A wearable device with automatic wearing detection and implementation method

Abstract

The present invention provides a wearable device with automatic wearing detection and an implementation method. The present invention is a wearable device with automatic wearing detection, which determines whether the user is wearing the wearable device by comparing the built-in temperature and external temperature of the device. In terms of method, the present invention also determines whether the user is wearing the wearable device by comparing the internal and external temperature difference through this implementation method. The temperature sensor of the present invention is much higher than the infrared sensor in sensitivity and accuracy, and the wearing monitoring is more accurate. The temperature sensor has low power consumption and can work throughout the whole process to realize real-time wearing monitoring. The temperature sensor is small in size and can be easily integrated into the wearable device, so that the wearing monitoring is convenient and reliable. It is more suitable for the wide application of wearable device wearing monitoring, is less affected by light intensity and skin color, and is applicable to a wider range of scenarios and personnel.

Description

Technical Field

[0001] The present invention relates to the field of intelligent wearable technology, and in particular to a wearable device with automatic wearing detection and an implementation method thereof. Background Art

[0002] At present, wearable devices refer to portable devices that can be worn directly on the human body or integrated into the user's clothes or accessories. Wearable devices are mostly in the form of portable accessories with some computing functions that can be connected to mobile phones and various terminals. The mainstream product forms include wrist-supported watches (including watches and wristbands), foot-supported shoes (including shoes, socks or other leg-worn products in the future), head-supported glasses (including glasses, helmets, headbands, etc.), and various non-mainstream product forms such as smart clothing, school bags, crutches, accessories, etc. With the popularization of intelligent and portable wearable devices, they have been widely used as personnel data collection terminals in different industries, realizing more intelligent personnel management, health monitoring, intelligent interaction and other application scenario solutions.

[0003] Pedometer wearable devices mainly use accelerometers to achieve motion step counting. Through this accelerometer, the acceleration of the bracelet in multiple different directions can be measured. By calculating the value of acceleration, the number of steps walked can be roughly measured. According to the standard wearing position of the human body, combined with the algorithm generated by the big data model, the movement form and the number of steps of the person can be accurately measured. Wearable devices such as heart rate chest wear, armband or bracelet mainly use optical heart rate sensors to detect changes in the human heart rate and pulse. It uses electro-photosolvent pulse wave recording (PPG) to measure heart rate and other biometric indicators. The light of the optical heart rate sensor is emitted to the skin through the capacitive light of the optical heart rate sensor, and the light reflected back through the skin tissue is received by the photosensitive sensor and converted into an electrical signal, which is then converted into a digital signal, and then the heart rate is calculated according to the absorbance of the blood. The simplified measurement process is: emission of light - conversion into electrical signal - conversion into digital signal. In the parts of the human body where the skin is thin and easy to wear, the emitted light of the optical heart rate sensor is more likely to penetrate the skin and capture the refracted light, thereby improving the accuracy of heart rate measurement. During measurement, the optical heart rate sensor needs to be fixed close to the skin, so it is more suitable to wear it on the wrist during strenuous exercise.

[0004] Whether a person is wearing a wearable device is determined by different types of built-in sensors in various wearable devices. There are two main forms: one is to determine whether the device is worn after obtaining data through sensor detection at a fixed frequency or under specific conditions; the other is to determine whether the device is worn in real time by obtaining data through full-time monitoring by sensors.

[0005] However, the prior art has the following defects:

[0006] Optical heart rate sensors consume a lot of power, and continuous monitoring will increase the charging frequency of wearable devices;

[0007] Wearing detection is inaccurate when the optical heart rate sensor is blocked by non-skin objects;

[0008] Optical heart rate sensors are affected by skin color, sweat and strong light, which can affect the accuracy of wearing monitoring.

[0009] The optical heart rate sensor is not accurate enough when worn with an accelerometer.

[0010] The optical heart rate sensor combined with the infrared optical sensor has high wearable monitoring accuracy, but it is difficult to implement and has high hardware costs. Summary of the invention

[0011] The present invention provides a wearable device with automatic wearing detection and an implementation method, so as to solve the above technical problems.

