A multi-state perception adaptive control method and system for a body temperature patch

Abstract

The application provides a body temperature patch multi-state sensing adaptive control method and system, and relates to the technical field of body temperature monitoring. The method comprises collecting skin temperature, ambient temperature and battery voltage; analyzing the skin and ambient temperature based on a multi-state sensing algorithm to generate a wearing state and a temperature trend; if the wearing state is invalid fitting, entering a sleep mode, which has intermittent detection and wake-up functions; if the wearing state is valid fitting, entering a monitoring mode, adaptively adjusting the sampling interval according to the temperature trend to generate a sampling time sequence, and collecting body temperature according to the sampling time sequence; constructing a heat flow compensation model to calculate the time sequence body temperature to generate body temperature data, and wirelessly and encryptedly transmitting the body temperature data and the battery voltage to a user end for state display and abnormality early warning, so as to realize intelligent detection of the body temperature patch fitting state, dynamic adjustment of the sampling interval, accurate compensation of the body temperature, and low-power safe transmission, and effectively improve the temperature measurement accuracy and the equipment endurance.

Description

Technical Field

[0001] This invention relates to the field of body temperature monitoring technology, and in particular to a multi-state sensing adaptive control method and system for body temperature patches. Background Technology

[0002] As a wearable medical monitoring device, body temperature patches achieve continuous body temperature measurement by adhering to the surface of the skin. They are widely used in scenarios such as home health monitoring, clinical temperature monitoring, and telemedicine. Traditional body temperature patches typically use NTC thermistors or infrared sensors to collect skin temperature and transmit the data to a mobile phone or monitoring terminal via wireless means such as Bluetooth, allowing users to view the trend of body temperature changes in real time.

[0003] However, existing body temperature patch technology has serious technical flaws. First, most body temperature patches only collect skin surface temperature, failing to consider the effects of ambient temperature, contact thermal resistance, and the thermal inertia of the human body. This leads to significant deviations between the measured results and the actual body temperature, especially during rapid temperature changes (such as the fever-raising or cooling-down phases), where sensor response lags, making the error even more pronounced. Second, existing devices typically use a fixed frequency for continuous sampling, neglecting the adhesion between the patch and the skin—even if the device is loose or not worn correctly, the system continues to collect data and send wireless signals at the same frequency, causing unnecessary power consumption, shortening battery life, and potentially misleading users. Furthermore, the lack of an effective encryption mechanism during wireless transmission poses a risk of privacy breaches to user temperature data; the user-end functionality is also limited, only displaying the raw temperature value and lacking intelligent warning functions for abnormal body temperatures or low battery levels.

[0004] Therefore, it is necessary to provide a multi-state sensing adaptive control method and system for body temperature patches to solve the above-mentioned technical problems. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides a multi-state sensing adaptive control method and system for body temperature patches, which solves the problems of existing body temperature patches having measurement accuracy easily affected by environmental interference, poor power consumption control, lack of adhesion state sensing, and insufficient data security.

[0006] This invention provides a multi-state sensing adaptive control method for a body temperature patch, the method comprising: The system collects skin temperature data, ambient temperature data, and battery voltage data when the body temperature patch is in contact with human skin using a multimodal sensor. The skin temperature data and the ambient temperature data are analyzed based on a multi-state perception detection algorithm to generate the wearing status of the body temperature patch and the temperature change trend status. If the temperature patch is in an invalid fit state, the temperature patch is controlled to enter a deep sleep mode, which has low power intermittent detection and automatic wake-up functions. If the temperature patch is in an effective fit, the temperature patch is controlled to enter an active monitoring mode. The temperature sampling interval is adaptively adjusted according to the temperature change trend to generate a dynamic sampling sequence, and the time-series temperature data is collected according to the dynamic sampling sequence. A heat flux compensation model is constructed, and temperature compensation calculations are performed on the time-series body temperature data to generate body temperature data. The body temperature data and the battery voltage data are transmitted to the user terminal via wireless communication encryption. The user terminal displays the status of the body temperature data and the battery voltage data and provides abnormal warnings.

[0007] Preferably, the step of analyzing the skin temperature data and the ambient temperature data based on the multi-state perception detection algorithm to generate the body temperature patch wearing status and temperature change trend status specifically includes: The skin temperature data and the ambient temperature data are subjected to time synchronization and sliding window filtering to generate a synchronized skin temperature sequence. and synchronous ambient temperature sequence ; According to the synchronized skin temperature sequence Calculate the rate of temperature change v and temperature fluctuation within a preset sliding window. The corresponding calculation formula is as follows: In the formula, N represents the total number of sampling points within the preset sliding window; This represents the i-th sampling time within the preset sliding window. ; Indicates at the sampling time The generated synchronized skin temperature value; Indicates at the sampling time The generated synchronized skin temperature value; This represents the arithmetic mean of the synchronized skin temperature sequence within the preset sliding window; Calculate the synchronized skin temperature sequence With the synchronized ambient temperature sequence At sampling time Real-time temperature difference ; At the current sampling moment, if the following conditions are met simultaneously: the temperature change rate is less than a preset change rate threshold, the current value of the synchronized skin temperature sequence is within a reasonable range of human body temperature, the real-time temperature difference meets the preset fitting temperature difference condition, and the temperature fluctuation is less than a preset fluctuation threshold, then the temperature patch is determined to be in an effective fitting state; otherwise, the temperature patch is determined to be in an invalid fitting state.

[0008] Preferably, the least squares method is used to analyze the synchronized skin temperature sequence. Perform linear regression fitting to calculate the slope k of the temperature trend over time. The corresponding calculation formula is as follows: In the formula, M represents the total number of sampling points within the linear regression fitting window; This represents the j-th sampling time within the linear regression fitting window. ; This represents the arithmetic mean of the sampling times within the linear regression fitting window; Indicates at the sampling time The generated synchronized skin temperature value; This represents the arithmetic mean of the synchronized skin temperature sequence within the linear regression fitting window; The temperature change trend state is generated based on the range of values ​​for the slope k of the temperature trend.

[0009] Preferably, if the temperature patch is in an ineffective contact state, the temperature patch is controlled to enter a deep sleep mode. This deep sleep mode has low-power intermittent detection and automatic wake-up functions, specifically including: If the body temperature patch is in the invalid contact state, the MCU of the body temperature patch is controlled to enter the deep sleep mode, all peripherals except for the low power timer and the button wake-up interface are turned off, and the system clock is switched to a low frequency clock source. In the deep sleep mode, the MCU is periodically woken up with a preset low-power wake-up cycle. After each wake-up, the temperature sensor is activated to collect the current skin temperature data and the current ambient temperature data. If the current skin temperature data is greater than the preset lower limit threshold of human body temperature and the difference between the current skin temperature data and the current ambient temperature data meets the preset fit temperature difference condition, then it is determined that the body temperature patch is in the effective fit state and automatically exits the deep sleep mode. Otherwise, if the temperature patch is determined to be in an invalid fit state, the MCU will re-enter the deep sleep mode and wait for the next low-power wake-up cycle.

