Infant and child health lighting control method and system based on dynamic adjustment of color temperature parameters

Abstract

The present invention relates to the field of healthy lighting technology, and solves the problem in the prior art that a suitable color temperature environment cannot be provided for infants and young children, and poor lighting conditions cause health damage to infants and young children, and provides a healthy lighting control method and system for infants and young children based on dynamic adjustment of color temperature parameters. The method comprises: obtaining real-time ambient light parameters, infant age, and data to be processed in an infant care scenario; classifying the data to be processed into training set data and test set data; inputting the training set data into a recurrent neural network to obtain an initial model for color temperature regulation; using the test set data for evaluation to obtain a color temperature regulation model; inputting the ambient light parameters and infant age into the color temperature regulation model to obtain a first lighting parameter; performing a secondary adjustment on the first lighting parameter to obtain a target lighting parameter, and controlling the lighting equipment to perform lighting. The present invention can provide a suitable color temperature environment for infants and young children, thereby improving the comfort of infants and young children.

Description

[0001] This application is a divisional application of the invention patent application filed on April 18, 2023, with the invention name “Scene-adaptive infant health lighting control method and system” and application number 202310411760.0. Technical Field

[0002] The present invention relates to the field of healthy lighting technology, and in particular to a healthy lighting control method and system for infants and young children based on dynamic adjustment of color temperature parameters. Background Art

[0003] Human evolution has continuously improved and utilized natural light, leaving a deep imprint on our evolutionary history. From the optical biological clock formed by sunrise and sunset, to the range of vision under sunlight and the shifting light colors throughout the day and night, all living things have adapted to the sun's illumination and bathing. The advent of artificial light has altered the natural circadian rhythm, and excessive use can cause visual fatigue, insomnia, light radiation hazards, and disruptions to our biological rhythms.

[0004] In the care scenarios for infants and young children, there are many types of infant care scenarios, such as infant sleeping scenes, dining scenes, crying scenes and playing scenes. However, in the above-mentioned multiple scenarios, traditional lighting control methods can only provide a single lighting method. Since infants and young children are young and their physical development is extremely incomplete compared to adults, the problems of immature body organs and imperfect system functions make infants and young children susceptible to adverse external lighting conditions. For example, when infants and young children are in a scene with inappropriate color temperature, the blue light in the cool light will also have an adverse effect on the infant's eye development; an environment with inappropriate color temperature will also slowly affect the infant's mental state and damage the infant's physical and mental health.

[0005] Therefore, how to provide infants and young children with a suitable color temperature environment and avoid poor lighting conditions that cause health damage to infants and young children is an urgent problem to be solved. Summary of the Invention

[0006] In view of this, the present invention provides a healthy lighting control method and system for infants and young children based on dynamic adjustment of color temperature parameters, which is used to solve the problem in the prior art that a suitable color temperature environment cannot be provided for infants and young children, and poor lighting conditions cause health damage to infants and young children.

[0007] The technical solution adopted in the present invention is:

[0008] In a first aspect, the present invention provides a method for controlling healthy lighting for infants and young children based on dynamic adjustment of color temperature parameters, the method comprising:

[0009] Acquiring real-time ambient lighting parameters in an infant care scenario, preset infant ages, and data to be processed under multiple target lighting conditions related to infant care, wherein the data to be processed includes: sample ambient lighting parameters under each of the target lighting conditions and multiple sample color temperature parameters matching each of the target lighting conditions;

[0010] Preprocessing the data to be processed, classifying the data to be processed into training set data and test set data after standardization;

[0011] Inputting the training set data into a recurrent neural network for deep learning and training to obtain an initial color temperature regulation model;

[0012] Evaluating the initial color temperature adjustment model using the test set data, and adjusting the initial model based on the evaluation result to obtain a color temperature adjustment model;

[0013] Inputting the ambient light parameters and the age of the infant into the color temperature adjustment model, adjusting the color temperature in the ambient light parameters to obtain first light parameters with a color temperature suitable for the current environment;

[0014] Performing a secondary adjustment on the first illumination parameter to obtain a second illumination parameter suitable for the current physiological state of the infant as a target illumination parameter;

[0015] According to the target lighting parameters, the lighting equipment is controlled to perform lighting to complete healthy lighting in the current infant care scene.

[0016] Preferably, the second adjustment of the first illumination parameter to obtain a second illumination parameter suitable for the current physiological state of the infant as the target illumination parameter includes:

[0017] Acquire real-time facial images of infants and young children in infant care scenarios;

[0018] Inputting the real-time facial image of the infant into a preset facial analysis model to obtain the real-time physiological state of the infant under the lighting conditions of the ambient lighting parameters;

[0019] According to the real-time physiological state of the infant, the first lighting parameter is adjusted for the second time to obtain a second lighting parameter suitable for the current physiological state of the infant as the target lighting parameter.

