A method and system for adaptive management of atmosphere lights based on emotion perception

Abstract

The present invention discloses an adaptive management method and system for atmosphere lamps based on emotion perception, and relates to the technical field of light adjustment. The system uses a high-precision camera to monitor employees' facial expressions, postures and movement changes, extracts key features, establishes an emotion data set, and uses a convolutional neural network (CNN) to build an emotion recognition model to generate an emotion index Em. At the same time, the environmental simulation model monitors indoor and outdoor light, obstacle distribution and weather conditions in real time, creates an environmental data set, and simulates the lighting effects under different emotional states to generate a light brightness coefficient Ll. When it is judged that the employee's concentration is unqualified, a corresponding early warning instruction is generated. According to the early warning instruction and the comprehensive emotional lighting adjustment coefficient Cl, corresponding atmosphere lamp adjustment instructions are generated for different office scenes to adjust the light brightness and color temperature to adapt to the current employee's emotional state and work scene requirements.

Description

Technical Field

[0001] The present invention relates to the technical field of lighting regulation, and in particular to an atmosphere lighting adaptive management method and system based on emotion perception. Background Art

[0002] As modern office environments become increasingly complex, lighting design has gradually become an important factor affecting employees' work efficiency and emotional state. Traditional office lighting systems mostly use fixed brightness and timed adjustment, ignoring individual needs and environmental changes, and have the following main disadvantages:

[0003] Traditional lighting systems only adjust according to a preset schedule or light intensity and cannot perceive employees' emotional changes. During long working hours, employees' emotional fluctuations often affect their concentration and work efficiency, but traditional lighting systems cannot adjust adaptively and thus cannot provide a comfortable working environment. Traditional lighting systems usually ignore the use of natural light and the linkage with outdoor weather. When outdoor light intensity or weather conditions change, traditional systems cannot flexibly adjust indoor light intensity, resulting in energy waste or unreasonable lighting. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides an atmosphere light adaptive management method and system based on emotion perception to solve the problems mentioned in the background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: an adaptive management method of atmosphere lights based on emotion perception, comprising the following steps:

[0006] S1. Establish an emotion perception model based on the meeting area, personal office area and rest area in the office, obtain employee emotion data set, and construct the emotion index Em;

[0007] S2. Use light sensors to monitor outdoor and indoor light brightness in real time, use ultrasonic sensors to scan obstacle distribution information in functional areas, and collect outdoor weather conditions in real time to establish an environmental data set; create an environmental simulation model associated with changes in external natural light intensity, combine the emotion perception model with the environmental simulation model, simulate the lighting control effect under different emotional states, and construct the light brightness coefficient Ll based on the environmental data set;

[0008] S3. When the emotion index Em is lower than the emotion threshold E, it indicates that the current employee's emotional state and concentration are not up to standard, and a corresponding warning instruction is generated, and the light brightness coefficient Ll is associated to calculate the comprehensive emotion light adjustment coefficient Cl;

[0009] S4. After receiving the corresponding warning instruction, the comprehensive emotional lighting adjustment coefficient Cl is evaluated, and corresponding atmosphere light adjustment instructions are generated according to different scenes to adapt to the current emotions and scene requirements.

[0010] Preferably, S1 comprises:

[0011] S11. Install high-precision cameras in several monitoring areas of the office to ensure coverage of all employees' work locations. Set the cameras to wide-angle mode to capture employees' facial expressions, postures, and movement changes, and obtain employee video streams;

[0012] S12. Using wavelet denoising technology, decompose the data information in several image frames in the employee video stream through wavelet transform, remove the noise component in the wavelet domain, and extract key feature information in continuous frames through image enhancement technology and image analysis technology. The key feature information includes employee concentration state characteristics and employee fatigue state characteristics;

[0013] The characteristics of employee concentration status include: whether the employee's face is facing the screen or the work object, the number of words discussed, and the characteristics of hand typing and mouse use;

[0014] The characteristics of employee fatigue status include: the number of times employees yawn, the characteristics of movement stagnation time, and the characteristics of related fatigue movement performance;

[0015] S13. Based on the characteristics of employees' concentration and fatigue states, an employee emotion dataset is established, and a convolutional neural network (CNN) is used to build an emotion recognition model. The collected employee emotion dataset is used for model training. The training data is divided into 70% training set and 30% validation set to train and validate the emotion recognition model.

[0016] Preferably, S1 further comprises:

[0017] S14. By extracting the employee's focus status characteristics, the concentration of the i-th employee is calculated using the following formula: :

[0018] ;

[0019] In the formula, It indicates the average number of words discussed by employees per unit time. It indicates the maximum number of words discussed by employees per unit time. It indicates the time that employees stare at the screen per unit time. Indicates the maximum time employees stare at the screen. Indicates the frequency of employee mouse operation and keyboard typing per unit time. Indicates the maximum frequency of mouse operation and keyboard typing of employees per unit time. , and represents the weight coefficient; and , , , .

[0020] Preferably, S1 further comprises:

[0021] S15. Extract the fatigue status characteristics of employees and calculate the fatigue level of the i-th employee using the following formula: :

[0022] ;

[0023] In the formula, Indicates the number of yawns per unit time. Indicates the maximum number of yawns per unit time. Indicates the stagnation time of the action per unit time. Indicates the maximum stagnation time of the action per unit time, which is used as a reference for fatigue assessment and is set to 15 minutes. Indicates the number of times employees stretch per unit time. Indicates the maximum number of times an employee stretches per unit time. Indicates the number of times an employee blinks per unit time. Indicates the maximum number of times an employee blinks per unit time. Indicates the number of times the employee's head droops per unit time. It indicates the maximum number of times the employee's head droops per unit time. , , , and represents the weight coefficient; ;

[0024] S16. Collect the number of people in the area in real time and associate it with the concentration of the i-th employee and fatigue , the emotion index Em is calculated by the following formula:

[0025] ;

[0026] Where N represents the total number of real-time employees in the current office area. represents the concentration of the i-th employee, represents the fatigue level of the i-th employee, The weight coefficient representing the concentration, Indicates the weight coefficient of fatigue.