[0012] A wearable device with automatic wearing detection, comprising:

[0013] Wearable device housing;

[0014] Built-in temperature sensor, set inside the wearable device housing to obtain internal temperature;

[0015] An external temperature sensor is arranged outside the housing of the wearable device to obtain the external temperature;

[0016] The optical heart rate sensor is placed outside the wearable device housing to obtain heart rate and temperature;

[0017] A computing component is connected to the built-in temperature sensor, the external temperature sensor and the optical heart rate sensor, and performs wearing detection by comparing the internal and external temperatures to determine whether the wearable device is worn, and determines whether the wearable device is worn based on the heart rate detection result;

[0018] The communication unit is arranged inside the housing of the wearable device, controls the data transmission of the built-in temperature sensor, the external temperature sensor and the computing component, and performs external communication.

[0019] Preferably, the wearable device housing further includes:

[0020] A memory, connected to the computing component and storing the detection data and calculation data of the wearable device;

[0021] The input-output component includes a display screen unit and an audio input-output unit, wherein the display screen unit and the audio input-output unit are connected to the computing component; wherein,

[0022] The display screen unit is used to display the body detection information of the sensor assembly, the temperature data of the built-in temperature sensor and the external temperature sensor;

[0023] The sensor component is connected to the computing component and is used to monitor the user's body through a variety of sensor devices to obtain dynamic data of the user's body; wherein,

[0024] The multiple sensing devices include at least: a gravity acceleration sensor, an optical heart rate sensor, an electrode heart rate sensor, a blood oxygen sensor, and an infrared sensor.

[0025] Preferably, the wearable device shell is a sealed waterproof shell, and the shell material of the sealed waterproof shell is a non-metallic material with poor thermal conductivity.

[0026] Preferably, the wearable device housing is also provided with a device wearing fixing accessory; wherein,

[0027] The equipment wearing and fixing accessories include but are not limited to: wristband, armband, chest strap, headband, and anklet.

[0028] Preferably, the communication unit comprises:

[0029] The FPGA module is used to receive sensor data, send the sensor data of the sensor device to the microprocessor, perform digital-to-analog conversion according to the timing of the sensor data, and then send it to the computing component;

[0030] A microprocessor, used for sensing data and analyzing and processing it for display and broadcasting by the display unit and the audio input and output unit, and sending it to the network communication module;

[0031] The network communication module is used to receive the sensor data sent by the microprocessor and send it to the target network server; wherein,

[0032] The network communication module also includes an external wireless communication device; wherein,

[0033] The external wireless communication unit includes: a WIFI device not limited to 2.4 GHz frequency, a Bluetooth device, a ZIGBEE device and a GPRS communication device;

[0034] The wireless communication unit complies with but is not limited to: 2.4G HZ frequency WIFI protocol, Bluetooth protocol, ZIGBEE protocol, GPRS protocol, 3G protocol, 4G protocol, 5G protocol, LORA protocol, NBIOT protocol;

[0035] A clock circuit is used to provide an operating clock for the microprocessor;

[0036] A memory for storing data received and processed by the microprocessor;

[0037] Interface circuit, used to realize data interaction with peripheral devices.

[0038] Preferably, the computing component is also used to calibrate the sensor data, which comprises the following steps:

[0039] According to the temperature data of the built-in temperature sensor, a first change relationship curve based on time series transformation is established;

[0040] Generate a first sensing curve of the sensing data by performing time-series correspondence between the first variation relationship curve and the sensing data of the sensing component;

[0041] According to the temperature data of the external temperature sensor, a second change relationship curve based on time series transformation is established;

[0042] The first change relationship curve and the second change relationship curve are processed into tiny line segments to obtain mutation points in the relationship curves, and constraint conditions are set according to geometric features of different temperature data;

[0043] Compare the mutation points according to the constraint conditions to determine the mutation time point;

[0044] According to the mutation time point, different sensor data are detected to determine whether there is a mutation;

[0045] When mutations are present, the sensing data are corrected;

[0046] When no mutation exists, the sensor data is labeled as trustworthy.

[0047] A method for realizing automatic wearing detection of a wearable device, the method comprising:

[0048] Acquiring first temperature information of a human body according to the built-in temperature sensor;

[0049] Acquiring second temperature information of a human body according to the external temperature sensor;

[0050] The first temperature information and the second temperature information are compared to generate a first wearing judgment result; wherein,

[0051] The first wearing judgment result includes: when the second temperature information is greater than the first temperature information, it indicates that the wearable device is worn; when the second temperature information is less than the first temperature information, it indicates that the wearable device is not worn;

[0052] According to the heart rate sensor, heart rate data is obtained, and a second wearing judgment result is generated according to the heart rate data; wherein,

[0053] The second wearing judgment result is: when the heart rate data exists, it indicates that the wearable device is worn; when the heart rate data does not exist, it indicates that the wearable device is not worn.

