Temperature measurement method and device based on rechargeable thermometer, medium and equipment

Abstract

The invention relates to the technical field of medical health equipment, in particular to a temperature measurement method and device based on a rechargeable thermometer, a medium and equipment. The method comprises the following steps: determining a body temperature acquisition time interval; according to the acquisition time interval, acquiring body temperature data of the target user at each preset acquisition time point in the target time window to obtain a body temperature sequence of the target user; according to the body temperature sequence of the target user, the residual electric quantity value of the super-capacitor charging thermometer and a power consumption prediction model, obtaining predicted average power consumption corresponding to the key time window and the predicted highest body temperature of the target user; obtaining an updated acquisition time interval according to the predicted average power consumption corresponding to the key time window, the predicted highest body temperature of the target user and a preset dynamic control algorithm; and skipping to the step of collecting the body temperature sequence of the target user. The electric quantity of the super-capacitor charging thermometer is reasonably used, and the problem that power consumption is too fast due to long-time high-frequency measurement is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical health equipment, in particular to a temperature measurement method and device based on a rechargeable thermometer, a medium and equipment. BACKGROUND

[0002] In the medical care scene, for patients who need to monitor body temperature continuously (such as fever patients, postoperative rehabilitation population, etc.), rechargeable thermometers are commonly used monitoring tools. However, there is a prominent problem in the use of existing rechargeable thermometers: in order to timely grasp the body temperature change of the patient, it is often necessary to maintain a high measurement frequency (for example, measuring once every 10 minutes), but this will cause the power consumption of the thermometer to be too fast, and frequent charging operations not only affect the continuity of monitoring, but also may miss critical body temperature data due to power depletion, causing inconvenience to medical care. Especially for patients who need to monitor body temperature for a long time and continuously, how to ensure the timeliness of body temperature monitoring while reducing the power consumption of the thermometer to prolong the use time has become a technical problem to be solved in the application of the current rechargeable thermometer. SUMMARY

[0003] The technical problem to be solved by the present application is how to ensure the timeliness of body temperature monitoring while reducing the power consumption of the thermometer to prolong the use time.

[0004] In order to solve the above technical problems, according to the first aspect of the present application, a temperature measurement method based on a rechargeable thermometer is provided, the method comprising: determining a body temperature collection time interval; collecting body temperature data of a target user at each preset collection time point within a target time window according to the collection time interval to obtain a body temperature sequence of the target user; wherein the end time of the target time window is the current time; wherein the time interval between any two adjacent preset collection time points is the same; obtaining a predicted average power consumption corresponding to a key time window and a predicted highest body temperature of the target user according to the body temperature sequence of the target user, the remaining power value of the supercapacitor rechargeable thermometer and a power consumption prediction model; wherein the start time of the key time window is the end time of the target time window; obtaining an updated collection time interval according to the predicted average power consumption corresponding to the key time window and the predicted highest body temperature of the target user, and a preset dynamic control algorithm; and jumping to the step of "collecting body temperature data of a target user at each preset collection time point within a target time window according to the collection time interval to obtain a body temperature sequence of the target user".

[0005] According to the second aspect of the present application, a temperature measurement device based on a rechargeable thermometer is provided, the device comprising: determining a body temperature collection time interval; collecting, by a collection unit, body temperature data of the target user at each preset collection time point within a target time window according to the collection time interval, to obtain a body temperature sequence of the target user; an end time of the target time window is a current time; a time interval between any two adjacent preset collection time points is the same; predicting, by a prediction unit, a predicted average power consumption corresponding to a key time window and a predicted highest body temperature of the target user according to the body temperature sequence of the target user, the residual power value of the supercapacitor charged thermometer, and a power consumption prediction model; a start time of the key time window is the end time of the target time window; updating, by an updating unit, the collection time interval according to the predicted average power consumption corresponding to the key time window, the predicted highest body temperature of the target user, and a preset dynamic control algorithm; and jumping to the collection unit.

[0006] According to a third aspect of the present application, a non-transitory computer readable storage medium is provided, and the storage medium stores at least one instruction or at least one program. The at least one instruction or at least one program is loaded and executed by a processor to implement the above-mentioned temperature measurement method based on the charged thermometer.

[0007] According to a fourth aspect of the present application, an electronic device is provided, which includes a processor and the above-mentioned non-transitory computer readable storage medium.