[0027] Preferably, S2 comprises:

[0028] S21. Use the light sensor to monitor the outdoor and indoor light brightness in real time, use the ultrasonic sensor to scan the obstacle distribution information in the functional area, and collect the outdoor weather conditions in real time to establish an environmental data set;

[0029] S22, cleaning the environmental data set, including removing outliers and filling missing data, and standardizing the cleaned environmental data set based on dimensionless processing technology;

[0030] S23. Use physical simulation software Dialux or Relux to build an environmental simulation model and simulate the propagation and reflection of light; set the geometric layout, material reflectivity and obstacle distribution information in the office to simulate the changes of light under different conditions;

[0031] S24. The light brightness coefficient L1 is calculated by the following formula:

[0032] ;

[0033] ;

[0034] ;

[0035] ;

[0036] In the formula, R represents the comprehensive material reflectivity, represents the surface area of ​​the i-th wall or desktop material, Represents the reflectivity of the corresponding surface of the i-th wall or desktop material, obtained according to the properties of the material; is the total surface area of ​​the room, including the walls and tabletop reflective surfaces; represents the obstacle distribution coefficient, represents the total projected area of ​​obstacles in the room, is the total surface area of ​​the room; represents the illumination uniformity coefficient; m is the number of illumination measurement points, represents the light intensity at the i-th point, Indicates the minimum value of light intensity, indicating that the light at a certain location is the weakest; and represents the weight coefficient;

[0037] in, Indicates the brightness of outdoor natural light. Indicates the brightness of indoor lights. represents the obstacle distribution coefficient, Indicates the outdoor weather coefficient, which is 0 for sunny days, 0.3 for cloudy days, 0.5 for rainy days, and 0.7 for snowy days. The specific value depends on the real-time weather conditions.

[0038] Preferably, S3 includes:

[0039] S31, comparing the emotion index Em with the preset emotion threshold E to obtain a judgment result:

[0040] When the emotion index Em ≥ the emotion threshold E, it means that the current employee's emotional concentration is qualified;

[0041] When the emotional threshold E*80%≤emotional index Em<emotional threshold E, it means that the current employee's emotional concentration is not up to standard, and the first warning instruction is generated, and the current lighting needs to be adjusted;

[0042] When the emotion index Em is less than the emotion threshold E*80%, it means that the current employee's emotional concentration is not up to standard, and a second warning instruction is generated, requiring the current lighting to be adjusted;

[0043] S32, combining the emotion index Em and the light brightness coefficient Ll, after dimensionless processing, the comprehensive emotion light adjustment coefficient Cl is calculated by the following formula:

[0044] ;

[0045] Where E represents the emotion threshold, and Represents the weight coefficient.

[0046] Preferably, after receiving the first warning instruction and the second warning instruction, when it is determined that the area is a meeting area, the comprehensive emotional lighting adjustment coefficient Cl is evaluated to obtain the corresponding atmosphere light adjustment instruction, including:

[0047] When the current scene requirement is a meeting discussion scene, when the first warning instruction is generated and the comprehensive emotional lighting adjustment coefficient Cl ≥ the first meeting brightness threshold Q1, the first atmosphere light adjustment instruction is generated to increase the current area light brightness by 1%-5% lumens and adjust it to a cold light of 4000K;

[0048] If the comprehensive emotional lighting adjustment coefficient Cl is less than the first meeting brightness threshold Q1, a second atmosphere light adjustment instruction is generated to increase the current area light brightness by 1%-5% lumens and adjust it to a cool light of 4500K;

[0049] When the current scene requirement is a meeting discussion scene, when the second warning instruction is generated and the comprehensive emotional lighting adjustment coefficient Cl ≥ the first meeting brightness threshold Q1, the third atmosphere light adjustment instruction is generated to increase the current area light brightness by 3%-8% lumens and adjust it to a cool light of 5000K;

[0050] If the comprehensive emotional lighting adjustment coefficient Cl is less than the first meeting brightness threshold Q1, a fourth atmosphere light adjustment instruction is generated to enhance the current area lighting by 9%-14% lumen brightness and adjust the lighting to a cool light of 5500K.

[0051] Preferably, after receiving the first warning instruction and the second warning instruction, when it is determined that the person is in the personal work area, the comprehensive emotional lighting adjustment coefficient Cl is evaluated to obtain the corresponding atmosphere light adjustment instruction, including:

[0052] When the current scene requirement is a personal work scene, when the first warning instruction is generated and the comprehensive emotional lighting adjustment coefficient Cl ≥ the second brightness threshold Q2, the fifth atmosphere light adjustment instruction is generated to enhance the current area light by 9%-14% lumen brightness and adjust to warm light of 3500K;

[0053] If the comprehensive emotional lighting adjustment coefficient Cl is less than the second brightness threshold Q2, a sixth ambient light adjustment instruction is generated to increase the current area light brightness by 9%-14% lumens and adjust the light to a cool color of 4000K;

[0054] When the current scene requires a personal work scene, when the second warning instruction is generated and the comprehensive emotional lighting adjustment coefficient Cl ≥ the second brightness threshold Q2, the seventh atmosphere light adjustment instruction is generated to increase the current area light brightness by 5%-6% lumens and adjust it to warm light of 3500K;

[0055] If the comprehensive emotional lighting adjustment coefficient Cl is less than the second brightness threshold Q2, the eighth atmosphere light adjustment instruction is generated to enhance the brightness of the light in the current area by 7%-8% lumens and adjust it to a cool light of 4000K.

[0056] Preferably, after receiving the first warning instruction and the second warning instruction, when it is determined that the area is in the rest area, the comprehensive emotional lighting adjustment coefficient Cl is evaluated to obtain the corresponding atmosphere light adjustment instruction, including:

[0057] When the current scene requirement is a leisure lunch break scene, when the first warning instruction is generated and the comprehensive emotional lighting adjustment coefficient Cl ≥ the third brightness threshold Q3, the ninth atmosphere light adjustment instruction is generated to reduce the current area light by 31%-40% lumen brightness and adjust it to warm light of 2700K;

[0058] If the comprehensive emotional lighting adjustment coefficient Cl is less than the third brightness threshold Q3, a tenth ambient light adjustment instruction is generated to reduce the current area light by 21%-30% lumen brightness and adjust it to a warm light of 3000K;

[0059] When the current scene requires a leisure lunch break scene, when the second warning instruction is generated and the comprehensive emotional lighting adjustment coefficient Cl ≥ the third brightness threshold Q3, the eleventh atmosphere light adjustment instruction is generated to reduce the current area light by 16%-20% lumen brightness and adjust it to warm light of 2700K;

[0060] If the comprehensive emotional lighting adjustment coefficient Cl is less than the third brightness threshold Q3, the twelfth ambient light adjustment instruction is generated to reduce the current area light by 10%-15% lumen brightness and adjust it to warm light of 3000K.

[0061] An adaptive management system for ambient lighting based on emotion perception, comprising:

[0062] The office area division module is used to divide the office into meeting area, personal office area and rest area according to its function;

[0063] The emotion perception model building module is used to install high-precision cameras in several monitoring areas of the office to ensure coverage of all employees' work locations. The cameras are set in wide-angle mode to capture employees' facial expressions, postures, and movement changes, and obtain employee video streams; and extract key feature information in employee video streams to establish employee emotion datasets. After using convolutional neural networks (CNN) to build emotion recognition models, the emotion index Em is constructed.