[0054] Preferably, the method further comprises:

[0055] generating a first temperature curve according to the first temperature information;

[0056] generating a second temperature curve according to the second temperature information;

[0057] Fitting the discrete temperature data of the first temperature curve and the second temperature curve to obtain a fitted temperature curve;

[0058] Mark the discrete temperature data whose distance from the corresponding fitted temperature curve is greater than a set threshold;

[0059] According to the mark, the erroneous temperature data detected by the wearable device at different times are determined.

[0060] Preferably, the method further comprises:

[0061] Collect optical heart rate signals through an optical heart rate sensor;

[0062] Performing filtering processing on the optical heart rate signal;

[0063] Selecting a signal segment of a preset length from the optical heart rate signal, and using an affinity propagation clustering algorithm to perform self-learning of a template from the signal segment to obtain an optical heart rate signal template;

[0064] The optical heart rate signal is continuously slid to the right on the optical heart rate signal template, and the highest point of each heartbeat of the optical heart rate signal is found according to the correlation to calculate the heart rate.

[0065] Preferably, the method further comprises:

[0066] After being powered on, the computing component establishes connections with different sensor devices through the communication unit. The host computer configures the computing component as a sensor node and initializes various communication services.

[0067] Create a timer task to collect sensor data regularly and store it in the storage module;

[0068] After receiving the sensor data, by building a user's vital signs model;

[0069] Through the vital signs model, the user's life status is detected and the life status information is output in real time.

[0070] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0071] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0073] Figure 1 A wearable device structure with automatic wearing detection in an embodiment of the present invention;

[0074] Figure 2 The present invention is a flowchart of a wearable device detection method for automatic wearing detection in an embodiment of the present invention. DETAILED DESCRIPTION

[0075] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0076] In the prior art: currently wearable devices mainly determine whether a person is wearing the device based on detecting whether there is a heart rate value; wearable devices detect the heart rate of the human body mainly by using optical heart rate sensors. When the optical heart rate sensor cannot detect the heart rate data, it is judged that the device is not worn correctly on the human body. The principle is: the optical heart rate sensor emits light to the skin tissue, and the light reflected back through the skin tissue is received by the photosensitive sensor and converted into an electrical signal, and the heart rate value can be obtained after data processing. If the wearable device is not worn on the human body, the optical heart rate sensor is not blocked. After the optical heart rate sensor emits light, the photosensitive sensor will not receive the reflected light, so the heart rate value cannot be measured, and the wearable device is judged to be not worn.

[0077] Since the optical heart rate sensor is a high-power component for wearable devices, in order to consider the battery life of wearable devices, the optical heart rate sensor cannot work continuously to monitor whether the user is wearing it. The common solution is to start the optical heart rate sensor at a fixed time period to detect whether there is a heart rate value to determine whether it is worn. Or cooperate with the acceleration sensor to drive the optical heart rate sensor to work. When the acceleration sensor detects that the device has a specific action, the optical heart rate sensor is started. At this time, if no heart rate value is detected, it is determined that the device is not worn. Obviously, neither of the two solutions can continuously monitor the heart rate in real time to determine whether it is worn. The best solution at present is to embed an infrared optical sensor in the optical heart rate sensor to cooperate with monitoring to realize wearing judgment. The principle is: the working power consumption of the infrared optical sensor is much lower than that of the optical heart rate sensor, so the infrared optical sensor can work continuously and uninterruptedly in the wearable device. Because the infrared optical sensor is sensitive to objects that have temperature and can radiate infrared light, when the infrared optical sensor detects an object close to the object that can radiate infrared light, it drives the optical heart rate sensor to detect the heart rate. If the heart rate is detected, it is judged as normal wearing, and the infrared optical sensor stops working. If the heart rate is not detected, it is judged as not being worn, and the infrared optical sensor is started to continue detecting. This can be repeated to achieve real-time monitoring of the wearing of wearable devices.

[0078] As attached Figure 1 As shown, a wearable device with automatic wearing detection includes:

[0079] Wearable device housing;

[0080] Built-in temperature sensor, set inside the wearable device housing to obtain internal temperature;

[0081] An external temperature sensor is arranged outside the housing of the wearable device to obtain the external temperature;

[0082] The optical heart rate sensor is placed outside the wearable device housing to obtain heart rate and temperature;

[0083] A computing component is connected to the built-in temperature sensor, the external temperature sensor and the optical heart rate sensor, and performs wearing detection by comparing the internal and external temperatures to determine whether the wearable device is worn, and determines whether the wearable device is worn based on the heart rate detection result;

[0084] The communication unit is arranged inside the housing of the wearable device, controls the data transmission of the built-in temperature sensor, the external temperature sensor and the computing component, and performs external communication.