[0008] The present application has at least the following beneficial effects: The temperature measurement method based on the charged thermometer provided in the application first acquires a body temperature sequence of a target user in a target time window according to a set collection time interval. Since the end time of the target time window is the current time, the body temperature sequence can reflect the recent body temperature change of the user. Then, the predicted average power consumption corresponding to a key time window and the predicted highest body temperature of the user are obtained by combining the body temperature sequence, the residual power value of the super capacitor charged thermometer and the power consumption prediction model. The start time of the key time window is the current time, which means that the predicted average power consumption and the predicted highest body temperature obtained are related to the next monitoring process. Then, the updated collection time interval is obtained through the preset dynamic control algorithm according to the predicted average power consumption corresponding to the key time window and the predicted highest body temperature of the user, and the body temperature data is collected again based on the updated time interval. In this way, when the predicted highest body temperature shows that the body temperature of the user needs to be closely monitored, the dynamic control algorithm can adjust a shorter collection time interval based on this, so as to ensure that the body temperature change can be captured in time, and at the same time, whether the power is sufficient to support the measurement under the interval is judged in combination with the average power consumption. If the power is insufficient, the interval is appropriately extended to avoid power failure in the middle. When the predicted highest body temperature shows that the body temperature of the user is relatively stable, the algorithm can adjust a longer collection time interval. At this time, it can be known in combination with the average power consumption that the power consumption under the longer interval is lower, which can reduce the power consumption, so that the collection frequency is dynamically adjusted according to the actual situation while the continuity and timeliness of the body temperature monitoring are met, the rational use of the power of the super capacitor charged thermometer is realized, and the problem of too fast power consumption caused by long-time high-frequency measurement is avoided. BRIEF DESCRIPTION OF DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0010] Figure 1 The flowchart of the temperature measurement method based on the charged thermometer provided in an embodiment of the present application is shown in the figure. Figure 2 The structural block diagram of the temperature measurement device based on the charged thermometer provided in an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0011] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0012] As Figure 1 shown, a temperature measurement method based on a charged thermometer is provided according to an embodiment of the present application, characterized in that the method comprises: S100, determining a body temperature collection time interval.

[0013] Specifically, the method of the present application is based on a super capacitor charged thermometer for temperature collection, wherein the super capacitor charged thermometer uses super capacitor energy storage technology to realize fast charging (1-5 seconds) to ensure long-term continuous use, improve user experience and reduce maintenance cost. In this embodiment, the super capacitor charged thermometer includes a super capacitor energy storage module: a high-energy-density super capacitor is used to support fast charging within 1-5 seconds. Low-power temperature sensor: such as NTC thermistor, to ensure high-precision temperature measurement while reducing power consumption. Low-power microprocessor: for data acquisition, processing and display control. Display and communication module: such as LCD, E-ink screen or wireless module such as Bluetooth, for data visualization and remote communication. Fast charging interface: using Type-C, magnetic interface, etc. to realize second-level charging. Intelligent power management unit (PMU): using intelligent power optimization strategy to ensure efficient use of super capacitor energy. The intelligent power optimization strategy can adjust the power output strategy according to different working modes (normal working, energy saving, sleep, etc.), such as reducing the microprocessor clock frequency or Bluetooth broadcast frequency in energy saving mode, and only keeping basic functions running. The intelligent power optimization strategy also has an adaptive working mode, that is, when it is judged that the user is in an abnormal body temperature state such as fever, the data sampling rate is increased to ensure temperature measurement accuracy, and the Bluetooth broadcast frequency is increased; when it is judged that the user is in a normal body temperature state, the data sampling rate and the Bluetooth broadcast frequency are reduced, and the energy saving mode is entered, so that the user can continuously monitor the body temperature for a long time. When it is predicted that the user will have a long period of stable body temperature, the deep sleep mode is entered, only the lowest power data sampling rate and Bluetooth broadcast frequency are reserved, and when the user intervenes, it is quickly restored. The intelligent power optimization strategy also sets an adaptive energy management algorithm: based on a long short-term memory (LSTM) neural network model, the energy consumption of the thermometer is predicted in real time, and a dynamic adjustment strategy is provided according to the prediction result. Specifically, it includes: analyzing historical power consumption data through the LSTM model to predict short-term and long-term power consumption trends; when there is a high power consumption demand such as a predicted user has a fever trend, the data sampling rate is increased to ensure temperature measurement accuracy; when there is a low power consumption demand such as a predicted user has a normal body temperature and no fever trend, the sampling rate is reduced to enter energy saving or sleep mode to prolong the battery life; combined with the environmental temperature and user usage habits, intelligent optimization is realized to improve the overall energy efficiency ratio.

