Offline physical energy scoring method and system for low-computing-power wearable devices

Abstract

The present application relates to the technical field of wearable devices, more particularly, to an offline physical energy scoring method and system for low-computing-power wearable devices. The scheme includes collecting physiological data from 00:00 of the previous day to 03:59 of the current day as the original input data set at 4:00 of the next morning as the fixed settlement time; calculating the sub-item sum based on the sleep parameters and deducting the wake-up time deduction, and clamping the sleep score; generating the HRV and resting heart rate personal baseline according to the cumulative effective morning-up number N, and mapping the output corresponding score; obtaining the exercise score by looking up the table according to the cumulative minute number of high-intensity heart rate in the previous day; after the five scores are weighted and summed according to 0.4, 0.3, 0.15, 0.1 and 0.05, the all-night deduction and physiological period scaling correction are executed in series, and the integral clamping output 0~100 points score and five-grade state level are obtained, the whole process is single settlement, the power consumption is low, and it is suitable for low-computing-power devices.

Description

Technical Field

[0001] This invention relates to the field of wearable device technology, and more specifically, to an offline physical energy scoring method and system for low-computing-power wearable devices. Background Technology

[0002] Low-computing-power wearable devices solve the bottleneck of wearable devices struggling to achieve daily comprehensive health status assessment under low power consumption and low storage constraints. They retain the core indicators with the most physiological representation value, enabling devices to stably output a comprehensive health score of 0-100 points and five levels of status judgment in an extremely energy-saving mode with only one settlement per day. They do not rely on the network, do not collect data frequently, and do not dynamically iterate, providing a low-cost and highly robust health status quantification solution for mass-produced wearable devices. At the same time, they take into account individual baseline differences and special corrections such as women's menstrual periods, achieving an effective balance between practicality and physiological rationality.

[0003] Prior to this invention, existing wearable or smart wearable devices typically rely on mobile apps to calculate near real-time heart rate variability (HRV), activity load, and sleep stages, and use dynamic thresholds to continuously track user status. This approach has extremely high requirements for computing power, memory, and communication power consumption, and cannot be directly ported to low-computing-power hardware. In addition, this invention designs a set of static, coded threshold rules so that the scoring is not affected by daytime disturbances and can adapt to individual differences through rolling baselines. It also properly handles special scenarios such as missing data, gender, menstrual cycle, and staying up late. Ultimately, while ensuring the physiological validity of the scoring, it meets the hard constraints of daily single-time settlement and microampere power consumption. Summary of the Invention

[0004] In view of the above problems, this invention proposes an offline physical energy scoring method and system for low-computing-power wearable devices. By replacing near-real-time calculation with a single offline settlement at 4:00 AM every day, and replacing dynamic threshold tracking with a firmware static threshold table and a three-level progressive personal baseline, the low-computing-power wearable device can stably output a physical energy score of 0 to 100 points and a five-level status determination under microampere power consumption.

[0005] According to a first aspect of the present invention, an offline method for scoring physical energy using a low-computing-power wearable device is provided.

[0006] In one or more embodiments, preferably, the offline physical energy scoring method of the low-computing-power wearable device includes: With 4:00 AM as the fixed settlement time each day, user physiological data from 00:00 the previous day to 03:59 the current day is collected as the raw input dataset; Calculate and sum the nighttime sleep parameters in the original input dataset, deduct the nighttime wakefulness time from the multi-level threshold interval, and output the sleep score after clamping. Based on the cumulative number of valid morning wake-up days N, the general fixed baseline, historical full average, and recent 30-day moving average are called in sequence to generate the HRV personal baseline and the resting heart rate personal baseline. The HRV score and resting heart rate score are output by mapping the percentage and difference between the measured value and the baseline, respectively. Get the cumulative minutes of moderate to high intensity heart rate Tnow from the previous day, and output the exercise score according to the preset multi-level minute threshold interval mapping. The scores of the five components—sleep, HRV, resting heart rate, exercise, and blood oxygen—are weighted and summed with fixed weights of 0.4, 0.3, 0.15, 0.1, and 0.05 to obtain the weighted raw total score. The total score is serially adjusted by deducting late nights and scaling for women's menstrual periods, rounded and clamped to 0-100, and the final comprehensive body score is output.

[0007] In one or more embodiments, preferably, the step of collecting user physiological data from 00:00 of the previous day to 03:59 of the current day, with 4:00 AM as the fixed settlement time each day, as the raw input dataset, specifically includes: The time window is from 00:00 of the previous day to 03:59 of the current day; Within the time window, the following raw data is collected and stored via local sensors on the wearable device: total sleep duration at night. Deep sleep duration, time to fall asleep Total nighttime awake time Mean HRV after 5 minutes of rest upon waking Morning resting heart rate Total minutes of moderate to high intensity heart rate throughout the previous day Sleep onset time and resting blood oxygen saturation ; The settlement is triggered at 4:00 AM every day. After the trigger, all stored data is read and used as the original input dataset.

[0008] In one or more embodiments, preferably, the step of calculating and summing the sub-items based on the nighttime sleep parameters in the original input dataset, deducting points for nighttime wakefulness duration according to multi-level threshold intervals, and outputting a clamped sleep score specifically includes: Extract the total nighttime sleep duration from the original input dataset. Deep sleep duration, time to fall asleep Total nighttime wakefulness ; Calculate the four sub-items separately: duration score Deep sleep percentage Time spent falling asleep Deduction of points for duration of sobriety ; The assignment rules are as follows:

[0009] The assignment rules are as follows:

[0010] Among them, deep sleep accounted for a certain percentage. =Deep sleep duration ÷ ; The assignment rules are as follows:

[0011] The assignment rules are as follows:

[0012] Calculate sleep score using the first calculation formula ; The first calculation formula is:

[0013] Using normalization processing Clamp to Interval, output sleep score .