[0020] Preferably, the step of inputting the ambient light parameters and the age of the infant into the color temperature adjustment model and adjusting the color temperature in the ambient light parameters to obtain the first light parameters with a color temperature suitable for the current environment includes:

[0021] Inputting the real-time ambient light parameters into the color temperature adjustment model, and matching the sample color temperature parameters to obtain preliminary color temperature parameters that meet the real-time ambient light conditions;

[0022] Acquire a plurality of preset infant age intervals, and derive a target age interval corresponding to the infant age in each of the age intervals;

[0023] The preliminary color temperature parameter is corrected twice according to the target age range to obtain the first lighting parameter.

[0024] Preferably, the acquiring of a real-time facial image of an infant in an infant care scene includes:

[0025] Acquire a real-time video stream in the infant care scene, and decompose the real-time video stream into multiple frames of images;

[0026] The multiple frames of images are input into a preset target detection model, and the images with marked infant faces in each frame are extracted and recorded as real-time images of infant faces, wherein the target detection model is a deep learning model based on the yolov6s structure.

[0027] Preferably, before inputting the real-time image of the infant's face into a preset face analysis model and deriving the real-time physiological state of the infant under the lighting conditions of the ambient lighting parameters, the method includes:

[0028] Acquire multiple frames of infant and child face images under various lighting conditions as training images;

[0029] Inputting each of the training images into a preset infant face classification model to obtain expression information corresponding to each training image;

[0030] According to each of the expression information, assigning each of the training images a label corresponding to the expression information;

[0031] Each of the training images with the label is input into a classification network based on the Mobilenet structure for training to obtain the facial analysis model.

[0032] Preferably, the step of inputting the real-time facial image of the infant into a preset facial analysis model to obtain the real-time physiological state of the infant under the lighting conditions of the ambient lighting parameters comprises:

[0033] Inputting the real-time image of the infant's face into the face analysis model, and matching the real-time image of the infant's face with each frame of the sample image;

[0034] When the real-time image of the infant's face matches a target image in each of the sample images, assigning the target label on the target image to the real-time image;

[0035] The real-time physiological state of the infant is obtained based on the target tag.

[0036] Preferably, the second adjustment of the first lighting parameter based on the real-time physiological state of the infant to obtain a second lighting parameter suitable for the current physiological state of the infant as the target lighting parameter includes:

[0037] Adjusting one or more parameters of the light intensity, light projection direction, brightness, color saturation, and color fidelity according to the real-time physiological state;

[0038] When the real-time physiological state of the infant is adjusted to be comfortable, the second lighting parameter at this time is used as the target lighting parameter.

[0039] Preferably, the lighting parameters include: color temperature, light intensity, light projection direction, brightness, color saturation and color fidelity.

[0040] In a second aspect, the present invention provides an infant health lighting control system based on dynamic adjustment of color temperature parameters, which is used to implement the above-mentioned infant health lighting control method based on dynamic adjustment of color temperature parameters. The system includes:

[0041] An ambient light sensor is used to detect ambient light conditions and input the real-time ambient light information and infant age information into a preset color temperature adjustment model;

[0042] A camera, configured to capture infant facial images in real time and input the infant facial images into a facial analysis model;

[0043] An intelligent analysis subsystem, which uses a trained classification model to determine how infants and young children adapt to lighting conditions;

[0044] The lighting adjustment subsystem is used to adjust the projection brightness of the light source according to the results of the intelligent analysis module.

[0045] Preferably, the system application scenarios include: at least one of infant sleeping, crying and playing scenarios.

[0046] In summary, the beneficial effects of the present invention are as follows:

[0047] The present invention provides a method and system for controlling healthy lighting for infants and young children based on dynamic adjustment of color temperature parameters. The method comprises: obtaining real-time ambient lighting parameters, a preset infant age, and a corresponding real-time image of the infant's face in an infant care scenario; inputting the ambient lighting parameters and the infant's age into a preset color temperature adjustment model, adjusting the color temperature in the ambient lighting parameters, and obtaining a first lighting parameter with a color temperature suitable for the current environment; inputting the real-time image of the infant's face into a preset facial analysis model to obtain the infant's real-time physiological state under the lighting conditions of the ambient lighting parameters; performing a secondary adjustment on the first lighting parameter based on the infant's real-time physiological state to obtain a second lighting parameter suitable for the infant's current physiological state as a target lighting parameter; and controlling the lighting equipment to illuminate based on the target lighting parameter to achieve healthy lighting in the current infant care scenario. The present invention obtains the ambient lighting parameters and the infant's age in the infant care scenario in real time, combines them with the preset color temperature adjustment model, and intelligently adjusts the lighting conditions to ensure that the color temperature is suitable for the current environment. First, the solution analyzes current lighting conditions and makes preliminary adjustments to obtain the first lighting parameters. Next, it makes a secondary adjustment to the lighting, ultimately generating the second lighting parameters optimal for infant health. This intelligent lighting adjustment effectively addresses the existing technology's inability to provide an optimal color temperature environment, reducing the potential harm to infant health caused by poor lighting and promoting healthy growth. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work, and these are all within the scope of protection of the present invention.

