An AI-based ambient lighting control data analysis system and method

Abstract

The present invention discloses an AI-based environmental lighting control data analysis system and method, which belongs to the field of lighting control technology. The present invention comprises the following steps: extracting real-time environmental data records of a lighting control area, and calculating real-time environmental characteristics of the lighting control area; judging the lighting scene of the lighting control area; when the lighting scene is a first scene, generating a lighting control scheme for the first scene; when the lighting scene is a second scene, generating a lighting control scheme for the second scene; when the lighting scene is a third scene, generating a lighting control scheme for the third scene; when the lighting scene is a fourth scene, generating a lighting control scheme for the fourth scene; and controlling lighting equipment according to the lighting control scheme. The present invention not only ensures the suitability of light in the lighting scene, improves the comfort and lighting effect of personnel, but also can effectively improve the lighting quality and avoid the visual experience of personnel being affected by uneven light or shadows.

Description

Technical Field

[0001] The present invention belongs to the field of lighting control technology, and specifically relates to an AI-based environmental lighting control data analysis system and method. Background Art

[0002] With the development of smart buildings and smart cities, ambient lighting control is gradually moving from traditional manual adjustment to automation and intelligence. In public areas such as conference rooms, parking lots, office buildings, factories, public areas, and warehouses, properly adjusting lighting intensity and distribution can not only improve user comfort but also significantly reduce energy consumption.

[0003] Currently, traditional conference room lighting control still relies on manual control or fixed preset modes, which makes it difficult to adapt to the diverse needs of meeting scenarios, such as presentations, video conferencing, and discussions. Because it ignores the perception of real-time environmental parameters and the needs of different meeting scenarios, it leads to inappropriate light intensity, affecting the meeting effect and the meeting experience of participants.

[0004] Therefore, people urgently need an AI-based ambient lighting control data analysis system to solve the above problems. Summary of the Invention

[0005] The purpose of the present invention is to provide an AI-based ambient lighting control data analysis system to solve the problems raised in the above background technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] An AI-based ambient lighting control data analysis method, the method comprising the following steps:

[0008] S1. Set up sensors in the conference room to collect and store environmental data of the conference room through the sensors; extract the real-time environmental data records of the conference room and calculate the real-time environmental characteristics of the conference room;

[0009] S2. Determine the conference scene of the conference room based on the real-time environmental characteristics of the conference room, where the conference scene includes a non-meeting scene, a discussion scene, a demonstration scene, and a video conference scene;

[0010] S3. When the meeting scene is a non-meeting scene, obtain the real-time on / off status of the lighting equipment and generate a lighting control plan for the non-meeting scene; when the meeting scene is a discussion scene, calculate the discussion lighting value of the conference room based on the real-time environmental data records of the conference room, and generate a lighting control plan for the discussion scene; when the meeting scene is a demonstration scene, calculate the demonstration lighting value of the conference room based on the real-time environmental data records of the conference room, and generate a lighting control plan for the demonstration scene; when the meeting scene is a video conference scene, use the image sensor of the conference room to obtain facial images of people indoors, calculate the average facial light intensity of people indoors, and calculate the video conference lighting value of the conference room in combination with the minimum lighting value of the lighting equipment, and generate a lighting control plan for the video conference scene; control the lighting equipment according to the lighting control plan.

[0011] According to the above technical solution, step S1 includes the following:

[0012] S1-1. Each time the sensors installed in the conference room collect data, a record of the conference room environment data is generated and stored in the database. The environmental data record includes the indoor light intensity value, the outdoor light intensity value, the number of people in the room, the noise intensity, and the screen light intensity value;

[0013] The indoor light intensity value indicates the current ambient light intensity in the conference room, while the outdoor light intensity value refers to the light intensity outside the conference room. This value is obtained using a light intensity sensor, such as an illuminance sensor or a photoelectric sensor. These sensors, typically based on the photoelectric effect, can sense ambient light and output a corresponding electrical signal proportional to the light intensity. Installed near the walls, ceiling, or windows of the conference room, the sensors can sense light changes in real time.

[0014] The screen light intensity value refers to the brightness intensity of the screens of electronic devices in the conference room, such as monitors, projectors, and TVs. The screen light intensity value is obtained by using an image sensor to capture the screen image and analyze the image brightness data.

