Intelligent bracelet with skin impedance detection function and emotion recognition system

Abstract

The invention provides an intelligent bracelet with a skin impedance detection function and an emotion recognition system, and relates to the field of emotion recognized.The intelligent bracelet comprises a shell, a main control board, a sensor board, a displayer and a lithium battery, the main control board, the sensor board, the displayer and the lithium battery are arranged on the shell, and the lithium battery is used for supplying power to the main control board, the sensor board and the displayer; the sensor board is electrically connected with the input end of the main control board; the display is electrically connected with the output end of the main control board; the main control board comprises a main control chip, a galvanic skin impedance detection assembly, a body temperature detection assembly, a storage chip, a battery management assembly and a motion detection chip, the galvanic skin impedance detection assembly, the body temperature detection assembly, the storage chip, the battery management assembly and the motion detection chip are all electrically connected with the main control chip, the battery management assembly is electrically connected with the lithium battery, and the lithium battery is electrically connected with the storage chip. The method has the advantage of realizing real-time and continuous monitoring of the emotional state of the autistic child.

Description

Technical Field

[0001] The present invention relates to the field of emotion recognition, and in particular to a smart bracelet with skin electrical impedance detection function and an emotion recognition system. Background Art

[0002] Autism spectrum disorder (Asperger Syndrome, ASD) is a complex neurodevelopmental disorder, mainly manifested by social communication disorders, narrow interests and repetitive stereotyped behaviors. Children with autism often have difficulty expressing and managing their emotions, which makes it difficult for parents and teachers to understand their inner emotional state, thus affecting effective intervention and support for their behavior. With the development of science and technology, more and more studies have begun to explore the use of physiological signal monitoring to assess the emotional state of children with autism.

[0003] Galvanic Skin Response (GSR) refers to the change in the conductivity of the skin when the psychological or physiological state changes, reflecting the activity level of the autonomic nervous system. Galvanic Skin Response has been widely used in emotion and stress assessment because it can sensitively reflect emotional arousal and stress response. Currently, there are a variety of devices that can measure galvanic skin impedance for emotion monitoring and psychological state assessment. However, these devices still have some limitations in practical applications: most existing wearable devices cannot simultaneously monitor galvanic skin impedance and other physiological parameters, such as skin temperature, heart rate, etc., and the comprehensive monitoring of these parameters is crucial for a comprehensive assessment of emotional state.

[0004] Therefore, it is necessary to provide a smart bracelet with skin impedance detection function and an emotion recognition system to achieve real-time and continuous monitoring of the emotional state of autistic children. Summary of the invention

[0005] The present invention provides a smart bracelet with a skin-electric impedance detection function, comprising a shell and a main control board, a sensor board, a display and a lithium battery arranged on the shell, wherein the lithium battery is used to power the main control board, the sensor board and the display, the sensor board is electrically connected to the input end of the main control board, and the display is electrically connected to the output end of the main control board; the main control board comprises a main control chip, a skin-electric impedance detection component, a body temperature detection component, a storage chip, a battery management component and a motion detection chip, wherein the skin-electric impedance detection component, the body temperature detection component, the storage chip, the battery management component and the motion detection chip are all electrically connected to the main control chip, and the battery management component is electrically connected to the lithium battery.

[0006] Furthermore, a skin-electrical impedance signal detector of the skin-electrical impedance detection component is arranged on the shell, and the skin-electrical impedance signal detector includes a first electrode and a second electrode, the first electrode serves as a skin-electrical impedance signal detection end, the second electrode is connected to the ground, and a transparent light window is arranged between the first electrode and the second electrode; the skin-electrical impedance detection unit also includes a first amplifier, a second amplifier, a third amplifier and an analog-to-digital converter, the first amplifier is a voltage follower, and a voltage reference signal is connected to the positive input end of the first amplifier after being divided by a first resistor and a second resistor, the second amplifier is a voltage follower, and a voltage reference signal is connected to the positive input end of the second amplifier after being divided by a third resistor and the skin-electrical impedance signal detector; the negative input end of the third amplifier is electrically connected to the output end of the first amplifier, the positive input end of the third amplifier is electrically connected to the output end of the second amplifier, and the analog-to-digital converter is electrically connected to the output end of the third amplifier, and the voltage signal output by the third amplifier is converted into a digital signal, and transmitted to the main control chip.