[0014] S200: Based on the collection time interval, collect the body temperature data of the target user at each preset collection time point within the target time window to obtain the body temperature sequence of the target user; wherein, the end time of the target time window is the current time; wherein, the time interval between any two adjacent preset collection time points is the same.

[0015] Specifically, step S200 also includes: S210 performs sliding window mean filtering and low-pass filtering on the target user's body temperature sequence.

[0016] Wherein, the target user's body temperature sequence T = (T1, T2, ..., T... i ,…,T N ); where i = 1, 2, ..., N; where N is the number of temperature data collected within the target time window; T i The i-th temperature data point collected within the target time window; the time interval between any two adjacent temperature data points is the same. For example, in one embodiment, the initial body temperature collection time interval is 20 seconds.

[0017] The body temperature sequence of the target user is subjected to sliding window mean filtering. The sliding window mean filtering process is as follows: ; Among them, T smooth (t) represents the mean-filtered body temperature data at time t; T(t) represents the original body temperature at time t.

[0018] A sliding window mean filter is applied to the target user's body temperature sequence. This involves selecting several consecutive temperature data points from the sequence, calculating their average value as the center of the filter within the window, and repeating this process with a fixed step size. This smooths out any random fluctuations or measurement noise that may exist in the original temperature data. Since body temperature acquisition may be affected by environmental interference and instantaneous equipment errors, the original data sequence may contain isolated outliers or high-frequency fluctuations. The sliding window mean filter can weaken the impact of these local disturbances while preserving the overall trend of body temperature changes. This makes the processed body temperature sequence closer to the true pattern of body temperature changes, providing a more stable and reliable data foundation for subsequent calculations of average power consumption in key time windows and predictions of maximum body temperature based on this sequence. This, in turn, improves the accuracy of dynamically adjusting the acquisition time interval.

[0019] Next, the temperature data after sliding window mean filtering is subjected to low-pass filtering. The specific process is as follows: ; Among them, T filtered (t) is the body temperature value after denoising by the sliding window mean at time t; α is the smoothing factor, α∈(0,1).

[0020] The temperature data after sliding window mean filtering is then subjected to low-pass filtering to further process any relatively high-frequency temperature fluctuations that may still exist after mean filtering. While sliding window mean filtering can smooth out random noise and isolated outliers, it may not completely eliminate residual high-frequency interference unrelated to the true trend of body temperature changes (such as instantaneous signal fluctuations caused by minute sensor vibrations). Low-pass filtering, by setting a specific cutoff frequency, allows low-frequency signals that conform to physiological patterns in body temperature changes (such as the slow rise and fall trend with disease progression) to pass through, while suppressing useless high-frequency signals above that frequency. This process further purifies the data while preserving the core characteristics of body temperature changes, making the processed body temperature sequence more stable and closer to the actual physiological temperature change patterns. This provides more accurate and reliable data for subsequent power consumption prediction, peak body temperature prediction, and dynamic adjustment of the acquisition time interval based on this sequence, thereby improving the stability and effectiveness of the entire body temperature monitoring and control process.

[0021] Furthermore, in one exemplary embodiment of this application, after low-pass filtering, anomaly determination is performed based on the processed body temperature sequence. The specific determination method is as follows: To determine whether body temperature data is persistently abnormal, in one embodiment, if n consecutive body temperature data points ≥ T within a time window of N body temperature data points... normal If n=3 times, and the condition is met, the target user is determined to be in a fever state, and a fever alarm is triggered. Here, T normal The normal body temperature threshold is usually set to 37.5℃.

[0022] S220, if the number of consecutive abnormal body temperature data in the target user's body temperature sequence is less than the preset abnormal number threshold, then jump to the step of obtaining the predicted average power consumption and the predicted highest body temperature of the target user corresponding to the key time window based on the target user's body temperature sequence, the remaining power value of the supercapacitor charging thermometer and the power consumption prediction model.

[0023] Here, if the number of consecutive abnormal body temperature data in the target user's body temperature sequence is less than the preset abnormal number threshold, it means that the target user's body temperature is likely normal at the current time. At this time, the process will jump to the step of obtaining the predicted average power consumption and the predicted highest body temperature of the target user corresponding to the key time window based on the target user's body temperature sequence, the remaining power value of the supercapacitor charging thermometer and the power consumption prediction model, so as to adjust the body temperature collection interval normally.

