A circadian rhythm lighting regulation method and system for the elderly

Abstract

The application provides a circadian rhythm lighting regulation method and system for the elderly, obtains a daytime blue light ERI cumulative value of a target object; outputs a corresponding first predicted night waking number through a preset CART decision tree, and then corrects the first predicted night waking number based on a night waking number of a second historical day to obtain a second predicted night waking number; obtains a blue light ERI quota at each night waking time of the day based on the daytime blue light ERI cumulative value and the second predicted night waking number; when receiving a night waking trigger information of the target object, obtains a corresponding real-time blue light ERI cumulative value based on a blue light power, then compares the real-time ERI cumulative value with the blue light ERI quota, and finally adjusts the blue light power of a lighting device based on the comparison result. The scheme can not only accurately match the circadian rhythm protection needs of the elderly, but also has strong universality and practical application value.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology, and in particular to a method and system for regulating circadian rhythm lighting for the elderly. Background Technology

[0002] As people age, their visual function gradually declines, with yellowing of the lens, decreased retinal sensitivity, and frequent nighttime urination (1-4 times per night). They need blue light illumination to ensure color rendering (Ra≥80) to avoid the risk of falls. At the same time, the hypothalamus's suprachiasmatic nucleus's regulatory function weakens in the elderly, leading to decreased circadian rhythm stability and a higher risk of sleep disorders. The appropriateness of the nighttime lighting environment directly affects their circadian rhythm balance, and inappropriate blue light exposure can further exacerbate sleep problems. Therefore, it is necessary to balance nighttime urination safety with circadian rhythm protection and to build a precise blue light regulation system.

[0003] ERI (Effective Retinal Irradiance, measured in μW·s / cm²) is a core indicator for measuring the intensity of blue light's effect on the retina, with the cumulative ERI of blue light in the 460-490nm wavelength range having the most significant impact. This wavelength of blue light interferes with the circadian rhythm regulation mechanism in the elderly by inhibiting melatonin secretion from the suprachiasmatic nucleus of the hypothalamus. When the cumulative ERI value throughout the day exceeds the biological threshold of 380 μW·s / cm², it can lead to circadian rhythm drift, manifesting as difficulty falling asleep, shallow sleep, and frequent awakenings at night, further exacerbating sleep disorders in the elderly. Therefore, precise quantitative control of blue light ERI accumulation is necessary.

[0004] Currently, there are significant technical shortcomings in the field of lighting regulation for the circadian rhythm of the elderly, especially in the scenario of nighttime lighting. Existing technical regulation methods are crude, simply adjusting the light intensity and color temperature of the lighting equipment. On the one hand, they do not consider the accumulation of blue light ERI, and cannot accurately match the circadian rhythm protection needs of the elderly; on the other hand, the regulation strategies lack individual physiological adaptability and have poor universality. Summary of the Invention

[0005] This invention provides a method and system for regulating circadian lighting for the elderly, which solves the problems of existing lighting regulation schemes not considering the accumulation of blue light ERI, failing to accurately match the circadian rhythm protection needs of the elderly, and lacking individual physiological adaptability and versatility in regulation strategies.

[0006] On the one hand, the present invention provides a method for regulating circadian rhythm lighting for the elderly, comprising: Collect ambient blue light power data and lighting device blue light power data of the target object during the daytime, and based on the ambient blue light power data and the lighting device blue light power data, obtain the cumulative daytime effective retinal irradiance (ERI) value of the target object; and The target subject's age, bedtime water intake, average number of nighttime urinations over a first preset historical period, ambient temperature at night, and lens transmittance are used as input parameters. These parameters are input into a preset classification regression tree (CART decision tree), which outputs the corresponding first predicted number of nighttime urinations. The first predicted number of nighttime urinations is then corrected based on the number of nighttime urinations over a second historical period to obtain the second predicted number of nighttime urinations. The preset CART decision tree is trained using a preset number of clinical data sample groups, each of which is labeled with a corresponding number of nighttime urinations. Based on the daytime blue light ERI cumulative value, the second predicted number of nighttime awakenings, and the blue light ERI cumulative threshold, the blue light ERI quota for each nighttime awakening of the target object on that day is obtained; When the target object is received to trigger a nighttime wake-up call, the blue light power of the lighting device is collected at preset time intervals until the nighttime wake-up call ends. After each blue light power collection, the real-time blue light ERI cumulative value corresponding to the blue light power collection is obtained based on the blue light power and the preset time interval. The real-time ERI cumulative value is then compared with the blue light ERI quota. Based on the comparison result, the blue light power of the lighting device is adjusted so that the real-time blue light ERI cumulative value of the nighttime wake-up call does not exceed the blue light ERI quota.

[0007] In one optional embodiment of this application, the step of correcting the first predicted number of nighttime awakenings based on the number of nighttime awakenings in the second historical days to obtain the second predicted number of nighttime awakenings includes: Obtain the moving average of the number of times you get up at night for the second historical number of days, and compare the first predicted number of times you get up at night with the moving average. If the deviation between the first predicted number of nighttime urinations and the sliding average value is not greater than a first preset value, then the first predicted number of nighttime urinations will be used as the second predicted number of nighttime urinations. If the deviation between the first predicted number of nighttime urinations and the moving average is greater than the first preset value but not greater than the second preset value, then the weighted average of the first predicted number of nighttime urinations and the moving average is taken as the second predicted number of nighttime urinations. If the deviation between the first predicted number of nighttime urinations and the moving average is greater than the second preset value, then the moving average is used as the second predicted number of nighttime urinations. Wherein, the first preset value is less than the second preset value.

[0008] In one optional embodiment of this application, obtaining the blue light ERI quota for each nighttime awakening of the target object based on the daytime blue light ERI cumulative value, the second predicted number of nighttime awakenings, and the blue light ERI cumulative threshold includes: The difference between the blue light ERI accumulation threshold and the daytime blue light ERI accumulation value is used as the nighttime blue light ERI upper limit; Based on the nighttime blue light ERI upper limit and the second predicted number of nighttime awakenings, the blue light ERI quota for each nighttime awakening is obtained.

[0009] In one optional embodiment of this application, the step of obtaining the blue light ERI quota for each nighttime awakening based on the nighttime blue light ERI upper limit and the second predicted number of nighttime awakenings is achieved by the following formula:

[0010] in, The Blu-ray ERI quota for each time you get up at night. The upper limit of the nighttime blue light ERI, The transmittance of the lens of the target object. This represents the second predicted number of nighttime urinations.

[0011] In one optional embodiment of this application, the real-time blue light ERI cumulative value corresponding to the blue light power acquisition is obtained based on the blue light power and the preset time interval, using the following formula:

[0012] Where j is the blue light power sampling sequence number during that nighttime awakening, and n is a natural number. This represents the real-time cumulative blue light ERI value corresponding to the j-th blue light power acquisition during this nighttime awakening. Let j be the blue light power value collected in the j-th sampling. The preset time interval is [the set time interval].

[0013] In one optional embodiment of this application, adjusting the blue light power of the lighting device based on the comparison result so that the real-time blue light ERI cumulative value of the nighttime awakening does not exceed the blue light ERI quota includes: If the real-time blue light ERI is less than the preset ratio of the blue light ERI quota, then the blue light power of the lighting device will be increased by the preset power. If the real-time blue light ERI is not less than the preset ratio of the blue light ERI quota, but less than the blue light ERI quota, then the blue light power of the lighting device remains unchanged. If the real-time blue light ERI is not less than the blue light ERI quota, then the blue light power of the lighting device is adjusted to zero.

[0014] In one optional embodiment of this application, the method further includes: The real-time accumulated ERI value is compared with the upper limit of the nighttime blue light ERI; If the real-time cumulative ERI value is not less than the upper limit of the nighttime blue light ERI, then the blue light power of the lighting device will be adjusted to zero during the current nighttime awakening and subsequent nighttime awakenings.

