A multifunctional integrated chip for a smartphone and application thereof

Abstract

This invention belongs to the field of integrated chip technology for mobile terminals, specifically relating to a multifunctional integrated chip for smartphones and its applications. The chip integrates a main processing module, a health monitoring module, an environmental sensing module, a motion state recognition module, a data processing module, an intelligent power management module, a communication interface module, and a speed calculation unit. The environmental sensing module integrates temperature, humidity, and air pressure data to calculate perceived temperature; the data processing module extracts physiological parameters through health analysis algorithms; and the intelligent power management module optimizes power consumption by switching between sleep, daily, and exercise modes based on the user's activity level. Smartphones equipped with this chip integrate biological, environmental, and motion sensors and a positioning module, displaying health parameters, environmental assessment results, and exercise data in real time on the screen. This invention, through highly integrated design and multi-module collaboration, achieves accurate monitoring of health, environment, and exercise while maintaining low power consumption, significantly improving the level of intelligence and user experience.

Description

Technical Field

[0001] This invention belongs to the field of mobile terminal integrated chip technology, specifically relating to a multi-functional integrated chip for smartphones and its applications. Background Technology

[0002] As smartphones evolve towards greater intelligence, multifunctionality, and thinness, users are demanding more sophisticated services from their devices in areas such as health management, environmental adaptation, and sports assistance. Multifunctional integrated chips, as the core carrier for achieving terminal intelligence, demonstrate significant advantages in improving performance, reducing power consumption, and minimizing size through high-density integration of processors, sensor interfaces, algorithm accelerators, and other functional modules. This makes them a key technological path for upgrading smartphones from "simple functional stacking" to "system-level intelligence."

[0003] While current smartphones integrate some sensors for health, environmental, and motion monitoring, they suffer from significant technological shortcomings: traditional solutions rely on discrete modules, such as separate biosensor modules for health monitoring and independent sensor components for environmental perception. This results in a fragmented hardware layout, large space requirements, and high communication latency between modules, making real-time data collaboration difficult. Health monitoring functions are limited to basic heart rate collection, lacking in-depth analysis of ECG signals and accurate calculation of physiological parameters such as heart rate variability, failing to meet the needs of professional health management. Environmental perception can only output data from a single sensor and does not dynamically optimize algorithms for regional and altitude differences. For example, the calculation error of perceived temperature in low-latitude, high-humidity areas is large, and the risk of altitude sickness in high-altitude areas cannot be accurately assessed. Motion status recognition relies on simple threshold judgments, without integrating machine learning to classify complex scenes. Furthermore, the fixed sampling rate leads to an imbalance between power consumption and accuracy, such as misjudging running and riding in a vehicle, and continuously high sampling rates increase power consumption. In addition, each functional module operates independently, lacking scene-based intelligent power consumption scheduling, putting significant pressure on smartphone battery life and failing to meet the needs of multi-scene monitoring and long battery life.

[0004] Therefore, there is an urgent need for an integrated, precise, low-power, multi-functional chip and smartphone that can adapt to multiple scenarios. Summary of the Invention

[0005] In view of the above-mentioned shortcomings in the prior art, the present invention provides a multifunctional integrated chip for smartphones and its application therein, so as to solve the problems in the background art.

[0006] To solve the above-mentioned technical problems, the present invention adopts the following technical solution: A multi-functional integrated chip for smartphones, comprising: Main processing module; The health monitoring module is used to connect to biosensors to acquire electrocardiogram and pulse signals and to preprocess them; The environmental perception module includes an environmental sensor interface and an environmental fusion unit. The environmental sensor interface is used to connect environmental sensors to collect temperature and humidity data, air pressure data, and ultraviolet intensity data. The environmental fusion unit is used to fuse the temperature and humidity data with the air pressure data to calculate the perceived temperature parameter, and to convert the air pressure data into altitude data and altitude sickness risk level. The motion state recognition module includes a motion sensor interface and a motion classification unit. The motion sensor interface is used to connect to a motion sensor to obtain acceleration data and angular velocity data. The motion classification unit adopts a machine learning model to extract step frequency and acceleration peak value through time domain feature analysis, extract the main frequency of the signal through frequency domain feature analysis, and output the motion state through classification decision. The data processing module has a built-in health analysis algorithm to identify the ECG waveform characteristics of ECG signals and calculate heart rate variability and resting heart rate based on the ECG waveform characteristics. The intelligent power consumption management module is used to switch the chip's working mode according to the motion state output by the motion classification unit. The working modes include sleep mode, daily mode and sports mode, and the chip power consumption is dynamically adjusted in different modes. The communication interface module is used for data interaction with smartphones.