[0015] S1-2, the environmental characteristics include the difference between the inside and outside, the screen impact value and the meeting activity value; extract the real-time environmental data records of the conference room from the database, and use the formula: A1=|A e -A o |, calculate the real-time difference between the inside and outside of the conference room, where A1 represents the real-time difference between the inside and outside of the conference room, and A e Indicates the real-time indoor light intensity value of the conference room, A o Indicates the real-time outdoor light intensity value of the conference room;

[0016] The inside-outside difference value is used to measure the difference between the indoor light intensity value and the outdoor light intensity value. By calculating the inside-outside difference value, the system can determine whether the current indoor light is sufficient and further determine whether the lighting equipment needs to be controlled;

[0017] According to the real-time indoor light intensity value and screen light intensity value of the conference room, use the formula: A2=A s / A e , calculate the real-time screen impact value of the conference room, where A2 represents the real-time screen impact value of the conference room, A s Indicates the real-time screen light intensity value of the conference room;

[0018] When the indoor light intensity is too strong, it causes screen reflection or reduced screen visibility, affecting the viewing experience of participants. By calculating the screen light intensity value in real time, it can be determined whether the current light intensity distribution has a negative impact on the screen, and the lighting conditions can be dynamically adjusted to ensure that the content displayed in the conference room is clearly visible, especially during presentations or video conferences.

[0019] According to the real-time number of people in the conference room and the noise intensity, the formula is: B=α×N 2 +β×ln(C) to calculate the real-time meeting activity value of the conference room, where B represents the real-time meeting activity value of the conference room, α represents the number of people weight, N represents the real-time number of people in the conference room, β represents the noise weight, and C represents the real-time noise intensity of the conference room;

[0020] According to the dynamic changes in noise intensity and the number of people indoors, the real-time meeting activity value of the conference room is obtained to provide data support for judging the meeting scene, thereby optimizing the lighting environment.

[0021] According to the above technical solution, step S2 includes the following:

[0022] S2-1. If the real-time number of people in the conference room is zero, the conference scene of the conference room is no meeting scene;

[0023] S2-2. If the real-time number of people in the conference room is not zero and the real-time conference activity value of the conference room is greater than or equal to the first threshold, the conference scene of the conference room is a discussion scene;

[0024] S2-3. If the real-time number of people in the conference room is not zero, the real-time conference activity value of the conference room is less than the first threshold, and the real-time screen impact value of the conference room is greater than or equal to the second threshold;

[0025] Use the image sensor in the conference room to obtain real-time screen images, and use the face detection algorithm to analyze whether a face is detected in the real-time screen image;

[0026] When no face is detected in the real-time screen image, the meeting scene in the conference room is a demonstration scene;

[0027] When a face is detected in the real-time screen image, the conference scene in the conference room is a video conference scene.

[0028] According to the above technical solution, step S3 includes the following:

[0029] S3-1. When the conference scene is a non-conference scene, extract the real-time switch status of the lighting equipment and the real-time environmental data record of the conference room from the database, where the real-time switch status includes on and off;

[0030] The lighting control solution for non-meeting scenes is as follows:

[0031] If the real-time on / off state of the lighting device is on, the lighting device is controlled to set the real-time on / off state of the lighting device to off;

[0032] If the real-time on / off state of the lighting device is off, the real-time number of people in the conference room is obtained by using the sensor of the conference room. When the real-time number of people in the conference room obtained by the sensor is not zero, and the real-time difference between the inside and outside of the conference room is greater than or equal to the third threshold, the lighting device is controlled to set the real-time on / off state of the lighting device to on, and the lighting value of the lighting device is set to D min Among them, D min Indicates the minimum lighting value of the lighting device; when the real-time number of people in the conference room obtained by the sensor is not zero, and the real-time difference between the inside and outside of the conference room is less than the third threshold, the lighting device is not controlled;

[0033] Ensure that the lighting status can be controlled according to actual needs in non-meeting scenarios to avoid wasting energy. At the same time, by judging the difference in light, ensure that even when there is no meeting activity, the lighting equipment can be automatically turned on when someone enters the meeting room and maintain basic lighting when light is insufficient;