[0049] Figure 1 This is a schematic diagram of the overall working process of the infant health lighting control method based on dynamic adjustment of color temperature parameters in Example 1 of the present invention;

[0050] Figure 2 This is a schematic diagram of the process of obtaining a real-time image of an infant's face in Example 1 of the present invention;

[0051] Figure 3 This is a schematic diagram of the process of constructing a color temperature adjustment model in Example 1 of the present invention;

[0052] Figure 4 Schematic diagram of a process for determining appropriate color temperature parameters in Example 1 of the present invention;

[0053] Figure 5 This is a schematic diagram of the process of constructing a facial analysis model in Example 1 of the present invention;

[0054] Figure 6 This is a schematic diagram of the process of determining real-time status information of an infant in Example 1 of the present invention;

[0055] Figure 7 Schematic diagram of the process of adjusting light source illumination information in Example 1 of the present invention;

[0056] Figure 8 This is a schematic diagram of a process for determining the normal physiological state of an infant in Example 1 of the present invention;

[0057] Figure 9 This is a schematic diagram of the process of determining whether an infant's body temperature is normal in Example 1 of the present invention;

[0058] Figure 10 This is a structural diagram of an infant health lighting control system based on dynamic adjustment of color temperature parameters in Example 2 of the present invention. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. It should be noted that, in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. In the description of the present invention, it should be understood that the orientation or position relationship indicated by the terms "center", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like is based on the orientation or position relationship shown in the drawings, and is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the present invention. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further limitations, elements defined by the phrase "comprising..." do not preclude the presence of additional identical elements in the process, method, article, or apparatus comprising the elements. The embodiments of the present invention and the features thereof may be combined with each other if there is no conflict, and all are within the scope of protection of the present invention.

[0060] Example 1

[0061] See Figure 1Embodiment 1 of the present invention discloses a method for controlling healthy lighting for infants and young children based on dynamic adjustment of color temperature parameters, the method comprising:

[0062] S1: Acquire real-time ambient lighting parameters, preset infant age, and corresponding real-time image of the infant's face in an infant care scene;

[0063] Specifically, real-time ambient lighting information collected by an ambient light sensor and a real-time infant facial image collected by a camera are obtained, wherein the real-time ambient lighting information includes real-time ambient light intensity and color temperature information. By analyzing and processing the real-time ambient lighting information and the infant facial image, the light source information is adjusted, which is conducive to achieving effective care for infants and promoting their healthy growth.

[0064] In one embodiment, see Figure 2 , said S1 comprises:

[0065] S11: Acquire a real-time video stream in the infant care scene, and decompose the real-time video stream into multiple frames of images;

[0066] S12: Input the multiple frames of images into a preset target detection model, extract the image with the marked infant's face in each frame of the image, and record it as the real-time image of the infant's face, wherein the target detection model is a deep learning model based on the yolov6s structure.

[0067] Specifically, a large number of publicly available images of infants at various growth stages are collected in advance for analysis, with a focus on daily activity images of younger infants. The infant faces and non-infant faces in these daily activity images are pre-labeled, and the labeled frames are input as training data for a deep learning model. A neural network detection algorithm model based on the YoloV6s structure is constructed and trained, and the neural network detection algorithm model is used as a target detection model. Multiple frames of images decomposed from a real-time video stream are sequentially input into the target detection model, and multiple frames of facial target images of infant faces and non-infant faces are identified. Images of infant faces are extracted from the facial target images, and recorded as real-time images of infant faces.

[0068] In one embodiment, see Figure 3 , the S2 includes:

[0069] S201: Acquire data to be processed under multiple target lighting conditions related to infant care, wherein the data to be processed includes: sample ambient lighting parameters under each of the target lighting conditions and multiple sample color temperature parameters matching each of the target lighting conditions;

[0070] Specifically, the ambient lighting parameters under different ambient lighting conditions and the appropriate color temperature corresponding to each ambient lighting condition are obtained, wherein the ambient lighting parameters include: light intensity, light projection direction and light source type, etc., and the color temperature is divided into warm tones, neutral tones and cool tones, wherein color temperature = <3300K corresponds to warm tones; 3300K < color temperature <6000K corresponds to neutral tones; color temperature >6000K corresponds to cool tones. For example, if the ambient light is yellowish, the appropriate color temperature should be warm tones, and the color temperature parameter = <3300K; if the ambient light is white light, the appropriate color temperature should be cool tones, and the color temperature parameter >6000K. By finding the appropriate color temperature under each ambient lighting condition and matching the ambient lighting conditions with the color temperature, it is helpful to improve the comfort of infants and young children in different environmental conditions and enhance the user's care experience.

[0071] S202: preprocessing the data to be processed, classifying the data to be processed into training set data and test set data after standardization;

[0072] S203: Inputting the training set data into a recurrent neural network for deep learning and training to obtain an initial color temperature regulation model;

[0073] Specifically, a deep learning model is designed, which can use a recurrent neural network (RNN). The training set data is input into the deep learning model for training. A loss function loss is predefined. By adjusting the network parameters of the recurrent neural network (RNN), the loss function loss is continuously optimized until the loss is less than a pre-set threshold. At this point, it is considered that the trained deep learning model is highly consistent with the training data, and the trained RNN-based deep learning model is output as the initial model. By defining the loss function and continuously optimizing the loss function, a high degree of consistency between the final generated initial model and the training data is ensured. Since the training data is preprocessed and standardized data, the accuracy of the initial model in adjusting the color temperature is improved.