[0007] Furthermore, the environmental fusion unit uses the following formula to calculate the perceived temperature parameter: Where: T is the temperature measurement, H is the humidity measurement, P is the air pressure measurement, P0 is the standard atmospheric pressure, α is the temperature and humidity co-contribution weighting factor, and β is the air pressure-altitude correction coefficient; and the values ​​of α and β are dynamically adjusted through a regional mapping table, which contains the α and β benchmark values ​​corresponding to different climate zones and altitude ranges.

[0008] Furthermore, the method for assessing the risk level of altitude sickness using the environmental fusion unit is as follows: when the altitude is greater than the first preset value and the increase in altitude within a preset time is greater than the preset range, it is determined to be high risk; when the altitude is greater than the first preset value and the increase in altitude within a preset time is less than the preset range, it is determined to be medium risk; when the altitude is less than or equal to the first preset value, it is determined to be low risk.

[0009] Furthermore, the machine learning model of the motion classification unit includes: a time-domain feature analysis layer that uses a three-layer convolutional neural network to extract step frequency and acceleration peak features; a frequency-domain feature analysis layer that uses a Fourier transform layer to extract the main frequency features of the signal; and a classification decision layer that uses a two-layer fully connected network to output the motion state.

[0010] Furthermore, the sampling rate of the motion sensor interface dynamically switches according to the motion state, with a higher sampling rate during running than during walking, and a higher sampling rate during walking than during riding in a vehicle.

[0011] Furthermore, the heart rate variability calculation steps of the health analysis algorithm are as follows: R-wave detection was performed on the preprocessed electrocardiogram signal; Calculate the time interval between adjacent R waves, i.e., the RR interval; Perform time-domain and frequency-domain analysis on the RR interval to output heart rate variability parameters.

[0012] Furthermore, it also includes a speed calculation unit, which uses a Kalman filter algorithm to fuse motion sensor data and smartphone built-in positioning module data to output real-time movement speed, including running pace and cycling speed.

[0013] Furthermore, the dynamic adjustment logic of the intelligent power consumption management module is as follows: In the sleep mode, the health monitoring module samples at a rate of 1 time / minute, and the environmental perception module and motion state recognition module are intermittently awakened, resulting in the lowest overall power consumption; in the daily mode, the health monitoring module samples at a rate of 1 time / second, the environmental perception module works continuously, and the motion state recognition module samples at a frequency of 5Hz, resulting in moderate overall power consumption; in the exercise mode, the sampling rate of all modules is increased to 100Hz, the data processing module operates at full load, and the overall power consumption is the highest.

[0014] Furthermore, the main processing module is connected to each functional module via the on-chip AXI bus and uses a priority scheduling mechanism to process real-time data from the health monitoring module, environmental perception module, and motion recognition module.

[0015] The present invention also provides a smartphone, including the above-mentioned multifunctional integrated chip, and further including a biosensor connected to the health monitoring module, an environmental sensor connected to the environmental perception module, a motion sensor connected to the motion sensor interface, a positioning module, and a display screen. The display screen is used to display the health parameters, environmental assessment results, motion status, and real-time motion speed output by the chip in real time.

[0016] Compared with the prior art, the present invention has the following beneficial effects: 1. Through a highly integrated design of a multi-functional integrated chip, health monitoring, environmental perception, and motion state recognition are deeply integrated into a single chip architecture. The main processing module relies on the AXI bus to achieve dynamic scheduling of multiple tasks. Health monitoring data is given the highest priority to ensure real-time performance, and the data interaction links between modules are clear and highly efficient. Compared with traditional discrete module solutions, this significantly simplifies the internal hardware layout of smartphones. At the same time, through high-speed communication interfaces such as SPI, efficient data flow with the baseband chip and application processor is achieved, improving system integration and operating efficiency from the hardware level, and providing support for smartphone function expansion and miniaturization design.