[0015] Secondly, the present invention also provides a circadian rhythm lighting control system for the elderly, comprising: The daytime blue light ERI cumulative value acquisition module is used to collect ambient blue light power data and lighting device blue light power data of the target object during the day, and obtain the daytime blue light effective retinal irradiance (ERI) cumulative value of the target object based on the ambient blue light power data and the lighting device blue light power data. The module for predicting the number of nighttime urinations is used to take the target object's age, daily bedtime water intake, average number of nighttime urinations over a first preset historical period, nighttime ambient temperature, and lens transmittance as input parameters, input them into a preset classification regression tree (CART decision tree), output the corresponding first predicted number of nighttime urinations, and then correct the first predicted number of nighttime urinations based on the number of nighttime urinations over a second historical period to obtain the second predicted number of nighttime urinations; wherein, the preset CART decision tree is trained through a preset number of clinical data sample groups, and each clinical data sample group is labeled with the corresponding number of nighttime urinations; The Blue Light ERI Quota Acquisition Module is used to acquire the Blue Light ERI quota for each nighttime ... The control module, upon receiving the nighttime trigger information from the target object, collects the blue light power of the lighting device at preset time intervals until the nighttime awakening ends. After each blue light power collection, it obtains the real-time blue light ERI cumulative value corresponding to that collection based on the blue light power and the preset time interval. Then, it compares the real-time ERI cumulative value with the blue light ERI quota, and adjusts the blue light power of the lighting device based on the comparison result so that the real-time blue light ERI cumulative value for that nighttime awakening does not exceed the blue light ERI quota.

[0016] In one optional embodiment of this application, the step of correcting the first predicted number of nighttime awakenings based on the number of nighttime awakenings in the second historical days to obtain the second predicted number of nighttime awakenings includes: Obtain the moving average of the number of times you get up at night for the second historical number of days, and compare the first predicted number of times you get up at night with the moving average. If the deviation between the first predicted number of nighttime urinations and the sliding average value is not greater than a first preset value, then the first predicted number of nighttime urinations will be used as the second predicted number of nighttime urinations. If the deviation between the first predicted number of nighttime urinations and the moving average is greater than the first preset value but not greater than the second preset value, then the weighted average of the first predicted number of nighttime urinations and the moving average is taken as the second predicted number of nighttime urinations. If the deviation between the first predicted number of nighttime urinations and the moving average is greater than the second preset value, then the moving average is used as the second predicted number of nighttime urinations. Wherein, the first preset value is less than the second preset value.

[0017] In one optional embodiment of this application, obtaining the blue light ERI quota for each nighttime awakening of the target object based on the daytime blue light ERI cumulative value, the second predicted number of nighttime awakenings, and the blue light ERI cumulative threshold includes: The difference between the blue light ERI accumulation threshold and the daytime blue light ERI accumulation value is used as the nighttime blue light ERI upper limit; Based on the nighttime blue light ERI upper limit and the second predicted number of nighttime awakenings, the blue light ERI quota for each nighttime awakening is obtained.

[0018] In one optional embodiment of this application, the step of obtaining the blue light ERI quota for each nighttime awakening based on the nighttime blue light ERI upper limit and the second predicted number of nighttime awakenings is achieved by the following formula:

[0019] in, The Blu-ray ERI quota for each time you get up at night. The upper limit of the nighttime blue light ERI, The transmittance of the lens of the target object. This represents the second predicted number of nighttime urinations.

[0020] In one optional embodiment of this application, the real-time blue light ERI cumulative value corresponding to the blue light power acquisition is obtained based on the blue light power and the preset time interval, using the following formula:

[0021] Where j is the blue light power sampling sequence number during that nighttime awakening, and n is a natural number. This represents the real-time cumulative blue light ERI value corresponding to the j-th blue light power acquisition during this nighttime awakening. Let j be the blue light power value collected in the j-th sampling. The preset time interval is [the set time interval].

[0022] In one optional embodiment of this application, adjusting the blue light power of the lighting device based on the comparison result so that the real-time blue light ERI cumulative value of the nighttime awakening does not exceed the blue light ERI quota includes: If the real-time blue light ERI is less than the preset ratio of the blue light ERI quota, then the blue light power of the lighting device will be increased by the preset power. If the real-time blue light ERI is not less than the preset ratio of the blue light ERI quota, but less than the blue light ERI quota, then the blue light power of the lighting device remains unchanged. If the real-time blue light ERI is not less than the blue light ERI quota, then the blue light power of the lighting device is adjusted to zero.

[0023] In one optional embodiment of this application, it further includes: The real-time accumulated ERI value is compared with the upper limit of the nighttime blue light ERI; If the real-time cumulative ERI value is not less than the upper limit of the nighttime blue light ERI, then the blue light power of the lighting device will be adjusted to zero during the current nighttime awakening and subsequent nighttime awakenings.

[0024] Thirdly, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement any of the above-described methods for regulating circadian rhythm lighting for the elderly.

[0025] Fourthly, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described methods for regulating circadian rhythm lighting for the elderly.

[0026] Fifthly, the present invention also provides a computer program product, including a computer program that, when executed by a processor, implements any of the above-described methods for regulating circadian rhythm lighting for the elderly.

[0027] The solution of this application collects ambient blue light power data and lighting device blue light power data of the target object during the day, and obtains the cumulative value of the daytime effective retinal irradiance (ERI) of the target object based on the ambient blue light power data and the lighting device blue light power data; and uses the target object's age, water intake before bedtime, average number of nighttime awakenings over a first preset historical number of days, ambient temperature at night, and lens transmittance as input parameters, inputs them into a preset classification regression tree (CART decision tree), outputs the corresponding first predicted number of nighttime awakenings, and then corrects the first predicted number of nighttime awakenings based on the number of nighttime awakenings over a second historical number of days to obtain the second predicted number of nighttime awakenings; based on the daytime blue light power data... The scheme uses the cumulative ERI value, the second predicted number of nighttime awakenings, and the cumulative ERI threshold of blue light to obtain the blue light ERI quota for each nighttime awakening of the target object. When the target object's nighttime awakening trigger information is received, the blue light power of the lighting equipment is collected at preset time intervals until the nighttime awakening ends. After each blue light power collection, the real-time cumulative ERI value corresponding to that blue light power collection is obtained based on the blue light power and the preset time interval. The real-time cumulative ERI value is then compared with the blue light ERI quota, and the blue light power of the lighting equipment is adjusted based on the comparison result to ensure that the real-time cumulative blue light ERI value for that nighttime awakening does not exceed the blue light ERI quota. This scheme relies on the individual physiological information of the target object to accurately predict the number of nighttime awakenings. Based on this, the blue light ERI quota for each nighttime awakening is further calculated, and the blue light power of the lighting equipment is dynamically adjusted in real time during the nighttime awakening process to ensure that the nighttime ERI accumulation does not exceed the standard. It can accurately match the circadian rhythm protection needs of the elderly and has strong versatility and practical application value. Attached Figure Description

[0028] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0029] Figure 1 A flowchart illustrating a method for regulating circadian lighting for the elderly, provided by the present invention; Figure 2 A structural block diagram of a circadian rhythm lighting control system for the elderly provided by the present invention; Figure 3 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0030] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0031] Figure 1 This is a flowchart illustrating a method for regulating circadian lighting for the elderly, as provided in an embodiment of the present invention. Figure 1 As shown, the method may include: Step S101: Collect ambient blue light power data and lighting device blue light power data of the target object during the day, and obtain the cumulative value of daytime effective retinal irradiance (ERI) of the target object based on the ambient blue light power data and the lighting device blue light power data.