[0085] In the above technical scheme: the present invention provides a method of realizing intelligent wear detection of wearable devices by comparing internal and external temperatures. In the prior art, when wearable devices are used as personnel identification and vital sign data collection terminals, they need to be correctly worn on the human body to obtain accurate data. Pedometer bracelets can also monitor pedometer data when they are not worn on the wrist, and heart rate armbands or bracelets can also measure heart rate data when they are not worn on the human body. Especially in the application scenarios of large-scale intelligent personnel management in various industries, how to judge whether personnel wear the equipment correctly, whether they are out of supervision, and how to improve the authenticity, reliability and accuracy of various data collection. The present invention performs wearing detection by comparing internal and external temperatures and heart rate detection to determine whether the user is wearing the wearable device normally. The present invention monitors the temperature in real time through the built-in temperature sensor and the external temperature sensor, and monitors and judges whether it is worn based on the difference between the temperature value in the wearable device and the temperature value of the human skin. The present invention realizes the wearing monitoring of the wearable device through a low-cost and low-power temperature sensor, and can realize the wearing monitoring of the wearable device without being affected by strong light and skin color factors. Of course, there may be judgment deviations under high temperature conditions. At this time, the temperature sensor and the heart rate sensor cooperate to monitor and realize the wearing monitoring in a high temperature environment. The optical heart rate sensor is one of the most popular sensors for heart rate detection in smart wearable devices. It uses electro-photosolvent pulse wave tracing (PPG) to measure heart rate and other biometric indicators. Measurement principle: The light is emitted to the skin through the capacitor, and the light reflected back through the skin tissue is received by the photosensitive sensor and converted into an electrical signal, which is then converted into a digital signal, and the heart rate is calculated based on the absorbance of the blood. The simplified measurement process is: emit light - convert into an electrical signal - convert into a digital signal.

[0086] Preferably, as attached Figure 1 As shown, the wearable device housing also includes:

[0087] A memory, connected to the computing component and storing the detection data and calculation data of the wearable device;

[0088] The input and output component includes a display screen unit and an audio input and output unit, wherein the display screen unit and the audio input and output unit are connected to the computing component; wherein,

[0089] The display screen unit is used to display the body detection information of the sensor assembly, the temperature data of the built-in temperature sensor and the external temperature sensor;

[0090] The sensor component is connected to the computing component and is used to monitor the user's body through a variety of sensor devices to obtain dynamic data of the user's body; wherein,

[0091] The multiple sensing devices include at least: a gravity acceleration sensor, an optical heart rate sensor, an electrode heart rate sensor, a blood oxygen sensor, and an infrared sensor.

[0092] In addition to wearing detection, the present invention is mainly used to obtain sensor data of the user's body. In this process, the present invention monitors the user's body in real time through the sensor component, and realizes the display of different data through the input and output components, and accepts the user's voice control.

[0093] Preferably, the wearable device shell is a sealed waterproof shell, and the shell material of the sealed waterproof shell is a non-metallic material with poor thermal conductivity.

[0094] The present invention also needs to be provided with a sealed waterproof shell because the present invention needs to adapt to different environments, and the use of non-metallic materials with poor thermal conductivity is because it is necessary to ensure the accuracy of temperature monitoring and accurately determine the deviation of internal and external temperatures.

[0095] Preferably, the wearable device housing is also provided with a device wearing fixing accessory; wherein,

[0096] The equipment wearing and fixing accessories include but are not limited to: wristband, armband, chest strap, headband, and anklet.