[0010] Preferably, the step of adaptively adjusting the temperature sampling interval according to the temperature change trend to generate a dynamic sampling time sequence, and collecting time-series body temperature data according to the dynamic sampling time sequence, specifically includes: Based on a preset sampling interval mapping rule, the temperature sampling interval is adaptively determined according to the temperature change trend state. If the temperature change trend is a rapid heating trend or a rapid cooling trend, then the temperature sampling interval is set to the first temperature sampling interval. If the temperature change trend is a slow heating trend or a slow cooling trend, then the temperature sampling interval is set to the second temperature sampling interval. If the temperature change trend is a stable temperature trend, then the temperature sampling interval is set to the third temperature sampling interval. The temperature sampling interval is set as the sampling period to generate the dynamic sampling sequence. According to the sampling time in the dynamic sampling sequence, the temperature sensor is activated to collect the current skin temperature data, and the current skin temperature data is stored in time sequence as the time-series body temperature data. Wherein, the first temperature sampling interval is smaller than the second temperature sampling interval, and the second temperature sampling interval is smaller than the third temperature sampling interval.

[0011] Preferably, the step of constructing a heat flux compensation model and performing temperature compensation calculations on the time-series body temperature data to generate body temperature data specifically includes: The contact thermal resistance of the surface of the body temperature patch in contact with human skin was obtained. Thermal resistance of convective heat transfer between the surface of the body temperature patch and the environment and the thermal conductivity of the flexible circuit board (FPC) of the body temperature patch. ; Based on the contact thermal resistance The convective heat transfer thermal resistance The thermal conductivity coefficient and the time-series body temperature data at the current time c The heat flux compensation model is constructed to generate the estimated body temperature at the current time c. The corresponding calculation formula is as follows: In the formula, This represents the synchronous ambient temperature value generated at the current time c; Indicated based on thermal conductivity coefficient A defined dynamic thermal time constant; This represents the rate of change of skin temperature at the current moment c; The dynamic compensation intensity of the heat flux compensation model is adaptively adjusted based on the temperature change trend. Based on the dynamic compensation intensity The estimated body temperature at the current time c Make corrections and generate corrected body temperature data for the current time c. ; The corrected body temperature data is processed using a Kalman filter algorithm to generate the body temperature data.

[0012] Preferably, based on a preset dynamic compensation mapping rule, the dynamic compensation intensity of the heat flux compensation model is adaptively adjusted according to the temperature change trend, specifically including: If the temperature change trend is a rapid heating trend or a rapid cooling trend, then the dynamic compensation intensity is set to the first compensation intensity value. If the temperature change trend is a slow heating trend or a slow cooling trend, then the dynamic compensation intensity is set to the second compensation intensity value. If the temperature change trend is a stable temperature trend, then the dynamic compensation intensity is set to the third compensation intensity value. Wherein, the first compensation strength value is greater than the second compensation strength value, and the second compensation strength value is greater than the third compensation strength value.

[0013] A multi-state sensing adaptive control system for body temperature patches, the system comprising: The data acquisition module is used to collect skin temperature data, ambient temperature data, and battery voltage data when the body temperature patch is in contact with human skin using a multimodal sensor; The state perception module is used to analyze the skin temperature data and the ambient temperature data based on a multi-state perception detection algorithm to generate the body temperature patch wearing status and temperature change trend status. The sleep control module is used to control the body temperature patch to enter a deep sleep mode if the body temperature patch is in an invalid contact state. The deep sleep mode has low power intermittent detection and automatic wake-up functions. The dynamic sampling module is used to control the body temperature patch to enter the active monitoring mode if the body temperature patch is in an effective fit state, adaptively adjust the temperature sampling interval according to the temperature change trend, generate a dynamic sampling sequence, and collect time-series body temperature data according to the dynamic sampling sequence. The compensation communication module is used to construct a heat flow compensation model, perform temperature compensation calculations on the time-series body temperature data, generate body temperature data, and transmit the body temperature data and battery voltage data to the user terminal via wireless communication encryption. The user terminal displays the status of the body temperature data and battery voltage data and provides abnormal warnings.

[0014] An electronic device includes a memory and a processor, wherein the memory stores a computer program, and when the processor runs the computer program stored in the memory, the processor executes the steps of a multi-state sensing adaptive control method for a body temperature patch as described in any of the above claims.

[0015] A readable storage medium storing a computer program, which, when executed by a processor, is used to implement the steps of a multi-state sensing adaptive control method for a body temperature patch as described in any of the above claims.

[0016] Compared with related technologies, the multi-state sensing adaptive control method and system for body temperature patches provided by this invention have the following beneficial effects: This invention collects skin temperature data, ambient temperature data, and battery voltage data when a body temperature patch is in contact with human skin using a multimodal sensor. Based on a multi-state perception detection algorithm, it analyzes the skin temperature and ambient temperature data to generate data on the patch's wearing status and temperature change trend. If the patch is in an invalid fit, it enters a deep sleep mode with low-power intermittent detection and automatic wake-up. If the patch is in an effective fit, it enters an active monitoring mode, adaptively adjusting the temperature sampling interval based on the temperature change trend to generate a dynamic sampling sequence, and collecting time-series body temperature data according to this sequence. A heat flow compensation model is constructed to perform temperature compensation calculations on the time-series body temperature data, generating body temperature data. The body temperature and battery voltage data are then transmitted wirelessly to the user terminal with encryption. The user terminal displays the status of the body temperature and battery voltage data and provides anomaly warnings. This achieves intelligent detection of the patch's fit status, dynamic adjustment of the sampling interval, accurate temperature compensation, and low-power secure transmission, effectively improving temperature measurement accuracy and device battery life.