[0064] The environment simulation model building module uses light sensors to monitor the brightness of outdoor and indoor lights in real time, ultrasonic sensors to scan the obstacle distribution information in the functional area, and collects outdoor weather conditions in real time to establish an environment data set; and creates an environment simulation model associated with changes in the intensity of external natural light. The emotion perception model is combined with the environment simulation model to simulate the lighting control effect under different emotional states, and the light brightness coefficient Ll is constructed based on the environment data set;

[0065] The first analysis module, when the emotion index Em is lower than the emotion threshold E, it means that the current employee's emotional state and concentration are not up to standard, generates corresponding warning instructions, and associates the light brightness coefficient Ll to calculate the comprehensive emotion light adjustment coefficient Cl;

[0066] The second control module, upon receiving the corresponding warning instruction, evaluates the comprehensive emotional lighting adjustment coefficient Cl and generates corresponding atmosphere light adjustment instructions according to different scenes to adapt to the current emotions and scene requirements.

[0067] The present invention provides an atmosphere light adaptive management method and system based on emotion perception, which has the following beneficial effects:

[0068] (1) Traditional lighting systems are difficult to meet the personalized needs of different employees. However, the present invention can adjust the brightness of the light in real time according to the emotional state of the employee by combining the emotion perception model and the environmental simulation model. When the system detects that the employee's emotional index Em is lower than the set threshold E, it will automatically generate an early warning instruction and adjust the light accordingly according to the light brightness coefficient Ll. In this way, the light can not only provide a comfortable working environment for employees with low moods, but also help improve the employees' concentration and emotional state through appropriate light adjustment.

[0069] (2) The present invention not only effectively avoids low work efficiency caused by excessive or insufficient light, but also maximizes the use of natural light, reduces energy consumption, and improves environmental protection effects. By combining the real-time emotional state of employees and external environmental conditions, the system can adaptively provide suitable lighting solutions for different areas (such as conference rooms, personal office areas, and rest areas). When it is detected that the employee's emotional index Em is lower than the threshold and his concentration decreases, the system calculates the comprehensive emotional lighting adjustment coefficient Cl to generate an atmosphere light adjustment instruction suitable for the current scene to help employees recover and improve work efficiency. For example, in the meeting area, when the system senses that the participants are emotionally fluctuating or tired, the light will automatically adjust to cool light. Cold light can reduce the impact of emotional fluctuations and help participants concentrate; in the rest area, warm light helps create a relaxing and warm atmosphere to help employees recover their emotions and energy.

[0070] (3) Traditional lighting systems cannot effectively perceive changes in employees' status, while the intelligent early warning mechanism of the present invention can generate early warning instructions and adjust the lighting environment in a timely manner by evaluating the emotional index Em when employees are in low mood or concentration. The system not only creates a comfortable working atmosphere through mood lighting adjustment, but also can evaluate the comprehensive emotional lighting adjustment coefficient Cl in real time to ensure that the lighting adjustment can accurately match the current scene requirements and provide employees with the most suitable lighting environment.

[0071] (4) Depending on the difference between the first warning instruction and the second warning instruction, the adjustment instructions generated by the system are also different. The first warning instruction generally reflects a slight emotional fluctuation, so the lighting adjustment amplitude is smaller; while the second warning instruction is aimed at a more significant drop in emotion, and the lighting adjustment is more active and larger. This hierarchical response mechanism ensures precise intervention in emotional fluctuations, can provide appropriate lighting support to participants in a timely manner, and effectively alleviate fatigue and inattention during meetings. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 A schematic diagram of the steps of an atmosphere light adaptive management method based on emotion perception according to the present invention;

[0073] Figure 2The present invention is a flowchart diagram of an adaptive management system for atmosphere lights based on emotion perception. DETAILED DESCRIPTION

[0074] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0075] Example 1

[0076] See also Figure 1 The present invention provides an adaptive management method for atmosphere lights based on emotion perception, comprising the following steps:

[0077] S1. Establish an emotion perception model based on the meeting area, personal office area and rest area in the office, obtain employee emotion data set, and construct the emotion index Em;

[0078] S2. Use light sensors to monitor outdoor and indoor light brightness in real time, use ultrasonic sensors to scan obstacle distribution information in functional areas, and collect outdoor weather conditions in real time to establish an environmental data set; create an environmental simulation model associated with changes in external natural light intensity, combine the emotion perception model with the environmental simulation model, simulate the lighting control effect under different emotional states, and construct the light brightness coefficient Ll based on the environmental data set;

[0079] S3. When the emotion index Em is lower than the emotion threshold E, it indicates that the current employee's emotional state and concentration are not up to standard, and a corresponding warning instruction is generated, and the light brightness coefficient Ll is associated to calculate the comprehensive emotion light adjustment coefficient Cl;

[0080] S4. After receiving the corresponding warning instruction, the comprehensive emotional lighting adjustment coefficient Cl is evaluated, and corresponding atmosphere light adjustment instructions are generated according to different scenes to adapt to the current emotions and scene requirements.

[0081] In this embodiment, the traditional lighting system is difficult to meet the personalized needs of different employees, but the present invention can adjust the brightness of the light in real time according to the emotional state of the employee through the combination of the emotion perception model and the environmental simulation model. When the system detects that the employee's emotional index Em is lower than the set threshold E, it will automatically generate an early warning instruction and adjust the light accordingly according to the light brightness coefficient Ll. In this way, the light can not only provide a comfortable working environment for employees with low moods, but also help improve the concentration and emotional state of employees through appropriate light adjustment.

[0082] The present invention uses a light sensor to monitor the brightness of outdoor and indoor lights in real time, and uses an ultrasonic sensor to scan the distribution of obstacles in the office area, collect outdoor weather information, and build an environmental data set. When the outdoor light intensity and weather conditions change, the system can adjust the indoor light intensity in time through the environmental simulation model to achieve dynamic linkage with the external environment. Compared with traditional lighting systems, the present invention not only effectively avoids low work efficiency caused by excessive or insufficient light, but also maximizes the use of natural light, reduces energy consumption, and improves environmental protection effects.

[0083] By combining the real-time emotional state of employees and external environmental conditions, the system can adaptively provide appropriate lighting solutions for different areas (such as conference rooms, personal office areas, and rest areas). When it is detected that the employee's emotional index Em is lower than the threshold and the concentration is reduced, the system calculates the comprehensive emotional lighting adjustment coefficient Cl to generate an atmosphere light adjustment instruction suitable for the current scene to help employees recover and improve work efficiency. For example, in the meeting area, when the system senses that the participants are emotionally fluctuating or tired, the light will automatically adjust to cool light, which can reduce the impact of emotional fluctuations and help participants concentrate; in the rest area, warm light helps create a relaxing and warm atmosphere to help employees restore their emotions and energy.

[0084] Traditional lighting systems cannot effectively perceive changes in employees' status, but the intelligent early warning mechanism of the present invention can generate early warning instructions and adjust the lighting environment in a timely manner through the evaluation of the emotional index Em when employees are in low mood or concentration. The system not only creates a comfortable working atmosphere through the adjustment of the mood light, but also can evaluate the comprehensive emotional lighting adjustment coefficient Cl in real time to ensure that the lighting adjustment can accurately match the current scene requirements and provide the most suitable lighting environment for employees.