[0074] S204: Evaluate the color temperature adjustment initial model using the test set data, and adjust the initial model according to the evaluation result to obtain the color temperature adjustment model.

[0075] Specifically, the test set data is input into the initial model to obtain appropriate color temperature parameters corresponding to the test set data. An evaluation result is provided based on the accuracy of the obtained appropriate color temperature parameters corresponding to the test set data. Based on the evaluation result, the initial model is adjusted a second time to obtain a final color temperature adjustment model. By inputting the test set data into the initial model to simulate actual testing and performing a second adjustment based on the test results, the accuracy of color temperature adjustment is further improved, making the final adjusted color temperature more suitable for actual environmental conditions, thereby improving the comfort of infants and young children.

[0076] S2: Inputting the ambient light parameters and the age of the infant into a preset color temperature adjustment model, adjusting the color temperature in the ambient light parameters to obtain first light parameters with a color temperature suitable for the current environment;

[0077] Specifically, since the development of infants and young children is not yet complete, for infants and young children who are too young, inappropriate color temperature will affect the development of their eyes. If the color temperature is inappropriate, it will cause visual fatigue or other eye problems for infants and young children. Therefore, the age of the infant and young child input in advance by the user through the mobile terminal is obtained, and the real-time ambient light is combined with the age of the infant and young child, and the color temperature is adjusted so that the adjusted color temperature is more in line with the actual physiological condition of the current infant and young child, which is helpful to help the healthy physical and mental development of the infant and young child.

[0078] In one embodiment, see Figure 4 , said S2 includes:

[0079] S21: Inputting the real-time ambient light parameters into the color temperature adjustment model, and matching the sample color temperature parameters to obtain preliminary color temperature parameters that meet the real-time ambient light conditions;

[0080] Specifically, the collected real-time ambient lighting information is input into a preset color temperature adjustment model. Since the color temperature adjustment model is trained with training set data and evaluated and calibrated with test set data, it can obtain color temperature parameters suitable for the real-time ambient lighting information. For example, if the suitable color temperature parameter obtained by the color temperature adjustment model is 4500K, 4500K is used as the preliminary color temperature parameter. According to the preliminary color temperature parameter, the color temperature should be adjusted to a neutral tone; if the obtained color temperature parameter is 2000K, the color temperature should be adjusted to a cool tone according to the preliminary color temperature parameter.

[0081] S22: Acquire a plurality of preset infant age intervals, and derive a target age interval corresponding to the infant age in each of the age intervals;

[0082] Specifically, the age of the infant input by the user is obtained. For example, the infant's age is divided into three different intervals: 0-4 months, 4 months-3 years, and 3 years-6 years. If the obtained infant's age is 3 months, the age interval corresponding to the infant's age is 0-4 months.

[0083] S23: Perform secondary correction on the preliminary color temperature parameter according to the target age range to obtain the first lighting parameter.

[0084] Specifically, by dividing the ages of infants and young children into different age ranges, the preliminary color temperature parameters obtained are corrected for different age ranges. For example, the above-mentioned infant age range corresponds to 0-4 months. At this time, the infants and young children are too young, and their eyes and other body parts are extremely incompletely developed. The color temperature should be as low as possible to reduce the adverse effects of cold color temperature on the physical development of infants and young children. The corrected results are used as the final output color temperature parameters. The secondary correction of the preliminary color temperature parameters further improves the accuracy of color temperature adjustment, which is more conducive to the healthy physical and mental development of infants and young children.

[0085] In one embodiment, see Figure 5 , the S3 previously includes:

[0086] S301: Acquire multiple frames of infant facial images under various lighting conditions as training images;

[0087] Specifically, a large number of infant facial images are collected under various brightness, light intensity, color saturation, color fidelity and projection directions. For infants with incomplete development, light intensity and projection direction will affect their physical health and comfort. For example, if infants live in places with too little light, the lack of light source stimulation will affect the development of their vision; if the light is too strong, it may cause visual fatigue or other eye problems in infants; at the same time, direct light is more likely to cause eye problems in infants than light from the side; brightness that is too high or too low will affect the eye development of infants; color saturation and fidelity will affect the comfort of infants, and lighting with high saturation and high fidelity is more likely to be liked by infants.

[0088] S302: Inputting each of the training images into a preset infant face classification model to obtain expression information corresponding to each training image;

[0089] Specifically, the facial expressions of infants and young children in a large number of collected images are used to judge the reaction of infants and young children to the current lighting conditions. Specifically, if the infant or young child's expression is smiling, it is considered that the infant or young child feels comfortable with the current lighting conditions; if the infant or young child's expression is crying or pouting, it is considered that the infant or young child feels uncomfortable with the current lighting conditions, and the user needs to be reminded to adjust the lighting parameters in time.

[0090] S303: assigning labels corresponding to the training images and the expression information according to the target expression information;

[0091] Specifically, the reaction of the above-mentioned infants to the current lighting conditions is obtained. If the infants feel comfortable, the corresponding images are assigned label information such as "comfortable" and "like"; similarly, if the infants feel uncomfortable, the corresponding images are assigned label information such as "painful" and "uncomfortable".