[0017] This invention constructs a heat flux compensation model, comprehensively considering the contact thermal resistance between the temperature patch and the skin, the thermal conductivity of the flexible circuit board, and the convective heat transfer thermal resistance between the device surface and the environment. This model performs real-time heat flux compensation on time-series body temperature data, effectively eliminating the interference of ambient temperature and contact thermal resistance on the measurement results. Simultaneously, it adaptively adjusts the dynamic compensation intensity based on the temperature change trend and further suppresses measurement noise using a Kalman filter algorithm, thereby obtaining high-precision body temperature data. This solves the problems of large measurement deviation and slow response of traditional temperature patches, significantly improving the accuracy and reliability of body temperature measurement. This invention uses a multi-state perception detection algorithm to identify the wearing status of the temperature patch in real time: when an invalid wearing state is determined, the control system immediately enters a deep sleep mode, retaining only a low-power timer and a button wake-up interface, periodically waking up with extremely low power consumption to recheck the wearing state; when an valid wearing state is determined, the system adaptively adjusts the temperature sampling interval based on the temperature change trend. This state-aware dynamic power management mechanism avoids energy waste caused by invalid sampling and frequent wireless transmission, significantly improving battery life. This invention employs encrypted wireless communication to securely transmit body temperature and battery voltage data to the user terminal, effectively preventing the leakage of personal health privacy. The user terminal not only displays real-time body temperature values ​​and temperature change curves, but also provides intelligent warnings based on preset normal body temperature ranges and low battery thresholds. It uses visual, auditory, and other methods to promptly alert users to abnormal body temperature or low device battery, enhancing data transmission security and user experience. Attached Figure Description

[0018] Figure 1 A flowchart of a multi-state sensing adaptive control method for a body temperature patch provided in an embodiment of the present invention; Figure 2 This is a system block diagram of a multi-state sensing adaptive control system for a body temperature patch provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] like Figure 1 The diagram shown is a flowchart of a multi-state sensing adaptive control method for a body temperature patch provided in an embodiment of the present invention. Figure 1The execution subject of the method shown can be a software and / or hardware device. The execution subject of this invention can include, but is not limited to, at least one of the following: user equipment, network equipment, etc. User equipment can include, but is not limited to, computers, smartphones, personal digital assistants (PDAs), and the aforementioned electronic devices. Network equipment can include, but is not limited to, a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing consisting of a large number of computers or network servers. Cloud computing is a type of distributed computing, consisting of a super virtual computer composed of a group of loosely coupled computers. This embodiment does not limit this. Steps S1 to S5 are detailed below: S1 collects skin temperature data, ambient temperature data, and battery voltage data when the body temperature patch is in contact with human skin using a multimodal sensor; The multimodal sensor includes at least a skin temperature sensor, an ambient temperature sensor, and an analog-to-digital converter for monitoring battery voltage. Skin temperature data is the surface temperature value collected at the point where the temperature patch is applied. Ambient temperature data is the air temperature surrounding the device, used to eliminate the influence of air thermal disturbances on temperature measurement. Battery voltage data reflects the real-time power status of the power supply components.

[0021] In practical applications, the body temperature patch is attached to the skin under the armpit via an adhesive backing. An NTC temperature sensor is in close contact with the skin to collect the body surface temperature, while an ambient temperature sensor is placed on the outside of the flexible circuit board to measure the surrounding air temperature. The analog-to-digital conversion channel inside the MCU (Microcontroller Unit) periodically reads the battery voltage. For example, after attachment, three-channel data are collected synchronously every 30 seconds.

[0022] Using the above method, the body temperature patch continuously and synchronously acquires three types of raw data in a low-power mode: skin temperature, ambient temperature, and battery voltage. Skin temperature data reflects the true thermal state of the body surface, ambient temperature data is used to eliminate interference from airborne thermal disturbances, and battery voltage data is used to monitor the remaining battery power.

[0023] S2, Based on the multi-state perception detection algorithm, analyze the skin temperature data and the ambient temperature data to generate the body temperature patch wearing status and temperature change trend status; The multi-state perception detection algorithm analyzes the skin temperature data and the ambient temperature data to generate the body temperature patch wearing status and temperature change trend status, specifically including: The skin temperature data and the ambient temperature data are subjected to time synchronization and sliding window filtering to generate a synchronized skin temperature sequence. and synchronous ambient temperature sequence ; According to the synchronized skin temperature sequence Calculate the rate of temperature change v and temperature fluctuation within a preset sliding window. The corresponding calculation formula is as follows: In the formula, N represents the total number of sampling points within the preset sliding window; This represents the i-th sampling time within the preset sliding window. ; Indicates at the sampling time The generated synchronized skin temperature value; Indicates at the sampling time The generated synchronized skin temperature value; This represents the arithmetic mean of the synchronized skin temperature sequence within the preset sliding window; Calculate the synchronized skin temperature sequence With the synchronized ambient temperature sequence At sampling time Real-time temperature difference ; At the current sampling moment, if the following conditions are met simultaneously: the temperature change rate is less than a preset change rate threshold, the current value of the synchronized skin temperature sequence is within a reasonable range of human body temperature, the real-time temperature difference meets the preset fitting temperature difference condition, and the temperature fluctuation is less than a preset fluctuation threshold, then the temperature patch is determined to be in an effective fitting state; otherwise, the temperature patch is determined to be in an invalid fitting state.

[0024] The multi-state sensing detection algorithm uses a combination of temperature change rate, temperature fluctuation, and real-time temperature difference between the skin and the environment to identify the current operating condition of the device. The body temperature patch wearing status indicates whether the device is in effective or ineffective contact with the skin. The temperature change trend status reflects whether the body temperature is in a rapid heating, rapid cooling, slow change, or stable phase. Time synchronization aligns the sampling times of skin temperature data and ambient temperature data to ensure temporal comparability. Sliding window filtering smooths the continuously acquired temperature values, reducing instantaneous noise interference. The synchronized skin temperature sequence and the synchronized ambient temperature sequence are sets of temperature values ​​obtained after the above processing.

[0025] Furthermore, the rate of temperature change measures the drastic change in skin temperature data per unit time; a higher value indicates a faster change in body temperature. Temperature fluctuation reflects the dispersion of skin temperature data within a preset sliding window; lower fluctuation indicates a more stable temperature. The preset sliding window refers to the number of continuous sampling points used to calculate the rate of temperature change and temperature fluctuation. The sampling time is the time point corresponding to each temperature value. The real-time temperature difference is the difference between the skin temperature value and the ambient temperature value at the same moment; during effective contact, the skin temperature value is significantly higher than the ambient temperature value.