[0024] S300 obtains the predicted average power consumption and the predicted maximum body temperature of the target user corresponding to the key time window based on the target user's body temperature sequence, the remaining power value of the supercapacitor charging thermometer, and the power consumption prediction model; wherein, the start time of the key time window is the end time of the target time window.

[0025] Specifically, step S300 also includes: S310 performs sliding window mid-range filtering on the target user's body temperature sequence.

[0026] Here, a sliding window median filter is applied to the target user's body temperature sequence to eliminate transient noise. The median filtering process is as follows: ; in, For t i-1 , t i , t i+1 The median value t obtained after sorting these three values. i-1 Let t be the body temperature value at the next time point after the i-th time point. i Let t be the body temperature value at time point i. i+1 Let be the body temperature value at the next time point after the i-th time point.

[0027] As an example: Suppose we have a set of raw body temperature data [36.5, 37.8, 36.6, 36.5, 36.7]. The value 37.8 is likely a measurement error or interference. When i=1 (i.e., processing the second data point 37.8), the window is [t{0}=36.5, t{1}=37.8, t{2}=36.6]. The data within the window is sorted as [36.5, 36.6, 37.8]. The median is 36.6. Therefore, the filtered t1'=36.6, and the abnormal value of 37.8 is effectively filtered out.

[0028] S320 standardizes the body temperature sequence after median filtering.

[0029] Here, the standardization process is as follows: ; where μ T σ represents the average body temperature over the past N time windows; T This represents the standard deviation of body temperature over the past N time windows.

[0030] The S330 uses the standardized body temperature sequence and the remaining power value of the supercapacitor-charged thermometer as inputs to the power consumption prediction model, and obtains the predicted average power consumption and the predicted maximum body temperature of the target user corresponding to the key time window based on the power consumption prediction model.

[0031] Specifically, a feature vector is constructed based on the standardized body temperature sequence and the remaining charge value of the supercapacitor-charged thermometer. The feature vector includes two temperatures: temperature and remaining charge, where the temperature is in sequence mode and the remaining charge is in point value form.

[0032] In one embodiment, the power consumption prediction model can be an LSTM model, wherein the forward propagation process of the LSTM model is as follows: ; where h t This is a hidden state used to capture temporal dependencies, c t It is a cellular state used to maintain long-term memory.

[0033] The LSTM model is used to perform multi-objective prediction output. The output results include the predicted average power consumption and the predicted maximum body temperature of the target user corresponding to the key time window. The key time window is a period of time after the current time.

[0034] In this embodiment, since the supercapacitor-charged thermometer relies on electrical energy to operate, its power consumption directly determines the device's battery life, operational stability, and the effectiveness of the charging strategy. By predicting power consumption over a future period, the device's energy needs can be anticipated, preventing measurement interruptions or data loss due to insufficient power.

[0035] Body temperature sequences are time-series data (reflecting the dynamic changes in a user's body temperature), while the power consumption of the device is strongly correlated with the measurement frequency, data transmission, sensor activation, and other operations. Fluctuations in a user's body temperature may affect the measurement frequency (e.g., high-frequency monitoring is required when the body temperature is abnormal), which in turn affects the power consumption.

[0036] Predicting peak body temperature requires understanding the temporal features of the body temperature sequence, and LSTM models are naturally adept at capturing temporal dependencies. By treating power consumption prediction and body temperature prediction as multi-objective outputs, the model's ability to extract temporal features can be shared, reducing the cost of separate modeling.

[0037] Critical time windows may include peak periods of user body temperature (such as nighttime fever), during which the device must continue operating to capture the highest body temperature. The core value of predicting average power consumption during critical time windows using a power consumption prediction model lies in providing the system with a forward-looking decision-making basis, enabling a shift from passive response to proactive optimization. Specifically, the benefits are: first, ensuring monitoring reliability; by anticipating high power consumption risks, the system can intelligently reduce the power consumption of non-core functions when current battery power is sufficient, reserving power for the temperature measurement module and ensuring uninterrupted monitoring throughout the high-risk period; second, achieving precise energy allocation; by 'peak shaving and valley filling' based on predicted power consumption needs, the system can deeply conserve energy when body temperature is stable and allocate energy only when needed, thereby maximizing battery life while ensuring monitoring effectiveness; and third, improving system energy efficiency and user experience, avoiding drastic measures due to emergency power shortages, making power consumption adjustments smoother, and reducing user interference and battery anxiety. Therefore, predicting power consumption allows the system to allocate energy in advance (such as reducing the power consumption of non-essential functions and prioritizing the operation of the temperature measurement module), ensuring uninterrupted monitoring when the highest body temperature occurs.