[0014] In one or more embodiments, preferably, the step of generating a personal HRV baseline and a personal resting heart rate baseline by sequentially calling a general fixed baseline, a historical full average, and a recent 30-day moving average based on the cumulative number of valid morning wake-up days N, and mapping and outputting the HRV score and resting heart rate score respectively using the percentage and difference relationship between the measured value and the baseline, specifically includes: Extract the measured morning HRV values ​​of the day from the original input dataset. and the measured resting heart rate value upon waking on the same day ; The number of days of valid morning data accumulated by statistical equipment Generate the individual HRV baseline for the current settlement period according to the second calculation formula. Personal baseline resting heart rate ; The second calculation formula is:

[0015] in, The personal baseline value used in the current period. These are common adult standard baseline constants built into the firmware. For the first The measured values ​​upon waking on a valid day. This represents the total number of days of cumulative valid data. by For reference, the HRV score is calculated using the third calculation formula. ; The third calculation formula is:

[0016] by For reference, the resting heart rate score is calculated using the fourth calculation formula. ; The fourth calculation formula is:

[0017] If data collection fails at dawn, the data for that day will not be included. Statistics and and The update, and the HRV score or resting heart rate score for the current day uses the valid score from the previous day; the and It is updated only once a day, and is synchronized with the settlement at 4:00 AM.

[0018] In one or more embodiments, preferably, obtaining the cumulative minutes of high-intensity heart rate Tnow from the previous day and outputting an exercise score according to a preset multi-level minute threshold interval specifically includes: Extract the cumulative minutes of moderate-to-high-intensity heart rate (Tnow) from the original input dataset; The fifth calculation formula is used to compare Tnow with the preset multi-level minute threshold range and map the output exercise score Sexer. The fifth calculation formula is: Sexer = 95 (0 ≤ Tnow ≤ 30) Sexer=75 (30) <Tnow≤60) Sexer=55(60) <Tnow≤90) Sexer=25 (90) <Tnow≤120) Sexer=10 (Tnow>120) Tnow only counts the cumulative time that the heart rate is in the preset high-intensity heart rate zone.

[0019] In one or more embodiments, preferably, the step of weighting and summing the scores of the five items—sleep, HRV, resting heart rate, exercise, and blood oxygen—with fixed weights of 0.4, 0.3, 0.15, 0.1, and 0.05 to obtain a weighted raw total score specifically includes: Obtain the following four scores that have been calculated: Sleep Score HRV score Resting heart rate score Sports score ; Extract static blood oxygen saturation from the original input dataset. Blood oxygen score is obtained according to the sixth calculation formula rule. ; The sixth calculation formula is:

[0020] Calculate the weighted raw total score using the seventh formula. ; The seventh calculation formula is:

[0021] All individual scores have been pre-clamped to The weighting coefficients for each interval are fixed at 0.4, 0.3, 0.15, 0.1, and 0.05 and are embedded in the firmware.

[0022] In one or more embodiments, preferably, the step of serially performing deductions for staying up late, scaling corrections for women's menstrual periods, rounding and clamping to 0-100 on the total score, and outputting the final comprehensive body score specifically includes: The weighted original total score As the sole object of correction; Perform the first-level correction, determining whether the person fell asleep later than 1:00 AM that day. If so, then... The weighted original total score is then corrected by subtraction: If not, then No operation is performed; Perform a second-level correction, determining whether the user's gender is marked as female and a menstrual period marker exists in the current billing cycle simultaneously. The menstrual period marker is manually set by the user in the app and synchronized to the wearable device via Bluetooth, and is only effective once within its corresponding billing cycle, automatically expiring at the next day's billing. If so, then... Perform multiplication scaling correction on the result of the previous step: If not, then No operation is performed; The final comprehensive physical score is calculated using the eighth calculation formula. ; The eighth calculation formula is:

[0023] in, This is the rounding function. ; The As the output of the day's comprehensive physical score, the status level is also determined according to the ninth calculation formula; The ninth calculation formula is:

[0024] The menstrual cycle marker is based on the current settlement cycle and is effective only once. The current settlement cycle is from 00:00 of the previous day to 03:59 of the current day. It will automatically expire the next day. If the corrected value is lower than 0, it will eventually be set to 0.

[0025] According to a second aspect of the present invention, an offline physical energy scoring system for low-computing-power wearable devices is provided.

[0026] In one or more embodiments, preferably, the offline physical energy scoring system of the low-computing-power wearable device includes: The timed settlement and data collection module is used to collect user physiological data from 00:00 the previous day to 03:59 the current day at a fixed settlement time of 4:00 AM every day, as the raw input dataset; The sleep scoring module is used to calculate and sum the nighttime sleep parameters based on the original input dataset, deduct the nighttime wakefulness time from the multi-level threshold interval, and output the sleep score after clamping. The baseline self-calibration module is used to generate HRV personal baseline and resting heart rate personal baseline by sequentially calling the general fixed baseline, historical full average, and the recent 30-day moving average based on the cumulative number of valid morning wake-up days N. The HRV score and resting heart rate score are mapped and output respectively by the percentage and difference relationship between the measured value and the baseline. The exercise load scoring module is used to obtain the cumulative minutes of moderate to high intensity heart rate Tnow from the previous day, and output the exercise score according to the preset multi-level minute threshold interval. The weighted fusion module is used to sum the scores of five items—sleep, HRV, resting heart rate, exercise, and blood oxygen—with fixed weights of 0.4, 0.3, 0.15, 0.1, and 0.05 to obtain the weighted raw total score. The correction output module is used to perform serial deduction for staying up late and scaling correction for women's menstrual periods on the total score, round it down and clamp it to 0~100, and output the final comprehensive body score.