[0085] Example 2

[0086] This embodiment is an explanation of the embodiment 1. Specifically, S1 includes:

[0087] S11. Install high-precision cameras in several monitoring areas in the office to ensure coverage of all employees' work locations. Set the cameras to wide-angle mode to capture employees' facial expressions, postures, and movement changes, and obtain employee video streams. This multi-angle and high-precision video acquisition method greatly reduces monitoring blind spots and enhances the accuracy of identifying employee emotions and behaviors.

[0088] S12. Using wavelet denoising technology, decompose the data information in several image frames in the employee video stream through wavelet transform, remove the noise component in the wavelet domain, and extract key feature information in continuous frames through image enhancement technology and image analysis technology. The key feature information includes employee concentration state characteristics and employee fatigue state characteristics;

[0089] Employee focus state features include: whether the employee's face is facing the screen or the work object, the number of words discussed, and the typing and mouse motion features of the hands; extracting employee focus state features and quantifying them into specific subordinate parameters, including: the average number of words discussed by employees per unit time , the time employees stare at the screen per unit time and the frequency of mouse operation and keyboard typing of employees per unit time ;

[0090] The characteristics of employee fatigue status include: the number of times employees yawn, the characteristics of motion stagnation time, and the related fatigue action performance characteristics; the characteristics of employee fatigue status are extracted and quantified into specific lower-level parameters, including: the number of yawns per unit time , Action stagnation time per unit time , the number of times employees stretch per unit time , Number of times employees blink per unit time and the number of times employees' heads droop per unit time ;

[0091] S13. Based on the characteristics of employees' concentration and fatigue states, an employee emotion dataset is established, and a convolutional neural network (CNN) is used to build an emotion recognition model. The collected employee emotion dataset is used for model training. The training data is divided into 70% training set and 30% validation set to train and validate the emotion recognition model.

[0092] S14. By extracting the employee's focus status characteristics, the concentration of the i-th employee is calculated using the following formula: :

[0093] ;

[0094] In the formula, It indicates the average number of words discussed by employees per unit time. It indicates the maximum number of words discussed by employees per unit time. It indicates the time that employees stare at the screen per unit time. Indicates the maximum time employees stare at the screen. Indicates the frequency of employee mouse operation and keyboard typing per unit time. Indicates the maximum frequency of mouse operation and keyboard typing of employees per unit time. , and represents the weight coefficient; and , , , . Through the calculation formula, the employee's concentration is quantified based on the average total number of discussion words, eye gaze time, keyboard and mouse operation frequency, etc. This formula takes into account multiple factors and assigns different weight coefficients, making the assessment of concentration more objective and accurate, which helps to monitor the concentration status of employees and make timely adjustments.

[0095] S15. Extract the fatigue status characteristics of employees and calculate the fatigue level of the i-th employee using the following formula: :

[0096] ;

[0097] In the formula, Indicates the number of yawns per unit time. Indicates the maximum number of yawns per unit time. Indicates the stagnation time of the action per unit time. Indicates the maximum stagnation time of the action per unit time, which is used as a reference for fatigue assessment and is set to 15 minutes. Indicates the number of times employees stretch per unit time. Indicates the maximum number of times an employee stretches per unit time. Indicates the number of times an employee blinks per unit time. Indicates the maximum number of times an employee blinks per unit time. Indicates the number of times the employee's head droops per unit time. It indicates the maximum number of times the employee's head droops per unit time. , , , and represents the weight coefficient; , , , , , ; Calculate the employee's fatigue level through features such as the number of yawns, motion stagnation time, and the number of stretches, and perform weighted processing based on the set weight coefficient. This calculation method can effectively identify the fatigue status of employees, provide quantitative data support, and ensure that the system can issue early warnings in time when employees show signs of fatigue, protect employee health, and improve work efficiency.

[0098] S16. Collect the number of people in the area in real time and associate it with the concentration of the i-th employee and fatigue , the emotion index Em is calculated by the following formula:

[0099] ;

[0100] Where N represents the total number of real-time employees in the current office area. represents the concentration of the i-th employee, represents the fatigue level of the i-th employee, The weight coefficient representing the concentration, Indicates the weight coefficient of fatigue.

[0101] In this embodiment, the comprehensive emotion index Em is calculated by combining the real-time number of people, concentration and fatigue in the office area. The emotion index Em can not only reflect the working status of a single employee, but also reflect the working atmosphere and stress level of the entire office environment through the change of the total number of people in the area. This emotion index calculation method provides a basis for office lighting and environmental control, realizes intelligent adaptive adjustment of the environment, and improves office comfort and work efficiency. Through the combination of these steps, the technology can provide office employees with more humane and intelligent work environment control.

[0102] Embodiment 3: This embodiment is an explanation of Embodiment 1. Specifically, S2 includes:

[0103] S21. Use light sensors to monitor outdoor and indoor light brightness in real time, use ultrasonic sensors to scan obstacle distribution information within the functional area, and collect outdoor weather conditions in real time to establish an environmental data set. By collecting outdoor weather conditions, the system can respond intelligently to changes in the environment, ensuring that indoor lighting conditions are adaptively adjusted as external light changes, thereby optimizing energy efficiency and improving employees' visual comfort.

[0104] S22. Clean the environmental data set, including removing outliers and filling missing data, and standardize the cleaned environmental data set based on dimensionless processing technology; dimensionless processing technology unifies the numerical range of different physical quantities, making data analysis more effective and flexible, thereby improving the accuracy of the simulation model. This step effectively reduces the system error caused by data noise or incompleteness, and ensures the scientificity and stability of lighting adjustment.

[0105] The environmental data set includes: comprehensive material reflectance R, surface area A of the wall or desktop material, reflectance r of the corresponding surface of the wall or desktop material, and total surface area of ​​the room. , the total projected area of ​​obstacles in the room , light intensity L, minimum light intensity , Brightness of outdoor natural light , Indoor lighting brightness and outdoor weather factor ;

[0106] S23. Use physical simulation software Dialux or Relux to build an environmental simulation model and simulate the propagation and reflection of light; set the geometric layout, material reflectivity and obstacle distribution information in the office to simulate the changes in light under different conditions; this simulation model can evaluate the lighting effects under different conditions in advance, provide data support to optimize indoor lighting design, and avoid problems such as uneven light caused by layout or obstacles.