[0017] 2. In health monitoring scenarios, the biosignal acquisition interface and preprocessing unit work together, in conjunction with high-precision health analysis algorithms, to accurately extract ECG and pulse signal features, dynamically calculate physiological parameters such as heart rate variability and resting heart rate, and provide users with professional-grade health data support. The environmental perception module uses a geographic mapping table to dynamically adapt algorithm parameters and combines multi-sensor data fusion to achieve accurate calculation of perceived temperature, altitude, and altitude sickness risk, covering complex scenarios from low-latitude islands to high-altitude mountainous areas. The motion state recognition module integrates machine learning and dynamic sampling strategies to accurately classify motion states such as walking, running, and riding in a vehicle. The speed calculation unit outputs high-precision pace and cycling speed through Kalman filtering, constructing a multi-scenario, fully covered intelligent perception service system from health management and environmental adaptation to exercise assistance.

[0018] 3. The intelligent power management module can intelligently switch between sleep, daily, and exercise modes based on the user's activity level. By dynamically adjusting the power supply voltage, clock frequency, and module wake-up cycle, it achieves fine-grained power consumption control. Meanwhile, the UI layer provides interactive feedback such as health warnings, environmental prompts, and exercise broadcasts based on data output from multiple modules. This creates a closed loop from hardware power consumption optimization to software experience, balancing device battery life and user experience. It drives the evolution of smartphones from feature phones to "intelligent health terminals," providing users with a long battery life and highly intelligent user experience. Attached Figure Description

[0019] Figure 1 This is a schematic diagram of the structure of a multi-functional integrated chip for smartphones according to the present invention; Figure 2 This is a schematic diagram of the structure of a health monitoring module for a multi-functional integrated chip used in a smartphone according to the present invention. Figure 3 This is a schematic diagram of the structure of an environmental sensing module for a multi-functional integrated chip used in a smartphone according to the present invention. Figure 4 This is a schematic diagram of the motion state recognition module of a multi-functional integrated chip for smartphones according to the present invention. Figure 5This is a schematic diagram of the structure of a smartphone that integrates a multi-functional integrated chip according to the present invention. Detailed Implementation

[0020] To enable those skilled in the art to better understand the present invention, the technical solution of the present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0021] The accompanying drawings are for illustrative purposes only and are schematic diagrams, not actual images. They should not be construed as limiting the scope of this patent. To better illustrate the embodiments of the present invention, some parts in the drawings may be omitted, enlarged, or reduced, and do not represent the actual dimensions of the product. It is understandable to those skilled in the art that some well-known structures and their descriptions may be omitted in the drawings.

[0022] In the accompanying drawings of the embodiments of the present invention, the same or similar reference numerals correspond to the same or similar components. In the description of the present invention, it should be understood that if terms such as "upper," "lower," "left," "right," "inner," and "outer" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, they are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, the terms used to describe positional relationships in the drawings are only for illustrative purposes and should not be construed as limiting the present patent. For those skilled in the art, the specific meaning of the above terms can be understood according to the specific circumstances.

[0023] In the description of this invention, unless otherwise explicitly specified and limited, the term "connection" or similar designation indicating a connection between components should be interpreted broadly. For example, it can refer to a fixed connection, a detachable connection, or an integral part; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can refer to the internal communication between two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0024] Example 1: like Figure 1-5 As shown, this invention provides a multi-functional integrated chip for smartphones, with the hardware architecture described below. Figure 1 As shown, the chip includes a main processing module, a health monitoring module, an environmental sensing module, a motion state recognition module, a data processing module, an intelligent power consumption management module, a communication interface module, and a speed calculation unit. Each module works collaboratively through specific hardware connections and data interaction mechanisms.

[0025] In this embodiment, the main processing module communicates with other modules via the AXI bus and is responsible for prioritizing tasks such as health monitoring, environmental perception, and motion state recognition. Among these, health monitoring data has the highest processing priority to ensure real-time requirements.