[0027] According to a third aspect of the present invention, a computer-readable storage medium is provided, on which computer program instructions are stored, which, when executed by a processor, implement the method as described in any one of the first aspects of the present invention.

[0028] According to a fourth aspect of the present invention, an electronic device is provided, including a memory and a processor, wherein the memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method described in any one aspect of the present invention.

[0029] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects: In this invention, daily timed settlement and firmware static threshold lookup replace near real-time dynamic calculation, enabling low-computing-power wearable devices to output stable comprehensive body scores offline under microampere power consumption constraints.

[0030] In this invention, a three-level progressive personal baseline self-calibration and a sequential correction mechanism for staying up late and menstruation are used to achieve a highly robust score that takes into account individual differences and special scenarios under low storage constraints.

[0031] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings.

[0032] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0033] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0034] Figure 1 This is a flowchart of an offline physical energy scoring method for a low-computing-power wearable device according to an embodiment of the present invention.

[0035] Figure 2 This is a flowchart illustrating an offline physical energy scoring method for a low-computing-power wearable device according to an embodiment of the present invention, which collects user physiological data from 00:00 of the previous day to 03:59 of the current day as the original input dataset, with 4:00 AM as the fixed settlement time each day.

[0036] Figure 3 This is a flowchart illustrating the offline physical energy scoring method for a low-computing-power wearable device according to an embodiment of the present invention. The method calculates and sums the nighttime sleep parameters based on the original input dataset, deducts points for nighttime wakefulness time according to multi-level threshold intervals, and outputs the sleep score after clamping.

[0037] Figure 4 This is a flowchart illustrating an offline physical energy scoring method for a low-computing-power wearable device according to an embodiment of the present invention. The method generates a personal HRV baseline and a personal resting heart rate baseline by sequentially calling a general fixed baseline, a historical full average, and a recent 30-day moving average, based on the cumulative number of valid morning wake-up days N. The flowchart then maps and outputs the HRV score and the resting heart rate score by the percentage and difference between the measured value and the baseline.

[0038] Figure 5 This is a flowchart illustrating the process of obtaining the cumulative minutes of high-intensity heart rate (Tnow) of the previous day and mapping and outputting the exercise score according to a preset multi-level minute threshold interval in an offline physical energy scoring method for a low-computing-power wearable device according to an embodiment of the present invention.

[0039] Figure 6 This is a flowchart illustrating the offline physical energy scoring method for a low-computing-power wearable device according to an embodiment of the present invention, which involves weighting and summing the scores of five items—sleep, HRV, resting heart rate, exercise, and blood oxygen—with fixed weights of 0.4, 0.3, 0.15, 0.1, and 0.05 to obtain a weighted raw total score.

[0040] Figure 7 This is a flowchart illustrating the offline physical energy scoring method for low-computing-power wearable devices according to an embodiment of the present invention, which serially performs deductions for staying up late, scaling corrections for women's menstrual periods, rounds and clamps the total score to 0-100, and outputs the final comprehensive physical score.

[0041] Figure 8 This is a structural diagram of an offline physical energy scoring system for a low-computing-power wearable device according to an embodiment of the present invention.

[0042] Figure 9 This is a structural diagram of an electronic device according to one embodiment of the present invention. Detailed Implementation

[0043] In some of the processes described in the specification, claims, and accompanying drawings of this invention, multiple operations appearing in a specific order are included. However, it should be clearly understood that these operations may not be executed in the order they appear herein, or may be executed in parallel. The operation numbers, such as 101, 102, etc., are merely used to distinguish different operations and do not represent any execution order. Furthermore, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel. It should be noted that the descriptions such as "first," "second," etc., in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to different types.

[0044] 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.

[0045] Low-computing-power wearable devices solve the bottleneck of wearable devices struggling to achieve daily comprehensive health status assessment under low power consumption and low storage constraints. They retain the core indicators with the most physiological representation value, enabling devices to stably output a comprehensive health score of 0-100 points and five levels of status judgment in an extremely energy-saving mode with only one settlement per day. They do not rely on the network, do not collect data frequently, and do not dynamically iterate, providing a low-cost and highly robust health status quantification solution for mass-produced wearable devices. At the same time, they take into account individual baseline differences and special corrections such as women's menstrual periods, achieving an effective balance between practicality and physiological rationality.

[0046] Prior to this invention, existing wearable or smart wearable devices typically rely on mobile apps to calculate near real-time heart rate variability (HRV), activity load, and sleep stages, and use dynamic thresholds to continuously track user status. This approach has extremely high requirements for computing power, memory, and communication power consumption, and cannot be directly ported to low-computing-power hardware. In addition, this invention designs a set of static, coded threshold rules so that the scoring is not affected by daytime disturbances and can adapt to individual differences through rolling baselines. It also properly handles special scenarios such as missing data, gender, menstrual cycle, and staying up late. Ultimately, while ensuring the physiological validity of the scoring, it meets the hard constraints of daily single-time settlement and microampere power consumption.

[0047] This invention provides an offline physical energy scoring method and system for low-computing-power wearable devices. This solution replaces near-real-time calculation with a single offline settlement at 4:00 AM daily, and replaces dynamic threshold tracking with a firmware static threshold table and a three-level progressive personal baseline, enabling low-computing-power wearable devices to stably output a physical energy score of 0-100 points and five-level status determination under microampere power consumption.

[0048] According to a first aspect of the present invention, an offline method for scoring physical energy using a low-computing-power wearable device is provided.