[0026] It is understandable that the reasonable range of human body temperature is the temperature range that a normal human body can reach, typically set based on clinical experience, between 32℃ and 42℃. Temperature values ​​exceeding this range usually indicate that the device is not being worn or has poor contact. The preset rate of change threshold and preset fluctuation threshold are empirical constants calibrated through numerous experiments. The contact temperature difference condition uses different temperature difference judgment rules based on different ambient temperature ranges, specifically calibrated through experiments. The preset rate of change threshold is used to distinguish whether the temperature is in a state of rapid change; the preset fluctuation threshold is used to determine whether the skin temperature is stable; the contact temperature difference condition is used to determine whether there is a significant heat conduction gradient between the skin and the environment. Only when all four conditions are met simultaneously is the temperature patch considered to be in an effective contact state, meaning the temperature patch is in close contact with the skin and the temperature measurement environment is normal; otherwise, the temperature patch is considered to be in an ineffective contact state, in which case the device may be loose, not being worn, or in an abnormal environment.

[0027] In practical applications, after the user applies the temperature patch to their armpit skin, the system continuously collects skin temperature and ambient temperature. For example, in a room temperature of 25℃, the temperature patch measures a stable skin temperature of approximately 36.5℃. At this point, the temperature change rate is approximately 0.02℃ / second, far below the preset change rate threshold of 0.1℃ / second; the temperature fluctuation is approximately 0.05℃, less than the preset fluctuation threshold of 0.2℃; and the real-time temperature difference is approximately 11.5℃, greater than the preset minimum temperature difference threshold of 5℃, thus meeting the temperature difference condition for effective application. The current skin temperature is 36.5℃, within the reasonable range of human body temperature (32℃ to 42℃). When all four conditions are met, the system determines it to be in an effective application state. If the temperature patch comes loose and the skin temperature rapidly drops to 28℃, with a real-time temperature difference of only 3℃, it is determined to be in an ineffective application state, and the system immediately enters deep sleep mode to reduce power consumption.

[0028] The synchronized skin temperature sequence was analyzed using the least squares method. Perform linear regression fitting to calculate the slope k of the temperature trend over time. The corresponding calculation formula is as follows: In the formula, M represents the total number of sampling points within the linear regression fitting window; This represents the j-th sampling time within the linear regression fitting window. ; This represents the arithmetic mean of the sampling times within the linear regression fitting window; Indicates at the sampling time The generated synchronized skin temperature value; This represents the arithmetic mean of the synchronized skin temperature sequence within the linear regression fitting window; The temperature change trend state is generated based on the range of values ​​for the slope k of the temperature trend.

[0029] Least squares is a mathematical method that finds the best-fitting straight line for data by minimizing the sum of squared errors. Linear regression fitting uses least squares to fit a straight line to the trend of skin temperature data over time. The slope of the temperature trend is the slope of the fitted straight line, reflecting the rate of temperature increase or decrease: a positive slope indicates rising temperature, a negative slope indicates falling temperature, and a larger absolute value indicates a more drastic change. The linear regression fitting window refers to the set of continuous sampling points used to calculate the slope of the temperature trend; the window size affects the sensitivity of temperature trend detection. The arithmetic mean is the average of all sampling times or temperature values ​​within the window.

[0030] Specifically, different states are defined based on the range of temperature trend slope: when the temperature trend slope is greater than the first positive threshold of 0.2℃ / min, it is determined to be a rapid temperature rise trend; when the temperature trend slope is between the second positive threshold of 0.05℃ / min and the first positive threshold of 0.2℃ / min, it is determined to be a slow temperature rise trend; when the absolute value of the temperature trend slope is less than the stability threshold of 0.05℃ / min, it is determined to be a stable temperature trend; when the temperature trend slope is between the first negative threshold of -0.2℃ / min and the second negative threshold of -0.05℃ / min, it is determined to be a slow temperature fall trend; and when the temperature trend slope is less than the first negative threshold of -0.2℃ / min, it is determined to be a rapid temperature fall trend.

[0031] The above method enables accurate identification of the wearing status of the body temperature patch and the temperature change trend. The wearing status determines whether the device enters deep sleep mode or active monitoring mode, while the temperature change trend provides a basis for adaptively adjusting the temperature sampling interval and dynamic compensation intensity, thus ensuring that the system can balance temperature measurement accuracy and low power consumption in different usage scenarios.

[0032] S3, if the temperature patch is in an invalid contact state, then control the temperature patch to enter a deep sleep mode, which has low power intermittent detection and automatic wake-up functions. If the temperature patch is in an ineffective contact state, the temperature patch is controlled to enter a deep sleep mode. The deep sleep mode has low-power intermittent detection and automatic wake-up functions, specifically including: If the body temperature patch is in the invalid contact state, the MCU of the body temperature patch is controlled to enter the deep sleep mode, all peripherals except for the low power timer and the button wake-up interface are turned off, and the system clock is switched to a low frequency clock source. In the deep sleep mode, the MCU is periodically woken up with a preset low-power wake-up cycle. After each wake-up, the temperature sensor is activated to collect the current skin temperature data and the current ambient temperature data. If the current skin temperature data is greater than the preset lower limit threshold of human body temperature and the difference between the current skin temperature data and the current ambient temperature data meets the preset fit temperature difference condition, then it is determined that the body temperature patch is in the effective fit state and automatically exits the deep sleep mode. Otherwise, if the temperature patch is determined to be in an invalid fit state, the MCU will re-enter the deep sleep mode and wait for the next low-power wake-up cycle.

[0033] Deep sleep mode refers to the MCU entering a state of minimum power consumption, stopping most modules to save energy. A low-power timer is a peripheral that maintains its timing function even in deep sleep mode, used to periodically wake the MCU. The button wake-up interface is used to detect external button input to manually wake the device. A low-frequency clock source uses a low-speed crystal oscillator (e.g., 32.768kHz), which consumes less power compared to high-frequency clocks. The low-power wake-up cycle is the time interval between two wake-ups, for example, 5 minutes, balancing power consumption and timely detection. The lower limit threshold for human body temperature is a temperature boundary value, typically set at 32℃; below this value, the device is considered not in contact with the human body.

[0034] Understandably, the temperature sensor is only briefly activated after the user wakes up, and is powered off the rest of the time. Automatic exit from deep sleep mode is triggered when the detected skin temperature exceeds the lower limit of human body temperature and the difference between the current skin temperature and the current ambient temperature meets the temperature difference requirement for proper contact. The system then resumes normal operation. This entire mechanism ensures that the device operates intermittently with extremely low power consumption during ineffective contact, and automatically resumes operation once contact is re-contacted.