[0007] Furthermore, the sensor board includes a heart rate detection chip, an LED light and a temperature sensor, the heart rate detection chip is electrically connected to the main control chip, the temperature sensor is electrically connected to the body temperature detection component, and the LED light is electrically connected to the heart rate detection chip.

[0008] Furthermore, the smart bracelet with epithelial impedance detection function includes multiple working modes, wherein the multiple working modes include at least child mode, parent master mode and parent slave mode; when the smart bracelet with epithelial impedance detection function works in child mode, the Bluetooth of the smart bracelet with epithelial impedance detection function works in slave mode, and the collected epithelial impedance data, heart rate data, body temperature data and motion data are sent to other smart bracelets with epithelial impedance detection function working in parent master mode or Bluetooth adapter working in host mode; when the smart bracelet with epithelial impedance detection function works in parent master mode, the The Bluetooth of the smart bracelet with skin electrical impedance detection function works in host mode, communicates with other smart bracelets with skin electrical impedance detection function working in child mode, obtains skin electrical impedance data, heart rate data, body temperature data and motion data collected by other smart bracelets with skin electrical impedance detection function working in child mode, and displays them; when the smart bracelet with skin electrical impedance detection function works in parent slave mode, the Bluetooth of the smart bracelet with skin electrical impedance detection function works in slave mode, receives skin electrical impedance data, heart rate data, body temperature data and motion data transmitted by the Bluetooth adapter and / or computer working in host mode, and displays them.

[0009] The present invention provides an emotion recognition system, which is applied to the smart bracelet with skin electrical impedance detection function described in any one of claims 1 to 4, and includes: a mode determination module, which is used to obtain a mode setting instruction and determine the current working mode according to the mode setting instruction; an emotion recognition module, which is used to identify the real-time emotions of children based on the skin electrical impedance data, heart rate data, body temperature data and motion data collected by the smart bracelet with skin electrical impedance detection function when the current working mode is the child mode; the emotion recognition module is also used to receive the real-time emotions of children transmitted by other smart bracelets with skin electrical impedance detection function working in child mode when the current working mode is the parent master mode, and perform status warning based on the real-time emotions of children; the emotion recognition module is also used to receive the real-time emotions of children transmitted by a Bluetooth adapter and / or computer working in host mode when the current working mode is the parent slave mode, and perform status warning based on the real-time emotions of children.

[0010] Furthermore, the smart bracelet with skin electrical impedance detection function collects skin electrical impedance data, heart rate data, body temperature data and motion data, including: determining the skin electrical impedance based on the output voltage signal of the third amplifier of the skin electrical impedance detection unit; converting the voltage value output by the temperature sensor of the sensor board into body temperature data through a voltage-temperature conversion formula; obtaining heart rate data through the heart rate detection chip of the sensor board; obtaining acceleration value characteristic values ​​through the motion detection chip, wherein the motion data at least includes acceleration value characteristic values.

[0011] Furthermore, the epithelial impedance is calculated according to the following formula: ,in, is the output voltage signal of the third amplifier of the epielectric impedance detection unit, is the amplification factor of the third amplifier of the epielectric impedance detection unit, is the voltage reference signal, is the skin impedance, is the resistance value of the first resistor of the epithelial impedance detection unit, is the resistance value of the second resistor of the epithelial impedance detection unit, is the resistance value of the third resistor of the epithelial impedance detection unit.

[0012] Furthermore, the emotion recognition module identifies the real-time emotions of children based on the skin electrical impedance data, heart rate data, body temperature data and motion data collected by the smart bracelet with skin electrical impedance detection function, including: preprocessing the skin electrical impedance data, heart rate data, body temperature data and motion data to obtain preprocessed skin electrical impedance data, heart rate data, body temperature data and motion data; performing feature enhancement on the preprocessed skin electrical impedance data, heart rate data, body temperature data and motion data to obtain a feature-enhanced data set; obtaining an emotion pre-classification result based on the feature-enhanced data set through an emotion classification model; and performing Kalman filtering on the emotion pre-classification result to obtain the real-time emotions of children.