[0097] Preferably, the communication unit comprises:

[0098] The FPGA module is used to receive sensor data, send the sensor data of the sensor device to the microprocessor, perform digital-to-analog conversion according to the timing of the sensor data, and then send it to the computing component;

[0099] A microprocessor, used for sensing data and analyzing and processing it for display and broadcasting by the display unit and the audio input and output unit, and sending it to the network communication module;

[0100] The network communication module is used to receive the sensor data sent by the microprocessor and send it to the target network server; wherein,

[0101] The network communication module also includes an external wireless communication device; wherein,

[0102] The external wireless communication unit includes: a WIFI device not limited to 2.4 GHz frequency, a Bluetooth device, a ZIGBEE device and a GPRS communication device;

[0103] The wireless communication unit complies with but is not limited to: 2.4G HZ frequency WIFI protocol, Bluetooth protocol, ZIGBEE protocol, GPRS protocol, 3G protocol, 4G protocol, 5G protocol, LORA protocol, NBIOT protocol;

[0104] A clock circuit is used to provide an operating clock for the microprocessor;

[0105] A memory for storing data received and processed by the microprocessor;

[0106] Interface circuit, used to realize data interaction with peripheral devices.

[0107] In the above technical scheme, the present invention processes and forwards the sensor data through the FPGA module during communication, the microprocessor parses the data into audio data and display data, and the network communication module is used to realize data transmission through a variety of wireless communication devices and a variety of wireless communication protocols.

[0108] Preferably, the computing component is also used to calibrate the sensor data, which comprises the following steps:

[0109] According to the temperature data of the built-in temperature sensor, a first change relationship curve based on time series transformation is established;

[0110] Generate a first sensing curve of the sensing data by performing time-series correspondence between the first variation relationship curve and the sensing data of the sensing component;

[0111] According to the temperature data of the external temperature sensor, a second change relationship curve based on time series transformation is established;

[0112] The first change relationship curve and the second change relationship curve are processed into tiny line segments to obtain mutation points in the relationship curves, and constraint conditions are set according to geometric features of different temperature data;

[0113] Compare the mutation points according to the constraint conditions to determine the mutation time point;

[0114] According to the mutation time point, different sensor data are detected to determine whether there is a mutation;

[0115] When mutations are present, the sensing data are corrected;

[0116] When no mutation exists, the sensor data is labeled as trustworthy.

[0117] In the present invention, different data sensing curves are established to realize the judgment of temperature changes through different data sensing curves. When the temperature changes, there are several mutation points of change, for example, when the wearable device is taken off, or when the wearable device is lost. Then, the error of the temperature data is judged through the mutation time points of these time periods, and the sensor data is corrected and credibly marked through the error of the temperature data.

[0118] A method for realizing automatic wearing detection of a wearable device, the method comprising:

[0119] Acquiring first temperature information of a human body according to the built-in temperature sensor;

[0120] Acquiring second temperature information of a human body according to the external temperature sensor;

[0121] The first temperature information and the second temperature information are compared to generate a first wearing judgment result; wherein,

[0122] The first wearing judgment result includes: when the second temperature information is greater than the first temperature information, it indicates that the wearable device is worn; when the second temperature information is less than the first temperature information, it indicates that the wearable device is not worn;

[0123] According to the heart rate sensor, heart rate data is obtained, and a second wearing judgment result is generated according to the heart rate data; wherein,

[0124] The second wearing judgment result is: when the heart rate data exists, it indicates that the wearable device is worn; when the heart rate data does not exist, it indicates that the wearable device is not worn.

[0125] The method adopted by the present invention also performs temperature comparison and heart rate monitoring.

[0126] Preferably, the method further comprises:

[0127] generating a first temperature curve according to the first temperature information;

[0128] generating a second temperature curve according to the second temperature information;

[0129] Fitting the discrete temperature data of the first temperature curve and the second temperature curve to obtain a fitted temperature curve;

[0130] Mark the discrete temperature data whose distance from the corresponding fitted temperature curve is greater than a set threshold;

[0131] According to the mark, the temperature data detected by the wearable device at different times is determined, and the temperature difference is used to determine whether the wearable device is not worn. Figure 2 As shown in the figure, in the daily human activity environment, the suitable temperature is about -10℃ to +30℃, and the surface temperature of human skin is between +33.5℃ and +37℃. The temperature sensor is a simple electronic component with low power consumption, low cost and continuous and reliable operation. It is very sensitive to the temperature change detection of the environment, with an accuracy within ±0.1℃.

[0132] When the wearable device temperature sensor 2 is not in contact with human skin, the temperature value monitored by the built-in temperature sensor 1 is the external ambient temperature value of the shell conducted by the shell. In addition, the built-in temperature sensor is in a small and closed space of the shell, and the electronic components inside the shell will generate heat when working, resulting in the temperature value monitored by the built-in temperature sensor 1 being about 0.3℃-0.5℃ higher than the ambient air temperature value outside the shell. When the external temperature sensor 2 is not worn, it is exposed to the ambient air outside the shell, and the heat dissipation conditions are good, so the temperature value monitored is the actual ambient air temperature value outside the shell. At this time, the temperature of the temperature sensor 1 is greater than the temperature of the temperature sensor 2, and the wearable device determines that the device is not worn on the human body after monitoring.