[0032] The target group refers to the elderly population requiring circadian lighting regulation. Environmental blue light power data refers to the real-time blue light power generated by natural light sources (such as sunlight) in the target group's daytime activity environment, measured in μW / cm². Lighting equipment blue light power data refers to the real-time blue light power generated by artificial lighting equipment (such as ceiling lights, table lamps, and floor lamps) used by the target group during the day, measured in μW / cm². The cumulative daytime blue light ERI value refers to the total blue light ERI received by the target group from natural light sources and artificial lighting equipment during the day; this is the basic data for calculating the total available blue light at night.

[0033] Specifically, this step is the basic data collection and quantification stage of the entire regulation method. The core principle is the time-domain cumulative calculation of blue light power. That is, by continuously collecting natural and artificial blue light power throughout the day, the instantaneous ERI value is obtained by multiplying the blue light power of a single collection by the collection time interval. Then, all instantaneous ERI values ​​are accumulated to obtain the daytime cumulative value, which provides a reference for the total blue light irradiance throughout the day for the subsequent calculation of the upper limit of blue light ERI at night. This is a prerequisite for realizing the total control of blue light ERI throughout the day. Specifically, spectral sensors are deployed in the main activity areas of the target object during the day (such as bedrooms, living rooms, and studies). The sensors continuously collect data at fixed time intervals of 1 second, simultaneously acquiring ambient blue light power data and blue light power data from lighting equipment. The two types of blue light power data collected each time are summed to obtain the total blue light power value at that time. The total blue light power value is multiplied by the collection time interval (1 second) to obtain the instantaneous blue light ERI value at that time. After the daytime period ends (which can be taken as 1 hour before the target object goes to sleep), the instantaneous blue light ERI values ​​of all collection times throughout the day are accumulated to finally obtain the cumulative daytime blue light ERI value of the target object.

[0034] For example, assuming the target object is active from 7:00 to 21:00 during the day, and the spectral sensor collects data once per second, the ambient blue light power at a certain collection moment is 0.8 μW / cm², the blue light power of the lighting equipment is 0.5 μW / cm², and the total blue light power at that moment is 1.3 μW / cm². The instantaneous ERI value is 1.3 μW / cm² × 1s = 1.3 μW·s / cm². After accumulation, the sum of the instantaneous ERI values ​​at all collection moments throughout the day is 120 μWs / cm², that is, the cumulative blue light ERI value of the target object during the day is 120 μW·s / cm².

[0035] Step S102: The target subject's age, bedtime water intake, average number of nighttime urinations over a first preset historical number of days, ambient temperature at night, and lens transmittance are used as input parameters and input into a preset classification regression tree (CART decision tree). The corresponding first predicted number of nighttime urinations is output, and then the first predicted number of nighttime urinations is corrected based on the number of nighttime urinations over a second historical number of days to obtain the second predicted number of nighttime urinations. The preset CART decision tree is trained using a preset number of clinical data sample groups, and each clinical data sample group is labeled with a corresponding number of nighttime urinations.

[0036] The first preset historical number of days refers to the pre-set historical number of days used to statistically analyze the target subject's recent average nighttime urination frequency, which can be 3 days, reflecting the target subject's short-term nighttime urination pattern. The ambient temperature at night refers to the real-time monitored temperature of the target subject's resting environment at night, in °C. Temperature changes affect the frequency of nighttime urination in the elderly. Lens transmittance refers to the proportion of light passing through the target subject's lens, ranging from 0.6 to 0.9, collected every 3 months by a portable lens transmittance meter. It reflects both the degree of visual function decline in the elderly and is related to their overall physical function, helping to predict the number of nighttime urinations. The water intake before bedtime can be the water intake collected from the target subject within one hour before bedtime. The input parameter set refers to a standardized dataset composed of five core feature parameters: the target subject's age, water intake before bedtime, average nighttime urination frequency over the first preset historical number of days, ambient temperature at night, and lens transmittance.

[0037] CART decision trees, or greedy decision models based on binary splitting rules, are suitable for predicting discrete results. In this application, they are specifically used for the quantitative prediction of nighttime urination frequency in the elderly. The first predicted number of nighttime urinations refers to the raw predicted number of nighttime urinations directly output by the CART decision tree after processing the input parameter set. The second historical number of days refers to a pre-set medium- to long-term historical number of days used to correct the predicted number of nighttime urinations, which can be 7 days, reflecting the long-term stable nighttime urination pattern of the target subject. The second predicted number of nighttime urinations refers to the final predicted value after correction by the moving average of the nighttime urinations over the second historical number of days, which better reflects the actual nighttime urination pattern of the target subject. The clinical data sample set refers to a labeled dataset containing the age, bedtime water intake, historical nighttime urination frequency, nighttime ambient temperature, lens transmittance, and corresponding actual nighttime urination frequency of elderly individuals of different age groups and physical functions. The sample size is generally no less than 1000 sets, providing data support for CART decision tree training.

[0038] This step is the core prediction link of the entire regulation method. It follows the basic data collection in step S101 and provides the core quantitative basis for the subsequent blue light ERI quota allocation. The core principle is the accurate prediction of the machine learning model plus the dynamic correction of historical time series data. That is, first, the CART decision tree model is trained through a large amount of clinical data, then the five core features of the target object are input into the model to obtain the original prediction value, and finally the original prediction value is corrected by combining the long-term nighttime urination pattern of the target object, so as to make up for the limitation of the single machine learning model ignoring the individual behavioral pattern and improve the prediction accuracy.

[0039] This step is divided into three sub-steps: CART decision tree model training, CART decision tree model application, and correction of the first predicted number of nighttime urinations. The specific implementation process is as follows: CART decision tree model training: A training set of over 1000 sets of clinical data samples from elderly individuals was selected. Each set included five input features: age, pre-sleep water intake, average number of nighttime urinations over 3 days, nighttime ambient temperature, and lens transmittance, all labeled with the corresponding actual number of nighttime urinations. Core parameters were set during training: the Gini coefficient was used as the node splitting criterion; the maximum tree depth was 4 levels; the iteration threshold was ≤80 times; and training termination conditions were: tree depth reaching 4 levels, Gini coefficient dropping below 0.05, and iterations reaching 80 times (any one of these conditions was sufficient). A greedy algorithm was used to train the decision tree. The nodes are split layer by layer. Each layer selects the feature that most significantly reduces the Gini coefficient and the corresponding splitting threshold. During the splitting process, the sample labels are used to verify the error. At the same time, a pre-pruning strategy is used to control the model complexity. If the classification accuracy of the validation subset does not reach the preset threshold (which can be 5%) after a branch node is split, the splitting of that node is stopped and it is set as a leaf node. Each leaf node corresponds to a unique label for predicting the number of times people get up at night. When any training termination condition is met, the trained CART decision tree model is output. This model can be directly used for inference and prediction of the number of times elderly people get up at night.

[0040] For example, a sample group in the training set is: "75 years old, 300ml of water intake before bed, 1.5 times of nighttime urination over 3 days, ambient temperature at night 20℃, and lens transmittance 0.75", with the actual number of nighttime urinations being 2. During model training, the root node selects "water intake before bed" as the splitting feature, with a splitting threshold of 250ml. This sample enters the right branch because the water intake of 300ml > 250ml. After multiple splits, it finally falls into the leaf node corresponding to the number of nighttime urinations of "2", thus completing the training and fitting of this sample.

[0041] CART decision tree model application: Collect 5 core feature parameters of the target object, perform standardization processing to form an input parameter group, and input the input parameter group into the CART decision tree model that has been trained above; the model performs layer-by-layer calculations through internally preset node splitting rules and thresholds, and finally outputs the first predicted number of times to get up at night.

[0042] For example, the core features of the target object are collected as "78 years old, 200ml of water intake before bedtime, 1.2 times of nighttime urination over 3 days, ambient temperature of 22℃ at night, and lens transmittance of 0.72". This set of parameters is input into the trained CART decision tree model. After the model performs internal node splitting operations, the first predicted number of nighttime urinations is 2.