[0013] Furthermore, the emotion recognition module preprocesses the epidermal impedance data, heart rate data, body temperature data and motion data to obtain preprocessed epidermal impedance data, heart rate data, body temperature data and motion data, including: filtering the epidermal impedance data, heart rate data, body temperature data and motion data to filter out noise data, and generate filtered epidermal impedance data, heart rate data, body temperature data and motion data; using a sampling window to sample the filtered epidermal impedance data, heart rate data, body temperature data and motion data to generate multiple groups of data groups; for each group of the data groups, detecting the peak value of the data group, and extracting time domain features and frequency domain features according to the position of the peak value of the data group; normalizing the extracted time domain features and frequency domain features to obtain preprocessed epidermal impedance data, heart rate data, body temperature data and motion data.

[0014] Furthermore, the emotion recognition module performs feature enhancement on the preprocessed skin electrical impedance data, heart rate data, body temperature data and motion data to obtain a feature-enhanced data set, including: determining weight parameters of the preprocessed skin electrical impedance data, heart rate data and body temperature data according to the characteristic value of the acceleration value through a weight generation network; multiplying the weight parameters of the preprocessed skin electrical impedance data, heart rate data and body temperature data with the preprocessed skin electrical impedance data, heart rate data and body temperature data to obtain enhanced skin electrical impedance data, heart rate data and body temperature data.

[0015] Compared with the prior art, the smart bracelet with skin electrical impedance detection function and the emotion recognition system provided by the present invention have at least the following beneficial effects: 1. The skin impedance detection function can evaluate the user's skin moisture, subcutaneous fat and other physiological indicators, which helps to monitor the health of children with autism. At the same time, the temperature detection and motion detection functions provide comprehensive health data to help users better understand the physical condition of children with autism. The smart bracelet supports multiple working modes, including child mode, parent master mode and parent slave mode, which facilitates data sharing and monitoring among family members. The Bluetooth communication function enables the bracelet to seamlessly connect with other devices (such as other bracelets, Bluetooth adapters or computers) to achieve real-time data transmission and display. The battery management component ensures the endurance of the bracelet and reduces the trouble of frequent charging. As a power source, the lithium battery provides sufficient energy to support the normal operation of the bracelet. The display provides an intuitive data display, and the health data and emotional state of children with autism can be viewed at any time.

[0016] 2. Through the skin impedance data, heart rate data, body temperature data and movement data collected by the smart bracelet, the emotion recognition system can identify the real-time emotional state of the child in real time. In the parent master mode and parent slave mode, the system can receive and process emotional data from other bracelets or devices, provide parents with timely emotional state warnings, and help parents better understand their children's emotional changes. Parents can understand their children's emotional state more accurately based on the emotional data provided by the emotion recognition system, so as to provide personalized care and education. By monitoring the emotional changes of their children, parents can promptly discover and solve potential emotional problems and promote the healthy growth of their children. Emotional state is closely related to physical health. By monitoring emotional changes, parents can promptly discover possible health problems of their children, such as stress, anxiety, etc., and take corresponding preventive measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0018] Figure 1 It is a structural block diagram of a smart bracelet with skin electrical impedance detection function according to some embodiments of this specification; Figure 2 is a schematic diagram of the structure of a smart bracelet with skin electrical impedance detection function according to some embodiments of this specification; Figure 3 is a schematic diagram of the structure of the first electrode and the second electrode according to some embodiments of this specification; Figure 4 is a circuit diagram of a skin electrical impedance detection unit according to some embodiments of this specification; Figure 5is a schematic diagram of the structure of a sensor board according to some embodiments of this specification; Figure 6 It is a schematic diagram of smart bracelet networking according to some embodiments of this specification; Figure 7 is a schematic diagram of data interaction in a child mode according to some embodiments of this specification; Figure 8 is a schematic diagram of data interaction in a parent-master mode according to some embodiments of this specification; Fig. 9 is a schematic diagram of data interaction in a parent-slave mode according to some embodiments of this specification; Fig.10 is a schematic diagram of a process for collecting skin electrical impedance data, heart rate data, body temperature data and motion data according to some embodiments of this specification; Fig.11 is a schematic diagram of a process for identifying a child's real-time emotions according to some embodiments of this specification; Fig.12 is a schematic diagram of a process for preprocessing skin electrical impedance data, heart rate data, body temperature data and motion data according to some embodiments of this specification; Fig.13 It is a flowchart of generating a feature-enhanced data set according to some embodiments of this specification.