[0034] S3-2, when the conference scene is a discussion scene, the real-time on / off state of the lighting equipment is off, and the real-time inside / outside difference value of the conference room is greater than or equal to the third threshold, according to the real-time indoor light intensity value A of the conference room e And the real-time outdoor light intensity value A of the conference room o , using the formula: D1=(A e +A o ) / 2+ΔA, calculate the discussion lighting value of the conference room, where D1 represents the discussion lighting value of the conference room and ΔA represents the lighting compensation value;

[0035] The lighting compensation value ΔA is used to adjust for insufficient or excessive lighting conditions to ensure a comfortable lighting environment. Through intelligent compensation and dynamic calculation, the system can adapt to changes in indoor and outdoor lighting to ensure lighting stability in the meeting environment.

[0036] Extract the discussion lighting values ​​of all conference rooms from the database, and calculate the average value of the discussion lighting values ​​of all conference rooms, which is recorded as D1';

[0037] The lighting control scheme for the discussion scenario is as follows:

[0038] If the real-time on / off state of the lighting device is off, the lighting device is controlled to set the real-time on / off state of the lighting device to on, and the lighting value of the lighting device is set to D1;

[0039] If the real-time on / off state of the lighting device is on, the lighting device is controlled to adjust the lighting value of the lighting device to D1'.

[0040] According to the above technical solution, step S3 includes the following:

[0041] S3-3, when the conference scene is a demonstration scene, the real-time on / off state of the lighting equipment is off, and the real-time inside / outside difference value of the conference room is greater than or equal to the third threshold, according to the real-time indoor light intensity value A of the conference room e And the real-time screen light intensity value A of the conference room s , using the formula: D2=max{0,A e -A s / 2}, calculate the demonstration lighting value of the conference room, where D2 represents the demonstration lighting value of the conference room, max{0, A e -A s / 2} means between 0 and A e -A s / 2 select the maximum value;

[0042] If A e -A s If / 2 is a negative value, select 0, which means that the screen lighting is already bright enough and no additional lighting is required. Excessive lighting will cause screen reflections, affecting the display effect of the projected or displayed content, thus affecting the viewing experience.

[0043] S3-3-1. Extract the demonstration lighting values ​​of all conference rooms from the database, and calculate the average value of the demonstration lighting values ​​of all conference rooms, which is recorded as D2';

[0044] S3-3-2. The lighting control scheme for the demonstration scene is as follows:

[0045] If the real-time on / off state of the lighting device is off, the lighting device is controlled to set the real-time on / off state of the lighting device to on, and the lighting value of the lighting device is set to D2;

[0046] If the real-time on / off state of the lighting device is on, the lighting device is controlled to adjust the lighting value of the lighting device to D2'.

[0047] According to the above technical solution, step S3 includes the following:

[0048] S3-4. When the conference scene is a video conference scene, the real-time on / off state of the lighting device is off, and the real-time difference between the inside and outside of the conference room is greater than or equal to a third threshold, use the image sensor of the conference room to obtain a facial image of the person indoors, and use a face detection algorithm to extract the facial contour in the facial image, convert the facial image into a grayscale image, and calculate the average grayscale value of all pixels in the area enclosed by the facial contour in the facial image as the average facial light intensity of the corresponding person indoors;

[0049] Currently, face detection algorithms such as those based on OpenCV, Haar cascade classifiers, MTCNN, or deep learning are already very mature. Existing technologies can extract facial contours from facial images.

[0050] S3-4-1. Calculate the average of the facial light intensities of all people in the room, denoted as E; set a fourth threshold, denoted as F;

[0051] If E<F, then use the formula: D3=D min +δ×(FE), calculate the video conferencing lighting value of the conference room, where D3 represents the video conferencing lighting value of the conference room and δ represents the adjustment coefficient;

[0052] If E≥F, then use the formula: D3=D min +δ×(EF), calculate the video conferencing lighting value of the conference room;

[0053] Dynamically adjust the lighting value of the video conferencing scene based on the difference between the real-time average facial light intensity and the set threshold to ensure uniform lighting, avoid uncomfortable light intensity or shadows, and improve video conferencing quality;

[0054] S3-4-2. Extract the video conferencing lighting values ​​of all conference rooms from the database, and calculate the average value of the video conferencing lighting values ​​of all conference rooms, which is recorded as D3';

[0055] S3-4-3. The lighting control scheme for video conferencing lighting values ​​is as follows:

[0056] If the real-time on / off state of the lighting device is off, the lighting device is controlled to set the real-time on / off state of the lighting device to on, and the lighting value of the lighting device is set to D3;

[0057] If the real-time on / off state of the lighting device is on, the lighting device is controlled to adjust the lighting value of the lighting device to D3'.