[0043] First predicted number of nighttime urinations correction: The first predicted number of nighttime urinations is corrected based on the number of nighttime urinations over the second historical days to obtain the second predicted number of nighttime urinations, including: Obtain the moving average of the number of times you get up at night for the second historical number of days, and compare the first predicted number of times you get up at night with the moving average. If the deviation between the first predicted number of nighttime urinations and the sliding average value is not greater than a first preset value, then the first predicted number of nighttime urinations will be used as the second predicted number of nighttime urinations. If the deviation between the first predicted number of nighttime urinations and the moving average is greater than the first preset value but not greater than the second preset value, then the weighted average of the first predicted number of nighttime urinations and the moving average is taken as the second predicted number of nighttime urinations. If the deviation between the first predicted number of nighttime urinations and the moving average is greater than the second preset value, then the moving average is used as the second predicted number of nighttime urinations. Wherein, the first preset value is less than the second preset value.

[0044] Specifically, the actual number of times a target person gets up at night each day over 7 days is statistically analyzed using intelligent monitoring equipment, and its moving average is calculated. The first predicted number of nighttime urinations is compared with this moving average, and the absolute deviation between the two is calculated. Based on the relationship between the deviation and a preset threshold, the corresponding correction rules are executed: if the deviation is ≤0.5 times (i.e., the first preset value), it means that the predicted value closely matches the long-term nighttime urination pattern, and the first predicted number of nighttime urinations is directly used as the second predicted number of nighttime urinations; if 0.5 times < deviation ≤1 time (i.e., the second preset value), it means that the predicted value deviates slightly from the long-term nighttime urination pattern, and the weighted average of the first predicted number of nighttime urinations (weight 0.6) and the moving average (weight 0.4) is calculated as the second predicted number of nighttime urinations; if the deviation is >1 time, it means that the predicted value deviates significantly from the long-term nighttime urination pattern, and the moving average is directly used as the second predicted number of nighttime urinations to ensure the reliability of the prediction results.

[0045] For example, the actual number of times the target person got up at night in the above 7 days was 1, 2, 1, 2, 1, 2, 1, with a moving average of 1.4 times. The deviation between the first predicted number of nighttime awakenings of 2 and the moving average of 1.4 times is 0.6 times (0.5 times < 0.6 times ≤ 1 time). The weighted average is calculated as: 2 × 0.6 + 1.4 × 0.4 = 1.76 times. After rounding, the second predicted number of nighttime awakenings is 2 times.

[0046] Step S103: Based on the daytime blue light ERI cumulative value, the second predicted number of nighttime awakenings, and the blue light ERI cumulative threshold, obtain the blue light ERI quota for each nighttime awakening of the target object on that day.

[0047] The cumulative ERI threshold for blue light refers to the safe total amount of blue light ERI that the human body can tolerate throughout the day. It is a fixed threshold determined based on biological experiments and clinical data on the protection of circadian rhythms in the elderly, generally 380 μW·s / cm². Exceeding this threshold will significantly disrupt the circadian rhythms of the elderly and affect sleep quality. The upper limit of blue light ERI at night (E max The blue light ERI (Electronic Resonance Index) refers to the total amount of blue light ERI that the target object can accept during the night. It can be obtained by the difference between the blue light ERI accumulation threshold and the blue light ERI accumulation value during the day. It is the basis for the allocation of blue light ERI quota for a single nighttime trip. The blue light ERI quota refers to the maximum limit of blue light ERI that the target object can use each nighttime trip. It is the core quantitative standard for dynamic adjustment of blue light power during subsequent nighttime trips.

[0048] Specifically, this step is the quota allocation stage of the entire regulation method. It follows the daytime blue light ERI cumulative value in step S201 and the second predicted number of nighttime urinations in step S202, providing a precise quantitative basis for the real-time regulation of blue light power during subsequent nighttime urinations. The core principle is the control of the total amount of blue light throughout the day, adaptation to individual physiological differences, and the reservation of safety redundancy. That is, firstly, the total amount of blue light available at night is determined by the safety threshold throughout the day, then the individual blue light tolerance is adapted by combining the lens transmittance of the elderly, and finally, safety redundancy is reserved and allocated according to the predicted number of nighttime urinations, so as to realize the personalized and safe calculation of the blue light ERI quota for a single nighttime urination.

[0049] Step S104: When the nighttime wake-up trigger information of the target object is received, the blue light power of the lighting device is collected at a preset time interval until the nighttime wake-up ends. After each blue light power collection, the real-time blue light ERI cumulative value corresponding to the blue light power collection is obtained based on the blue light power and the preset time interval. The real-time ERI cumulative value is then compared with the blue light ERI quota. Based on the comparison result, the blue light power of the lighting device is adjusted so that the real-time blue light ERI cumulative value of the nighttime wake-up does not exceed the blue light ERI quota.

[0050] Among them, the nighttime wake-up trigger information refers to the electrical signal trigger command generated when intelligent detection devices such as millimeter-wave radar, human infrared sensors, and mattress pressure sensors detect nighttime wake-up behavior (such as getting up, getting out of bed, or leaving the bed) in the target object's resting area. It is the signal source for starting the nighttime blue light control process. The preset time interval refers to the fixed time period for collecting the blue light power of the lighting equipment, which can be 1 second. The blue light power of the lighting equipment refers to the real-time value of the blue light power generated by the dedicated low blue light lighting equipment (such as bedroom night light, corridor sensor light, and bathroom light) used by the target object when getting up at night, and the unit is μW / cm². The real-time blue light ERI cumulative value refers to the cumulative blue light ERI value obtained after each blue light power collection during a single nighttime wake-up process. It is continuously updated as the number of collections increases, reflecting the cumulative blue light irradiance during a single nighttime wake-up process.

[0051] Specifically, this step is the real-time execution and closed-loop management link of the entire control method. Following the blue light ERI quota in step S203, it is the final implementation link for realizing the circadian rhythm lighting control of the elderly. The core principle is real-time blue light collection, ERI accumulation calculation, and multi-level dynamic power adjustment. That is, the intelligent device detects the behavior of getting up at night and starts the control process. It can continuously collect blue light power at 1-second intervals and calculate the real-time ERI accumulation value. The accumulation value is compared with the quota in real time, and the blue light power is adjusted in stages according to the comparison results. This ensures the clarity of lighting and walking safety of the elderly when getting up at night, while strictly controlling the blue light ERI accumulation value of a single nighttime trip to not exceed the quota, so as to avoid blue light exceeding the standard and interfering with their circadian rhythm.

[0052] Specifically, the process begins with three steps: First, a smart detection device deployed in the target's bedroom monitors their resting state in real time. Upon detecting a nighttime wake-up trigger, the nighttime blue light control process is immediately initiated, and dedicated nighttime lighting is activated. Second, real-time blue light power acquisition is performed. At preset 1-second intervals, a spectral sensor continuously collects blue light power data from the lighting equipment until the smart detection device detects that the target has completed the nighttime wake-up action (e.g., returning to bed, mattress pressure recovery). Each acquisition action is sequentially numbered (j=1, 2, 3, ..., n, where n is the total number of acquisitions). Third, real-time blue light ERI cumulative value calculation is performed. After each blue light power acquisition, the blue light power value (Bj) collected in the j-th acquisition is calculated. real，j ) and preset time interval (T) real =1s) multiply to obtain the instantaneous blue light ERI value of this collection. Then, the instantaneous ERI values ​​from the first to the jth collection are accumulated using the summation formula to obtain the real-time blue light ERI cumulative value corresponding to this collection. The cumulative value is continuously updated as the number of collections increases. The fourth step is real-time comparison and dynamic power adjustment. The real-time blue light ERI cumulative value calculated each time is compared with the blue light ERI quota obtained in step S203 in real time. The power adjustment rules of the lighting equipment are executed according to the comparison results to ensure that the real-time blue light ERI cumulative value of a single nighttime awakening never exceeds the quota.