[0019] In the figure, 1. main control board; 2. sensor board; 3. display; 4. lithium battery; 5. shell; 51. first electrode; 52. second electrode; 53. transparent light window; 11. main control chip; 12. epithelial impedance detection component; 13. body temperature detection component; 14. storage chip; 15. motion detection chip; 16. battery management component; 121. first amplifier; 122. second amplifier; 123. third amplifier; 124. analog-to-digital converter; 21. heart rate detection chip; 22. temperature sensor; 23. first three-color LED light; 24. second three-color LED light; 25. first spring sheet; 26. second spring sheet. DETAILED DESCRIPTION

[0020] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0021] Figure 1is a structural block diagram of a smart wristband with skin electrical impedance detection function according to some embodiments of this specification, Figure 2 is a schematic diagram of the structure of a smart wristband with skin electrical impedance detection function according to some embodiments of this specification, such as Figure 1 and Figure 2 As shown, the smart bracelet with skin electrical impedance detection function includes a housing 5 and a main control board 1, a sensor board 2, a display 3 and a lithium battery 4 arranged on the housing 5, wherein the lithium battery 4 is used to power the main control board 1, the sensor board 2 and the display 3. The sensor board 2 is electrically connected to the input end of the main control board 1, and the display 3 is electrically connected to the output end of the main control board 1. The main control board 1 includes a main control chip 11, a skin electrical impedance detection component 12, a body temperature detection component 13, a storage chip 14, a battery management component 16 and a motion detection chip 15, wherein the skin electrical impedance detection component 12, the body temperature detection component 13, the storage chip 14, the battery management component 16 and the motion detection chip 15 are all electrically connected to the main control chip 11, and the battery management component 16 is electrically connected to the lithium battery 4.

[0022] Specifically, the main control chip 11 integrates a Bluetooth communication function. In this embodiment, the main control chip 11 may be nRF52840.

[0023] Figure 3 is a schematic diagram of the structure of the first electrode 51 and the second electrode 52 according to some embodiments of this specification, such as Figure 3 As shown, preferably, a skin-electric impedance signal detector of a skin-electric impedance detection component 12 is provided on the shell 5, and the skin-electric impedance signal detector includes a first electrode 51 and a second electrode 52, the first electrode 51 serves as a skin-electric impedance signal detection end, the second electrode 52 is connected to the ground, and a transparent light window 53 is provided between the first electrode 51 and the second electrode 52.

[0024] Figure 4 is a circuit diagram of a skin electrical impedance detection unit according to some embodiments of this specification, such as Figure 4As shown, preferably, the epi-electric impedance detection unit also includes a first amplifier 121, a second amplifier 122, a third amplifier 123 and an analog-to-digital converter 124. The first amplifier 121 is a voltage follower, and the voltage reference signal is connected to the positive input terminal of the first amplifier 121 after being divided by the first resistor and the second resistor. The second amplifier 122 is a voltage follower, and the voltage reference signal is connected to the positive input terminal of the second amplifier 122 after being divided by the third resistor and the epi-electric impedance signal detector; the negative input terminal of the third amplifier 123 is electrically connected to the output terminal of the first amplifier 121, the positive input terminal of the third amplifier 123 is electrically connected to the output terminal of the second amplifier 122, and the analog-to-digital converter 124 is electrically connected to the output terminal of the third amplifier 123, and the voltage signal output by the third amplifier 123 is converted into a digital signal, and transmitted to the main control chip 11.

[0025] Specifically, the voltage signal output by the third amplifier 123 is transmitted to the main control chip 11 via I2C. The first amplifier 121, the second amplifier 122, and the third amplifier 123 may be TLV9004, and the analog-to-digital converter 124 may be AD7685.

[0026] Preferably, the sensor board 2 includes a heart rate detection chip 21, an LED light and a temperature sensor 22. The heart rate detection chip 21 is electrically connected to the main control chip 11, the temperature sensor 22 is electrically connected to the body temperature detection component 13, and the LED light is electrically connected to the heart rate detection chip 21.

[0027] Specifically, the sensor board 2 includes a PPG (photoplethysmographic) heart rate detection chip 21, a first three-color LED lamp 23, a second three-color LED lamp 24, and a temperature sensor 22. The PPG heart rate detection chip is connected to the main control chip 11 through I2C, the temperature sensor 22 is electrically connected to the body temperature detection unit through an analog signal, and the first three-color LED lamp 23, the second three-color LED lamp 24 are electrically connected to the PPG heart rate detection chip.