[0092] S304: Inputting each of the training images with the label into a classification network based on the Mobilenet structure for training to obtain the facial analysis model.

[0093] Specifically, the target images assigned with different label information are obtained, and the target images are input into a classification model based on the Mobilenet structure for classification training. By continuously adjusting the network parameters of the classification model, the data generated by the classification model and the input training data are made to fit each other. Finally, a model is obtained that can judge the infant's reaction to the current lighting conditions based on the input infant's facial image, and the trained model is output as the facial analysis model.

[0094] S3: inputting the real-time facial image of the infant into a preset facial analysis model to obtain the real-time physiological state of the infant under the lighting conditions of the ambient lighting parameters;

[0095] Specifically, each frame of the infant's face, derived from the decomposition of the real-time video, is fed into the trained facial analysis model to determine the infant's response under the current real-time lighting conditions, which serves as the infant's real-time state information. By obtaining this real-time state information, it is possible to determine whether the infant's real-time physiological state under the current lighting conditions is normal, thereby adjusting the lighting based on the infant's real-time physiological state and improving the infant's comfort.

[0096] In one embodiment, see Figure 6 , said S3 includes:

[0097] S31: inputting the real-time image of the infant's face into the face analysis model, and matching the real-time image of the infant's face with the sample images of each frame;

[0098] Specifically, a real-time facial image of each infant or child is acquired and each frame of the real-time image is input into a facial analysis model. By comparing the real-time image with the training images of the facial analysis model, a similar image to the real-time image is found in the training images, and the label information of the similar image is used as the target label information for the real-time image. For example, if the difference between the feature information extracted from the real-time image and the feature information extracted from the i-th frame of the training images is small, where i is a positive integer, and the label information for the i-th frame is "comfortable", the label "comfortable" is assigned to the real-time image as the target label information.

[0099] S32: when the real-time image of the infant's face matches a target image in each of the sample images, assigning a target label on the target image to the real-time image;

[0100] S33: Determine the real-time physiological state of the infant based on the target tag.

[0101] S4: adjusting the first lighting parameter a second time based on the real-time physiological state of the infant to obtain a second lighting parameter suitable for the current physiological state of the infant as a target lighting parameter;

[0102] In one embodiment, see Figure 7 , said S4 includes:

[0103] S41: adjusting one or more parameters of the light intensity, light projection direction, brightness, color saturation, and color fidelity according to the real-time physiological state;

[0104] Specifically, the appropriate color temperature parameters are obtained. For example, if the appropriate color temperature parameter is 3000K, the color temperature of the light emitted by the corresponding light source is adjusted to 3000K. Since the appropriate color temperature parameter is obtained through the color temperature adjustment model and takes into account the age of the infant, the infant can obtain a more comfortable lighting experience.

[0105] S42: When the real-time physiological state of the infant is adjusted to be normal, the second lighting parameter at this time is used as the target lighting parameter.

[0106] Specifically, based on the feedback information of the infant on the current ambient lighting conditions, the light intensity and projection direction of the light emitted by the light source are further adjusted. When the real-time physiological state of the infant is normal, it is considered that the light intensity and projection direction at this time are most suitable and beneficial to the physical and mental health of the infant. By further adjusting the light intensity and projection direction of the light emitted by the light source, the healthy growth of the infant is ensured and the comfort of the infant is improved.

[0107] In one embodiment, the physiological state includes: the infant's body temperature, emotional response, and food intake.

[0108] In one embodiment, see Figure 8 , the S42 includes:

[0109] S421: Obtaining a preset normal body temperature range, and determining whether the current body temperature of the infant is normal based on the normal body temperature range;

[0110] In one embodiment, see Figure 9 , the S421 includes:

[0111] S4211: Determining normal body temperature ranges corresponding to the various temperature measurement methods based on the various temperature measurement methods;

[0112] S4212: Using each of the temperature measurement methods to measure the temperature of the infant in sequence, and obtaining the current body temperature of the infant corresponding to each of the temperature measurement methods;

[0113] S4213: Determine, based on the current body temperature of each infant, whether the current body temperature of the infant is within the corresponding normal body temperature range;

[0114] S4214: If the infant's current body temperature is within the corresponding normal temperature range, the infant's body temperature is considered normal;

[0115] S4215: If the infant's current body temperature is not within the corresponding normal body temperature range, the infant's body temperature is considered abnormal.

[0116] Specifically, a preset normal body temperature range is obtained, wherein, according to a variety of different temperature measurement methods, various temperature measurement methods are set to correspond to normal body temperature ranges. For example, the normal body temperature range of the rectal temperature measurement method is set to be between 36.6℃-37.8℃, the normal body temperature range of the oral temperature measurement method is between 36.3℃-37.2℃, and the normal body temperature range of the axillary temperature method is between 36℃-37℃. If the current infant's body temperature is measured to be 36.5 by the axillary temperature method, it is considered that the infant's body temperature is normal under the current lighting conditions. If the current infant's body temperature is measured to be 37.5 by the axillary temperature method, it is considered that the infant's body temperature is abnormal under the current lighting conditions. Similarly, the corresponding infant's body temperature is measured using the above-mentioned rectal temperature method and oral temperature method, and it is determined whether the infant's body temperature is in the corresponding normal body temperature range, so that it can be determined whether the infant's body temperature is normal under the current lighting conditions. By determining whether the infant's body temperature is normal under the current lighting conditions, it is possible to determine whether the current lighting conditions will have an adverse effect on the infant's body temperature.