[0053] Understandably, after the target user gets up at night, the blue light power of the lighting equipment will be continuously collected. Each time a data point is collected, a real-time cumulative blue light ERI value will be calculated and compared in real-time with the blue light ERI quota. Based on the comparison result, the blue light power of the lighting equipment will be adjusted. If the preset time interval for data collection is set to 1 second, second-level adjustment is achieved. Furthermore, after one nighttime use, the adjustment process will be repeated for the next nighttime use, ensuring that the cumulative blue light from each nighttime use does not exceed the blue light ERI quota, thus ensuring that the total blue light ERI at night does not exceed the nighttime blue light ERI upper limit.

[0054] The solution provided in this application collects ambient blue light power data and lighting device blue light power data of the target object during the day, and obtains the cumulative daytime effective retinal irradiance (ERI) value of the target object based on the ambient blue light power data and the lighting device blue light power data; and uses the target object's age, pre-sleep water intake, average number of nighttime awakenings over a first preset historical number of days, nighttime ambient temperature, and lens transmittance as input parameters, inputs them into a preset classification regression tree (CART decision tree), outputs the corresponding first predicted number of nighttime awakenings, and then corrects the first predicted number of nighttime awakenings based on the number of nighttime awakenings over a second historical number of days to obtain the second predicted number of nighttime awakenings; based on the daytime... The scheme uses the accumulated blue light ERI value, the second predicted number of nighttime awakenings, and the accumulated blue light ERI threshold to obtain the blue light ERI quota for each nighttime awakening of the target individual. When the target individual's nighttime awakening trigger information is received, the blue light power of the lighting equipment is collected at preset time intervals until the nighttime awakening ends. After each blue light power collection, the real-time accumulated blue light ERI value corresponding to that blue light power collection is obtained based on the blue light power and the preset time interval. The real-time accumulated ERI value is then compared with the blue light ERI quota, and the blue light power of the lighting equipment is adjusted based on the comparison result to ensure that the real-time accumulated blue light ERI value for that nighttime awakening does not exceed the blue light ERI quota. This scheme relies on the individual physiological information of the target individual to accurately predict the number of nighttime awakenings, and based on this, further calculates the blue light ERI quota for each nighttime awakening. During the nighttime awakening process, the blue light power of the lighting equipment is dynamically adjusted in real time to ensure that the nighttime ERI accumulation does not exceed the standard. This scheme can accurately match the circadian rhythm protection needs of the elderly and has strong versatility and practical application value.

[0055] In one optional embodiment of this application, obtaining the blue light ERI quota for each nighttime awakening of the target object based on the daytime blue light ERI cumulative value, the second predicted number of nighttime awakenings, and the blue light ERI cumulative threshold includes: The difference between the blue light ERI accumulation threshold and the daytime blue light ERI accumulation value is used as the nighttime blue light ERI upper limit; Based on the nighttime blue light ERI upper limit and the second predicted number of nighttime awakenings, the blue light ERI quota for each nighttime awakening is obtained.

[0056] The step of obtaining the blue light ERI quota for each nighttime awakening based on the nighttime blue light ERI upper limit and the second predicted number of nighttime awakenings is achieved through the following formula:

[0057] in, The Blu-ray ERI quota for each time you get up at night. The upper limit of the nighttime blue light ERI, The transmittance of the lens of the target object. This represents the second predicted number of nighttime urinations.

[0058] Specifically, to determine the blue light ERI quota, the total nighttime blue light ERI (i.e., the upper limit of nighttime blue light ERI) is first determined, and then allocated on a per-use basis after individual difference correction and safety redundancy reservation. That is, the total nighttime usable blue light ERI is determined by subtracting the accumulated blue light ERI value during the day from the all-day blue light ERI safety threshold. Then, the individual blue light tolerance is adapted to the lens transmittance of the elderly, while reserving a safety redundancy space to avoid the risk of exceeding the limit in actual application. Finally, it is evenly allocated according to the second predicted number of nighttime awakenings to obtain a precise and personalized single-use nighttime blue light ERI quota. This ensures that the quota calculation meets the safety control requirements of the total all-day blue light amount, adapts to the individual physiological characteristics of the elderly, and takes into account the safety and rationality of actual application, providing a clear and quantitative core basis for the dynamic adjustment of blue light power during subsequent nighttime awakenings.

[0059] Specifically, the first step is to calculate the upper limit of blue light ERI at night. The cumulative blue light ERI threshold is taken as the safe total amount of blue light ERI that the human body can accept throughout the day. This threshold can be directly subtracted from the cumulative blue light ERI value of the target object during the day. The difference is the upper limit of blue light ERI at night, E. max This value represents the total accumulated blue light ERI that the target object can use during all nighttime awakenings, ensuring from the source that nighttime blue light use will not lead to an excessive accumulated blue light ERI throughout the day; the second step is to obtain the core parameters for quota calculation, in addition to the already obtained nighttime blue light ERI upper limit E. max It also simultaneously extracts the lens transmittance K of the target object and the second predicted number of nighttime urination N. final This prepares for subsequent quantitative calculations; the third step is to perform individual difference correction, using the upper limit of ERI for nighttime blue light. max Subtract the product of 20 and K, where 20 is an individual difference correction coefficient calibrated based on clinical data of lens transmittance in the elderly (this coefficient can also be adjusted according to actual needs and verification). The smaller K is, the worse the visual function of the elderly and the more sensitive they are to blue light. This calculation can be used to specifically reduce their nighttime blue light availability value, achieving personalized adaptation of blue light quota. Fourth step, reserve safety redundancy: multiply the value after individual difference correction by 0.9 (safety redundancy coefficient) to reserve 10% blue light ERI space, effectively avoiding the problem of nighttime blue light ERI accumulation exceeding the standard caused by uncertainties in actual application such as equipment acquisition error, sudden changes in nighttime urination duration, and power adjustment delay. Fifth step, allocate the single-use blue light ERI quota: divide the value after individual correction and safety redundancy processing by the second predicted number of nighttime urinations N. finalThe result is the blue light ERI quota for each time the target gets up at night on that day, thus completing the precise quantitative calculation of the entire quota.

[0060] For example, given that the cumulative ERI threshold for blue light is 380 μW·s / cm², the cumulative blue light ERI of the target object during the day is 150 μW·s / cm², the lens transmittance K=0.65, and the second predicted number of nighttime awakenings N... final =3 times. First, calculate the upper limit of blue light ERI at night, E. max =380-150=230μW·s / cm 2 The first step is to determine that the cumulative blue light ERI of the target object on that day and night must not exceed 230 μW·s / cm²; the second step is to confirm the core calculation parameters: E max =230μW·s / cm 2 K=0.65, N final =3 times; Third step, individual difference correction: 230 - 20 × 0.65 = 230 - 13 = 217 μW·s / cm 2 Fourth step, reserve a safety redundancy: 217 × 0.9 = 195.3 μW·s / cm 2 Step 5: Allocate quotas by batch: 195.3 ÷ 3 = 65.1 μW·s / cm 2 That is, the blue light ERI quota for the target object is 65.1 μW·s / cm² for each nighttime awakening.

[0061] In one optional embodiment of this application, the real-time blue light ERI cumulative value corresponding to the blue light power acquisition is obtained based on the blue light power and the preset time interval, using the following formula:

[0062] Where j is the blue light power sampling sequence number during that nighttime awakening, and n is a natural number. This represents the real-time cumulative blue light ERI value corresponding to the j-th blue light power acquisition during this nighttime awakening. Let j be the blue light power value collected in the j-th sampling. The preset time interval is [the set time interval].