[0035] In practical applications, after the user removes the temperature patch from their skin, the system detects a rapid drop in skin temperature to 28°C, below the human body temperature threshold of 32°C, with minimal temperature fluctuation, indicating an invalid application. The MCU immediately enters deep sleep mode, disabling wireless communication, indicator lights, and other peripherals, retaining only the low-power timer, and switching the system clock to a 32.768kHz low-frequency clock source. The low-power wake-up cycle is preset to 5 minutes, with the MCU waking up every 5 minutes to quickly activate the temperature sensor to collect current skin temperature data, while all other peripherals remain off. If the user does not reapply the patch, and the skin temperature remains below 32°C, the MCU immediately re-enters deep sleep after each wake-up, reducing the overall average operating current to the microamp level and significantly extending battery life. When the user reapplies the temperature patch to their armpit, a skin temperature of 36.2°C is collected after a single wake-up, exceeding 32°C. Furthermore, the skin temperature of 36.2°C and the ambient temperature of 35°C are greater than the dynamic temperature difference threshold of 0.5°C, satisfying the application temperature difference condition. The system automatically exits deep sleep mode and resumes wireless communication and normal operation. Throughout the process, the button wake-up interface also supports users to manually press and hold the button to force wake up the device, which is convenient for operation in special situations.

[0036] The above method minimizes device power consumption in invalid bonding states. Periodically waking the MCU using a low-power timer for bonding state re-inspection avoids energy waste from continuous sampling and ensures timely exit from deep sleep mode after re-bonding, significantly extending battery life.

[0037] S4, if the temperature patch is in an effective fit, control the temperature patch to enter the active monitoring mode, adaptively adjust the temperature sampling interval according to the temperature change trend, generate a dynamic sampling sequence, and collect time-series temperature data according to the dynamic sampling sequence. The step of adaptively adjusting the temperature sampling interval based on the temperature change trend to generate a dynamic sampling sequence, and collecting time-series body temperature data according to the dynamic sampling sequence, specifically includes: Based on a preset sampling interval mapping rule, the temperature sampling interval is adaptively determined according to the temperature change trend state. If the temperature change trend is a rapid heating trend or a rapid cooling trend, then the temperature sampling interval is set to the first temperature sampling interval. If the temperature change trend is a slow heating trend or a slow cooling trend, then the temperature sampling interval is set to the second temperature sampling interval. If the temperature change trend is a stable temperature trend, then the temperature sampling interval is set to the third temperature sampling interval. The temperature sampling interval is set as the sampling period to generate the dynamic sampling sequence. According to the sampling time in the dynamic sampling sequence, the temperature sensor is activated to collect the current skin temperature data, and the current skin temperature data is stored in time sequence as the time-series body temperature data. Wherein, the first temperature sampling interval is smaller than the second temperature sampling interval, and the second temperature sampling interval is smaller than the third temperature sampling interval.

[0038] The preset sampling interval mapping rule is a table that corresponds to the temperature change trend state and the temperature sampling interval, defining the sampling interval values ​​to be used under different states. The temperature sampling interval refers to the time length between two adjacent temperature acquisitions. The first, second, and third temperature sampling intervals are three progressively increasing time values, for example, set to 5 seconds, 30 seconds, and 120 seconds respectively, corresponding to three trend states: rapid change, slow change, and stable. The sampling period is the currently effective temperature sampling interval, used to control the temperature acquisition frequency. The dynamic sampling sequence is a sequence of sampling time points that is dynamically adjusted according to real-time state changes; its interval is not a fixed value but adapts to the temperature change trend state. Time-series body temperature data is a set of skin temperature values ​​stored in chronological order of acquisition time, preserving the time dimension information.

[0039] In practical applications, taking the process of a child's fever as an example, when the temperature patch determines that the temperature trend is a rapid rise, the system sets the temperature sampling interval to the first temperature sampling interval, for example, 5 seconds. The MCU activates the temperature sensor every 5 seconds to collect the current skin temperature and stores it as time-series body temperature data. As the body temperature stabilizes, the temperature trend switches to a stable temperature trend, and the temperature sampling interval automatically adjusts to the third temperature sampling interval, for example, 120 seconds. At this time, the device samples at a lower frequency, significantly reducing power consumption. If the user's body temperature drops rapidly after taking antipyretics, the temperature trend changes to a rapid cooling trend, and the temperature sampling interval returns to 5 seconds, ensuring intensive collection of data throughout the cooling process. The dynamic sampling sequence adapts to the real-time status, avoiding data redundancy and ensuring measurement accuracy during critical stages.

[0040] S5. Construct a heat flow compensation model, perform temperature compensation calculations on the time-series body temperature data, generate body temperature data, and transmit the body temperature data and battery voltage data to the user terminal via wireless communication encryption. The user terminal displays the status of the body temperature data and battery voltage data and provides abnormal warnings.

[0041] Understandably, the wireless communication encryption transmission uses Bluetooth protocol BLE 5.0 or higher, and AES encryption is applied to the packaged body temperature and battery voltage data to prevent data theft or tampering during transmission, ensuring user privacy and security. After receiving the data, the user terminal decrypts it using the corresponding key, displays the real-time body temperature value and temperature change curve, and judges the status based on a preset normal body temperature range: the normal body temperature range is set to axillary temperature of 36.0℃~37.5℃; when the body temperature exceeds 37.5℃, a high body temperature warning is generated; when the body temperature is below 36.0℃, a low body temperature warning is generated; simultaneously, battery voltage data is monitored. If the battery voltage falls below the low battery threshold of 2.7V, a low battery warning is generated. The low battery threshold is an empirical value obtained through constant current discharge experiments calibrated on selected batteries. Warning information is output through interface pop-ups, sound prompts, or message pushes, allowing users to promptly grasp abnormal body temperature or insufficient device battery status, achieving closed-loop monitoring from data collection and encrypted transmission to intelligent feedback.

[0042] The construction of the heat flux compensation model, which performs temperature compensation calculations on the time-series body temperature data to generate body temperature data, specifically includes: The contact thermal resistance of the surface of the body temperature patch in contact with human skin was obtained. Thermal resistance of convective heat transfer between the surface of the body temperature patch and the environment and the thermal conductivity of the flexible circuit board (FPC) of the body temperature patch. ; Based on the contact thermal resistance The convective heat transfer thermal resistance The thermal conductivity coefficient and the time-series body temperature data at the current time c The heat flux compensation model is constructed to generate the estimated body temperature at the current time c. The corresponding calculation formula is as follows: In the formula, This represents the synchronous ambient temperature value generated at the current time c; Indicated based on thermal conductivity coefficient A defined dynamic thermal time constant; This represents the rate of change of skin temperature at the current moment c; The dynamic compensation intensity of the heat flux compensation model is adaptively adjusted based on the temperature change trend. Based on the dynamic compensation intensity The estimated body temperature at the current time c Make corrections and generate corrected body temperature data for the current time c. ; The corrected body temperature data is processed using a Kalman filter algorithm to generate the body temperature data.