[0117] S422: Acquire the infant's facial expression information, and determine whether the infant's current emotional response is happy or sad based on the facial expression information;

[0118] Specifically, the infant's current facial expression is obtained. If the infant's current expression is smiling, the infant's emotional response under the current lighting conditions is considered happy. If the infant's current expression is crying, the infant's emotional response under the current lighting conditions is considered sad. By determining whether the infant's emotional response is happy or sad under the current lighting conditions, it is possible to determine whether the current lighting conditions have a negative impact on the infant's emotions.

[0119] S423: Obtaining a preset threshold value for the number of times the infant eats independently and a normal interval for meal times, and determining the current feeding status of the infant based on the threshold value for the number of times the infant eats independently and the normal interval for meal times;

[0120] Specifically, for example, the threshold value of the number of times an infant or young child eats independently is pre-set to 100 times, and the normal range of meal time is set to 20 to 30 minutes. The current number of times the infant or young child eats independently and the current meal time are statistically obtained. If the current number of times the infant or young child eats independently is greater than 100 times and the current meal time is within the normal range of meal time, the current infant or young child's eating situation is considered normal; if the current number of times the infant or young child eats independently is not greater than 100 times or the current meal time is not within the normal range of meal time, the current infant or young child's eating situation is considered abnormal.

[0121] S424: When the current infant's body temperature is normal, the current infant's emotional response is happy, and the current infant's eating situation is normal, it is considered that the real-time physiological state of the infant is adjusted to be normal, and the second lighting parameter at this time is used as the target lighting parameter.

[0122] Specifically, the physiological state integrates multiple parameters such as the infant's body temperature, emotional response and eating habits, and can comprehensively evaluate the impact of current lighting conditions on infants. Only the second lighting parameter adjusted to the normal real-time physiological state of the infant is used as the target lighting parameter, thereby avoiding the adverse effects of inappropriate lighting conditions on infants.

[0123] S5: Control the lighting equipment to perform lighting according to the target lighting parameters to achieve healthy lighting in the current infant care scene.

[0124] Example 2

[0125] See Figure 10 The embodiment of the present invention further provides an infant health lighting control system based on dynamic adjustment of color temperature parameters, characterized in that the system is used to implement the above-mentioned infant health lighting control method based on dynamic adjustment of color temperature parameters, and includes:

[0126] An ambient light sensor is used to detect ambient light conditions and input the real-time ambient light information and infant age information into a preset color temperature adjustment model;

[0127] A camera, configured to capture infant facial images in real time and input the infant facial images into a facial analysis model;

[0128] An intelligent analysis subsystem, which uses a trained classification model to determine how infants and young children adapt to lighting conditions;

[0129] The lighting adjustment subsystem is used to adjust the projection brightness of the light source according to the results of the intelligent analysis module.

[0130] Specifically, an embodiment of the present invention provides an infant health lighting control system based on dynamic adjustment of color temperature parameters. The system includes: an ambient light sensor for detecting ambient lighting conditions and inputting the real-time ambient lighting information and infant age information into a preset color temperature adjustment model; a camera for capturing infant facial images in real time and inputting the infant facial images into a facial analysis model; an intelligent analysis subsystem for using a trained classification model to determine the infant's adaptability to lighting conditions; and a lighting adjustment subsystem for adjusting the projection brightness of the light source based on the results of the intelligent analysis module. This system derives real-time appropriate color temperature parameters through the color temperature adjustment model, and further adjusts the lighting parameters based on the infant's real-time physiological state under ambient lighting conditions to derive accurate target lighting parameters suitable for the infant. Controlling lighting equipment based on the target lighting parameters can prevent the physical and mental health of infants from being harmed by poor lighting conditions, thereby improving the comfort of infants and the user's care experience for the elderly.

[0131] Example 3

[0132] Application scenarios of the infant health lighting control system based on dynamic adjustment of color temperature parameters include: infant sleeping scenarios.

[0133] Specifically, before an infant falls asleep at night, parents activate a healthy infant lighting control system based on dynamic color temperature parameters. The system first uses an ambient light sensor to detect indoor lighting conditions and determine whether it is daytime or nighttime. If dim light is detected, the system inputs the current lighting conditions and the infant's age into a color temperature adjustment model. Using a pre-trained deep neural network model, the color temperature adjustment model calculates an appropriate color temperature. Based on this calculation, the system automatically adjusts the color temperature of the bedroom light source to a warmer hue, helping the infant relax and fall asleep. The system also sets an appropriate light intensity based on the infant's age and sleeping habits. A camera then captures the infant's facial image in real time and feeds it into the intelligent analysis subsystem. The intelligent analysis subsystem uses a pre-trained classification model to determine the infant's adaptation to the current lighting conditions. If the infant's expression is deemed comfortable, the system maintains the current lighting setting. If the infant's expression is deemed uncomfortable, the lighting adjustment subsystem adjusts the projected brightness and color temperature of the light source based on the intelligent analysis subsystem's results until the infant's expression returns to a comfortable state. When the intelligent analysis subsystem determines that the infant has fallen asleep, the lighting adjustment subsystem gradually reduces the light brightness and turns off the light when the infant is completely asleep. During the sleep process, parents can view the infant's facial expressions and lighting conditions in real time through the mobile app and manually adjust the lighting parameters as needed to ensure the infant falls asleep in the most comfortable environment.