[0063] Specifically, the blue light power collected at preset time intervals is multiplied by the time interval to obtain the instantaneous blue light ERI value of a single collection. Then, through summation, all instantaneous ERI values ​​from the start of nighttime awakening to the current collection are accumulated to obtain the real-time cumulative blue light ERI value up to the current collection. This achieves second-level, real-time statistics of the accumulated blue light ERI during nighttime awakening, providing accurate and real-time data support for subsequent dynamic adjustments of blue light power, ensuring that each power adjustment is based on the current actual accumulated blue light irradiance. Specifically, the first step is to initiate collection and numbering. Upon receiving the nighttime awakening trigger information from the target object, the blue light power of the lighting equipment is collected at preset time intervals. Each collection action is sequentially numbered, denoted as collection sequence number j, starting from 1 and incrementing sequentially. The second step is to calculate the single instantaneous ERI value, taking the blue light power value B obtained from the j-th collection... real,j , with a fixed preset time interval T real Multiply the values ​​to obtain the instantaneous blue light ERI value corresponding to the j-th acquisition. This value reflects the actual intensity of the blue light effect on the retina during this acquisition cycle. In the third step, accumulate the values ​​to obtain the real-time cumulative value. By summing all the instantaneous blue light ERI values ​​from the 1st to the j-th acquisition, the result is the real-time blue light ERI cumulative value corresponding to the j-th blue light power acquisition during this nighttime awakening. As the nighttime awakening process progresses, j continuously increases, and the real-time blue light ERI cumulative value will also be continuously updated until the nighttime awakening ends.

[0064] In one optional embodiment of this application, adjusting the blue light power of the lighting device based on the comparison result so that the real-time blue light ERI cumulative value of the nighttime awakening does not exceed the blue light ERI quota includes: If the real-time blue light ERI is less than the preset ratio of the blue light ERI quota, then the blue light power of the lighting device will be increased by the preset power. If the real-time blue light ERI is not less than the preset ratio of the blue light ERI quota, but less than the blue light ERI quota, then the blue light power of the lighting device remains unchanged. If the real-time blue light ERI is not less than the blue light ERI quota, then the blue light power of the lighting device is adjusted to zero.

[0065] Specifically, this step involves implementing the specific rules for dynamic adjustment of blue light power. The core principle is tiered threshold control, which involves setting two key thresholds (the preset ratio of the blue light ERI quota and the blue light ERI quota itself). The real-time accumulated blue light ERI value is divided into three intervals, each corresponding to a clear set of power adjustment rules. This enables automated and precise dynamic adjustment of blue light power during nighttime awakenings, ensuring both the clarity of lighting and walking safety for the elderly while strictly controlling the accumulated blue light ERI value from exceeding the quota, thus balancing the dual needs of "lighting safety" and "circadian rhythm protection". Specifically, firstly, the control threshold is determined by pre-setting a preset ratio (e.g., 80%) of the blue light ERI quota. This ratio is then multiplied by the blue light ERI quota obtained in claims 3 and 4 to obtain the warning threshold, while the blue light ERI quota is used as the over-limit threshold. Secondly, the interval is compared in real time. During nighttime awakenings, each time a real-time accumulated blue light ERI value is calculated, it is immediately compared with the warning threshold and the over-limit threshold to determine its corresponding value interval. Thirdly, the corresponding adjustment rule is executed. Based on the interval assignment of the real-time accumulated blue light ERI value, the corresponding power adjustment action is executed. This comparison and adjustment process is carried out synchronously with the blue light power acquisition, achieving second-level dynamic control. For example, if the blue light ERI quota for a single nighttime awakening of a target object is known to be 65.1 μW·s / cm², and the preset ratio is 80%, then the warning threshold is 65.1 × 80% = 52.08 μW·s / cm², the over-limit threshold is 65.1 μW·s / cm², the preset power adjustment range is 0.5 μW / cm², and the initial blue light power of the lighting equipment is 0.4 μW / cm². When the cumulative real-time blue light ERI value collected in a certain instance is 40 μW·s / cm², which is less than the warning threshold of 52.08 μW·s / cm², the blue light power is increased by the preset power, i.e., 0.4 + 0.5 = 0.9 μW / cm². When the cumulative real-time blue light ERI value collected in a certain instance is 55 μW·s / cm², which is not less than the warning threshold of 52.08 μW·s / cm² and less than the over-limit threshold of 65.1 μW·s / cm², the current blue light power of 0.9 μW / cm² is maintained unchanged. If the cumulative real-time blue light ERI value collected in a certain instance is 65.2 μW·s / cm², which is not less than the over-limit threshold of 65.1 μW·s / cm², the blue light power of the lighting equipment will be immediately adjusted to zero, and the blue light output will be stopped.

[0066] In one optional embodiment of this application, the method further includes: The real-time accumulated ERI value is compared with the upper limit of the nighttime blue light ERI; If the real-time cumulative ERI value is not less than the upper limit of the nighttime blue light ERI, then the blue light power of the lighting device will be adjusted to zero during the current nighttime awakening and subsequent nighttime awakenings.

[0067] Specifically, the first step is a dual real-time comparison: during the nighttime awakening process, each time a real-time blue light ERI cumulative value is calculated, it is compared not only with the single blue light ERI quota, but also simultaneously compared with the nighttime blue light ERI upper limit. The second step is to determine if the limit is exceeded: if the real-time blue light ERI cumulative value is less than the nighttime blue light ERI upper limit, the tiered power adjustment rule continues to be executed; if the real-time blue light ERI cumulative value is not less than the nighttime blue light ERI upper limit, the fallback shutdown rule is immediately triggered. The third step is to execute the shutdown rule: once the fallback rule is triggered, the blue light power of the lighting equipment is immediately adjusted to zero, and the blue light power remains at zero throughout the remaining nighttime awakening process. At the same time, the blue light control process for all subsequent nighttime awakenings that day is locked, and regardless of the real-time blue light ERI cumulative value of subsequent nighttime awakenings, blue light lighting will not be started again, and the blue light power will be directly adjusted to zero.

[0068] Figure 2 This invention provides a circadian rhythm lighting control system for the elderly, such as... Figure 2 As shown, it includes: The daytime blue light ERI cumulative value acquisition module 201 is used to collect the ambient blue light power data and the lighting device blue light power data of the target object during the day, and based on the ambient blue light power data and the lighting device blue light power data, to obtain the daytime blue light effective retinal irradiance (ERI) cumulative value of the target object. The module 202 for predicting the number of nighttime urinations is used to take the target object's age, pre-bedtime water intake, average number of nighttime urinations over a first preset historical period, ambient temperature at night, and lens transmittance as input parameters, input them into a preset classification regression tree (CART decision tree), output the corresponding first predicted number of nighttime urinations, and then correct the first predicted number of nighttime urinations based on the number of nighttime urinations over a second historical period to obtain the second predicted number of nighttime urinations; wherein, the preset CART decision tree is trained through a preset number of clinical data sample groups, and each clinical data sample group is labeled with the corresponding number of nighttime urinations; The blue light ERI quota acquisition module 203 is used to acquire the blue light ERI quota of the target object for each nighttime ... When the control module 204 receives the nighttime trigger information from the target object, it collects the blue light power of the lighting device at preset time intervals until the nighttime trip ends. After each blue light power collection, it obtains the real-time blue light ERI cumulative value corresponding to the blue light power collection based on the blue light power and the preset time interval. Then, it compares the real-time ERI cumulative value with the blue light ERI quota, and adjusts the blue light power of the lighting device based on the comparison result so that the real-time blue light ERI cumulative value of the nighttime trip does not exceed the blue light ERI quota.