[0107] S24. The light brightness coefficient L1 is calculated by the following formula:

[0108] ;

[0109] ;

[0110] ;

[0111] ;

[0112] In the formula, R represents the comprehensive material reflectivity, represents the surface area of ​​the i-th wall or desktop material, Represents the reflectivity of the corresponding surface of the i-th wall or desktop material, obtained according to the properties of the material; is the total surface area of ​​the room, including the walls and tabletop reflective surfaces; represents the obstacle distribution coefficient, represents the total projected area of ​​obstacles in the room, is the total surface area of ​​the room; represents the illumination uniformity coefficient; m is the number of illumination measurement points, represents the light intensity at the i-th point, Indicates the minimum value of light intensity, indicating that the light at a certain location is the weakest; if Close to 1 means that the light distribution is relatively uniform, which means that the light intensity difference in different positions of the room is small. A value close to 0 indicates that the light distribution is uneven, meaning that the light in some areas is significantly weaker than in other areas. and represents the weight coefficient; , , ;

[0113] in, Indicates the brightness of outdoor natural light. Indicates the brightness of indoor lights. represents the obstacle distribution coefficient, Indicates the outdoor weather coefficient, which is 0 for sunny days, 0.3 for cloudy days, 0.5 for rainy days, and 0.7 for snowy days. The specific value depends on the real-time weather conditions. The system can flexibly adjust the indoor lighting brightness according to different weather conditions (such as sunny, cloudy, rainy, snowy, etc.). This lighting control mode linked to weather conditions can maximize the use of natural light, reduce unnecessary artificial lighting energy consumption, reduce electricity costs, and provide indoor lighting effects that are more in line with environmental needs, ensuring that indoor light meets work needs without generating waste.

[0114] In this embodiment, the light illuminance coefficient L1 is calculated by comprehensively calculating multiple factors such as wall reflectivity, surface area, obstacle distribution, and illumination uniformity, so that the illumination effect of the entire space can be scientifically evaluated. The formula takes into account the reflectivity of different materials and the influence of obstacles to ensure that the distribution of light is more uniform, thereby providing a comfortable light environment. In addition, the illumination uniformity coefficient can help identify areas with uneven illumination, and then adjust the lighting plan to achieve a reasonable distribution of light and avoid discomfort caused by excessive or weak local illumination.

[0115] Example 4

[0116] This embodiment is an explanation of the embodiment 1. Specifically, S3 includes:

[0117] S31, comparing the emotion index Em with the preset emotion threshold E to obtain a judgment result:

[0118] When the emotion index Em ≥ the emotion threshold E, it means that the current employee's emotional concentration is qualified;

[0119] When the emotional threshold E*80%≤emotional index Em<emotional threshold E, it means that the current employee's emotional concentration is not up to standard, and the first warning instruction is generated, and the current lighting needs to be adjusted;

[0120] When the emotion index Em is less than the emotion threshold E*80%, it means that the current employee's emotional concentration is not up to standard, and a second warning instruction is generated, requiring the current lighting to be adjusted;

[0121] S32, combining the emotion index Em and the light brightness coefficient Ll, after dimensionless processing, the comprehensive emotion light adjustment coefficient Cl is calculated by the following formula:

[0122] ;

[0123] In the formula, E represents the emotion threshold, and Represents the weight coefficient. , , ;

[0124] In this embodiment, by comparing the employee's emotional index Em with the preset emotional threshold E, it is possible to effectively judge whether the employee's emotional state and concentration meet the standard. This precise judgment mechanism can detect changes in employee emotions in a timely manner, especially when emotional concentration is insufficient, the system will issue different levels of early warning instructions according to different emotional indexes. The first early warning instruction is used to prompt the situation where concentration is slightly unqualified, and the environment can be improved by adjusting the brightness of the light. The second early warning instruction is used for more serious concentration decline, and the system will intervene more strongly to help employees restore their concentration. This multi-level early warning mechanism ensures that the system responds sensitively to employee emotional fluctuations and improves the comfort and efficiency of the working environment. By calculating the comprehensive emotional lighting adjustment coefficient Cl through the formula, it can not only comprehensively consider the employee's emotional state and the current lighting conditions, but also intelligently adjust the lighting intensity in different situations. The introduction of this adjustment coefficient can make lighting control more personalized and precise, thereby optimizing the lighting environment to adapt to the different emotional states of employees.

[0125] Example 5

[0126] This embodiment is an explanation of the embodiment 1. Specifically, after receiving the first warning instruction and the second warning instruction, when it is determined that the area is a meeting area, the comprehensive emotional lighting adjustment coefficient Cl is evaluated to obtain the corresponding atmosphere light adjustment instruction, including:

[0127] When the current scene requirement is a meeting discussion scene, when the first warning instruction is generated and the comprehensive emotional lighting adjustment coefficient Cl ≥ the first meeting brightness threshold Q1, the first atmosphere light adjustment instruction is generated to increase the current area light brightness by 1%-5% lumens and adjust it to a cold light of 4000K;

[0128] If the comprehensive emotional lighting adjustment coefficient Cl is less than the first meeting brightness threshold Q1, a second atmosphere light adjustment instruction is generated to increase the current area light brightness by 1%-5% lumens and adjust it to a cool light of 4500K;

[0129] When the current scene requirement is a meeting discussion scene, when the second warning instruction is generated and the comprehensive emotional lighting adjustment coefficient Cl ≥ the first meeting brightness threshold Q1, the third atmosphere light adjustment instruction is generated to increase the current area light brightness by 3%-8% lumens and adjust it to a cool light of 5000K;

[0130] If the comprehensive emotional lighting adjustment coefficient Cl is less than the first meeting brightness threshold Q1, a fourth atmosphere light adjustment instruction is generated to enhance the current area lighting by 9%-14% lumen brightness and adjust the lighting to a cool light of 5500K.

[0131] In this embodiment, the light brightness and color temperature can be flexibly adjusted according to the current scene requirements (such as meeting discussion scenes). By generating different atmosphere light adjustment instructions, the system can provide accurate light adjustment for different degrees of emotional warning. This scene-based adaptive adjustment makes lighting control more intelligent, which helps to improve employees' concentration and discussion efficiency in meetings, especially adjusting different lighting environments at different stages, which can better support the smooth progress of meetings.

[0132] The light brightness is adjusted in a gradual enhancement mode (such as 1%-5%, 3%-8%, etc.), avoiding discomfort to participants caused by sudden brightness changes. This gradual adjustment can effectively reduce visual fatigue and help employees maintain their attention during long meetings. In addition, combined with the gradual adjustment of cool light, it can provide participants with a clearer and brighter visual environment, which is suitable for meeting discussions that require concentration.

[0133] After receiving the early warning instruction, the system evaluates the comprehensive emotional lighting adjustment coefficient Cl and reasonably generates adjustment instructions of different brightness and color temperature to ensure that the lighting adjustment can better respond to the current emotional state and lighting needs. For example, when Cl is high, the light adjustment range is small to avoid over-stimulation; when Cl is low, the light intensity is increased to activate the attention of employees.

