyzed to judge whether the gesture operation is a gesture operation without false touch, false instructions generated by false operations (such as false touch caused by clothes friction, natural body shaking and the like) can be effectively reduced, the accuracy and the reliability of equipment control are improved, unnecessary equipment false actions are avoided, and the trust degree of a user on equipment control is improved. The associated equipment to be controlled and control operation can be analyzed according to different gesture actions, so that diversified control of various equipment is realized. The user can conveniently control various intelligent devices through different gestures, such as intelligent household devices, intelligent watches, intelligent glasses and the like, different control modes are not required to be provided for different devices, flexibility and convenience of device control are improved, and the intelligent and integrated living and working environments are constructed. The whole process realizes an automatic process from sensor data acquisition, action analysis to control instruction generation and execution, and embodies a higher degree of intellectualization. The intelligent control mode can better meet the requirements of modern people on convenient and efficient life, promotes the development and application of intelligent equipment and the Internet of things technology, and provides technical support for realizing more intelligent man-machine interaction and intelligent environment.

In addition, the present disclosure further provides an electronic device, as shown in fig. 3, which shows a schematic structural diagram of the electronic device according to the present disclosure, specifically:

the electronic device may include one or more processing cores 'processors 301, one or more computer-readable storage media's memory 302, power supply 303, and input unit 304, among other components. Those skilled in the art will appreciate that the electronic device structure shown in fig. 3 is not limiting of the electronic device and may include more or fewer components than shown, or may combine certain components, or may be arranged in different components. Wherein:

The processor 301 is a control center of the electronic device, connects various parts of the entire electronic device using various interfaces and lines, and performs various functions of the electronic device and processes data by running or executing software programs and/or modules stored in the memory 302, and calling data stored in the memory 302, thereby performing overall monitoring of the electronic device. Optionally, the processor 301 may include one or more processing cores, and preferably, the processor 301 may integrate an application processor and a modem processor, wherein the application processor primarily processes operating systems, user interfaces, application programs, etc., and the modem processor primarily processes wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 301.

The memory 302 may be used to store software programs and modules, and the processor 301 executes various functional applications and data processing by executing the software programs and modules stored in the memory 302. The memory 302 may mainly include a storage program area that may store an operating system, application programs required for at least one function (such as a sound playing function, an image playing function, etc.), etc., and a storage data area that may store data created according to the use of the electronic device, etc. In addition, memory 302 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 302 may also include a memory controller to provide the processor 301 with access to the memory 302.

The electronic device further comprises a power supply 303 for powering the various components, preferably the power supply 303 is logically connected to the processor 301 by a power management system, whereby the functions of managing charging, discharging, and power consumption are performed by the power management system. The power supply 303 may also include one or more of any components, such as a direct current or alternating current power supply, a recharging system, a power device commissioning circuit, a power converter or inverter, a power status indicator, etc.

The electronic device may further comprise an input unit 304, which input unit 304 may be used for receiving input digital or character information and for generating keyboard, mouse, joystick, optical or trackball signal inputs in connection with user settings and function control.

Although not shown, the electronic device may further include a display unit or the like, which is not described herein. In particular, in this embodiment, the processor 301 in the electronic device loads executable files corresponding to the processes of one or more application programs into the memory 302 according to the following instructions, and the processor 301 runs the application programs stored in the memory 302, so as to implement any one of the steps in the multifunctional wearable device and the vehicle handling and health data processing method provided in the embodiments of the present disclosure.

The specific implementation of each operation above may be referred to the previous embodiments, and will not be described herein.

Those of ordinary skill in the art will appreciate that all or a portion of the steps of the various methods of the above embodiments may be performed by instructions, or by instructions controlling associated hardware, which may be stored in a computer-readable storage medium and loaded and executed by a processor.

To this end, the present disclosure provides a computer readable storage medium having stored thereon a computer program that is loadable by a processor to perform the steps in any of the multi-functional wearable devices and vehicle handling and health data processing methods provided by the present disclosure.

The specific implementation of each operation above may be referred to the previous embodiments, and will not be described herein.

The computer readable storage medium may include, among others, read Only Memory (ROM), random access Memory (RAM, random Access Memory), magnetic or optical disks, and the like.

Because the instructions stored in the computer readable storage medium can execute the steps in any one of the multifunctional wearable device and the vehicle control and health data processing method provided by the present disclosure, the beneficial effects that any one of the multifunctional wearable device and the vehicle control and health data processing method provided by the present disclosure can be realized, which are detailed in the foregoing embodiments and are not described herein.