[0028] Figure 5 is a schematic diagram of the structure of the sensor board 2 according to some embodiments of this specification, such as Figure 5As shown, a spring sheet (i.e., a first spring sheet 25 and a second spring sheet 26) is designed on each side of the sensor board 2, which is used to be electrically connected to the first electrode 51 and the second electrode 52 respectively. Further, the temperature sensor 22 is installed in the corresponding area mapped to the sensor board 2 by the first electrode 51, and is insulated and connected to the first electrode 51 through thermal conductive silicone. Preferably, the model of the PPG heart rate detection chip can be HX3918, the model of the first three-color LED lamp 23 and the second three-color LED lamp 24 can be HXLED-S006, and the model of the temperature sensor 22 can be NTC thermistor NCP15WF104F03RC.

[0029] The body temperature detection component 13 is composed of an operational amplifier, which is electrically connected to the main control chip 11 through an analog signal, and is used to amplify and filter the voltage signal detected by the temperature sensor 22, and transmit it to the main control chip 11. Further, the voltage signal is detected by an analog-to-digital converter 124 built into the main control chip 11. Preferably, the model of the operational amplifier can be TLV9004.

[0030] The storage chip 14 is connected to the main control chip 11 via SPI (Serial Peripheral Interface) and is used to store skin impedance data, heart rate data, body temperature data, motion data, etc. Preferably, the model of the storage chip 14 may be W25Q128JVPIQ.

[0031] The battery management component 16 includes a charging management chip and a fuel gauge. The fuel gauge is connected to the main control chip 11 via I2C to detect the battery power. The charging management chip is electrically connected to the lithium battery 4 to manage the charging of the lithium battery 4. Preferably, the model of the charging management chip may be LGS4084HB5, and the model of the fuel gauge may be MAX17048G.

[0032] The motion detection chip 15 is electrically connected to the main control chip 11 via I2C to detect the characteristic value of the acceleration value. Preferably, the model of the motion detection chip 15 can be LIS3DHTR.

[0033] The display 3 includes an AMOLED display screen and a touch screen. The AMOLED display screen and the main control chip 11 are connected via QSPI (Queued SPI), and the touch screen and the main control chip 11 are connected via I2C.

[0034] Figure 6 is a schematic diagram of a smart bracelet network according to some embodiments of this specification, such as Figure 6 As shown, multiple smart bracelets, Bluetooth adapters, mobile phones, computers, etc. with skin electrical impedance detection functions can communicate to form a data transmission network.

[0035] Preferably, the smart bracelet with skin electrical impedance detection function includes multiple working modes, wherein the multiple working modes at least include a child mode, a parent master mode and a parent slave mode.

[0036] Figure 7 is a schematic diagram of data interaction in a child mode according to some embodiments of this specification, such as Figure 7 As shown, when the smart bracelet with skin electrical impedance detection function works in child mode, the Bluetooth of the smart bracelet with skin electrical impedance detection function works in slave mode, and the collected skin electrical impedance data, heart rate data, body temperature data and motion data are sent to other smart bracelets with skin electrical impedance detection function working in parent master mode or Bluetooth adapters working in host mode.

[0037] Figure 8 is a schematic diagram of data interaction in a parent-host mode according to some embodiments of this specification, such as Figure 8 As shown, when the smart bracelet with skin electrical impedance detection function works in the parent host mode, the Bluetooth of the smart bracelet with skin electrical impedance detection function works in the host mode, communicates with other smart bracelets with skin electrical impedance detection function working in the child mode, obtains the skin electrical impedance data, heart rate data, body temperature data and motion data collected by other smart bracelets with skin electrical impedance detection function working in the child mode, and displays them.

[0038] Fig. 9 is a schematic diagram of data interaction in a parent-slave mode according to some embodiments of this specification, such as Fig. 9 As shown, when the smart bracelet with skin electrical impedance detection function works in the parent slave mode, the Bluetooth of the smart bracelet with skin electrical impedance detection function works in the slave mode, receives the skin electrical impedance data, heart rate data, body temperature data and exercise data transmitted by the Bluetooth adapter and / or computer working in the host mode, and displays them.