[0058] An AI-based environmental lighting control data analysis system, which includes an information acquisition module, an environmental feature judgment module, and a lighting control module;

[0059] The information acquisition module is used to collect and store the environmental data of the conference room; the environmental feature judgment module is used to judge the current conference scene based on real-time environmental data; and the lighting control module is used to adjust the switch status and lighting value of the lighting equipment according to the conference scene.

[0060] According to the above technical solution, the information collection module includes a conference room information unit and a lighting equipment information unit;

[0061] The conference room information unit is used to collect the indoor light intensity value, outdoor light intensity value, noise intensity, number of people indoors and screen light intensity value of the conference room in real time through sensors, and store the environmental data in the database to ensure that the system can continuously update the environmental status; the lighting equipment information unit is used to monitor and record the switch status and lighting value of the lighting equipment in real time to ensure that the system can dynamically adjust according to real-time data.

[0062] According to the above technical solution, the environmental feature judgment module includes an environmental feature calculation unit and a meeting scene judgment unit;

[0063] The environmental feature calculation unit is used to calculate the internal and external difference value, screen impact value and meeting activity value as environmental features based on the real-time environmental data of the conference room; the meeting scene judgment unit is used to judge the current meeting scene based on the environmental features.

[0064] According to the above technical solution, the lighting control module includes a solution generation unit and a dynamic control unit;

[0065] The solution generation unit is used to generate corresponding lighting control solutions for different conference scenes; the dynamic control unit is used to dynamically control the lighting equipment.

[0066] Compared with the prior art, the present invention has the following beneficial effects:

[0067] The present invention collects and analyzes the environmental data records of the conference room in real time, dynamically adjusts the ambient lighting based on AI technology, and can intelligently optimize lighting control according to different conference scenarios, significantly improving the intelligence level of conference room lighting. Compared with traditional lighting systems that rely on manual control or fixed modes, the present invention can intelligently adjust the switch status and lighting value of lighting equipment according to personnel activities and indoor and outdoor lighting differences, further reducing energy consumption, and can flexibly respond to different conference needs, ensuring the suitability of light in conference scenes, and improving the comfort of participants and conference effects. At the same time, the present invention effectively improves the lighting quality of video conferences through precise facial light intensity mean detection and dynamic adjustment of video conference lighting, avoiding the impact of uneven light or shadows on the visual experience of participants. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0069] Figure 1 1 is a flow chart of an AI-based ambient lighting control data analysis method of the present invention;

[0070] Figure 2 It is a structural schematic diagram of an AI-based ambient lighting control data analysis system of the present invention. DETAILED DESCRIPTION

[0071] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 a person of ordinary skill in the art without making any creative effort shall fall within the scope of protection of the present invention.

[0072] See also Figure 1 , the present invention provides a technical solution:

[0073] An AI-based ambient lighting control data analysis method, the method comprising the following steps:

[0074] S1. Set up sensors in the conference room to collect and store environmental data of the conference room through the sensors; extract the real-time environmental data records of the conference room and calculate the real-time environmental characteristics of the conference room;

[0075] According to the above technical solution, step S1 includes the following:

[0076] S1-1. Each time the sensors installed in the conference room collect data, a record of the conference room environment data is generated and stored in the database. The environmental data record includes the indoor light intensity value, the outdoor light intensity value, the number of people in the room, the noise intensity, and the screen light intensity value;

[0077] The indoor light intensity value indicates the current ambient light intensity in the conference room, while the outdoor light intensity value refers to the light intensity outside the conference room. This value is obtained using a light intensity sensor, such as an illuminance sensor or a photoelectric sensor. These sensors, typically based on the photoelectric effect, can sense ambient light and output a corresponding electrical signal proportional to the light intensity. Installed near the walls, ceiling, or windows of the conference room, the sensors can sense light changes in real time.