[0026] Secondly, the health monitoring module includes a biosignal acquisition interface and a health preprocessing unit. The biosignal acquisition interface connects to a built-in metal electrode sensor and a photoelectric sensor, supporting the simultaneous acquisition of electrocardiogram and pulse signals; the health preprocessing unit is used to perform noise reduction and amplification processing on the collected signals.

[0027] Meanwhile, the environmental perception module includes an environmental sensor interface and an environmental fusion unit. The environmental sensor interface connects to temperature and humidity sensors, barometric pressure sensors, and ultraviolet sensors; the environmental fusion unit is responsible for calculating perceived temperature, converting altitude, and assessing the risk level of altitude sickness. A formula is used to calculate perceived temperature. Where: T is the temperature measurement value in °C; H is the humidity measurement value in %; P is the air pressure measurement value in hPa; P0 is the standard atmospheric pressure value, with a value of 1013.25 hPa; α is the temperature and humidity synergistic contribution weighting factor, with a value range of 0.1-0.3; β is the air pressure-altitude correction coefficient, with a value range of 0.05-0.2.

[0028] The specific values ​​of α and β are dynamically adjusted through a geographic mapping table, which uses latitude and altitude ranges as dual-dimensional indexes. As shown in Table 1... Table 1. Regional Mapping Table As shown in the table, for example, in low-latitude, low-altitude regions (such as Hainan): α=0.3, β=0.05; in mid-latitude, mid-altitude regions (such as the Qinling Mountains): α=0.18, β=0.12; and in high-latitude, high-altitude regions (such as the Qinghai-Tibet Plateau): α=0.1, β=0.2. After the chip acquires the latitude, longitude, and altitude data from the smartphone's positioning module, the main processing module uses a linear interpolation algorithm to match the nearest neighbor interval in the mapping table and dynamically calls the α and β values ​​to the environment fusion unit.

[0029] Secondly, altitude conversion is done using a formula. For example, when the current air pressure P is 800 hPa, the calculated altitude H is approximately 2000 meters. When assessing the risk level of altitude sickness, a high-risk level is defined as follows: if the altitude is greater than a first preset value and the altitude increase within a preset time exceeds a preset range; if the altitude is greater than the first preset value and the altitude increase within a preset time is less than a preset range; and if the altitude is less than or equal to the first preset value, it is defined as low-risk. The first preset value can be set to 3000 meters, the preset time to 24 hours, and the preset range to 1000 meters. The altitude increase is... H1 is the altitude value 24 hours ago, and H2 is the current altitude value.

[0030] Meanwhile, the motion state recognition module includes a motion sensor interface and a motion classification unit. The motion sensor interface connects to an accelerometer and a gyroscope; the motion classification unit employs a machine learning model, which includes a time-domain feature analysis layer, a frequency-domain feature analysis layer, and a classification decision layer. The time-domain feature analysis layer uses a three-layer convolutional neural network with 32 3×3 convolutional kernels to extract step frequency and peak acceleration features. The frequency-domain feature analysis layer extracts the main frequency features of the signal through a Fourier transform layer. The classification decision layer uses a two-layer fully connected network to output the motion state, which includes walking, running, and riding in a vehicle. A threshold of 0.5 is used to determine the specific state during output. The sampling rate of the motion sensor interface dynamically switches according to the motion state: 50-100Hz for running, 20-50Hz for walking, and 5-20Hz for riding in a vehicle, to balance detection accuracy and power consumption.

[0031] Meanwhile, the data processing module integrates a floating-point arithmetic unit and incorporates a built-in health analysis algorithm implemented in C language. This algorithm includes an ECG signal analysis sub-algorithm and a physiological parameter calculation sub-algorithm. The ECG signal analysis sub-algorithm is used to identify ECG waveform features, while the physiological parameter calculation sub-algorithm calculates heart rate variability and resting heart rate based on ECG waveform features. The heart rate variability calculation steps are as follows: The Pan-Tompkins algorithm is used to detect the R-wave peak value by setting an adaptive threshold on the preprocessed ECG signal; the time interval between adjacent R waves, i.e., the RR interval, is calculated, and abnormal intervals with a difference exceeding 200ms are removed; the RR interval is analyzed in the time domain to calculate the standard deviation and mean, and simultaneously, frequency domain analysis is performed using Fast Fourier Transform to obtain high-frequency components (frequency range 0.15-0.4Hz) and low-frequency components (frequency range 0.04-0.15Hz), finally outputting the heart rate variability parameters.