[0043] The heat flux compensation model is a mathematical model based on the physical principles of heat conduction. It is used to eliminate heat exchange interference between skin surface temperature and ambient temperature, thus allowing the core body temperature to be deduced from the surface temperature measurement. Contact thermal resistance refers to the resistance to heat transfer between the temperature patch and the skin due to microscopic gaps and material properties; a smaller value facilitates heat conduction. Convective heat transfer resistance describes the degree of obstruction between the temperature patch surface and the surrounding air via convection, and is affected by wind speed and surface material. The thermal conductivity coefficient of the flexible printed circuit board (FPC) reflects the heat conduction capacity of this flexible material. Due to the thinness and flexibility of FPC, its thermal resistance has a significant impact on body temperature measurement. The estimated body temperature is an approximate value calculated based on the heat flux compensation model.

[0044] Next, the ambient temperature and skin temperature values ​​are synchronized in time to eliminate environmental interference. The dynamic thermal time constant depends on the thermal conductivity of the FPC and describes the speed of temperature change response. The skin temperature change rate is the amount of change in skin temperature per unit time. The dynamic compensation intensity is an adjustable weighting factor used to correct the body temperature estimate, automatically changing according to the temperature change trend. The Kalman filter algorithm is a recursive filtering method that effectively suppresses measurement noise and outputs smooth and stable body temperature data. The final generated body temperature data is the value reported to the user.

[0045] In practical applications, taking the process of a child's fever as an example, the following steps are taken: After acquiring the time-series body temperature data (36.2℃), the synchronous ambient temperature (26℃), a temperature difference of 10.2℃, contact thermal resistance, convective heat transfer resistance, and the FPC thermal conductivity coefficient, these values ​​are substituted into the heat flow compensation model to calculate an initial estimated body temperature of 37.5℃. Simultaneously, based on the temperature change trend, a rapid temperature rise is identified, and a larger dynamic compensation intensity of 0.7 is used to correct the estimated body temperature, resulting in a corrected body temperature of 37.11℃. Subsequently, a Kalman filter algorithm is used to smooth the corrected body temperature data from multiple consecutive time points, filtering out sensor noise, and finally generating a stable body temperature of 37.1℃, which is then sent to the user. Once the body temperature data stabilizes, the dynamic compensation intensity automatically decreases to avoid over-correction.

[0046] Through the above methods, the heat flow compensation model effectively eliminates the measurement deviation caused by environmental heat exchange and FPC heat conduction. At the same time, the dynamic compensation intensity is adaptively adjusted according to the temperature change trend, making the displayed body temperature data closer to the true value, taking into account both response speed and steady-state accuracy.

[0047] Based on a preset dynamic compensation mapping rule, the dynamic compensation intensity of the heat flux compensation model is adaptively adjusted according to the temperature change trend, specifically including: If the temperature change trend is a rapid heating trend or a rapid cooling trend, then the dynamic compensation intensity is set to the first compensation intensity value. If the temperature change trend is a slow heating trend or a slow cooling trend, then the dynamic compensation intensity is set to the second compensation intensity value. If the temperature change trend is a stable temperature trend, then the dynamic compensation intensity is set to the third compensation intensity value. Wherein, the first compensation strength value is greater than the second compensation strength value, and the second compensation strength value is greater than the third compensation strength value.

[0048] The preset dynamic compensation mapping rule establishes a correspondence between the temperature change trend and the dynamic compensation intensity value, automatically selecting an appropriate dynamic compensation intensity value based on the real-time status. The dynamic compensation intensity is a weighting factor between 0 and 1, used to adjust the proportion of the estimated and measured body temperature values ​​in the correction result. The first compensation intensity value corresponds to a rapid temperature rise or fall trend, taking a larger value (e.g., 0.7) to give the estimated body temperature a higher weight in the correction, thus accelerating the model's response to sudden temperature changes. The second compensation intensity value corresponds to a slow temperature rise or fall trend, taking a moderate value (e.g., 0.4) to balance response speed and stability. The third compensation intensity value corresponds to a stable temperature trend, taking a smaller value (e.g., 0.1) to allow the measured body temperature to dominate, achieving a smooth steady-state output. The three compensation intensity values ​​decrease sequentially to ensure reasonable switching of the correction strategy under different rates of change.

[0049] The above method enables the dynamic compensation intensity to be adaptively adjusted according to the temperature change trend, effectively balancing the timeliness of response when body temperature changes rapidly with the measurement stability in steady state.

[0050] like Figure 2 The diagram shown is a system block diagram of a multi-state sensing adaptive control system for a body temperature patch provided in an embodiment of the present invention. The system includes: The data acquisition module is used to collect skin temperature data, ambient temperature data, and battery voltage data when the body temperature patch is in contact with human skin using a multimodal sensor; The state perception module is used to analyze the skin temperature data and the ambient temperature data based on a multi-state perception detection algorithm to generate the body temperature patch wearing status and temperature change trend status. The sleep control module is used to control the body temperature patch to enter a deep sleep mode if the body temperature patch is in an invalid contact state. The deep sleep mode has low power intermittent detection and automatic wake-up functions. The dynamic sampling module is used to control the body temperature patch to enter the active monitoring mode if the body temperature patch is in an effective fit state, adaptively adjust the temperature sampling interval according to the temperature change trend, generate a dynamic sampling sequence, and collect time-series body temperature data according to the dynamic sampling sequence. The compensation communication module is used to construct a heat flow compensation model, perform temperature compensation calculations on the time-series body temperature data, generate body temperature data, and transmit the body temperature data and battery voltage data to the user terminal via wireless communication encryption. The user terminal displays the status of the body temperature data and battery voltage data and provides abnormal warnings.

[0051] Figure 2 The apparatus of the illustrated embodiment can be used to perform corresponding actions. Figure 1 The steps in the method embodiments shown are implemented in a similar manner and have similar technical effects, and will not be repeated here.

[0052] An electronic device includes a memory and a processor, wherein the memory stores a computer program, and when the processor runs the computer program stored in the memory, the processor executes the steps of a multi-state sensing adaptive control method for a body temperature patch as described in any of the above claims.

[0053] like Figure 3 The diagram shown is a hardware structure schematic of an electronic device according to an embodiment of the present invention. The electronic device 30 includes: a processor 31, a memory 32, and a computer program; wherein... The memory 32 is used to store the computer program, and the memory may also be flash memory. The computer program is, for example, an application program or functional module that implements the above method.