[0038] S400: Based on the predicted average power consumption corresponding to the key time window, the predicted highest body temperature of the target user, and the preset dynamic control algorithm, the updated acquisition time interval is obtained; and the process jumps to the step of "According to the acquisition time interval, the body temperature data of the target user at each preset acquisition time point within the target time window is acquired to obtain the body temperature sequence of the target user".

[0039] Specifically, step S400 also includes: S410, determine the minimum sampling interval and the maximum sampling interval.

[0040] S420 obtains the updated sampling time interval based on the minimum sampling interval, the maximum sampling interval, the predicted average power consumption corresponding to the key time window, the predicted maximum body temperature of the target user, and the preset dynamic control algorithm.

[0041] The preset dynamic control algorithm meets the following requirements: ; Among them, S （t） S represents the sampling interval; min S is the minimum sampling interval; max k is the maximum sampling interval. p P is the power sensitivity coefficient; P0 is the power consumption reference value; P avg T represents the predicted average power consumption corresponding to the critical time window. max The predicted peak body temperature for the target user within the critical time window; K T T is the body temperature sensitivity coefficient. normal This is the normal body temperature threshold.

[0042] Here, firstly through S min and S max After determining the basic interval, As an adjustment term for the power consumption dimension, a larger predicted average power consumption corresponding to the key time window means a smaller sampling interval should be used, and vice versa. Conversely, for the adjustment term for the body temperature dimension... The higher the predicted maximum body temperature of the target user corresponding to the critical time window, the more frequently body temperature should be collected. If the body temperature is normal, the adjustment term of the body temperature dimension approaches 0. At this time, the sampling interval is mainly determined by the power consumption dimension (leaning towards a low frequency that saves power).

[0043] This embodiment uses dual-dimensional feedback of power consumption and body temperature to enable the device to intelligently switch between power saving and accurate monitoring. This ensures medical-grade body temperature monitoring accuracy while maximizing device battery life and hardware lifespan, representing the core embodiment of self-optimization in intelligent medical devices.

[0044] It should be noted that, to prevent the sampling interval from jumping around under slight fluctuations in body temperature, smoothing can be performed. The smoothed sampling interval is as follows: S final =α×S prev +(1-α)×S(T; Where α is the smoothing parameter; S prev S(T) represents the actual sampling interval used in the previous calculation cycle; S(T) represents the target sampling interval for the current calculation.

[0045] The recommended value for α is 0.8. You can also set a minimum threshold for switching (e.g., do not update if the difference is less than 3 seconds).

[0046] This embodiment makes the changes in the sampling interval smoother, avoiding drastic, abrupt changes, thereby improving system stability and user experience. When the α value is large (close to 1): historical values ​​S are more trusted. prev When α is small (close to 0), the change is very slow, and the system behaves inertly or stably. When α is small (close to 0), the formula trusts the new calculated value S(T) more, the change is very rapid, and the system responds sensitively.

[0047] In one exemplary embodiment of this application, the method further includes: S500, according to P avg T max and T normal The screen brightness B of the supercapacitor-charged thermometer is dynamically adjusted; wherein B meets the following conditions: ; Where σ is the Sigmoid function; x=k b×(P avg -P0); k b P0 is the sensitivity coefficient; W is the reference power consumption value. b Based on brightness weight; w t Increase the weight of body temperature.

[0048] σ is a sigmoid function whose input is the difference between the predicted power consumption and the reference power consumption. When P avg When k is very low (much less than P0) b ×(P avg -P0) is a very large negative number, and the Sigmoid function output approaches 0. When P avg When k is very high (much greater than P0) b ×(P avg -P0) is a very large positive number, and the output of the Sigmoid function approaches 1.

[0049] It means that when high future power consumption is predicted (P) avg The system only allows higher brightness when the predicted power consumption is very high (far greater than P0). This is because high power consumption means the system is in a high-performance monitoring mode (e.g., frequently sampling and calculating). At this time, the device is actively working, and the user (possibly a healthcare worker or patient) is highly likely to be viewing the device, thus requiring a bright screen to clearly display the data. Conversely, if the predicted power consumption is very low (P...), the system will not allow higher brightness. avg A very low brightness (far below P0) indicates the system is in a low-power sleep or standby mode. The user is likely not looking at the screen, and to save power, the brightness should be limited to a very low range. This ensures that brightness increases only occur when the system is already active, avoiding wasted power when not needed.

[0050] w b It is the base brightness weight, used to set the user's or product's preset base brightness level, ranging from 0 to 1, such as 0.2, 0.3, etc.