[0134] This application example demonstrates a healthy infant lighting control system based on dynamic color temperature parameter adjustment, creating a comfortable and appropriate sleeping environment for infants at night, helping them achieve good sleep quality. Parents can also ensure their infants fall asleep under optimal lighting conditions through real-time monitoring and adjustments.

[0135] Example 4

[0136] Application scenarios of the infant health lighting control system based on dynamic adjustment of color temperature parameters include: infant crying scenes.

[0137] Specifically, a healthy infant lighting control system based on dynamic color temperature parameter adjustment is installed in the infant's room. The system includes an ambient light sensor, a camera, an intelligent analysis subsystem, and a light source adjustment subsystem. Parents use a mobile app to set information such as the infant's age and nighttime crying patterns. When the infant starts crying at night, the parent activates the healthy infant lighting control system based on dynamic color temperature parameter adjustment. The system first uses the ambient light sensor to detect the room's lighting conditions, obtaining parameters such as light intensity and light direction. The current lighting conditions and the infant's age are input into a color temperature adjustment model, which calculates the appropriate color temperature based on a pre-trained deep neural network model. Based on the calculated results, the system automatically adjusts the color temperature and intensity of the room's light source to create a soft and comfortable lighting environment. At this time, the camera captures an image of the infant's face under these lighting conditions. The image is fed into the intelligent analysis subsystem to obtain the infant's facial response. The intelligent analysis subsystem uses a pre-trained deep learning classification model to determine the infant's adaptation to the current lighting conditions. The facial response is then fed into the light adjustment subsystem, which adjusts the projected brightness of the light source in real time. The lighting control subsystem uses an intelligent controller and an algorithm for adjusting light intensity and projection angle to adjust the lighting based on the infant's facial reactions. If the infant's expression indicates discomfort, the system automatically reduces the light intensity or changes the projection angle. Conversely, if the infant's expression indicates comfort, the system maintains the current lighting settings. The system continuously monitors the infant's facial reactions until the crying subsides and the infant appears comfortable. At this point, parents can choose to turn off the healthy lighting system to allow their infant to sleep peacefully.

[0138] Example 5

[0139] The infant health lighting control system based on dynamic adjustment of color temperature parameters also includes: a sound sensor.

[0140] Specifically, based on the infant health lighting control system based on dynamic adjustment of color temperature parameters provided in Example 3, the system further includes a sound sensor for detecting the indoor environmental noise level. When the indoor noise level exceeds a preset threshold, the system adjusts the color or brightness of the light source to remind parents or caregivers to reduce noise in order to maintain the infant's sleeping environment. At the same time, the intelligent analysis subsystem can also identify the crying of infants to determine whether further adjustment of lighting conditions is needed. When the crying of an infant is recognized, the lighting adjustment subsystem will automatically adjust the lighting parameters such as the projection brightness, projection direction, color saturation, color fidelity and color temperature of the light source in an attempt to improve the comfort of the infant. In addition, the infant health lighting system can also be linked with other smart home devices, for example, by adjusting the air conditioning temperature or humidity to improve the comfort of the indoor environment.

[0141] In summary, the embodiments of the present invention provide a method and system for controlling healthy lighting for infants and young children based on dynamic adjustment of color temperature parameters.

[0142] It should be understood that the present invention is not limited to the specific configurations and processes described above and illustrated in the figures. For the sake of brevity, a detailed description of known methods is omitted. In the above embodiments, several specific steps are described and illustrated as examples. However, the method of the present invention is not limited to the specific steps described and illustrated. Those skilled in the art may make various changes, modifications, and additions, or change the order of the steps after understanding the spirit of the present invention.

[0143] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in unit, a function card or the like. When implemented in software, the elements of the present invention are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROMs, flash memories, erasable ROMs (EROMs), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0144] It should also be noted that the exemplary embodiments described herein describe methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the steps described above. In other words, the steps may be performed in the order described in the embodiments, or in a different order, or several steps may be performed simultaneously.

[0145] The above description is only a specific embodiment of the present invention. Those skilled in the art will clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present invention is not limited to this. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention.