[0134] This intelligent adjustment mechanism ensures that the lighting changes more closely match the actual needs under different emotional states. The system helps employees maintain a higher level of concentration by adjusting the light color temperature to cool light ranges such as 4000K, 4500K, 5000K and 5500K. Cool light usually stimulates brain activity, making employees more awake and focused, and is particularly suitable for occasions that require efficient interaction, such as conference discussions. Through different levels of cool light adjustment, the system can provide the best lighting environment according to the employee's state, helping employees overcome fatigue and improve the productivity of meetings.

[0135] Depending on the difference between the first warning instruction and the second warning instruction, the adjustment instructions generated by the system are also different. The first warning instruction generally reflects a slight mood swing, so the lighting adjustment is smaller; while the second warning instruction is aimed at a more significant mood drop, and the lighting adjustment is more active and larger. This hierarchical response mechanism ensures precise intervention in mood swings, can provide appropriate lighting support to participants in a timely manner, and effectively alleviate fatigue and inattention during meetings.

[0136] Example 6

[0137] This embodiment is an explanation of the embodiment 1. Specifically, after receiving the first warning instruction and the second warning instruction, when it is determined that the person is in the personal work area, the comprehensive emotional lighting adjustment coefficient Cl is evaluated to obtain the corresponding atmosphere light adjustment instruction, including:

[0138] When the current scene requirement is a personal work scene, when the first warning instruction is generated and the comprehensive emotional lighting adjustment coefficient Cl ≥ the second brightness threshold Q2, the fifth atmosphere light adjustment instruction is generated to enhance the current area light by 9%-14% lumen brightness and adjust to warm light of 3500K;

[0139] If the comprehensive emotional lighting adjustment coefficient Cl is less than the second brightness threshold Q2, a sixth ambient light adjustment instruction is generated to increase the current area light brightness by 9%-14% lumens and adjust the light to a cool color of 4000K;

[0140] When the current scene requires a personal work scene, when the second warning instruction is generated and the comprehensive emotional lighting adjustment coefficient Cl ≥ the second brightness threshold Q2, the seventh atmosphere light adjustment instruction is generated to increase the current area light brightness by 5%-6% lumens and adjust it to warm light of 3500K;

[0141] If the comprehensive emotional lighting adjustment coefficient Cl is less than the second brightness threshold Q2, the eighth atmosphere light adjustment instruction is generated to enhance the brightness of the light in the current area by 7%-8% lumens and adjust it to a cool light of 4000K.

[0142] In this embodiment, the system can flexibly adjust the brightness and color temperature of the light according to the needs of individual work scenes. When an early warning instruction is generated, the adjustment of the light is not only based on the emotional index Em, but also combined with the changes in the light adjustment coefficient Cl to accurately match the current work status of the employee. Through different atmosphere light adjustment instructions (such as warm or cold light), the comfort of the personal work area can be enhanced, which helps employees get better lighting support when they are focused on their work. The system has designed different light color temperature adjustment schemes: when Cl is higher than the second brightness threshold Q2, the system tends to use warm light (3500K) to create a comfortable environment and help employees relax; when Cl is lower than Q2, the system automatically switches to cold light (4000K) to stimulate employees' attention and alertness. This reasonable switching between warm and cold colors can effectively adjust the emotional state of employees and help them maintain optimal concentration and emotional balance at work.

[0143] Example 7

[0144] This embodiment is an explanation of the embodiment 1. Specifically, after receiving the first warning instruction and the second warning instruction, when it is determined that the area is in the rest area, the comprehensive emotional lighting adjustment coefficient Cl is evaluated to obtain the corresponding atmosphere light adjustment instruction, including:

[0145] When the current scene requirement is a leisure lunch break scene, when the first warning instruction is generated and the comprehensive emotional lighting adjustment coefficient Cl ≥ the third brightness threshold Q3, the ninth atmosphere light adjustment instruction is generated to reduce the current area light by 31%-40% lumen brightness and adjust it to warm light of 2700K;

[0146] If the comprehensive emotional lighting adjustment coefficient Cl is less than the third brightness threshold Q3, a tenth ambient light adjustment instruction is generated to reduce the current area light by 21%-30% lumen brightness and adjust it to a warm light of 3000K;

[0147] When the current scene requires a leisure lunch break scene, when the second warning instruction is generated and the comprehensive emotional lighting adjustment coefficient Cl ≥ the third brightness threshold Q3, the eleventh atmosphere light adjustment instruction is generated to reduce the current area light by 16%-20% lumen brightness and adjust it to warm light of 2700K;

[0148] If the comprehensive emotional lighting adjustment coefficient Cl is less than the third brightness threshold Q3, the twelfth ambient light adjustment instruction is generated to reduce the current area light by 10%-15% lumen brightness and adjust it to warm light of 3000K.

[0149] In this embodiment, the system can accurately identify the current scene as a leisure lunch break scene and flexibly adjust the light brightness and color temperature. By reducing the light brightness and adjusting it to warm light, a soft and comfortable environment is created, which helps employees relax during breaks and improves the overall balance between work and rest. Warm light adjustment schemes with different brightness are set, such as 2700K and 3000K color temperature selections to simulate the warm effect of natural light. Lower color temperatures help relax the brain, relieve fatigue, and improve the quality of employees' lunch breaks, which is conducive to improving work efficiency after rest. The system is divided into multiple brightness adjustment levels based on the changes in the comprehensive emotional lighting adjustment coefficient Cl. Under the first warning instruction, the light brightness decreases by a large margin (31%-40% or 21%-30%), helping employees quickly enter a relaxed state; while under the second warning instruction, the brightness adjustment range is relatively small (16%-20% or 10%-15%), avoiding excessive dimming while providing a moderate rest environment. This multi-level adjustment ensures that the system can flexibly adjust the light according to emotional state and environmental requirements to adapt to different rest needs. In the rest area, the system automatically generates adjustment instructions by monitoring the emotional state of employees and changes in ambient light in real time, so that the lighting adjustment process does not require manual intervention. This intelligent adjustment method reduces external interference during the rest process and provides a more peaceful and comfortable rest environment.

[0150] Example 8

[0151] See also Figure 2, an adaptive management system for atmosphere lights based on emotion perception, comprising:

[0152] The office area division module is used to divide the office into meeting area, personal office area and rest area according to its function;

[0153] The emotion perception model building module is used to install high-precision cameras in several monitoring areas of the office to ensure coverage of all employees' work locations. The cameras are set in wide-angle mode to capture employees' facial expressions, postures, and movement changes, and obtain employee video streams; and extract key feature information in employee video streams to establish employee emotion datasets. After using convolutional neural networks (CNN) to build emotion recognition models, the emotion index Em is constructed.