[0051] This is the difference between the predicted highest body temperature and the normal body temperature threshold, then scaled by dividing by 2. max The higher the brightness, the more urgent the medical situation, and the more frequently and urgently healthcare workers need to review the data. Therefore, the screen must be brighter to ensure information can be read quickly and clearly in any environment. max Close to or below T normal When this factor approaches 0, it will greatly suppress the final brightness, because there is no urgent information to display at this time, and saving power is the top priority.

[0052] The product of all the preceding factors is magnified by a factor of 100. This is to map the output brightness to a more intuitive percentage range (e.g., 0% to 100%). In practical applications, this value is also clamped, for example, by limiting it to B ∈ [5%, 95%], to ensure there is always a minimum visible brightness and to avoid the screen from being too bright.

[0053] Brightness can also be smoothly transitioned, and the brightness B after the smooth transition is... final Meets the following conditions: B final =b×B pre +(1-b)×B new ; Where b is the parameter for eliminating screen flicker, b∈[0,1]; B pre B is the previous brightness value. new This is the newly calculated brightness value.

[0054] To make screen brightness changes smoother and avoid drastic, abrupt changes, thereby improving system stability and user experience, if the system wants a smoother change, b can be made closer to 1, so that the adjusted brightness is closer to the previous brightness. Conversely, b should be made closer to 0.

[0055] In one exemplary embodiment of this application, the daily energy quota E daily =0.101mw × (24 / 30) = 0.08i08mw; Here, the supercapacitor-charged thermometer has a battery life of 30 hours, and 0.101mw is the average power of a device assuming it is operating in reference mode (or nominal mode).

[0056] In one exemplary embodiment of this application, if the cumulative energy consumption is equal to or greater than 90% of the daily energy quota, the system is forced to enter an extreme power-saving mode. In this mode, the sampling interval is 1 hour.

[0057] The method provided in this application is described below with reference to a specific embodiment 1: A hospital emergency room receives a suspected influenza patient whose body temperature rises rapidly, requiring continuous monitoring and real-time alarm.

[0058] Input parameters: Body temperature sequence: 36.5℃→37.8℃→38.5℃→39.0℃ (sampling interval 20 seconds); Remaining battery power (SOC): 0.8; Historical power consumption data: average 2.5mW (past 1 hour) The data processing flow is as follows: Data preprocessing: Sliding window mean filtering (N=3): 38.5℃ → 38.5℃; Low-pass filtering (α=0.6): 38.5℃ → 38.3℃; Fever detection: Three consecutive measurements ≥37.5℃ → trigger fever alarm; LSTM prediction: Input features: [filtered body temperature sequence, SOC=0.8].

[0059] Predicted output: Average power consumption in the next 30 minutes is 6.2mw, and the predicted highest body temperature in the next 30 minutes is 39.2℃.

[0060] Dynamic control: Sampling intervals are as follows: However, due to fever, the restraint was forcibly extended for 2 seconds.

[0061] Screen brightness: .

[0062] The final output results are as follows: Sampling interval: 2 seconds (highest frequency); Screen brightness: 95% (high brightness); Bluetooth broadcast: real-time transmission; System alarm: continuous beeping + red screen flashing.

[0063] Here, if a fever occurs, even if the calculated sampling interval is large, the minimum sampling interval can be forced to be used to obtain more body temperature data.

[0064] The method provided in this application is described below with reference to a specific embodiment 2: When a user monitors their body temperature at home daily, the body temperature is stable, and the device needs to maximize its battery life.

[0065] Input parameters: Body temperature sequence: 36.6℃±0.1℃ (fluctuation); Ambient temperature: 22℃ (room temperature); Remaining power (SOC): 0.4; Historical power consumption data: average 1.2mW (past 3 hours).

[0066] Processing flow: Data preprocessing: sliding window mean filtering (N=3): 36.6℃; low-pass filtering (α=0.6): 36.6℃.

[0067] Fever assessment: No abnormal data → No alarm.

[0068] LSTM prediction Input features: [filtered body temperature sequence, SOC=0.4].

[0069] Predicted output: Average power consumption in the next 30 minutes is 1.5mw, and the predicted highest body temperature in the next 30 minutes is 36.7℃.

[0070] Dynamic control: Sampling intervals are as follows: Forced constraint for 30 seconds.

[0071] Screen brightness: .