[0069] The solution provided in this application collects ambient blue light power data and lighting device blue light power data of the target object during the day, and obtains the cumulative daytime effective retinal irradiance (ERI) value of the target object based on the ambient blue light power data and the lighting device blue light power data; and uses the target object's age, pre-sleep water intake, average number of nighttime awakenings over a first preset historical number of days, nighttime ambient temperature, and lens transmittance as input parameters, inputs them into a preset classification regression tree (CART decision tree), outputs the corresponding first predicted number of nighttime awakenings, and then corrects the first predicted number of nighttime awakenings based on the number of nighttime awakenings over a second historical number of days to obtain the second predicted number of nighttime awakenings; based on the daytime... The scheme uses the accumulated blue light ERI value, the second predicted number of nighttime awakenings, and the accumulated blue light ERI threshold to obtain the blue light ERI quota for each nighttime awakening of the target individual. When the target individual's nighttime awakening trigger information is received, the blue light power of the lighting equipment is collected at preset time intervals until the nighttime awakening ends. After each blue light power collection, the real-time accumulated blue light ERI value corresponding to that blue light power collection is obtained based on the blue light power and the preset time interval. The real-time accumulated ERI value is then compared with the blue light ERI quota, and the blue light power of the lighting equipment is adjusted based on the comparison result to ensure that the real-time accumulated blue light ERI value for that nighttime awakening does not exceed the blue light ERI quota. This scheme relies on the individual physiological information of the target individual to accurately predict the number of nighttime awakenings, and based on this, further calculates the blue light ERI quota for each nighttime awakening. During the nighttime awakening process, the blue light power of the lighting equipment is dynamically adjusted in real time to ensure that the nighttime ERI accumulation does not exceed the standard. This scheme can accurately match the circadian rhythm protection needs of the elderly and has strong versatility and practical application value.

[0070] In one optional embodiment of this application, the step of correcting the first predicted number of nighttime awakenings based on the number of nighttime awakenings in the second historical days to obtain the second predicted number of nighttime awakenings includes: Obtain the moving average of the number of times you get up at night for the second historical number of days, and compare the first predicted number of times you get up at night with the moving average. If the deviation between the first predicted number of nighttime urinations and the sliding average value is not greater than a first preset value, then the first predicted number of nighttime urinations will be used as the second predicted number of nighttime urinations. If the deviation between the first predicted number of nighttime urinations and the moving average is greater than the first preset value but not greater than the second preset value, then the weighted average of the first predicted number of nighttime urinations and the moving average is taken as the second predicted number of nighttime urinations. If the deviation between the first predicted number of nighttime urinations and the moving average is greater than the second preset value, then the moving average is used as the second predicted number of nighttime urinations. Wherein, the first preset value is less than the second preset value.

[0071] In one optional embodiment of this application, obtaining the blue light ERI quota for each nighttime awakening of the target object based on the daytime blue light ERI cumulative value, the second predicted number of nighttime awakenings, and the blue light ERI cumulative threshold includes: The difference between the blue light ERI accumulation threshold and the daytime blue light ERI accumulation value is used as the nighttime blue light ERI upper limit; Based on the nighttime blue light ERI upper limit and the second predicted number of nighttime awakenings, the blue light ERI quota for each nighttime awakening is obtained.

[0072] In one optional embodiment of this application, the step of obtaining the blue light ERI quota for each nighttime awakening based on the nighttime blue light ERI upper limit and the second predicted number of nighttime awakenings is achieved by the following formula:

[0073] in, The Blu-ray ERI quota for each time you get up at night. The upper limit of the nighttime blue light ERI, The transmittance of the lens of the target object. This represents the second predicted number of nighttime urinations.

[0074] In one optional embodiment of this application, the real-time blue light ERI cumulative value corresponding to the blue light power acquisition is obtained based on the blue light power and the preset time interval, using the following formula:

[0075] Where j is the blue light power sampling sequence number during that nighttime awakening, and n is a natural number. This represents the real-time cumulative blue light ERI value corresponding to the j-th blue light power acquisition during this nighttime awakening. Let j be the blue light power value collected in the j-th sampling. The preset time interval is [the set time interval].

[0076] In one optional embodiment of this application, adjusting the blue light power of the lighting device based on the comparison result so that the real-time blue light ERI cumulative value of the nighttime awakening does not exceed the blue light ERI quota includes: If the real-time blue light ERI is less than the preset ratio of the blue light ERI quota, then the blue light power of the lighting device will be increased by the preset power. If the real-time blue light ERI is not less than the preset ratio of the blue light ERI quota, but less than the blue light ERI quota, then the blue light power of the lighting device remains unchanged. If the real-time blue light ERI is not less than the blue light ERI quota, then the blue light power of the lighting device is adjusted to zero.

[0077] In one optional embodiment of this application, it further includes: The real-time accumulated ERI value is compared with the upper limit of the nighttime blue light ERI; If the real-time cumulative ERI value is not less than the upper limit of the nighttime blue light ERI, then the blue light power of the lighting device will be adjusted to zero during the current nighttime awakening and subsequent nighttime awakenings.

[0078] Figure 3 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 3As shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 can call logic instructions in the memory 330 to execute a circadian lighting regulation method for the elderly. This method includes: collecting ambient blue light power data and lighting device blue light power data of the target object during the day; and obtaining the cumulative daytime effective retinal irradiance (ERI) value of the target object based on the ambient blue light power data and the lighting device blue light power data; and inputting the target object's age, bedtime water intake, average number of nighttime awakenings over a first preset historical number of days, nighttime ambient temperature, and lens transmittance as input parameters into a preset classification regression tree (CART decision tree), outputting the corresponding first predicted number of nighttime awakenings, and then correcting the first predicted number of nighttime awakenings based on the number of nighttime awakenings over a second historical number of days to obtain a second predicted number of nighttime awakenings; wherein, the preset CART decision tree... The algorithm is trained using a preset number of clinical data sample groups, each labeled with a corresponding number of nighttime awakenings. Based on the daytime blue light ERI cumulative value, the second predicted number of nighttime awakenings, and the blue light ERI cumulative threshold, the blue light ERI quota for each nighttime awakening of the target object is obtained. When the nighttime awakening trigger information of the target object is received, the blue light power of the lighting device is collected at preset time intervals until the nighttime awakening ends. After each blue light power collection, the real-time blue light ERI cumulative value corresponding to the blue light power collection is obtained based on the blue light power and the preset time interval. The real-time ERI cumulative value is then compared with the blue light ERI quota, and the blue light power of the lighting device is adjusted based on the comparison result so that the real-time blue light ERI cumulative value of the nighttime awakening does not exceed the blue light ERI quota.

[0079] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0080] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the circadian rhythm lighting regulation method for the elderly provided by the above methods. The method includes: collecting ambient blue light power data and lighting device blue light power data of the target object during the day, and obtaining the daytime effective retinal irradiance (ERI) cumulative value of the target object based on the ambient blue light power data and the lighting device blue light power data; and taking the target object's age, bedtime water intake, average number of nighttime awakenings over a first preset historical number of days, nighttime ambient temperature, and lens transmittance as input parameter groups, inputting them into a preset classification regression tree (CART decision tree), outputting the corresponding first predicted number of nighttime awakenings, and then adjusting the first predicted number of nighttime awakenings based on the number of nighttime awakenings over a second historical number of days. The number of times a person gets up at night is measured and corrected to obtain a second predicted number of times a person gets up at night. The preset CART decision tree is trained through a preset number of clinical data sample groups, each of which is labeled with a corresponding number of times a person gets up at night. Based on the daytime blue light ERI cumulative value, the second predicted number of times a person gets up at night, and the blue light ERI cumulative threshold, the blue light ERI quota for each time a person gets up at night is obtained. When the person gets up at night triggers information, the blue light power of the lighting device is collected at preset time intervals until the person gets up at night. After each blue light power collection, the real-time blue light ERI cumulative value corresponding to the blue light power collection is obtained based on the blue light power and the preset time interval. The real-time ERI cumulative value is then compared with the blue light ERI quota. Based on the comparison result, the blue light power of the lighting device is adjusted so that the real-time blue light ERI cumulative value for that person does not exceed the blue light ERI quota.