[0133] When the temperature sensor 2 is in contact with human skin, the temperature value of the temperature sensor 2 changes rapidly to the same temperature value as the skin after contacting the skin. The close contact between the temperature sensor 2 and the skin makes the heat dissipation condition of the temperature sensor 2 worse, and the temperature value of the temperature sensor 2 will be greater than the actual external ambient temperature value by 0.3℃-0.5℃. Since the human skin temperature is as low as 33℃, the monitoring value of the temperature sensor 2 is between 33.3℃-33.5℃; when the actual ambient temperature value is as high as 30℃, the detection value of the temperature sensor 1 is between 30.3℃-30.5℃; at this time, the temperature value monitored by the temperature sensor 2 is much greater than the temperature value monitored by the temperature sensor 1, and the wearable device is determined to be in the human wearing state after monitoring.

[0134] To sum up, when the temperature value monitored by the temperature sensor 1 is greater than the temperature value monitored by the temperature sensor 2, the wearable device determines that the wearable device is in a not-worn state; when the temperature value monitored by the temperature sensor 1 is less than the temperature value monitored by the temperature sensor 2, the wearable device determines that the wearable device is in a worn state.

[0135] Preferably, the method further comprises:

[0136] Collect optical heart rate signals through an optical heart rate sensor;

[0137] Performing filtering processing on the optical heart rate signal;

[0138] Selecting a signal segment of a preset length from the optical heart rate signal, and using an affinity propagation clustering algorithm to perform self-learning of a template from the signal segment to obtain an optical heart rate signal template;

[0139] The optical heart rate signal is continuously slid to the right on the optical heart rate signal template, and the highest point of each heartbeat of the optical heart rate signal is found according to the correlation to calculate the heart rate.

[0140] During the monitoring process, the present invention also includes using an optical heart rate signal to determine the highest point of the heart rate at different times, and judging whether a wearable device is worn based on the highest point of the heart rate signal.

[0141] Preferably, the method further comprises:

[0142] After being powered on, the computing component establishes connections with different sensor devices through the communication unit. The host computer configures the computing component as a sensor node and initializes various communication services.

[0143] Create a timer task to collect sensor data regularly and store it in the storage module;

[0144] After receiving the sensor data, by building a user's vital signs model;

[0145] Through the vital signs model, the user's life status is detected and the life status information is output in real time.

[0146] The main purpose of the present invention is to realize the detection of life status through wearable devices. During this detection process, the present invention establishes a detection model of vital signs and records the life status information at all times through the detection model.

[0147] In an optional embodiment of the present invention, the built-in temperature sensor and the external temperature sensor further include the following detection steps: comparing the temperature data of the built-in temperature sensor and the external temperature sensor within a certain time series to generate a comparison chart; the comparison chart is in the form of a line chart, and the two lines in it represent the built-in temperature sensor and the external temperature sensor respectively;

[0148] Step 1: Perform edge detection on the image data at each moment. First, perform comparison calculation on the image at each moment:

[0149]

[0150] in, Indicates the comparison value between the built-in temperature sensor and the external temperature sensor. express The gradient function of Represents the function corresponding to the coordinates of the built-in temperature sensor at each moment, express The gradient function of Represents the function corresponding to the coordinates of the external temperature sensor at each moment; Indicates an external temperature sensor; Indicates built-in temperature sensor;

[0151] The purpose of the above formula is mainly to obtain the comparison value of the built-in temperature sensor and the external temperature sensor at each moment. This comparison value has a certain gradient, which is the gradient of temperature change. It is used to indicate the temperature difference coefficient of the internal and external temperatures determined by this comparison value. The calculation result is also to make the temperature comparison difference in different peak interval time periods clearer in step 2.