[0154] The environment simulation model building module uses light sensors to monitor the brightness of outdoor and indoor lights in real time, ultrasonic sensors to scan the obstacle distribution information in the functional area, and collects outdoor weather conditions in real time to establish an environment data set; and creates an environment simulation model associated with changes in the intensity of external natural light. The emotion perception model is combined with the environment simulation model to simulate the lighting control effect under different emotional states, and the light brightness coefficient Ll is constructed based on the environment data set;

[0155] The first analysis module, when the emotion index Em is lower than the emotion threshold E, it means that the current employee's emotional state and concentration are not up to standard, generates corresponding warning instructions, and associates the light brightness coefficient Ll to calculate the comprehensive emotion light adjustment coefficient Cl;

[0156] The second control module, upon receiving the corresponding warning instruction, evaluates the comprehensive emotional lighting adjustment coefficient Cl and generates corresponding atmosphere light adjustment instructions according to different scenes to adapt to the current emotions and scene requirements.

[0157] The threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technicians in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0158] The above formulas are obtained by collecting a large amount of data for software simulation and selecting a formula that is close to the actual value. The coefficients in the formula are set by technical personnel in this field according to actual conditions. The above is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited to this. Any technical personnel familiar with the technical field within the technical scope disclosed by the present invention, according to the technical solution and the inventive concept of the present invention, make equivalent replacement or change, which should be covered within the protection scope of the present invention.

Claims

1. An adaptive management method for atmosphere lighting based on emotion perception, characterized in that: The following steps are involved: S1. Establish an emotion perception model based on the meeting area, personal office area and rest area in the office, obtain employee emotion data set, and construct the emotion index Em; S1 specifically includes: S11. Install high-precision cameras in several monitoring areas of the office to ensure coverage of all employees' work locations. Set the cameras to wide-angle mode to capture employees' facial expressions, postures, and movement changes, and obtain employee video streams; S12. Using wavelet denoising technology, decompose the data information in several image frames in the employee video stream through wavelet transform, remove the noise component in the wavelet domain, and extract key feature information in continuous frames through image enhancement technology and image analysis technology. The key feature information includes employee concentration state characteristics and employee fatigue state characteristics; The characteristics of employee concentration status include: whether the employee's face is facing the screen or the work object, the number of words discussed, and the characteristics of hand typing and mouse use; The characteristics of employee fatigue status include: the number of times employees yawn, the characteristics of movement stagnation time, and the characteristics of related fatigue movement performance; S13. Based on the characteristics of employee concentration and employee fatigue, establish an employee emotion dataset, use a convolutional neural network (CNN) to build an emotion recognition model, and use the collected employee emotion dataset to train the model; the training data is divided into 70% training set and 30% validation set to train and validate the emotion recognition model; S14, extracting the employee's concentration state characteristics and calculating the employee's concentration degree; S15, extracting the characteristics of the employee's fatigue state and calculating the employee's fatigue degree; S16. Collect the number of people in the area in real time, associate it with the concentration and fatigue of the employees, and calculate the emotion index Em; S2. Use light sensors to monitor outdoor and indoor light brightness in real time, use ultrasonic sensors to scan obstacle distribution information in functional areas, and collect outdoor weather conditions in real time to establish an environmental data set; create an environmental simulation model associated with changes in external natural light intensity, combine the emotion perception model with the environmental simulation model, simulate the lighting control effect under different emotional states, and construct the light brightness coefficient Ll based on the environmental data set; S3. When the emotion index Em is lower than the emotion threshold E, it indicates that the current employee's emotional state and concentration are not up to standard, and a corresponding warning instruction is generated, and the light brightness coefficient Ll is associated to calculate the comprehensive emotion light adjustment coefficient Cl; S4. After receiving the corresponding warning instruction, the comprehensive emotional lighting adjustment coefficient Cl is evaluated, and corresponding atmosphere light adjustment instructions are generated according to different scenes to adapt to the current emotions and scene requirements.

2. The method for adaptive management of atmosphere lighting based on emotion perception according to claim 1, characterized in that: S14 specifically includes: By extracting the employee's focus status characteristics, the concentration of the i-th employee is calculated using the following formula: : ； In the formula, It indicates the average number of words discussed by employees per unit time. It indicates the maximum number of words discussed by employees per unit time. It indicates the time that employees stare at the screen per unit time. Indicates the maximum time employees stare at the screen. Indicates the frequency of employee mouse operation and keyboard typing per unit time. Indicates the maximum frequency of mouse operation and keyboard typing of employees per unit time. , and represents the weight coefficient; and , , , .

3. The method for adaptive management of atmosphere lighting based on emotion perception according to claim 1, characterized in that: S15 specifically includes: Extract the employee fatigue status characteristics and calculate the fatigue level of the i-th employee using the following formula: : ； In the formula, Indicates the number of yawns per unit time. Indicates the maximum number of yawns per unit time. Indicates the stagnation time of the action per unit time. Indicates the maximum stagnation time of the action per unit time, which is used as a reference for fatigue assessment and is set to 15 minutes. Indicates the number of times employees stretch per unit time. Indicates the maximum number of times an employee stretches per unit time. Indicates the number of times an employee blinks per unit time. Indicates the maximum number of times an employee blinks per unit time. Indicates the number of times the employee's head droops per unit time. It indicates the maximum number of times the employee's head droops per unit time. , , , and represents the weight coefficient; ; S16 specifically includes: real-time collection of the number of people in the area and association with the concentration of the i-th employee and fatigue , the emotion index Em is calculated by the following formula: ； Where N represents the total number of real-time employees in the current office area. represents the concentration of the i-th employee, represents the fatigue level of the i-th employee, The weight coefficient representing the concentration, Indicates the weight coefficient of fatigue.

4. The method for adaptive management of atmosphere lighting based on emotion perception according to claim 1, characterized in that S2 include: S21. Use the light sensor to monitor the outdoor and indoor light brightness in real time, use the ultrasonic sensor to scan the obstacle distribution information in the functional area, and collect the outdoor weather conditions in real time to establish an environmental data set; S22, cleaning the environmental data set, including removing outliers and filling missing data, and standardizing the cleaned environmental data set based on dimensionless processing technology; S23. Use physical simulation software Dialux or Relux to build an environmental simulation model and simulate the propagation and reflection of light; set the geometric layout, material reflectivity and obstacle distribution information in the office to simulate the changes of light under different conditions; S24. The light brightness coefficient L1 is calculated by the following formula: ； ； ； ； In the formula, R represents the comprehensive material reflectivity, represents the surface area of ​​the i-th wall or desktop material, Represents the reflectivity of the corresponding surface of the i-th wall or desktop material, obtained according to the properties of the material; is the total surface area of ​​the room, including the walls and tabletop reflective surfaces; represents the obstacle distribution coefficient, represents the total projected area of ​​obstacles in the room, is the total surface area of ​​the room; represents the illumination uniformity coefficient; m is the number of illumination measurement points, represents the light intensity at the i-th point, Indicates the minimum value of light intensity, indicating that the light at a certain location is the weakest; and represents the weight coefficient; in, Indicates the brightness of outdoor natural light. Indicates the brightness of indoor lights. It represents the obstacle distribution coefficient, TQ represents the outdoor weather coefficient, which is 0 for sunny days, 0.3 for cloudy days, 0.5 for rainy days, and 0.7 for snowy days. The specific value depends on the real-time weather conditions.