[0078] The screen light intensity value refers to the brightness intensity of the screens of electronic devices in the conference room, such as monitors, projectors, and TVs. The screen light intensity value is obtained by using an image sensor to capture the screen image and analyze the image brightness data.

[0079] S1-2, the environmental characteristics include the difference between the inside and outside, the screen impact value and the meeting activity value; extract the real-time environmental data records of the conference room from the database, and use the formula: A1=|A e -A o |, calculate the real-time difference between the inside and outside of the conference room, where A1 represents the real-time difference between the inside and outside of the conference room, and A e Indicates the real-time indoor light intensity value of the conference room, A o Indicates the real-time outdoor light intensity value of the conference room;

[0080] The inside-outside difference value is used to measure the difference between the indoor light intensity value and the outdoor light intensity value. By calculating the inside-outside difference value, the system can determine whether the current indoor light is sufficient and further determine whether the lighting equipment needs to be controlled;

[0081] According to the real-time indoor light intensity value and screen light intensity value of the conference room, use the formula: A2=A s / A e , calculate the real-time screen impact value of the conference room, where A2 represents the real-time screen impact value of the conference room, A s Indicates the real-time screen light intensity value of the conference room;

[0082] When the indoor light intensity is too strong, it causes screen reflection or reduced screen visibility, affecting the viewing experience of participants. By calculating the screen light intensity value in real time, it can be determined whether the current light intensity distribution has a negative impact on the screen, and the lighting conditions can be dynamically adjusted to ensure that the content displayed in the conference room is clearly visible, especially during presentations or video conferences.

[0083] According to the real-time number of people in the conference room and the noise intensity, the formula is: B=α×N 2 +β×ln(C) to calculate the real-time meeting activity value of the conference room, where B represents the real-time meeting activity value of the conference room, α represents the number of people weight, N represents the real-time number of people in the conference room, β represents the noise weight, and C represents the real-time noise intensity of the conference room;

[0084] According to the dynamic changes in noise intensity and the number of people indoors, the real-time meeting activity value of the conference room is obtained to provide data support for judging the meeting scene, thereby optimizing the lighting environment.

[0085] S2. Determine the conference scene of the conference room based on the real-time environmental characteristics of the conference room, where the conference scene includes a non-meeting scene, a discussion scene, a demonstration scene, and a video conference scene;

[0086] According to the above technical solution, step S2 includes the following:

[0087] S2-1. If the real-time number of people in the conference room is zero, the conference scene of the conference room is no meeting scene;

[0088] S2-2. If the real-time number of people in the conference room is not zero and the real-time conference activity value of the conference room is greater than or equal to the first threshold, the conference scene of the conference room is a discussion scene;

[0089] S2-3. If the real-time number of people in the conference room is not zero, the real-time conference activity value of the conference room is less than the first threshold, and the real-time screen impact value of the conference room is greater than or equal to the second threshold;

[0090] Use the image sensor in the conference room to obtain real-time screen images, and use the face detection algorithm to analyze whether a face is detected in the real-time screen image;

[0091] When no face is detected in the real-time screen image, the meeting scene in the conference room is a demonstration scene;

[0092] When a face is detected in the real-time screen image, the conference scene in the conference room is a video conference scene.

[0093] S3. When the meeting scene is a non-meeting scene, obtain the real-time on / off status of the lighting equipment and generate a lighting control plan for the non-meeting scene; when the meeting scene is a discussion scene, calculate the discussion lighting value of the conference room based on the real-time environmental data records of the conference room, and generate a lighting control plan for the discussion scene; when the meeting scene is a demonstration scene, calculate the demonstration lighting value of the conference room based on the real-time environmental data records of the conference room, and generate a lighting control plan for the demonstration scene; when the meeting scene is a video conference scene, use the image sensor of the conference room to obtain facial images of people in the room, calculate the average facial light intensity of people in the room, and calculate the video conference lighting value of the conference room in combination with the minimum lighting value of the lighting equipment, and generate a lighting control plan for the video conference scene; control the lighting equipment according to the lighting control plan;

[0094] According to the above technical solution, step S3 includes the following:

[0095] S3-1. When the conference scene is a non-conference scene, extract the real-time switch status of the lighting equipment and the real-time environmental data record of the conference room from the database, where the real-time switch status includes on and off;