[0039] The emotion recognition system can be applied to the above-mentioned smart bracelet with skin electrical impedance detection function, including: A mode determination module, used to obtain a mode setting instruction and determine the current working mode according to the mode setting instruction; The emotion recognition module is used to identify the real-time emotions of children based on the skin impedance data, heart rate data, body temperature data and movement data collected by the smart bracelet with skin impedance detection function when the current working mode is the child mode; The emotion recognition module is also used to receive the real-time emotions of children transmitted by other smart bracelets with skin impedance detection function working in child mode when the current working mode is parent master mode, and to issue status warnings based on the real-time emotions of children, for example, to issue a warning to the user when the emotional state is in a bad state; The emotion recognition module is also used to receive the real-time emotions of children transmitted by the Bluetooth adapter and / or computer working in host mode when the current working mode is the parent slave mode, and to issue status warnings based on the real-time emotions of children. For example, when the emotional state is in a bad state, a warning is issued to the user.

[0040] Fig.10 is a flow chart of collecting skin electrical impedance data, heart rate data, body temperature data and motion data according to some embodiments of this specification, such as Fig.10 As shown, as a preferred embodiment, the smart bracelet with skin electrical impedance detection function collects skin electrical impedance data, heart rate data, body temperature data and motion data, including: Determine the epithelial impedance based on the output voltage signal of the third amplifier 123 of the epithelial impedance detection unit; The voltage value output by the temperature sensor 22 of the sensor board 2 is converted into body temperature data by a voltage-temperature conversion formula; Acquire heart rate data through the heart rate detection chip 21 of the sensor board 2; The acceleration value characteristic value is acquired through the motion detection chip 15, wherein the motion data at least includes the acceleration value characteristic value.

[0041] Specifically, the voltage-temperature conversion formula can be obtained from the manual of the selected temperature sensor 22 .

[0042] Preferably, the skin electrical impedance is calculated according to the following formula: in, is the output voltage signal of the third amplifier 123 of the epielectric impedance detection unit, is the amplification factor of the third amplifier 123 of the epithelial impedance detection unit, is the voltage reference signal, is the skin impedance, is the resistance value of the first resistor of the epithelial impedance detection unit, is the resistance value of the second resistor of the epithelial impedance detection unit, is the resistance value of the third resistor of the epielectric impedance detection unit.

[0043] Fig.11 is a schematic diagram of a process for identifying a child's real-time emotions according to some embodiments of this specification, such as Fig.11As shown, as a preferred embodiment, the emotion recognition module recognizes the real-time emotions of children based on the skin impedance data, heart rate data, body temperature data and movement data collected by the smart bracelet with skin impedance detection function, including: Preprocessing the skin electrical impedance data, heart rate data, body temperature data and motion data to obtain preprocessed skin electrical impedance data, heart rate data, body temperature data and motion data; Perform feature enhancement on the preprocessed skin electrical impedance data, heart rate data, body temperature data and motion data to obtain a feature-enhanced data set; The emotion classification model is used to obtain the emotion pre-classification result based on the feature-enhanced data set; The emotion pre-classification results are processed by Kalman filtering to obtain the child's real-time emotions. Since the change of physiological emotions requires another process rather than a sudden change, the emotion pre-classification results need to be sent to Kalman filtering for processing to obtain the true real-time emotions of the child, and the real-time emotions of the child are associated with the previous real-time emotions of the child.

[0044] Further extending the electrical impedance based on the fixed value of emotional state , body temperature value T, heart rate data P and emotional state, such as the increase or decrease of the three data, the frequency of increase or decrease, and the influence of the increase or decrease relationship on the emotional state. Because the value of the emotional state itself is changing, the result of the change of this value itself can be plotted to obtain its change curve, that is, the corresponding increase or decrease frequency of the curve, and the amplitude difference between high and low frequency points can show the emotional state of the monitored child in a monitoring cycle, combined with the emotional state at the monitoring time point, the combination of the two reflects whether the child's emotional state is normal.

[0045] Fig.12 is a schematic diagram of a process for preprocessing skin electrical impedance data, heart rate data, body temperature data and motion data according to some embodiments of this specification, such as Fig.12 As shown, as a preferred embodiment, the emotion recognition module preprocesses the skin electrical impedance data, heart rate data, body temperature data and motion data to obtain the preprocessed skin electrical impedance data, heart rate data, body temperature data and motion data, including: Filtering the skin electrical impedance data, heart rate data, body temperature data and motion data, filtering out noise data, and generating filtered skin electrical impedance data, heart rate data, body temperature data and motion data; Using a sampling window to sample the filtered skin impedance data, heart rate data, body temperature data and motion data to generate multiple data sets; For each data group, the peak value of the data group is detected, and the time domain features and frequency domain features are extracted according to the location of the peak value of the data group; The extracted time domain features and frequency domain features are normalized to obtain preprocessed skin electrical impedance data, heart rate data, body temperature data and motion data.