[0032] Meanwhile, the intelligent power management module switches the chip's operating mode based on the motion status output by the motion classification unit. Operating modes include sleep mode, daily mode, and exercise mode. In sleep mode, the health monitoring module samples at 1 time / minute, the environmental sensing module and motion status recognition module wake up every 10 minutes, and the overall power consumption is controlled at 30μA. In daily mode, the health monitoring module samples at 1 time / second, the environmental sensing module works continuously, and the motion status recognition module samples at a frequency of 5Hz, with an overall power consumption of 150μA. In exercise mode, the sampling rate of all modules increases to 100Hz, the data processing module operates at full load, and the overall power consumption is 450μA. Power consumption optimization is achieved through dynamic adjustment of these three modes.

[0033] Meanwhile, the speed calculation unit uses the Kalman filter algorithm to fuse motion sensor data and data from the smartphone's built-in positioning module. The state equation of the Kalman filter includes velocity and acceleration parameters, and the observation equation is constructed based on the displacement data of the positioning module. The output real-time motion speed includes running pace and cycling speed, with running pace accuracy of ±0.5 minutes / km and cycling speed accuracy of ±1km / h.

[0034] Meanwhile, the communication interface module is used to interact with the smartphone baseband chip or application processor, supporting I2C, SPI or high-speed synchronous serial protocols. In practical applications, data transmission is achieved through the SPI protocol to ensure efficiency.

[0035] Example 2: This embodiment provides a smartphone equipped with the multifunctional integrated chip described in Embodiment 1. In addition to the aforementioned chip, the smartphone also includes a biosensor connected to a biosignal acquisition interface, an environmental sensor connected to an environmental sensor interface, a motion sensor connected to a motion sensor interface, a positioning module, and a display screen. The biosensor's metal electrode sensor is integrated into the back frame of the phone, and the photoelectric sensor is embedded below the screen. The environmental sensor's temperature and humidity sensor and barometric pressure sensor are located next to the earpiece at the top of the phone, and the ultraviolet sensor is integrated into the rear camera module. The positioning module uses a BeiDou / GPS dual-mode chip to provide real-time longitude, latitude, and altitude data. The display screen is a 6.5-inch OLED screen used to display real-time health parameters, environmental assessment results, exercise status, and real-time exercise speed output by the chip. Based on the above data, the UI layer displays corresponding health, environmental, or exercise information. The UI layer is designed with three pages: a health information page, an environmental information page, and an exercise information page, displaying resting heart rate, heart rate variability, HRV frequency domain indicators, perceived temperature, ultraviolet index, altitude sickness risk level, and exercise status, speed, pace, and supporting historical data curve queries.

[0036] Working principle: The multifunctional integrated chip of the present invention and the smartphone equipped with it achieve comprehensive functions of health monitoring, environmental perception and motion state recognition through the collaborative work of various modules. Its core workflow includes three stages: data acquisition and preprocessing, multi-module collaborative work and data output and interaction.

[0037] In the data acquisition and preprocessing process, each sensor module works in parallel to acquire raw data and perform preliminary processing. For health data, biosensors acquire ECG and pulse signals in real time. After noise reduction and amplification by the health preprocessing unit, the data is transmitted to the data processing module via the AXI bus, providing high-quality signals for subsequent physiological parameter calculations. For environmental data, environmental sensors simultaneously acquire temperature, humidity, air pressure, and ultraviolet data. The environmental fusion unit first calculates the perceived temperature using a formula including regional correction parameters α and β, then converts the air pressure data to altitude data using the air pressure-altitude formula. Combined with the 24-hour altitude change ΔH, the risk level of altitude sickness is assessed, forming an environmental assessment result. For motion data, motion sensors acquire triaxial acceleration and angular velocity. The motion classification unit analyzes the data in real time and classifies motion states using a machine learning model. Simultaneously, the velocity calculation unit integrates displacement data from the positioning module and outputs quantitative indicators such as running pace and cycling speed using a Kalman filter algorithm.