[0152] Step 2: Calculate the fuzzy parameters of the built-in temperature sensor and the external temperature sensor in different peak time periods:

[0153]

[0154] in, Represents the mean value function of the built-in temperature sensor in different peak interval time periods, Different peak interval time periods; Represents the mean value function of the external temperature sensor in different peak interval time periods; The fuzzy parameter representing the average temperature difference between each peak of the built-in temperature sensor and the external temperature sensor, Respectively represent the values ​​of the horizontal and vertical coordinates of the built-in temperature sensor and the external temperature sensor at each corresponding moment;

[0155] The main purpose of the above formula is to calculate the fuzzy function of the average value in different peak interval time periods, because there is a certain temperature deviation in this temperature. Between different peak time periods, if the user is not wearing the inside and outside peak temperature difference is very large, and this fuzzy parameter also becomes very large, because as long as different peak time periods are brought in, it can be more clearly judged whether the wearable device is worn.

[0156] Step 3: Perform weighted processing on the temperature difference data of the built-in temperature sensor and the external temperature to obtain the weighted fuzzy parameters:

[0157]

[0158] in, The fuzzy parameter represents the temperature difference data of the built-in temperature sensor and the external temperature after weighted processing. The main purpose of the above formula is to make the temperature difference between the built-in temperature sensor and the external temperature sensor in different peak intervals at different coordinates more obvious through weighted calculation, so as to more easily trigger the wearing detection mechanism of the present invention and more easily detect whether the wearable device is worn.

[0159] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A wearable device with automatic wearing detection, characterized in that: include: Wearable device housing; Built-in temperature sensor, set inside the wearable device housing to obtain internal temperature; An external temperature sensor is arranged outside the housing of the wearable device to obtain the external temperature; An optical heart rate sensor is placed outside the wearable device housing to obtain heart rate and temperature; A computing component is connected to the built-in temperature sensor, the external temperature sensor and the optical heart rate sensor, and performs wearing detection by comparing the internal and external temperatures to determine whether the wearable device is worn, and determines whether the wearable device is worn based on the heart rate detection result; A communication unit, disposed inside the housing of the wearable device, controls data transmission of the built-in temperature sensor, the external temperature sensor and the computing component, and performs external communication; The built-in temperature sensor and the external temperature sensor also include the following detection steps: Step 1: Compare the temperature data of the built-in temperature sensor and the external temperature sensor within a certain time series to generate a comparison chart; Step 2: Perform edge detection on the image data at each moment and perform comparative calculation on the image at each moment; in, Indicates the comparison value between the built-in temperature sensor and the external temperature sensor. express The gradient function of Represents the function corresponding to the coordinates of the built-in temperature sensor at each moment, express The gradient function of Represents the function corresponding to the coordinates of the external temperature sensor at each moment; Indicates an external temperature sensor; Indicates built-in temperature sensor; Step 3: Calculate the fuzzy parameters of the built-in temperature sensor and the external temperature sensor in different peak time periods: in, Represents the mean value function of the built-in temperature sensor in different peak interval time periods, Different peak interval time periods; Represents the mean value function of the external temperature sensor in different peak interval time periods; The fuzzy parameter representing the average temperature difference between each peak of the built-in temperature sensor and the external temperature sensor, Respectively represent the values ​​of the horizontal and vertical coordinates of the built-in temperature sensor and the external temperature sensor at each corresponding moment; Step 4: Perform weighted processing on the temperature difference data of the built-in temperature sensor and the external temperature to obtain the weighted fuzzy parameters: in, Represents the fuzzy parameter after weighted processing of the temperature difference data between the built-in temperature sensor and the external temperature; Step 5: According to the weighted fuzzy parameters, determine the temperature difference between the built-in temperature sensor and the external temperature sensor at different peak intervals at different coordinates.

2. A wearable device with automatic wearing detection as claimed in claim 1, characterized in that: The wearable device housing also includes: A memory, connected to the computing component and storing the detection data and calculation data of the wearable device; The input and output component includes a display screen unit and an audio input and output unit, wherein the display screen unit and the audio input and output unit are connected to the computing component; wherein, The display screen unit is used to display the body detection information of the sensor assembly, the temperature data of the built-in temperature sensor and the external temperature sensor; The sensor component is connected to the computing component and is used to monitor the user's body through a variety of sensor devices to obtain dynamic data of the user's body; wherein, The multiple sensing devices include at least: a gravity acceleration sensor, an optical heart rate sensor, an electrode heart rate sensor, a blood oxygen sensor, and an infrared sensor.

3. A wearable device with automatic wearing detection as claimed in claim 1, characterized in that: The wearable device shell is a sealed waterproof shell, and the shell material of the sealed waterproof shell is a non-metallic material with poor thermal conductivity.