[0049] Figure 1 This is a flowchart of an offline physical energy scoring method for a low-computing-power wearable device according to an embodiment of the present invention.

[0050] In one or more embodiments, preferably, the offline physical energy scoring method of the low-computing-power wearable device includes: S101. Using 4:00 AM daily as the fixed settlement time, collect user physiological data from 00:00 the previous day to 03:59 the current day as the raw input dataset. S102. Calculate and sum the nighttime sleep parameters based on the original input dataset, deduct the nighttime wakefulness time score according to the multi-level threshold interval, and output the sleep score after clamping. S103. Based on the cumulative number of valid morning wake-up days N, the general fixed baseline, historical full average, and recent 30-day moving average are called in sequence to generate the HRV personal baseline and the resting heart rate personal baseline. The HRV score and resting heart rate score are output by mapping the percentage and difference between the measured value and the baseline, respectively. S104. Obtain the cumulative minutes of moderate to high intensity heart rate Tnow from the previous day, and output the exercise score according to the preset multi-level minute threshold interval mapping. S105. The scores of the five items—sleep, HRV, resting heart rate, exercise, and blood oxygen—are weighted and summed with fixed weights of 0.4, 0.3, 0.15, 0.1, and 0.05 to obtain the weighted raw total score. S106. Perform a deduction for staying up late and a scaling correction for women's menstrual periods on the total score, round it down and clamp it to 0~100, and output the final comprehensive body score.

[0051] In this embodiment of the invention, for wearable devices with low computing power, 4:00 AM is the only settlement time each day. Offline data is collected from 00:00 the previous day to 03:59 the current day, including sleep, morning HRV and resting heart rate, minutes of moderate to high intensity exercise the previous day, sleep onset time, and blood oxygen data. The sleep score is obtained by static threshold lookup and deduction of awake time. The HRV and resting heart rate scores are obtained by three-level progressive personal baseline self-calibration mapping. The exercise score is obtained by inverse mapping according to the minute threshold range. Each individual score is weighted and summed with fixed weights of 0.4, 0.3, 0.15, 0.1, and 0.05. After being corrected by deduction for staying up late and serial correction by menstrual period scaling, the score is clamped and rounded to output a comprehensive score of 0-100 and five status levels.

[0052] Figure 2 This is a flowchart illustrating an offline physical energy scoring method for a low-computing-power wearable device according to an embodiment of the present invention, which collects user physiological data from 00:00 of the previous day to 03:59 of the current day as the original input dataset, with 4:00 AM as the fixed settlement time each day.

[0053] like Figure 2 As shown, in one or more embodiments, preferably, the step of collecting user physiological data from 00:00 of the previous day to 03:59 of the current day, with 4:00 AM as the fixed settlement time each day, as the raw input dataset, specifically includes: S201, using the time window from 00:00 of the previous day to 03:59 of the current day; S202. Within the time window, the following raw data is collected and stored by the local sensors of the wearable device: total sleep duration at night. Deep sleep duration, time to fall asleep Total nighttime awake time Mean HRV after 5 minutes of rest upon waking Morning resting heart rate Total minutes of moderate to high intensity heart rate throughout the previous day Sleep onset time and resting blood oxygen saturation ; S203. Set 4:00 AM daily as the fixed settlement trigger time. After triggering, read all stored data as the original input dataset.

[0054] In this embodiment of the invention, the wearable device includes a PPG photoelectric sensor, a triaxial accelerometer, a low-power MCU, and an RTC real-time clock. During 24-hour operation, the MCU maintains only a few counters. The real-time heart rate is compared with the aforementioned medium-to-high intensity heart rate threshold; if a match is found, the time is accumulated to generate Tnow, but the original waveform is not stored. At night, sleep onset time, light sleep, deep sleep, and awakening segments are determined based on changes in body momentum and heart rate, and Tsleep, deep sleep duration, Tlatency, and Tawake are statistically analyzed, along with the sleep onset time. Upon waking in the morning, after resting for 5 minutes, the RMSSD is calculated to obtain HRVmorning and RHRmorning. SpO2 is measured during sleep periods without body movement. These nine values ​​are stored in a fixed address in the local Flash memory. The RTC wakes the MCU at 4:00 AM daily, reads the above values ​​at once to form the original input dataset, and completes the daily calculation. After calculation, the MCU returns to sleep mode.

[0055] Figure 3 This is a flowchart illustrating the offline physical energy scoring method for a low-computing-power wearable device according to an embodiment of the present invention. The method calculates and sums the nighttime sleep parameters based on the original input dataset, deducts points for nighttime wakefulness time according to multi-level threshold intervals, and outputs the sleep score after clamping.

[0056] like Figure 3 As shown, in one or more embodiments, preferably, the step of calculating and summing the sub-items based on the nighttime sleep parameters in the original input dataset, deducting points for nighttime wakefulness duration according to multi-level threshold intervals, and outputting a sleep score after clamping, specifically includes: S301. Extract the total nighttime sleep duration from the original input dataset. Deep sleep duration, time to fall asleep Total nighttime wakefulness ; S302. Calculate the four component values ​​respectively: duration. Deep sleep percentage Time spent falling asleep Deduction of points for duration of sobriety ; The assignment rules are as follows:

[0057] The assignment rules are as follows:

[0058] Among them, deep sleep accounted for a certain percentage. =Deep sleep duration ÷ ; The assignment rules are as follows:

[0059] The assignment rules are as follows:

[0060] Calculate sleep score using the first calculation formula ; The first calculation formula is:

[0061] Using normalization processing Clamp to Interval, output sleep score .