[0081] Furthermore, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program performs the diurnal rhythm lighting regulation method for the elderly provided by the methods described above. This method includes: collecting ambient blue light power data and lighting device blue light power data of the target object during the day; and obtaining the cumulative daytime effective retinal irradiance (ERI) value of the target object based on the ambient blue light power data and the lighting device blue light power data; and inputting the target object's age, pre-sleep water intake, average number of nighttime awakenings over a first preset historical number of days, nighttime ambient temperature, and lens transmittance as a set of input parameters into a preset classification regression tree (CART decision tree), outputting the corresponding first predicted number of nighttime awakenings, and then correcting the first predicted number of nighttime awakenings based on the number of nighttime awakenings over a second historical number of days to obtain a second predicted number of nighttime awakenings. The number of times a person gets up at night is measured. The preset CART decision tree is trained using a preset number of clinical data sample groups, each labeled with a corresponding number of nighttime awakenings. Based on the daytime blue light ERI cumulative value, the second predicted number of nighttime awakenings, and the blue light ERI cumulative threshold, the blue light ERI quota for each nighttime awakening of the target object is obtained. When the target object's nighttime awakening trigger information is received, the blue light power of the lighting device is collected at preset time intervals until the nighttime awakening ends. After each blue light power collection, the real-time blue light ERI cumulative value corresponding to that blue light power collection is obtained based on the blue light power and the preset time interval. The real-time ERI cumulative value is then compared with the blue light ERI quota, and the blue light power of the lighting device is adjusted based on the comparison result to ensure that the real-time blue light ERI cumulative value for that nighttime awakening does not exceed the blue light ERI quota.

[0082] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0083] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0084] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for regulating circadian rhythm lighting for the elderly, characterized in that, include: Collect ambient blue light power data and lighting device blue light power data of the target object during the day, and obtain the cumulative value of daytime effective retinal irradiance (ERI) of the target object based on the ambient blue light power data and the lighting device blue light power data; as well as The target subject's age, bedtime water intake, average number of nighttime urinations over a first preset historical period, ambient temperature at night, and lens transmittance are used as input parameters. These parameters are input into a preset classification regression tree (CART decision tree), which outputs the corresponding first predicted number of nighttime urinations. The first predicted number of nighttime urinations is then corrected based on the number of nighttime urinations over a second historical period to obtain the second predicted number of nighttime urinations. The preset CART decision tree is trained using a preset number of clinical data sample groups, each of which is labeled with a corresponding number of nighttime urinations. Based on the daytime blue light ERI cumulative value, the second predicted number of nighttime awakenings, and the blue light ERI cumulative threshold, the blue light ERI quota for each nighttime awakening of the target object on that day is obtained; When the target object is received to trigger a nighttime wake-up call, the blue light power of the lighting device is collected at preset time intervals until the nighttime wake-up call ends. After each blue light power collection, the real-time blue light ERI cumulative value corresponding to the blue light power collection is obtained based on the blue light power and the preset time interval. The real-time ERI cumulative value is then compared with the blue light ERI quota. Based on the comparison result, the blue light power of the lighting device is adjusted so that the real-time blue light ERI cumulative value of the nighttime wake-up call does not exceed the blue light ERI quota.

2. The method according to claim 1, characterized in that, The second predicted number of nighttime urinations is obtained by correcting the first predicted number of nighttime urinations based on the number of nighttime urinations based on the number of nighttime urinations in the second historical days, including: Obtain the moving average of the number of times you get up at night for the second historical number of days, and compare the first predicted number of times you get up at night with the moving average. If the deviation between the first predicted number of nighttime urinations and the sliding average value is not greater than a first preset value, then the first predicted number of nighttime urinations will be used as the second predicted number of nighttime urinations. If the deviation between the first predicted number of nighttime urinations and the moving average is greater than the first preset value but not greater than the second preset value, then the weighted average of the first predicted number of nighttime urinations and the moving average is taken as the second predicted number of nighttime urinations. If the deviation between the first predicted number of nighttime urinations and the moving average is greater than the second preset value, then the moving average is used as the second predicted number of nighttime urinations. Wherein, the first preset value is less than the second preset value.

3. The method according to claim 1, characterized in that, The step of obtaining the blue light ERI quota for each nighttime awakening of the target object based on the daytime blue light ERI cumulative value, the second predicted number of nighttime awakenings, and the blue light ERI cumulative threshold includes: The difference between the blue light ERI accumulation threshold and the daytime blue light ERI accumulation value is used as the nighttime blue light ERI upper limit; Based on the nighttime blue light ERI upper limit and the second predicted number of nighttime awakenings, the blue light ERI quota for each nighttime awakening is obtained.

4. The method according to claim 3, characterized in that, The blue light ERI quota for each nighttime nighttime awakening, based on the nighttime blue light ERI upper limit and the second predicted number of nighttime awakenings, is obtained using the following formula: in, The Blu-ray ERI quota for each time you get up at night. The upper limit of the nighttime blue light ERI, The transmittance of the lens of the target object. This represents the second predicted number of nighttime urinations.

5. The method according to claim 1, characterized in that, The real-time cumulative blue light ERI value corresponding to this blue light power acquisition is obtained based on the blue light power and the preset time interval, using the following formula: Where j is the blue light power sampling sequence number during that nighttime awakening, and n is a natural number. This represents the real-time cumulative blue light ERI value corresponding to the j-th blue light power acquisition during this nighttime awakening. Let j be the blue light power value collected in the j-th sampling. The preset time interval is [the set time interval].

6. The method according to claim 1, characterized in that, The adjustment of the blue light power of the lighting device based on the comparison results, so that the real-time blue light ERI cumulative value during this nighttime awakening does not exceed the blue light ERI quota, includes: If the real-time blue light ERI is less than the preset ratio of the blue light ERI quota, then the blue light power of the lighting device will be increased by the preset power. If the real-time blue light ERI is not less than the preset ratio of the blue light ERI quota, but less than the blue light ERI quota, then the blue light power of the lighting device remains unchanged. If the real-time blue light ERI is not less than the blue light ERI quota, then the blue light power of the lighting device is adjusted to zero.

7. The method according to claim 3, characterized in that, The method further includes: The real-time accumulated ERI value is compared with the upper limit of the nighttime blue light ERI; If the real-time cumulative ERI value is not less than the upper limit of the nighttime blue light ERI, then the blue light power of the lighting device will be adjusted to zero during the current nighttime awakening and subsequent nighttime awakenings.

8. A circadian rhythm lighting control system for the elderly, characterized in that, include: The daytime blue light ERI cumulative value acquisition module is used to collect ambient blue light power data and lighting device blue light power data of the target object during the day, and obtain the daytime blue light effective retinal irradiance (ERI) cumulative value of the target object based on the ambient blue light power data and the lighting device blue light power data. The module for predicting the number of nighttime urinations is used to take the target object's age, daily bedtime water intake, average number of nighttime urinations over a first preset historical period, nighttime ambient temperature, and lens transmittance as input parameters, input them into a preset classification regression tree (CART decision tree), output the corresponding first predicted number of nighttime urinations, and then correct the first predicted number of nighttime urinations based on the number of nighttime urinations over a second historical period to obtain the second predicted number of nighttime urinations; wherein, the preset CART decision tree is trained through a preset number of clinical data sample groups, and each clinical data sample group is labeled with the corresponding number of nighttime urinations; The Blue Light ERI Quota Acquisition Module is used to acquire the Blue Light ERI quota for each nighttime ... The control module, upon receiving the nighttime trigger information from the target object, collects the blue light power of the lighting device at preset time intervals until the nighttime awakening ends. After each blue light power collection, it obtains the real-time blue light ERI cumulative value corresponding to that collection based on the blue light power and the preset time interval. Then, it compares the real-time ERI cumulative value with the blue light ERI quota, and adjusts the blue light power of the lighting device based on the comparison result so that the real-time blue light ERI cumulative value for that nighttime awakening does not exceed the blue light ERI quota.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 7.

Images