4. A wearable device with automatic wearing detection as claimed in claim 1, characterized in that: The wearable device housing is also provided with a device wearing fixing accessory; wherein, The equipment wearing and fixing accessories include: wristband, armband, chest strap, headband and anklet.

5. A wearable device with automatic wearing detection as claimed in claim 1, characterized in that: The communication unit comprises: The FPGA module is used to receive sensor data, send the sensor data of the sensor device to the microprocessor, perform digital-to-analog conversion according to the timing of the sensor data, and then send it to the computing component; A microprocessor, used for sensing data and analyzing and processing it for display and broadcasting by the display unit and the audio input and output unit, and sending it to the network communication module; The network communication module is used to receive the sensor data sent by the microprocessor and send it to the target network server; wherein, The network communication module also includes an external wireless communication device; wherein, The external wireless communication device includes: a WIFI device, a Bluetooth device, a ZIGBEE device and a GPRS communication device; The external wireless communication device complies with: WIFI protocol, Bluetooth protocol, ZIGBEE protocol, GPRS protocol, 3G protocol, 4G protocol, 5G protocol, LORA protocol, NBIOT protocol; A clock circuit is used to provide an operating clock for the microprocessor; A memory for storing data received and processed by the microprocessor; Interface circuit, used to realize data interaction with peripheral devices.

6. A wearable device with automatic wearing detection as claimed in claim 2, characterized in that: The computing component is also used to calibrate the sensor data, which includes the following steps: According to the temperature data of the built-in temperature sensor, a first change relationship curve based on time series transformation is established; Generate a first sensing curve of the sensing data by performing time-series correspondence between the first variation relationship curve and the sensing data of the sensing component; According to the temperature data of the external temperature sensor, a second change relationship curve based on time series transformation is established; The first change relationship curve and the second change relationship curve are processed into tiny line segments to obtain mutation points in the relationship curves, and constraint conditions are set according to geometric features of different temperature data; Compare the mutation points according to the constraint conditions to determine the mutation time point; According to the mutation time point, different sensor data are detected to determine whether there is a mutation; When mutations are present, the sensing data are corrected; When no mutation exists, the sensor data is labeled as trustworthy.

7. A method for implementing an automatic wearing detection wearable device, applicable to a wearable device with automatic wearing detection as claimed in any one of claims 1 to 6, characterized in that: The method comprises: Acquiring first temperature information of a human body according to the built-in temperature sensor; Acquiring second temperature information of a human body according to the external temperature sensor; The first temperature information and the second temperature information are compared to generate a first wearing judgment result; wherein, The first wearing judgment result includes: when the second temperature information is greater than the first temperature information, it indicates that the wearable device is worn; when the second temperature information is less than the first temperature information, it indicates that the wearable device is not worn; According to the heart rate sensor, heart rate data is obtained, and a second wearing judgment result is generated according to the heart rate data; wherein, The second wearing judgment result is: when the heart rate data exists, it indicates that the wearable device is worn; when the heart rate data does not exist, it indicates that the wearable device is not worn.

8. A method for realizing automatic wearing detection of a wearable device as claimed in claim 7, characterized in that: The method further comprises: generating a first temperature curve according to the first temperature information; generating a second temperature curve according to the second temperature information; Fitting the discrete temperature data of the first temperature curve and the second temperature curve to obtain a fitted temperature curve; Mark the discrete temperature data whose distance from the corresponding fitted temperature curve is greater than a set threshold; According to the mark, the erroneous temperature data detected by the wearable device at different times are determined.

9. A method for realizing automatic wearing detection of a wearable device as claimed in claim 7, characterized in that: The method further comprises: Collect optical heart rate signals through an optical heart rate sensor; Performing filtering processing on the optical heart rate signal; Selecting a signal segment of a preset length from the optical heart rate signal, and using an affinity propagation clustering algorithm to perform self-learning of a template from the signal segment to obtain an optical heart rate signal template; The optical heart rate signal is continuously slid to the right on the optical heart rate signal template, and the highest point of each heartbeat of the optical heart rate signal is found according to the correlation to calculate the heart rate.

10. A method for realizing automatic wearing detection of a wearable device as claimed in claim 7, characterized in that: The method further comprises: After being powered on, the computing component establishes connections with different sensor devices through the communication unit. The host computer configures the computing component as a sensor node and initializes various communication services. Create a timer task to collect sensor data regularly and store it in the storage module; After receiving the sensor data, by building a user's vital signs model; Through the vital signs model, the user's life status is detected and the life status information is output in real time.

Images