[0046] Specifically, in this stage, the data collected by the sensor is first filtered through a Butterworth filter to remove noise data; then the data is sampled with a window of 60 seconds to obtain a set of sensor data; then feature extraction is performed, and this step first detects the peak value, and then extracts different time domain and frequency domain features according to the location of the peak value; finally, the extracted features are normalized, and the obtained value range is [0,1].

[0047] Fig.13 is a flow chart of generating a feature-enhanced data set according to some embodiments of this specification, such as Fig.13 As shown, as a preferred embodiment, the emotion recognition module performs feature enhancement on the preprocessed skin electrical impedance data, heart rate data, body temperature data and motion data to obtain a feature-enhanced data set, including: Generate a network by weights According to the acceleration value characteristic value , determine the weight parameters of the preprocessed skin impedance data, heart rate data and body temperature data , , ; The weight parameters of the preprocessed skin impedance data, heart rate data and body temperature data are , , The preprocessed epithelial impedance data , heart rate data And body temperature data Multiply them together to get the enhanced skin impedance data, heart rate data and body temperature data , , .

[0048] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A smart bracelet with skin electrical impedance detection function, characterized in that: It comprises a housing and a main control board, a sensor board, a display and a lithium battery arranged on the housing, wherein the lithium battery is used to supply power to the main control board, the sensor board and the display, the sensor board is electrically connected to the input end of the main control board, and the display is electrically connected to the output end of the main control board; The main control board includes a main control chip, an epithelial impedance detection component, a body temperature detection component, a storage chip, a battery management component and a motion detection chip, wherein the epithelial impedance detection component, the body temperature detection component, the storage chip, the battery management component and the motion detection chip are all electrically connected to the main control chip, and the battery management component is electrically connected to the lithium battery.

2. The smart bracelet with skin electrical impedance detection function according to claim 1, characterized in that: The shell is provided with a skin-electrical impedance signal detector of the skin-electrical impedance detection component, the skin-electrical impedance signal detector comprises a first electrode and a second electrode, the first electrode serves as a skin-electrical impedance signal detection end, the second electrode is connected to the ground, and a transparent light window is provided between the first electrode and the second electrode; The epithelial impedance detection unit also includes a first amplifier, a second amplifier, a third amplifier and an analog-to-digital converter. The first amplifier is a voltage follower. The voltage reference signal is connected to the positive input terminal of the first amplifier after being divided by the first resistor and the second resistor. The second amplifier is a voltage follower. The voltage reference signal is connected to the positive input terminal of the second amplifier after being divided by the third resistor and the epithelial impedance signal detector. The negative input terminal of the third amplifier is electrically connected to the output terminal of the first amplifier, and the positive input terminal of the third amplifier is electrically connected to the output terminal of the second amplifier. The analog-to-digital converter is electrically connected to the output terminal of the third amplifier, and converts the voltage signal output by the third amplifier into a digital signal, which is transmitted to the main control chip.

3. The smart bracelet with skin electrical impedance detection function according to claim 1, characterized in that: The sensor board includes a heart rate detection chip, an LED light and a temperature sensor. The heart rate detection chip is electrically connected to the main control chip, the temperature sensor is electrically connected to the body temperature detection component, and the LED light is electrically connected to the heart rate detection chip.

4. The smart bracelet with skin electrical impedance detection function according to any one of claims 1 to 3, characterized in that: The smart bracelet with skin electrical impedance detection function includes multiple working modes, wherein the multiple working modes at least include a child mode, a parent master mode and a parent slave mode; When the smart bracelet with skin-electric impedance detection function works in child mode, the Bluetooth of the smart bracelet with skin-electric impedance detection function works in slave mode, and the collected skin-electric impedance data, heart rate data, body temperature data and motion data are sent to other smart bracelets with skin-electric impedance detection function working in parent master mode or Bluetooth adapters working in host mode; When the smart bracelet with skin electrical impedance detection function works in the parent host mode, the Bluetooth of the smart bracelet with skin electrical impedance detection function works in the host mode, communicates with other smart bracelets with skin electrical impedance detection function working in the child mode, obtains the skin electrical impedance data, heart rate data, body temperature data and motion data collected by other smart bracelets with skin electrical impedance detection function working in the child mode, and displays them; When the smart bracelet with skin electrical impedance detection function works in the parent slave mode, the Bluetooth of the smart bracelet with skin electrical impedance detection function works in the slave mode, receives the skin electrical impedance data, heart rate data, body temperature data and exercise data transmitted by the Bluetooth adapter and / or computer working in the host mode, and displays them.