[0054] Processor 31 is configured to execute the computer program stored in the memory to implement the various steps performed by the device in the above method. For details, please refer to the relevant descriptions in the preceding method embodiments.

[0055] Alternatively, the memory 32 can be either standalone or integrated with the processor 31.

[0056] When the memory 32 is a device independent of the processor 31, the device may further include: Bus 33 is used to connect the memory 32 and the processor 31.

[0057] A readable storage medium storing a computer program, which, when executed by a processor, is used to implement the steps of a multi-state sensing adaptive control method for a body temperature patch as described in any of the above claims.

[0058] The readable storage medium can be a computer storage medium or a communication medium. A communication medium includes any medium that facilitates the transfer of computer programs from one location to another. A computer storage medium can be any available medium accessible to a general-purpose or special-purpose computer. For example, a readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application-Specific Integrated Circuit (ASIC). Alternatively, the ASIC can be located in a user equipment. Of course, the processor and the readable storage medium can also exist as discrete components in a communication device. The readable storage medium can be a read-only memory (ROM), random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0059] The present invention also provides a program product including executable instructions stored in a readable storage medium. At least one processor of the device can read the executable instructions from the readable storage medium, and the at least one processor executes the executable instructions to cause the device to implement the methods provided in the various embodiments described above.

[0060] In the embodiments of the above-described device, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly manifested as execution by a hardware processor, or execution by a combination of hardware and software modules within the processor.

[0061] Through the above embodiments, this invention collects skin temperature data, ambient temperature data, and battery voltage data when the temperature patch is in contact with human skin using a multimodal sensor; it analyzes the skin temperature data and ambient temperature data based on a multi-state perception detection algorithm to generate the temperature patch wearing status and temperature change trend status; if the temperature patch is in an invalid wearing state, it is controlled to enter a deep sleep mode, which has low-power intermittent detection and automatic wake-up functions; if the temperature patch is in an effective wearing state, it is controlled to enter an active monitoring mode, adaptively adjusting the temperature sampling interval according to the temperature change trend status, generating a dynamic sampling sequence, and collecting time-series body temperature data according to the dynamic sampling sequence; a heat flow compensation model is constructed to perform temperature compensation calculations on the time-series body temperature data, generating body temperature data, and transmitting the body temperature data and battery voltage data to the user terminal via encrypted wireless communication. The user terminal displays the status of the body temperature data and battery voltage data and provides abnormal warnings, thereby realizing intelligent detection of the temperature patch wearing status, dynamic adjustment of the sampling interval, accurate body temperature compensation, and low-power secure transmission, effectively improving the accuracy of temperature measurement and the device's battery life.

[0062] This invention constructs a heat flux compensation model, comprehensively considering the contact thermal resistance between the temperature patch and the skin, the thermal conductivity of the flexible circuit board, and the convective heat transfer thermal resistance between the device surface and the environment. This model performs real-time heat flux compensation on time-series body temperature data, effectively eliminating the interference of ambient temperature and contact thermal resistance on the measurement results. Simultaneously, it adaptively adjusts the dynamic compensation intensity based on the temperature change trend and further suppresses measurement noise using a Kalman filter algorithm, thereby obtaining high-precision body temperature data. This solves the problems of large measurement deviation and slow response of traditional temperature patches, significantly improving the accuracy and reliability of body temperature measurement. This invention uses a multi-state perception detection algorithm to identify the wearing status of the temperature patch in real time: when an invalid wearing state is determined, the control system immediately enters a deep sleep mode, retaining only a low-power timer and a button wake-up interface, periodically waking up with extremely low power consumption to recheck the wearing state; when an valid wearing state is determined, the system adaptively adjusts the temperature sampling interval based on the temperature change trend. This state-aware dynamic power management mechanism avoids energy waste caused by invalid sampling and frequent wireless transmission, significantly improving battery life. This invention employs encrypted wireless communication to securely transmit body temperature and battery voltage data to the user terminal, effectively preventing the leakage of personal health privacy. The user terminal not only displays real-time body temperature values ​​and temperature change curves, but also provides intelligent warnings based on preset normal body temperature ranges and low battery thresholds. It uses visual, auditory, and other methods to promptly alert users to abnormal body temperature or low device battery, enhancing data transmission security and user experience.

[0063] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A multi-state sensing adaptive control method for a body temperature patch, characterized in that, The method includes: The system collects skin temperature data, ambient temperature data, and battery voltage data when the body temperature patch is in contact with human skin using a multimodal sensor. The skin temperature data and the ambient temperature data are analyzed based on a multi-state perception detection algorithm to generate the wearing status of the body temperature patch and the temperature change trend status. If the temperature patch is in an invalid fit state, the temperature patch is controlled to enter a deep sleep mode, which has low power intermittent detection and automatic wake-up functions. If the temperature patch is in an effective fit, the temperature patch is controlled to enter an active monitoring mode. The temperature sampling interval is adaptively adjusted according to the temperature change trend to generate a dynamic sampling sequence, and the time-series temperature data is collected according to the dynamic sampling sequence. A heat flux compensation model is constructed, and temperature compensation calculations are performed on the time-series body temperature data to generate body temperature data. The body temperature data and the battery voltage data are transmitted to the user terminal via wireless communication encryption. The user terminal displays the status of the body temperature data and the battery voltage data and provides abnormal warnings.

2. The multi-state sensing adaptive control method for a body temperature patch according to claim 1, characterized in that, The multi-state perception detection algorithm analyzes the skin temperature data and the ambient temperature data to generate the body temperature patch wearing status and temperature change trend status, specifically including: The skin temperature data and the ambient temperature data are subjected to time synchronization and sliding window filtering to generate a synchronized skin temperature sequence. and synchronous ambient temperature sequence ; According to the synchronized skin temperature sequence Calculate the rate of temperature change v and temperature fluctuation within a preset sliding window. The corresponding calculation formula is as follows: In the formula, N represents the total number of sampling points within the preset sliding window; This represents the i-th sampling time within the preset sliding window. ; Indicates at the sampling time The generated synchronized skin temperature value; Indicates at the sampling time The generated synchronized skin temperature value; This represents the arithmetic mean of the synchronized skin temperature sequence within the preset sliding window; Calculate the synchronized skin temperature sequence With the synchronized ambient temperature sequence At sampling time Real-time temperature difference ; At the current sampling moment, if the following conditions are met simultaneously: the temperature change rate is less than a preset change rate threshold, the current value of the synchronized skin temperature sequence is within a reasonable range of human body temperature, the real-time temperature difference meets the preset fitting temperature difference condition, and the temperature fluctuation is less than a preset fluctuation threshold, then the temperature patch is determined to be in an effective fitting state; otherwise, the temperature patch is determined to be in an invalid fitting state.