Claims

1. A method for controlling healthy lighting for infants and young children based on dynamic adjustment of color temperature parameters, characterized in that: The method comprises: Acquiring real-time ambient lighting parameters in an infant care scenario, preset infant ages, and data to be processed under multiple target lighting conditions related to infant care, wherein the data to be processed includes: sample ambient lighting parameters under each of the target lighting conditions and multiple sample color temperature parameters matching each of the target lighting conditions; Preprocessing the data to be processed, classifying the data to be processed into training set data and test set data after standardization; Inputting the training set data into a recurrent neural network for deep learning and training to obtain an initial color temperature regulation model; Evaluating the initial color temperature adjustment model using the test set data, and adjusting the initial model based on the evaluation result to obtain a color temperature adjustment model; Inputting the ambient light parameters and the age of the infant into the color temperature adjustment model, adjusting the color temperature in the ambient light parameters to obtain first light parameters with a color temperature suitable for the current environment; Performing a secondary adjustment on the first illumination parameter to obtain a second illumination parameter suitable for the current physiological state of the infant as a target illumination parameter; According to the target lighting parameters, the lighting equipment is controlled to perform lighting to complete healthy lighting in the current infant care scene.

2. The infant health lighting control method based on dynamic adjustment of color temperature parameters according to claim 1, characterized in that: The second adjustment of the first illumination parameter to obtain a second illumination parameter suitable for the current physiological state of the infant as the target illumination parameter includes: Acquire real-time facial images of infants and young children in infant care scenarios; Inputting the real-time facial image of the infant into a preset facial analysis model to obtain the real-time physiological state of the infant under the lighting conditions of the ambient lighting parameters; According to the real-time physiological state of the infant, the first lighting parameter is adjusted for the second time to obtain a second lighting parameter suitable for the current physiological state of the infant as the target lighting parameter.

3. The infant health lighting control method based on dynamic adjustment of color temperature parameters according to claim 1, characterized in that: Inputting the ambient light parameters and the age of the infant into the color temperature adjustment model, adjusting the color temperature in the ambient light parameters, and obtaining the first light parameters with a color temperature suitable for the current environment includes: Inputting the real-time ambient light parameters into the color temperature adjustment model, and matching the sample color temperature parameters to obtain preliminary color temperature parameters that meet the real-time ambient light conditions; Acquire a plurality of preset infant age intervals, and derive a target age interval corresponding to the infant age in each of the age intervals; The preliminary color temperature parameter is corrected twice according to the target age range to obtain the first lighting parameter.

4. The infant health lighting control method based on dynamic adjustment of color temperature parameters according to claim 2, characterized in that: The step of obtaining a real-time facial image of an infant in an infant care scenario includes: Acquire a real-time video stream in the infant care scene, and decompose the real-time video stream into multiple frames of images; The multiple frames of images are input into a preset target detection model, and the images with marked infant faces in each frame are extracted and recorded as real-time images of infant faces, wherein the target detection model is a deep learning model based on the yolov6s structure.

5. The infant health lighting control method based on dynamic adjustment of color temperature parameters according to claim 2, characterized in that: In inputting the real-time image of the infant's face into a preset face analysis model, before obtaining the real-time physiological state of the infant under the lighting conditions of the ambient lighting parameters, the method includes: Acquire multiple frames of infant and child face images under various lighting conditions as training images; Inputting each of the training images into a preset infant face classification model to obtain expression information corresponding to each training image; According to each of the expression information, assigning each of the training images a label corresponding to the expression information; Each of the training images with the label is input into a classification network based on the Mobilenet structure for training to obtain the facial analysis model.

6. The infant health lighting control method based on dynamic adjustment of color temperature parameters according to claim 2, characterized in that: Inputting the real-time facial image of the infant into a preset facial analysis model to obtain the real-time physiological state of the infant under the lighting conditions of the ambient lighting parameters includes: Inputting the real-time image of the infant's face into the face analysis model, and matching the real-time image of the infant's face with each frame of sample image; When the real-time image of the infant's face matches a target image in each of the sample images, assigning the target label on the target image to the real-time image; The real-time physiological state of the infant is obtained based on the target tag.

7. The infant health lighting control method based on dynamic adjustment of color temperature parameters according to claim 2, characterized in that: The second adjustment of the first lighting parameter based on the real-time physiological state of the infant to obtain a second lighting parameter suitable for the current physiological state of the infant as the target lighting parameter includes: Adjusting one or more parameters of light intensity, light projection direction, brightness, color saturation, and color fidelity based on the real-time physiological state; When the real-time physiological state of the infant is adjusted to be comfortable, the second lighting parameter at this time is used as the target lighting parameter.

8. The infant health lighting control method based on dynamic adjustment of color temperature parameters according to claim 1, characterized in that: The lighting parameters include: color temperature, light intensity, light projection direction, brightness, color saturation and color fidelity.

9. A healthy lighting control system for infants and young children based on dynamic adjustment of color temperature parameters, characterized in that: For implementing the method according to any one of claims 1 to 7, the system comprises: An ambient light sensor is used to detect ambient light conditions and input the real-time ambient light parameters and infant age information into a preset color temperature adjustment model; A camera, configured to capture infant facial images in real time and input the infant facial images into a facial analysis model; An intelligent analysis subsystem, which uses a trained classification model to determine how infants and young children adapt to lighting conditions; The lighting adjustment subsystem is used to adjust the projection brightness of the light source according to the results of the intelligent analysis module.

10. The infant health lighting control system based on dynamic adjustment of color temperature parameters according to claim 9, characterized in that: The application scenarios of the system include at least one of the following scenarios: infants sleeping, crying, and playing.

Images