5. Emotion recognition system, characterized in that The smart bracelet with skin electrical impedance detection function as claimed in any one of claims 1 to 4 comprises: A mode determination module, used to obtain a mode setting instruction and determine a current working mode according to the mode setting instruction; An emotion recognition module, used for identifying the real-time emotions of children based on the skin impedance data, heart rate data, body temperature data and movement data collected by the smart bracelet with skin impedance detection function when the current working mode is the child mode; The emotion recognition module is also used to receive the real-time emotions of children transmitted by other smart bracelets with skin electrical impedance detection function working in child mode when the current working mode is the parent master mode, and to perform status warning based on the real-time emotions of children; The emotion recognition module is also used to receive the real-time emotions of the child transmitted by the Bluetooth adapter and / or computer working in the host mode when the current working mode is the parent slave mode, and to issue a status warning based on the real-time emotions of the child.

6. The emotion recognition system according to claim 5, characterized in that: The smart bracelet with skin electrical impedance detection function collects skin electrical impedance data, heart rate data, body temperature data and motion data, including: determining the epithelial impedance based on the output voltage signal of the third amplifier of the epithelial impedance detection unit; Converting the voltage value output by the temperature sensor of the sensor board into body temperature data by using a voltage-temperature conversion formula; Acquiring heart rate data through the heart rate detection chip of the sensor board; The acceleration value characteristic value is obtained through the motion detection chip, wherein the motion data at least includes the acceleration value characteristic value.

7. The emotion recognition system according to claim 5, characterized in that: The epithelial impedance was calculated according to the following formula: in, is the output voltage signal of the third amplifier of the epielectric impedance detection unit, is the amplification factor of the third amplifier of the epielectric impedance detection unit, is the voltage reference signal, is the skin impedance, is the resistance value of the first resistor of the epithelial impedance detection unit, is the resistance value of the second resistor of the epithelial impedance detection unit, is the resistance value of the third resistor of the epithelial impedance detection unit.

8. The emotion recognition system according to claim 5, characterized in that: The emotion recognition module recognizes the child's real-time emotions based on the skin impedance data, heart rate data, body temperature data and movement data collected by the smart bracelet with skin impedance detection function, including: Preprocessing the skin electrical impedance data, heart rate data, body temperature data and motion data to obtain preprocessed skin electrical impedance data, heart rate data, body temperature data and motion data; Perform feature enhancement on the preprocessed skin electrical impedance data, heart rate data, body temperature data and motion data to obtain a feature-enhanced data set; Obtaining a sentiment pre-classification result based on the feature-enhanced data set using a sentiment classification model; The emotion pre-classification result is processed by Kalman filtering to obtain the real-time emotion of the child.

9. The emotion recognition system according to claim 8, characterized in that: The emotion recognition module preprocesses the skin electrical impedance data, heart rate data, body temperature data and motion data to obtain preprocessed skin electrical impedance data, heart rate data, body temperature data and motion data, including: Filtering the skin electrical impedance data, heart rate data, body temperature data and motion data to remove noise data and generate filtered skin electrical impedance data, heart rate data, body temperature data and motion data; Using a sampling window to sample the filtered skin impedance data, heart rate data, body temperature data and motion data to generate multiple data sets; For each of the data groups, detecting the peak value of the data group, and extracting time domain features and frequency domain features according to the position of the peak value of the data group; The extracted time domain features and frequency domain features are normalized to obtain preprocessed skin electrical impedance data, heart rate data, body temperature data and motion data.

10. The emotion recognition system according to claim 8, characterized in that: The emotion recognition module performs feature enhancement on the preprocessed skin impedance data, heart rate data, body temperature data and motion data to obtain a feature-enhanced data set, including: Determining weight parameters of the preprocessed skin electrical impedance data, heart rate data, and body temperature data according to the acceleration value characteristic value through a weight generation network; The weight parameters of the preprocessed skin electrical impedance data, heart rate data and body temperature data are multiplied by the preprocessed skin electrical impedance data, heart rate data and body temperature data to obtain enhanced skin electrical impedance data, heart rate data and body temperature data.

Images