5. The method for adaptive management of atmosphere lighting based on emotion perception according to claim 1, characterized in that S3 include: S31, comparing the emotion index Em with the preset emotion threshold E to obtain a judgment result: When the emotion index Em ≥ the emotion threshold E, it means that the current employee's emotional concentration is qualified; When the emotional threshold E*80%≤emotional index Em<emotional threshold E, it means that the current employee's emotional concentration is not up to standard, and the first warning instruction is generated, and the current lighting needs to be adjusted; When the emotion index Em is less than the emotion threshold E*80%, it means that the current employee's emotional concentration is not up to standard, and a second warning instruction is generated, requiring the current lighting to be adjusted; S32, combining the emotion index Em and the light brightness coefficient Ll, after dimensionless processing, the comprehensive emotion light adjustment coefficient Cl is calculated by the following formula: ； Where E represents the emotion threshold, and Represents the weight coefficient.

6. The method for adaptive management of atmosphere lighting based on emotion perception according to claim 5, characterized in that: After receiving the first warning instruction and the second warning instruction, when it is determined that the area is in the meeting area, the comprehensive emotional lighting adjustment coefficient Cl is evaluated to obtain the corresponding atmosphere light adjustment instruction, including: When the current scene requirement is a meeting discussion scene, when the first warning instruction is generated and the comprehensive emotional lighting adjustment coefficient Cl ≥ the first meeting brightness threshold Q1, the first atmosphere light adjustment instruction is generated to increase the current area light brightness by 1%-5% lumens and adjust it to a cold light of 4000K; If the comprehensive emotional lighting adjustment coefficient Cl is less than the first meeting brightness threshold Q1, a second atmosphere light adjustment instruction is generated to increase the current area light brightness by 1%-5% lumens and adjust it to a cool light of 4500K; When the current scene requirement is a meeting discussion scene, when the second warning instruction is generated and the comprehensive emotional lighting adjustment coefficient Cl ≥ the first meeting brightness threshold Q1, the third atmosphere light adjustment instruction is generated to increase the current area light brightness by 3%-8% lumens and adjust it to a cool light of 5000K; If the comprehensive emotional lighting adjustment coefficient Cl is less than the first meeting brightness threshold Q1, a fourth atmosphere light adjustment instruction is generated to enhance the current area lighting by 9%-14% lumen brightness and adjust the lighting to a cool light of 5500K.

7. The method for adaptive management of atmosphere lighting based on emotion perception according to claim 6, characterized in that: After receiving the first warning instruction and the second warning instruction, when it is determined that the person is in the personal work area, the comprehensive emotional lighting adjustment coefficient Cl is evaluated to obtain the corresponding atmosphere light adjustment instruction, including: When the current scene requirement is a personal work scene, when the first warning instruction is generated and the comprehensive emotional lighting adjustment coefficient Cl ≥ the second brightness threshold Q2, the fifth atmosphere light adjustment instruction is generated to enhance the current area light by 9%-14% lumen brightness and adjust to warm light of 3500K; If the comprehensive emotional lighting adjustment coefficient Cl is less than the second brightness threshold Q2, a sixth ambient light adjustment instruction is generated to increase the current area light brightness by 9%-14% lumens and adjust the light to a cool color of 4000K; When the current scene requires a personal work scene, when the second warning instruction is generated and the comprehensive emotional lighting adjustment coefficient Cl ≥ the second brightness threshold Q2, the seventh atmosphere light adjustment instruction is generated to increase the current area light brightness by 5%-6% lumens and adjust it to warm light of 3500K; If the comprehensive emotional lighting adjustment coefficient Cl is less than the second brightness threshold Q2, the eighth atmosphere light adjustment instruction is generated to enhance the brightness of the light in the current area by 7%-8% lumens and adjust it to a cool light of 4000K.

8. The method for adaptive management of atmosphere lighting based on emotion perception according to claim 7, characterized in that: After receiving the first warning instruction and the second warning instruction, when it is determined that the area is in the rest area, the comprehensive emotional lighting adjustment coefficient Cl is evaluated to obtain the corresponding atmosphere light adjustment instruction, including: When the current scene requirement is a leisure lunch break scene, when the first warning instruction is generated and the comprehensive emotional lighting adjustment coefficient Cl ≥ the third brightness threshold Q3, the ninth atmosphere light adjustment instruction is generated to reduce the current area light by 31%-40% lumen brightness and adjust it to warm light of 2700K; If the comprehensive emotional lighting adjustment coefficient Cl is less than the third brightness threshold Q3, a tenth ambient light adjustment instruction is generated to reduce the current area light by 21%-30% lumen brightness and adjust it to a warm light of 3000K; When the current scene requires a leisure lunch break scene, when the second warning instruction is generated and the comprehensive emotional lighting adjustment coefficient Cl ≥ the third brightness threshold Q3, the eleventh atmosphere light adjustment instruction is generated to reduce the current area light by 16%-20% lumen brightness and adjust it to warm light of 2700K; If the comprehensive emotional lighting adjustment coefficient Cl is less than the third brightness threshold Q3, the twelfth ambient light adjustment instruction is generated to reduce the current area light by 10%-15% lumen brightness and adjust it to warm light of 3000K.

9. An adaptive management system for atmosphere lights based on emotion perception, applied to the adaptive management method for atmosphere lights based on emotion perception according to any one of claims 1 to 8, characterized in that: include: The office area division module is used to divide the office into meeting area, personal office area and rest area according to its function; The emotion perception model building module is used to install high-precision cameras in several monitoring areas of the office to ensure coverage of all employees' work locations. The cameras are set in wide-angle mode to capture employees' facial expressions, postures, and movement changes, and obtain employee video streams; and extract key feature information in employee video streams to establish employee emotion datasets. After using convolutional neural networks (CNN) to build emotion recognition models, the emotion index Em is constructed. The environment simulation model establishment module is used to monitor the outdoor and indoor light brightness in real time through the light sensor, the ultrasonic sensor scans the obstacle distribution information in the functional area, and collects the outdoor weather conditions in real time to establish the environment data set; and creates an environment simulation model associated with the change of external natural light intensity. The emotion perception model is combined with the environment simulation model to simulate the lighting control effect under different emotional states, and the light brightness coefficient Ll is constructed according to the environment data set; The first analysis module is used to generate corresponding warning instructions when the emotion index Em is lower than the emotion threshold E, indicating that the current employee's emotional state and concentration are unqualified, and associate the light brightness coefficient Ll to calculate the comprehensive emotion light adjustment coefficient Cl; The second control module is used to evaluate the comprehensive emotional lighting adjustment coefficient Cl after receiving the corresponding early warning instruction, and generate corresponding atmosphere light adjustment instructions according to different scenes to adapt to the current emotions and scene requirements.

Images