3. The multi-state sensing adaptive control method for a body temperature patch according to claim 2, characterized in that, The synchronized skin temperature sequence was analyzed using the least squares method. Perform linear regression fitting to calculate the slope k of the temperature trend over time. The corresponding calculation formula is as follows: In the formula, M represents the total number of sampling points within the linear regression fitting window; This represents the j-th sampling time within the linear regression fitting window. ; This represents the arithmetic mean of the sampling times within the linear regression fitting window; Indicates at the sampling time The generated synchronized skin temperature value; This represents the arithmetic mean of the synchronized skin temperature sequence within the linear regression fitting window; The temperature change trend state is generated based on the range of values ​​for the slope k of the temperature trend.

4. The multi-state sensing adaptive control method for a body temperature patch according to claim 1, characterized in that, If the temperature patch is in an ineffective contact state, the temperature patch is controlled to enter a deep sleep mode. The deep sleep mode has low-power intermittent detection and automatic wake-up functions, specifically including: If the body temperature patch is in the invalid contact state, the MCU of the body temperature patch is controlled to enter the deep sleep mode, all peripherals except for the low power timer and the button wake-up interface are turned off, and the system clock is switched to a low frequency clock source. In the deep sleep mode, the MCU is periodically woken up with a preset low-power wake-up cycle. After each wake-up, the temperature sensor is activated to collect the current skin temperature data and the current ambient temperature data. If the current skin temperature data is greater than the preset lower limit threshold of human body temperature and the difference between the current skin temperature data and the current ambient temperature data meets the preset fit temperature difference condition, then it is determined that the body temperature patch is in the effective fit state and automatically exits the deep sleep mode. Otherwise, if the temperature patch is determined to be in an invalid fit state, the MCU will re-enter the deep sleep mode and wait for the next low-power wake-up cycle.

5. The multi-state sensing adaptive control method for a body temperature patch according to claim 1, characterized in that, The step of adaptively adjusting the temperature sampling interval based on the temperature change trend to generate a dynamic sampling sequence, and collecting time-series body temperature data according to the dynamic sampling sequence, specifically includes: Based on a preset sampling interval mapping rule, the temperature sampling interval is adaptively determined according to the temperature change trend state. If the temperature change trend is a rapid heating trend or a rapid cooling trend, then the temperature sampling interval is set to the first temperature sampling interval. If the temperature change trend is a slow heating trend or a slow cooling trend, then the temperature sampling interval is set to the second temperature sampling interval. If the temperature change trend is a stable temperature trend, then the temperature sampling interval is set to the third temperature sampling interval. The temperature sampling interval is set as the sampling period to generate the dynamic sampling sequence. According to the sampling time in the dynamic sampling sequence, the temperature sensor is activated to collect the current skin temperature data, and the current skin temperature data is stored in time sequence as the time-series body temperature data. Wherein, the first temperature sampling interval is smaller than the second temperature sampling interval, and the second temperature sampling interval is smaller than the third temperature sampling interval.

6. The multi-state sensing adaptive control method for a body temperature patch according to claim 1, characterized in that, The construction of the heat flux compensation model, which performs temperature compensation calculations on the time-series body temperature data to generate body temperature data, specifically includes: The contact thermal resistance of the surface of the body temperature patch in contact with human skin was obtained. Thermal resistance of convective heat transfer between the surface of the body temperature patch and the environment and the thermal conductivity of the flexible circuit board (FPC) of the body temperature patch. ; Based on the contact thermal resistance The convective heat transfer thermal resistance The thermal conductivity coefficient and the time-series body temperature data at the current time c The heat flux compensation model is constructed to generate the estimated body temperature at the current time c. The corresponding calculation formula is as follows: In the formula, This represents the synchronous ambient temperature value generated at the current time c; Indicated based on thermal conductivity coefficient A defined dynamic thermal time constant; This represents the rate of change of skin temperature at the current moment c; The dynamic compensation intensity of the heat flux compensation model is adaptively adjusted based on the temperature change trend. Based on the dynamic compensation intensity The estimated body temperature at the current time c Make corrections and generate corrected body temperature data for the current time c. ; The corrected body temperature data is processed using a Kalman filter algorithm to generate the body temperature data.

7. The multi-state sensing adaptive control method for a body temperature patch according to claim 6, characterized in that, Based on a preset dynamic compensation mapping rule, the dynamic compensation intensity of the heat flux compensation model is adaptively adjusted according to the temperature change trend, specifically including: If the temperature change trend is a rapid heating trend or a rapid cooling trend, then the dynamic compensation intensity is set to the first compensation intensity value. If the temperature change trend is a slow heating trend or a slow cooling trend, then the dynamic compensation intensity is set to the second compensation intensity value. If the temperature change trend is a stable temperature trend, then the dynamic compensation intensity is set to the third compensation intensity value. Wherein, the first compensation strength value is greater than the second compensation strength value, and the second compensation strength value is greater than the third compensation strength value.

8. A multi-state sensing adaptive control system for a body temperature patch, characterized in that, The system, applied to the multi-state sensing adaptive control method for a body temperature patch as described in any one of claims 1-7, comprises: The data acquisition module is used to collect skin temperature data, ambient temperature data, and battery voltage data when the body temperature patch is in contact with human skin using a multimodal sensor; The state perception module is used to analyze the skin temperature data and the ambient temperature data based on a multi-state perception detection algorithm to generate the body temperature patch wearing status and temperature change trend status. The sleep control module is used to control the body temperature patch to enter a deep sleep mode if the body temperature patch is in an invalid contact state. The deep sleep mode has low power intermittent detection and automatic wake-up functions. The dynamic sampling module is used to control the body temperature patch to enter the active monitoring mode if the body temperature patch is in an effective fit state, adaptively adjust the temperature sampling interval according to the temperature change trend, generate a dynamic sampling sequence, and collect time-series body temperature data according to the dynamic sampling sequence. The compensation communication module is used to construct a heat flow compensation model, perform temperature compensation calculations on the time-series body temperature data, generate body temperature data, and transmit the body temperature data and battery voltage data to the user terminal via wireless communication encryption. The user terminal displays the status of the body temperature data and battery voltage data and provides abnormal warnings.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor runs the computer program stored in the memory, the processor executes the steps of the multi-state sensing adaptive control method for body temperature patches as described in any one of claims 1-7.

10. A readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it is used to implement the steps of the multi-state sensing adaptive control method for body temperature patches as described in any one of claims 1-7.

Images