[0072] The final output results are as follows: Sampling interval: 10 seconds (lowest frequency); Screen brightness: 5% (sleep display only); Bluetooth broadcast: off; Working mode: deep sleep (wakes up every 2 hours to upload data).

[0073] It should be noted that users can charge the thermometer via Type-C, magnetic charging, or wireless charging. The charging current is optimized by the power management module and stored in the supercapacitor. Charging time is controlled within 1-5 seconds to ensure quick use.

[0074] During temperature measurement and use: The low-power temperature sensor collects body temperature data and transmits it to the microprocessor. The processor performs data processing and displays the temperature measurement results. An ultra-low power consumption strategy ensures that the supercapacitor can support continuous use for extended periods. The intelligent power management unit reduces power consumption and extends battery life during standby or low-usage states.

[0075] In one exemplary embodiment of this application, such as Figure 2 As shown, this application also provides a temperature measuring device 100 based on a rechargeable thermometer, the device comprising: The determination unit 110 is used to determine the time interval for body temperature collection.

[0076] The acquisition unit 120 is used to acquire the body temperature data of the target user at each preset acquisition time point within the target time window according to the acquisition time interval, so as to obtain the body temperature sequence of the target user; wherein the end time of the target time window is the current time; wherein the time interval between any two adjacent preset acquisition time points is the same.

[0077] The prediction unit 130 is used to obtain the predicted average power consumption and the predicted maximum body temperature of the target user corresponding to the key time window based on the target user's body temperature sequence, the remaining power value of the supercapacitor charging thermometer, and the power consumption prediction model; wherein, the start time of the key time window is the end time of the target time window.

[0078] The update unit 140 is used to obtain the updated acquisition time interval based on the predicted average power consumption corresponding to the key time window, the predicted maximum body temperature of the target user, and the preset dynamic control algorithm; and then jump to the acquisition unit.

[0079] Embodiments of this application also provide a computer program product including program code that, when the program product is run on an electronic device, causes the electronic device to perform the steps of the methods described above according to various exemplary embodiments of this application.

[0080] Furthermore, although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0081] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, mobile terminal, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0082] In an exemplary embodiment of this disclosure, an electronic device capable of implementing the above-described method is also provided.

[0083] Those skilled in the art will understand that various aspects of this application can be implemented as a system, method, or program product. Therefore, various aspects of this application can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, collectively referred to herein as a "circuit," "module," or "system."

[0084] An electronic device according to this embodiment of the present application. The electronic device is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present application.

[0085] Electronic devices are manifested in the form of general-purpose computing devices. Components of an electronic device may include, but are not limited to: at least one processor, at least one memory, and buses connecting different system components (including memory and processor).

[0086] The memory stores program code that can be executed by a processor, causing the processor to perform the steps described in the "Exemplary Methods" section above, according to various exemplary embodiments of this application.

[0087] The storage may include readable media in the form of volatile storage, such as random access memory (RAM) and / or cache memory, and may further include read-only memory (ROM).

[0088] The storage may also include programs / utilities having a set (at least one) of program modules, including but not limited to: an operating system, one or more applications, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0089] A bus can represent one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus that uses any of the various bus architectures.

[0090] The electronic device can also communicate with one or more external devices (such as keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device, and / or any device that enables the electronic device to communicate with one or more other computing devices (such as routers, modems, etc.). This communication can be performed via input / output (I / O) interfaces. Furthermore, the electronic device can communicate with one or more networks (such as local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter. As shown in the figure, the network adapter communicates with other modules of the electronic device via a bus. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0091] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0092] In exemplary embodiments of this disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the methods described above is stored. In some possible implementations, various aspects of this application may also be implemented as a program product including program code, which, when the program product is run on a terminal device, causes the terminal device to perform the steps of the various exemplary embodiments of this application described in the "Exemplary Methods" section above.

[0093] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0094] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0095] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0096] Program code for performing the operations of this application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0097] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of this application, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0098] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0099] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A temperature measurement method based on a rechargeable thermometer, characterized in that, The method includes: Determine the time interval for temperature collection; Based on the collection time interval, the body temperature data of the target user is collected at each preset collection time point within the target time window to obtain the body temperature sequence of the target user; wherein, the end time of the target time window is the current time; wherein, the time interval between any two adjacent preset collection time points is the same. Based on the target user's body temperature sequence, the remaining power value of the supercapacitor charging thermometer, and the power consumption prediction model, the predicted average power consumption and the predicted maximum body temperature of the target user corresponding to the key time window are obtained; where the start time of the key time window is the end time of the target time window. Based on the predicted average power consumption corresponding to the key time window, the predicted highest body temperature of the target user, and the preset dynamic control algorithm, the updated collection time interval is obtained; and the process jumps to the step of "collecting the body temperature data of the target user at each preset collection time point within the target time window according to the collection time interval, so as to obtain the body temperature sequence of the target user".