[0038] The multi-module collaborative working logic centers on the main processing module, using the AXI bus to achieve data interaction and task scheduling among the modules. Based on the motion status output by the motion classification unit, the main processing module sends mode switching commands to the intelligent power management module. For example, when running is detected, it triggers a motion mode, increasing the sampling rate of all sensors to 100Hz and running the data processing module at full load; when riding in a vehicle is detected, it switches to a daily mode, reducing the motion sensor sampling rate to 5Hz to lower power consumption; when the user is detected to be stationary for an extended period, it switches to a sleep mode, shutting down some unnecessary modules and retaining only the low-frequency sampling of the health monitoring module. The intelligent power management module dynamically adjusts power consumption by regulating the clock frequency, supply voltage, and duty cycle of each module. Actual testing shows that after 24 hours of continuous monitoring, the overall power consumption does not exceed 15mAh, meeting the battery life requirements of smartphones.

[0039] In the data output and interaction phase, the communication interface module transmits the processed health parameters, environmental assessment results, exercise status, and real-time exercise speed to the smartphone's application processor via the SPI protocol. The application processor then pushes this data to the UI layer of the display screen. The UI layer displays corresponding information and triggers prompts based on the data type. For example, when the risk level of altitude sickness is high, a red warning is displayed and the user is advised to stop ascending; when the heart rate variability (SDNN) is less than 50ms, a message indicating high stress is suggested to rest; and in exercise mode, pace and heart rate data are announced via voice per kilometer, enabling real-time interaction between the user and the device.

[0040] This invention's multi-functional integrated chip integrates health monitoring, environmental sensing, and motion recognition into a single chip through a highly integrated design. Utilizing a geographic mapping table and dynamic parameter adjustment mechanism, the chip maintains high accuracy even in extreme environments such as tropical and high-altitude regions, meeting the needs of various application scenarios. The intelligent power management module dynamically adjusts power consumption through three operating modes, supporting 24 / 7 continuous monitoring by smartphones without requiring additional battery capacity, thus balancing rich functionality with low power consumption. Smartphones equipped with this chip can provide users with comprehensive health, environmental, and motion information, enhancing the overall usability of mobile devices.

[0041] The above are merely embodiments of the present invention. The circuits, electronic components, and modules involved are all prior art, fully achievable by those skilled in the art, and require no further explanation. The scope of protection in this application does not involve improvements to the software and methods. Commonly known structures and characteristics in the solutions are not described in detail here. Those skilled in the art are aware of all common technical knowledge in the field prior to the application date or priority date, are aware of all prior art in that field, and have the ability to apply conventional experimental methods prior to that date. Those skilled in the art can, under the guidance of this application, improve and implement this solution in combination with their own capabilities. Some typical known structures or methods should not be obstacles for those skilled in the art to implement this application. It should be noted that those skilled in the art can make several modifications and improvements without departing from the structure of the present invention. These should also be considered within the scope of protection of the present invention, and will not affect the effectiveness of the implementation of the present invention or the practicality of the patent.

Claims

1. A multi-functional integrated chip for smartphones, characterized in that, include: Main processing module; The health monitoring module is used to connect to biosensors to acquire electrocardiogram and pulse signals and to preprocess them; The environmental perception module includes an environmental sensor interface and an environmental fusion unit. The environmental sensor interface is used to connect environmental sensors to collect temperature and humidity data, air pressure data, and ultraviolet intensity data. The environmental fusion unit is used to fuse the temperature and humidity data with the air pressure data to calculate the perceived temperature parameter, and to convert the air pressure data into altitude data and altitude sickness risk level. The motion state recognition module includes a motion sensor interface and a motion classification unit. The motion sensor interface is used to connect to a motion sensor to obtain acceleration data and angular velocity data. The motion classification unit adopts a machine learning model to extract step frequency and acceleration peak value through time domain feature analysis, extract the main frequency of the signal through frequency domain feature analysis, and output the motion state through classification decision. The data processing module has a built-in health analysis algorithm to identify the ECG waveform characteristics of ECG signals and calculate heart rate variability and resting heart rate based on the ECG waveform characteristics. The intelligent power consumption management module is used to switch the chip's working mode according to the motion state output by the motion classification unit. The working modes include sleep mode, daily mode and sports mode, and the chip power consumption is dynamically adjusted in different modes. The communication interface module is used for data interaction with smartphones.