[0062] In this embodiment of the invention, taking user A (female, 30 years old)'s data on a certain day as an example: Tsleep = 432 minutes, deep sleep duration = 90 minutes, Tlatency = 28 minutes, Tawake = 35 minutes. Looking up the table, we get: 420 ≤ 432 ≤ 510, Sduration = 50; Rdeep = 90 ÷ 432 × 100% ≈ 20.83%, which falls within the range of 18% ≤ Rdeep < 22%, so Sdeep = 20; 20 ≤ 28 ≤ 40, Slatency = 5; 30 ≤ 35 ≤ 60, Sawake = 5. Substituting into the first calculation formula: Sleep = 50 + 20 + 5 - 5 = 70, which falls within the range of [0, 100] and does not require clamping, so the sleep score is 70. It should be noted that the theoretical range of Sleep is [-10, 90], and clamping is only used as a fallback for abnormal data.

[0063] Figure 4This is a flowchart illustrating an offline physical energy scoring method for a low-computing-power wearable device according to an embodiment of the present invention. The method generates a personal HRV baseline and a personal resting heart rate baseline by sequentially calling a general fixed baseline, a historical full average, and a recent 30-day moving average, based on the cumulative number of valid morning wake-up days N. The flowchart then maps and outputs the HRV score and the resting heart rate score by the percentage and difference between the measured value and the baseline.

[0064] like Figure 4 As shown, in one or more embodiments, preferably, the step of generating a personal HRV baseline and a personal resting heart rate baseline by sequentially calling a general fixed baseline, a historical full average, and a recent 30-day moving average based on the cumulative number of valid morning wake-up days N, and mapping and outputting the HRV score and resting heart rate score respectively using the percentage and difference relationship between the measured value and the baseline, specifically includes: S401. Extract the measured morning HRV values ​​of the day from the original input dataset. and the measured resting heart rate value upon waking on the same day ; S402, Number of days of valid morning data accumulated by statistical equipment Generate the individual HRV baseline for the current settlement period according to the second calculation formula. Personal baseline resting heart rate ; The second calculation formula is:

[0065] in, The personal baseline value used in the current period. These are common adult standard baseline constants built into the firmware. For the first The measured values ​​upon waking on a valid day. This represents the total number of days of cumulative valid data. S403, with For reference, the HRV score is calculated using the third calculation formula. ; The third calculation formula is:

[0066] S404, with For reference, the resting heart rate score is calculated using the fourth calculation formula. ; The fourth calculation formula is:

[0067] If data collection fails at dawn, the data for that day will not be included. Statistics and and The update, and the HRV score or resting heart rate score for the current day uses the valid score from the previous day; the and It is updated only once a day, and is synchronized with the settlement at 4:00 AM.

[0068] In this embodiment of the invention, user A's measured HRVmorning on that day was 48 milliseconds and RHRmorning was 60 beats / minute. The device's cumulative valid morning data days N=25. Since 7<25<30, the average of all 25 valid days is taken, with BaselineHRV=50 milliseconds and BaselineRHR=55 beats / minute. HRV score: 48÷50=96%≥90%, referring to the third calculation formula, Shrv=95; Resting heart rate score: 55+3≤60<55+7, i.e., 58≤60<62, referring to the fourth calculation formula, Srhr=60. Alternatively, if N=5 is assumed, for a new user, the built-in constants BaselineHRV=50 milliseconds and BaselineRHR=60 beats / minute are directly used. If N=40 is assumed, the sliding window average of the most recent 30 valid days is taken. If the signal quality is substandard on a certain morning, that day will not be included in the statistics of N and baseline updates, and the scores of Shrv and Srhr on that day will continue from the previous valid day.

[0069] Figure 5 This is a flowchart illustrating the process of obtaining the cumulative minutes of high-intensity heart rate (Tnow) of the previous day and mapping and outputting the exercise score according to a preset multi-level minute threshold interval in an offline physical energy scoring method for a low-computing-power wearable device according to an embodiment of the present invention.

[0070] like Figure 5 As shown, in one or more embodiments, preferably, obtaining the cumulative minutes of high-intensity heart rate Tnow from the previous day and outputting the exercise score according to a preset multi-level minute threshold interval specifically includes: S501. Extract the cumulative minutes of moderate to high-intensity heart rate Tnow from the original input dataset; S502. Using the fifth calculation formula, Tnow is compared with the preset multi-level minute threshold range, and the motion score Sexer is mapped and output. The fifth calculation formula is: Sexer = 95 (0 ≤ Tnow ≤ 30) Sexer=75 (30) <Tnow≤60) Sexer=55(60) <Tnow≤90) Sexer=25 (90) <Tnow≤120) Sexer=10 (Tnow>120) Tnow only counts the cumulative time that the heart rate is in the preset high-intensity heart rate zone.

[0071] In this embodiment of the invention, sleep-related duration and Tnow are in minutes, HRV is in milliseconds, RMSSD is used, resting heart rate is beats per minute, and blood oxygen saturation is a percentage value. The preset high-intensity heart rate zone is defined as: heart rate ≥ (220 - age) × 64%, where age is set by the user during APP registration and synchronized to the wearable device via Bluetooth; if not set, the default age is 30, corresponding to a threshold of 122 beats per minute. The static blood oxygen saturation refers to the median blood oxygen saturation value measured during a resting segment without body movement during nighttime sleep. The effective morning data refers to the data corresponding to the date when the PPG signal integrity rate is ≥ 80% for 5 consecutive minutes at rest after waking up in the morning. The firmware's built-in general baseline constant BuiltInDefault is: HRV baseline 50 milliseconds, resting heart rate baseline 60 beats per minute. User A is 30 years old, and the high-intensity heart rate threshold is (220 - 30) × 64% ≈ 122 beats per minute. The cumulative duration of a heart rate ≥122 beats / min on the previous day, Tnow, is 45 minutes (excluding slow walking and daily low-intensity activities). Referring to the fifth calculation formula: 30 < 45 ≤ 60, the mapped output is Sexer = 75. If Tnow = 0, it falls within the range of 0 ≤ Tnow ≤ 30, and the output is Sexer = 95, indicating that the individual was fully rested the previous day, and thus receives full marks for the exercise load item.