2. The temperature measurement method based on a rechargeable thermometer according to claim 1, characterized in that, Before obtaining the predicted average power consumption and the predicted maximum body temperature of the target user corresponding to the key time window based on the target user's body temperature sequence, the remaining power value of the supercapacitor charging thermometer, and the power consumption prediction model, the method further includes: Sliding window mean filtering and low-pass filtering are applied to the body temperature sequence of the target user; If the number of consecutive abnormal body temperature data in the target user's body temperature sequence is less than the preset abnormal number threshold, then proceed to the step of obtaining the predicted average power consumption and the predicted highest body temperature of the target user corresponding to the key time window based on the target user's body temperature sequence, the remaining power value of the supercapacitor charging thermometer, and the power consumption prediction model.

3. The temperature measurement method based on a rechargeable thermometer according to claim 1, characterized in that, Based on the target user's body temperature sequence, the remaining charge value of the supercapacitor-charged thermometer, and the power consumption prediction model, the predicted average power consumption and the predicted maximum body temperature of the target user corresponding to the key time window are obtained, including: Apply sliding window mid-value filtering to the target user's body temperature sequence; The body temperature sequence after median filtering was standardized. The standardized body temperature sequence and the remaining power value of the supercapacitor-charged thermometer are used as inputs to the power consumption prediction model. Based on the power consumption prediction model, the predicted average power consumption and the predicted maximum body temperature of the target user are obtained for the key time window.

4. The temperature measurement method based on a rechargeable thermometer according to claim 1, characterized in that, Based on the predicted average power consumption corresponding to the key time window, the predicted maximum body temperature of the target user, and the preset dynamic control algorithm, the updated data acquisition time interval is obtained, including: Determine the minimum and maximum sampling intervals; The updated sampling time interval is obtained based on the minimum sampling interval, the maximum sampling interval, the predicted average power consumption corresponding to the key time window, the predicted maximum body temperature of the target user, and the preset dynamic control algorithm.

5. The temperature measurement method based on a rechargeable thermometer according to claim 4, characterized in that, The preset dynamic control algorithm meets the following requirements: ； Among them, S （t） S represents the sampling interval; min S is the minimum sampling interval; max k is the maximum sampling interval. p P is the power sensitivity coefficient; P0 is the power consumption reference value; P avg T represents the predicted average power consumption corresponding to the critical time window. max The predicted peak body temperature for the target user within the critical time window; K T T is the body temperature sensitivity coefficient. normal This is the normal body temperature threshold.

6. The temperature measurement method based on a rechargeable thermometer according to claim 5, characterized in that, The method further includes: According to P avg T max and T normal The screen brightness B of the supercapacitor-charged thermometer is dynamically adjusted; wherein B meets the following conditions: ； Where σ is the Sigmoid function; x=k b ×(P avg -P0); k b P0 is the sensitivity coefficient; W is the reference power consumption value. b Based on brightness weight; w t Weight is increased for body weight.

7. A temperature measuring device based on a rechargeable thermometer, characterized in that, The device includes: A determination unit is used to determine the time interval for body temperature collection. The data acquisition unit is used to acquire body temperature data of the target user at each preset acquisition time point within the target time window according to the acquisition time interval, so as to obtain the body temperature sequence of the target user; wherein, the end time of the target time window is the current time; wherein, the time interval between any two adjacent preset acquisition time points is the same. The prediction unit is used to obtain the predicted average power consumption and the predicted maximum body temperature of the target user corresponding to the key time window based on the target user's body temperature sequence, the remaining power value of the supercapacitor charging thermometer, and the power consumption prediction model; wherein, the start time of the key time window is the end time of the target time window. The update unit is used to obtain the updated acquisition time interval based on the predicted average power consumption corresponding to the key time window, the predicted maximum body temperature of the target user, and the preset dynamic control algorithm; and then jump to the acquisition unit.

8. A non-transitory computer-readable storage medium, wherein the storage medium stores at least one instruction or at least one program segment, characterized in that, The at least one instruction or the at least one program segment is loaded and executed by the processor to implement the method as described in any one of claims 1-6.

9. An electronic device, characterized in that, Includes a processor and the non-transitory computer-readable storage medium as described in claim 9.

Images