The foregoing describes in detail a method, apparatus, electronic device and computer readable storage medium for handling and processing health data of a multifunctional wearable device and a vehicle, which are provided in the present disclosure, and specific examples are provided herein to illustrate the principles and embodiments of the present invention, and the above examples are provided to facilitate understanding of the method and core ideas of the present invention, and meanwhile, to those skilled in the art, according to the ideas of the present invention, there are variations in the specific embodiments and application scope, and in this summary, the present disclosure should not be construed as limiting the present invention.

Claims (10)

1. A multifunctional wearable device and a vehicle control and health data processing method, characterized by comprising: Acquiring sensor data currently collected by a wearable device worn by a human body, wherein the sensor data at least includes motion data; Analyzing the action data to determine whether the action data is a non-accidental touch gesture; When the action data is a non-accidental touch gesture, analyzing the to-be-controlled device and the control operation associated with the action data to generate a control instruction; Based on the control instruction, the device to be controlled is controlled to perform the corresponding control operation. 2. The method according to claim 1, wherein the wearable device is a ring, the device to be controlled is a vehicle, the control action is a door opening operation or a door closing operation, the sensor data further includes heart rate data and temperature data, and the method further comprises: Determining a first sending frequency corresponding to the device to be controlled; Processing the first sending frequency based on the second sending frequency of the control instruction to obtain a third sending frequency; According to the third sending frequency, the heart rate data and temperature data are uploaded to the cloud server for storage and recording. 3. The method according to claim 2, wherein obtaining sensor data currently collected by a wearable device worn by a human body comprises: The main control board sends instructions to each sensor based on Bluetooth low energy consumption and receives sensor data returned by each sensor module, wherein each sensor includes a gravity sensor, a photoplethysmography sensor, and a temperature sensor; After obtaining the sensor data currently collected by the wearable device worn by the human body, the method further includes: Sending the sensor data to a mobile client for storage and recording; Analyzing and processing the sensor data to obtain analysis results; The analysis results are displayed on a designated page of the mobile client. 4. The method according to claim 1, wherein controlling the device to be controlled to perform the corresponding control operation based on the control instruction comprises: When the control instruction is a door opening control instruction and the device to be controlled is a vehicle, sending the door opening control instruction to a car key control module in the vehicle, so that the car key control module performs a door opening control action based on the door opening control instruction; or, When the control instruction is a door closing control instruction and the device to be controlled is a vehicle, the door closing control instruction is sent to a car key control module in the vehicle, so that the car key control module performs a door closing control action based on the door closing control instruction. 5. The method according to claim 1, further comprising: Based on a preset detection module, detecting the monitoring parameters corresponding to the sensor; Comparing the monitoring parameters with preset reference parameters according to a preset period to obtain a matching degree; When the matching degree is greater than or equal to a preset threshold, the monitoring parameters are synchronously sent to the mobile client; When the matching degree is less than the preset threshold, an early warning prompt is issued. 6. The method according to claim 1, characterized in that after obtaining the sensor data currently collected by the ring worn by the human body, it also includes: detecting whether the sensor data is valid; If the sensor data is invalid, the sensor data is discarded. 7. The method according to claim 1, further comprising: Receive emergency alarm information sent by the vehicle, and control the wearable device to vibrate and increase the temperature according to the emergency alarm information. 8. The method according to claim 1, further comprising: Receive sensing instructions sent by the cloud server; processing the sensing instruction to determine an identifier of a target device contained in the sensing instruction; Determining whether the identifier is a target identifier; If the identifier is the target identifier, the wearable device is controlled to operate according to the target setting method. 9. The method according to claim 1, wherein the wearable device is a ring, the device to be controlled is a vehicle, and the controlling the device to be controlled to perform the corresponding control operation based on the control instruction comprises: Based on the wearable device, monitoring the wearer's heart rate characteristics, comparing them with a pre-stored heart rate template, and determining whether the wearer is a target user; If the wearer is the target user, the ring and the vehicle are authenticated using a key; If the identity authentication is passed, the control instruction is sent to the vehicle in a preset anti-interference manner to execute the corresponding control operation. 10. A multifunctional wearable device and a vehicle control and health data processing device, comprising: an acquisition module, configured to acquire sensor data currently collected by a wearable device worn by a human body, wherein the sensor data includes at least motion data; a first analysis module, configured to analyze the motion data to determine whether the motion data is a non-accidental touch gesture; A second analysis module is configured to analyze the to-be-controlled device and the control operation associated with the action data to generate a control instruction when the action data is a non-accidental touch gesture action; The control module is used to control the device to be controlled to perform the corresponding control operation based on the control instruction.