2. The multi-functional integrated chip for smartphones as described in claim 1, characterized in that: The environmental fusion unit uses the following formula to calculate the perceived temperature parameter: Where: T is the temperature measurement, H is the humidity measurement, P is the air pressure measurement, P0 is the standard atmospheric pressure, α is the temperature and humidity co-contribution weighting factor, and β is the air pressure-altitude correction coefficient; and the values ​​of α and β are dynamically adjusted through a regional mapping table, which contains the α and β benchmark values ​​corresponding to different climate zones and altitude ranges.

3. The multi-functional integrated chip for smartphones as described in claim 1, characterized in that: The method for assessing the risk level of altitude sickness by the environmental fusion unit is as follows: when the altitude is greater than a first preset value and the increase in altitude within a preset time is greater than a preset range, it is determined to be high risk; when the altitude is greater than the first preset value and the increase in altitude within a preset time is less than a preset range, it is determined to be medium risk; when the altitude is less than or equal to the first preset value, it is determined to be low risk.

4. A multi-functional integrated chip for smartphones as described in claim 1, characterized in that: The machine learning model of the motion classification unit includes: a time-domain feature analysis layer that uses a three-layer convolutional neural network to extract step frequency and acceleration peak features; a frequency-domain feature analysis layer that uses a Fourier transform layer to extract the main frequency features of the signal; and a classification decision layer that uses a two-layer fully connected network to output the motion state.

5. A multi-functional integrated chip for smartphones as described in claim 1, characterized in that: The sampling rate of the motion sensor interface dynamically switches according to the motion state; the sampling rate is higher when running than when walking, and higher when walking than when riding in a vehicle.

6. A multi-functional integrated chip for smartphones as described in claim 1, characterized in that: The heart rate variability calculation steps of the health analysis algorithm are as follows: R-wave detection was performed on the preprocessed electrocardiogram signal; Calculate the time interval between adjacent R waves, i.e., the RR interval; Perform time-domain and frequency-domain analysis on the RR interval to output heart rate variability parameters.

7. A multi-functional integrated chip for smartphones as described in claim 1, characterized in that: It also includes a speed calculation unit, which uses a Kalman filter algorithm to fuse motion sensor data and smartphone built-in positioning module data to output real-time motion speed, including running pace and cycling speed.

8. A multi-functional integrated chip for smartphones as described in claim 1, characterized in that: The dynamic adjustment logic of the intelligent power consumption management module is as follows: In the sleep mode, the health monitoring module samples at a rate of 1 time / minute, and the environmental sensing module and motion state recognition module are intermittently woken up; in the daily mode, the health monitoring module samples at a rate of 1 time / second, the environmental sensing module works continuously, and the motion state recognition module samples at a frequency of 5Hz; in the exercise mode, the sampling rate of all modules is increased to 100Hz, and the data processing module operates at full load.

9. A multi-functional integrated chip for smartphones as described in claim 1, characterized in that: The main processing module is connected to each functional module via an on-chip AXI bus and uses a priority scheduling mechanism to process real-time data from the health monitoring module, environmental perception module, and motion recognition module.

10. A smartphone, characterized in that, The device includes the multifunctional integrated chip according to any one of claims 1 to 9, and further includes a biosensor connected to the health monitoring module, an environmental sensor connected to the environmental sensing module, a motion sensor connected to the motion sensor interface, a positioning module, and a display screen, wherein the display screen is used to display the health parameters, environmental assessment results, motion status, and real-time motion speed output by the chip in real time.

Images