[0072] Figure 6 This is a flowchart illustrating the offline physical energy scoring method for a low-computing-power wearable device according to an embodiment of the present invention, which involves weighting and summing the scores of five items—sleep, HRV, resting heart rate, exercise, and blood oxygen—with fixed weights of 0.4, 0.3, 0.15, 0.1, and 0.05 to obtain a weighted raw total score.

[0073] like Figure 6 As shown, in one or more embodiments, preferably, the step of weighting and summing the scores of the five items—sleep, HRV, resting heart rate, exercise, and blood oxygen—with fixed weights of 0.4, 0.3, 0.15, 0.1, and 0.05 to obtain a weighted raw total score specifically includes: S601. Obtain the following four scores that have been calculated: Sleep Score HRV score Resting heart rate score Sports score ; S602, Extract static blood oxygen saturation from the original input dataset. Blood oxygen score is obtained according to the sixth calculation formula rule. ; The sixth calculation formula is:

[0074] Calculate the weighted raw total score using the seventh formula. ; The seventh calculation formula is:

[0075] All individual scores have been pre-clamped to The weighting coefficients for each interval are fixed at 0.4, 0.3, 0.15, 0.1, and 0.05 and are embedded in the firmware.

[0076] In this embodiment of the invention, User A's scores for the five items on a given day are: Sleep=70, Shrv=95, Srhr=60, Sexer=75, SpO2=94%. Referring to the sixth calculation formula (93%≤94%<95%), we get Sspo2=70. Substituting this into the seventh calculation formula: RawScore=70×0.4+95×0.3+60×0.15+75×0.1+70×0.05=28+28.5+9+7.5+3.5=76.5. Each item's score naturally falls within the [0,100] range from the assignment table. The weighting coefficients 0.4, 0.3, 0.15, 0.1, and 0.05 are fixed in the firmware, consistent across the entire network, and do not change with the user.

[0077] Figure 7 This is a flowchart illustrating the offline physical energy scoring method for low-computing-power wearable devices according to an embodiment of the present invention, which serially performs deductions for staying up late, scaling corrections for women's menstrual periods, rounds and clamps the total score to 0-100, and outputs the final comprehensive physical score.

[0078] like Figure 7 As shown, in one or more embodiments, preferably, the step of serially performing deductions for staying up late, scaling corrections for women's menstrual periods, rounding and clamping to 0-100 on the total score, and outputting the final comprehensive body score specifically includes: S701, calculate the weighted original total score. As the sole object of correction; S702, Execute the first-level correction, determine whether the bedtime of the day is later than 1:00 AM, if so, then... The weighted original total score is then corrected by subtraction: If not, then No operation is performed; S703. Perform the second-level correction, determining whether the user's gender is marked as female and the current settlement period has a menstrual period marker simultaneously; wherein, the menstrual period marker is manually set by the user in the APP and synchronized to the wearable device via Bluetooth, and is only effective once within its corresponding settlement period, automatically deactivating upon settlement the next day; if so, then... Perform multiplication scaling correction on the result of the previous step: If not, then No operation is performed; S704. Calculate the final comprehensive physical score using the eighth calculation formula. ; The eighth calculation formula is:

[0079] in, This is the rounding function. ; The As the output of the day's comprehensive physical score, the status level is also determined according to the ninth calculation formula; The ninth calculation formula is: .

[0081] In this embodiment of the invention, User A falls asleep at 01:20 on the same day, which is later than 1:00 AM. Let Covertime = 15, and perform the first-level correction: 76.5 - 15 = 61.5. User A's gender is marked as female, and the current settlement cycle has a menstrual period marker (set via APP and synchronized to the wearable device via Bluetooth the previous day). Let Cphysiology = 0.85, and perform the second-level correction: 61.5 × 0.85 = 52.275. Substituting into the eighth calculation formula: round(52.275) = 52, clamp(52,0,100) = 52, the output FinalScore = 52. Checking the ninth calculation formula, 40 ≤ 52 < 60, it is determined to be LEVEL 3 mild fatigue, and the wearable device will indicate the corresponding level with vibration rhythm. If the user is male or has no menstrual period marker, Cphysiology = 1.0 and no scaling is performed; the menstrual period marker automatically expires at 4:00 AM the next day. This score is only for reference regarding daily physical and mental state and does not constitute a basis for disease diagnosis.

[0082] According to a second aspect of the present invention, an offline physical energy scoring system for low-computing-power wearable devices is provided.

[0083] Figure 8 This is a structural diagram of an offline physical energy scoring system for a low-computing-power wearable device according to an embodiment of the present invention.

[0084] In one or more embodiments, preferably, the offline physical energy scoring system of the low-computing-power wearable device includes: The timed settlement and data collection module 801 is used to collect user physiological data from 00:00 of the previous day to 03:59 of the current day at a fixed settlement time of 4:00 AM every day, as the raw input dataset; The sleep scoring module 802 is used to calculate and sum the sub-items based on the nighttime sleep parameters in the original input dataset, deduct the nighttime wakefulness time from the score according to the multi-level threshold interval, and output the sleep score after clamping. The baseline self-calibration module 803 is used to generate HRV personal baseline and resting heart rate personal baseline by sequentially calling the general fixed baseline, historical full average, and the recent 30-day moving average based on the cumulative number of valid morning wake-up days N. The HRV score and resting heart rate score are mapped and output respectively by the percentage and difference relationship between the measured value and the baseline. The exercise load scoring module 804 is used to obtain the cumulative minutes of moderate to high intensity heart rate Tnow from the previous day and output the exercise score according to the preset multi-level minute threshold interval mapping. The weighted fusion module 805 is used to sum the scores of five items—sleep, HRV, resting heart rate, exercise, and blood oxygen—with fixed weights of 0.4, 0.3, 0.15, 0.1, and 0.05 to obtain the weighted raw total score. The correction output module 806 is used to perform serial deduction for staying up late and scaling correction for women's menstrual periods on the total score, round it down and clamp it to 0~100, and output the final comprehensive body score.

[0085] In this embodiment of the invention, a system suitable for different structures is realized through a series of modular designs. This system can achieve closed-loop, reliable, and efficient execution through data acquisition, analysis, and control.

[0086] According to a third aspect of the present invention, a computer-readable storage medium is provided, on which computer program instructions are stored, which, when executed by a processor, implement the method as described in any one of the first aspects of the present invention.

[0087] According to a fourth aspect of the present invention, an electronic device is provided. Figure 9 This is a structural diagram of an electronic device according to one embodiment of the present invention. Figure 9The illustrated electronic device is an offline physical energy scoring device for low-computing-power wearable devices. It includes a general computer hardware architecture, comprising at least a processor 901 and a memory 902. The processor 901 and memory 902 are connected via a bus 903. The memory 902 is adapted to store instructions or programs executable by the processor 901. The processor 901 can be a standalone microprocessor or a collection of one or more microprocessors. Thus, the processor 901 executes the instructions stored in the memory 902 to perform the method flow described in the embodiments of the present invention, thereby realizing data processing and control of other devices. The bus 903 connects the aforementioned components together, and also connects these components to a display controller 904, a display device, and an input / output (I / O) device 905. The input / output (I / O) device 905 can be a mouse, keyboard, modem, network interface, touch input device, motion-sensing input device, printer, and other devices known in the art. Typically, the input / output device 905 is connected to the system via an input / output (I / O) controller 906.

[0088] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects: In this invention, daily timed settlement and firmware static threshold lookup replace near real-time dynamic calculation, enabling low-computing-power wearable devices to output stable comprehensive body scores offline under microampere power consumption constraints.

[0089] In this invention, a three-level progressive personal baseline self-calibration and a sequential correction mechanism for staying up late and menstruation are used to achieve a highly robust score that takes into account individual differences and special scenarios under low storage constraints.

[0090] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0091] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0092] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0093] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0094] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. An offline physical energy assessment method for low-computing-power wearable devices, characterized in that, The method includes: With 4:00 AM as the fixed settlement time each day, user physiological data from 00:00 the previous day to 03:59 the current day is collected as the raw input dataset; Calculate and sum the nighttime sleep parameters in the original input dataset, deduct the nighttime wakefulness time from the multi-level threshold interval, and output the sleep score after clamping. Based on the cumulative number of valid morning wake-up days N, the general fixed baseline, historical full average, and recent 30-day moving average are called in sequence to generate the HRV personal baseline and the resting heart rate personal baseline. The HRV score and resting heart rate score are output by mapping the percentage and difference between the measured value and the baseline, respectively. Get the cumulative minutes of moderate to high intensity heart rate Tnow from the previous day, and output the exercise score according to the preset multi-level minute threshold interval mapping. The scores of the five components—sleep, HRV, resting heart rate, exercise, and blood oxygen—are weighted and summed with fixed weights of 0.4, 0.3, 0.15, 0.1, and 0.05 to obtain the weighted raw total score. The total score is serially adjusted by deducting late nights and scaling for women's menstrual periods, rounded and clamped to 0-100, and the final comprehensive body score is output.

2. The offline physical energy scoring method for low-computing-power wearable devices as described in claim 1, characterized in that, The system uses 4:00 AM daily as the fixed settlement time and collects user physiological data from 00:00 the previous day to 03:59 the current day as the raw input dataset, specifically including: The time window is from 00:00 of the previous day to 03:59 of the current day; Within the time window, the following raw data is collected and stored via local sensors on the wearable device: total sleep duration at night. Deep sleep duration, time to fall asleep Total nighttime awake time Mean HRV after 5 minutes of rest upon waking Morning resting heart rate Total minutes of moderate to high intensity heart rate throughout the previous day Sleep onset time and resting blood oxygen saturation ; The settlement is triggered at 4:00 AM every day. After the trigger, all stored data is read and used as the original input dataset.

3. The offline physical energy scoring method for low-computing-power wearable devices as described in claim 1, characterized in that, The process involves calculating and summing the nighttime sleep parameters based on the original input dataset, deducting points for nighttime wakefulness duration according to multi-level threshold intervals, and then outputting a clamped sleep score. Specifically, this includes: Extract the total nighttime sleep duration from the original input dataset. Deep sleep duration, time to fall asleep Total nighttime wakefulness ; Calculate the four sub-items separately: duration score Deep sleep percentage Time spent falling asleep Deduction of points for duration of sobriety ; The assignment rules are as follows: The assignment rules are as follows: Among them, deep sleep accounted for a certain percentage. =Deep sleep duration ÷ ; The assignment rules are as follows: The assignment rules are as follows: Calculate sleep score using the first calculation formula ; The first calculation formula is: Using normalization processing Clamp to Interval, output sleep score .

4. The offline physical energy scoring method for low-computing-power wearable devices as described in claim 1, characterized in that, The process involves generating a personal HRV baseline and a personal resting heart rate baseline based on the cumulative number of valid morning wake-up days (N), sequentially using a general fixed baseline, historical full average, and the recent 30-day moving average. The HRV score and resting heart rate score are then mapped and output using the percentage and difference between the measured value and the baseline, respectively. Specifically, this includes: Extract the measured morning HRV values ​​of the day from the original input dataset. and the measured resting heart rate value upon waking on the same day ; The number of days of valid morning data accumulated by statistical equipment Generate the individual HRV baseline for the current settlement period according to the second calculation formula. Personal baseline resting heart rate ; The second calculation formula is: in, The personal baseline value used in the current period. These are common adult standard baseline constants built into the firmware. For the first The measured values ​​upon waking on a valid day. This represents the total number of days of cumulative valid data. by For reference, the HRV score is calculated using the third calculation formula. ; The third calculation formula is: by For reference, the resting heart rate score is calculated using the fourth calculation formula. ; The fourth calculation formula is: If data collection fails at dawn, the data for that day will not be included. Statistics and and The update, and the HRV score or resting heart rate score for the current day uses the valid score from the previous day; the and It is updated only once a day, and is synchronized with the settlement at 4:00 AM.

5. The offline physical energy scoring method for low-computing-power wearable devices as described in claim 1, characterized in that, The process of obtaining the cumulative minutes of high-intensity heart rate (Tnow) from the previous day and outputting an exercise score based on a preset multi-level minute threshold range specifically includes: Extract the cumulative minutes of moderate-to-high-intensity heart rate (Tnow) from the original input dataset; The fifth calculation formula is used to compare Tnow with the preset multi-level minute threshold range and map the output exercise score Sexer. The fifth calculation formula is: Sexer = 95 (0 ≤ Tnow ≤ 30) Sexer=75 (30) <Tnow≤60) Sexer=55(60) <Tnow≤90) Sexer=25 (90) <Tnow≤120) Sexer=10 (Tnow>120) Tnow only counts the cumulative time that the heart rate is in the preset high-intensity heart rate zone.

6. The offline physical energy scoring method for low-computing-power wearable devices as described in claim 1, characterized in that, The weighted raw total score is obtained by summing the scores of five items—sleep, HRV, resting heart rate, exercise, and blood oxygen—with fixed weights of 0.4, 0.3, 0.15, 0.1, and 0.05, respectively. Specifically, it includes: Obtain the following four scores that have been calculated: Sleep Score HRV score Resting heart rate score Sports score ; Extract static blood oxygen saturation from the original input dataset. Blood oxygen score is obtained according to the sixth calculation formula rule. ; The sixth calculation formula is: Calculate the weighted raw total score using the seventh formula. ; The seventh calculation formula is: All individual scores have been pre-clamped to The weighting coefficients for each interval are fixed at 0.4, 0.3, 0.15, 0.1, and 0.05 and are embedded in the firmware.

7. The offline physical energy scoring method for low-computing-power wearable devices as described in claim 1, characterized in that, The process involves sequentially deducting late nights and applying menstrual cycle scaling corrections to the total score, rounding and clamping it to 0-100, and outputting the final comprehensive body score. Specifically, this includes: The weighted original total score As the sole object of correction; Perform the first-level correction, determining whether the person fell asleep later than 1:00 AM that day. If so, then... The weighted original total score is then corrected by subtraction: If not, then No operation is performed; Perform a second-level correction, determining whether the user's gender is marked as female and a menstrual period marker exists in the current billing cycle simultaneously. The menstrual period marker is manually set by the user in the app and synchronized to the wearable device via Bluetooth, and is only effective once within its corresponding billing cycle, automatically expiring at the next day's billing. If so, then... Perform multiplication scaling correction on the result of the previous step: If not, then No operation is performed; The final comprehensive physical score is calculated using the eighth calculation formula. ; The eighth calculation formula is: in, This is the rounding function. ; The As the output of the day's comprehensive physical score, the status level is also determined according to the ninth calculation formula; The ninth calculation formula is: 。 8. An offline physical energy scoring system for low-computing-power wearable devices, characterized in that, The system is used to implement the method as described in any one of claims 1-7, the system comprising: The timed settlement and data collection module is used to collect user physiological data from 00:00 the previous day to 03:59 the current day at a fixed settlement time of 4:00 AM every day, as the raw input dataset; The sleep scoring module is used to calculate and sum the nighttime sleep parameters based on the original input dataset, deduct the nighttime wakefulness time from the multi-level threshold interval, and output the sleep score after clamping. The baseline self-calibration module is used to generate HRV personal baseline and resting heart rate personal baseline by sequentially calling the general fixed baseline, historical full average, and the recent 30-day moving average based on the cumulative number of valid morning wake-up days N. The HRV score and resting heart rate score are mapped and output respectively by the percentage and difference relationship between the measured value and the baseline. The exercise load scoring module is used to obtain the cumulative minutes of moderate to high intensity heart rate Tnow from the previous day, and output the exercise score according to the preset multi-level minute threshold interval. The weighted fusion module is used to sum the scores of five items—sleep, HRV, resting heart rate, exercise, and blood oxygen—with fixed weights of 0.4, 0.3, 0.15, 0.1, and 0.05 to obtain the weighted raw total score. The correction output module is used to perform serial deduction for staying up late and scaling correction for women's menstrual periods on the total score, round it down and clamp it to 0~100, and output the final comprehensive body score.

9. A computer-readable storage medium storing computer program instructions thereon, characterized in that, The computer program instructions, when executed by a processor, implement the method as described in any one of claims 1-7.

10. An electronic device comprising a memory and a processor, characterized in that, The memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method as described in any one of claims 1-7.

Images