[0096] The lighting control solution for non-meeting scenes is as follows:

[0097] If the real-time on / off state of the lighting device is on, the lighting device is controlled to set the real-time on / off state of the lighting device to off;

[0098] If the real-time on / off state of the lighting device is off, the real-time number of people in the conference room is obtained by using the sensor of the conference room. When the real-time number of people in the conference room obtained by the sensor is not zero, and the real-time difference between the inside and outside of the conference room is greater than or equal to the third threshold, the lighting device is controlled to set the real-time on / off state of the lighting device to on, and the lighting value of the lighting device is set to D min Among them, D min Indicates the minimum lighting value of the lighting device; when the real-time number of people in the conference room obtained by the sensor is not zero, and the real-time difference between the inside and outside of the conference room is less than the third threshold, the lighting device is not controlled;

[0099] For example:

[0100] The system determines that the conference scene of a conference room is no meeting scene. At this time, the real-time on / off status of the lighting equipment in the conference room is off until the system detects that a person enters the conference room. The system calculates that the real-time inside-outside difference value of the conference room when the person enters is greater than or equal to the third threshold, and then controls the lighting equipment to turn on at the minimum lighting value;

[0101] Ensure that the lighting status can be controlled according to actual needs in non-meeting scenarios to avoid wasting energy. At the same time, by judging the difference in light, ensure that even when there is no meeting activity, the lighting equipment can be automatically turned on when someone enters the meeting room and maintain basic lighting when light is insufficient;

[0102] S3-2, when the conference scene is a discussion scene, the real-time on / off state of the lighting equipment is off, and the real-time inside / outside difference value of the conference room is greater than or equal to the third threshold, according to the real-time indoor light intensity value A of the conference room e And the real-time outdoor light intensity value A of the conference room o , using the formula: D1=(A e +A o ) / 2+ΔA, calculate the discussion lighting value of the conference room, where D1 represents the discussion lighting value of the conference room and ΔA represents the lighting compensation value;

[0103] The lighting compensation value ΔA is used to adjust for insufficient or excessive lighting conditions to ensure a comfortable lighting environment. Through intelligent compensation and dynamic calculation, the system can adapt to changes in indoor and outdoor lighting to ensure lighting stability in the meeting environment.

[0104] Extract the discussion lighting values ​​of all conference rooms from the database, and calculate the average value of the discussion lighting values ​​of all conference rooms, which is recorded as D1';

[0105] The lighting control scheme for the discussion scenario is as follows:

[0106] If the real-time on / off state of the lighting device is off, the lighting device is controlled to set the real-time on / off state of the lighting device to on, and the lighting value of the lighting device is set to D1;

[0107] If the real-time on / off state of the lighting device is on, the lighting device is controlled to adjust the lighting value of the lighting device to D1';

[0108] For example:

[0109] The system determines that the meeting scene of a conference room is a discussion scene. At this time, the real-time switch state of the lighting equipment in the conference room is on, and the lighting value of the lighting equipment is D min The system calculates the average value D1' of the discussion lighting value of all conference rooms and controls the lighting value of the lighting equipment. min Adjust to D1'.

[0110] According to the above technical solution, step S3 includes the following:

[0111] S3-3, when the conference scene is a demonstration scene, the real-time on / off state of the lighting equipment is off, and the real-time inside / outside difference value of the conference room is greater than or equal to the third threshold, according to the real-time indoor light intensity value A of the conference room e And the real-time screen light intensity value A of the conference room s , using the formula: D2=max{0,A e -A s / 2}, calculate the demonstration lighting value of the conference room, where D2 represents the demonstration lighting value of the conference room, max{0, A e -A s / 2} means between 0 and A e -A s / 2 select the maximum value;

[0112] If A e -A s If / 2 is a negative value, select 0, which means that the screen lighting is already bright enough and no additional lighting is required. Excessive lighting will cause screen reflections, affecting the display effect of the projected or displayed content, thus affecting the viewing experience.

[0113] S3-3-1. Extract the demonstration lighting values ​​of all conference rooms from the database, and calculate the average value of the demonstration lighting values ​​of all conference rooms, which is recorded as D2';

[0114] S3-3-2. The lighting control scheme for the demonstration scene is as follows:

[0115] If the real-time on / off state of the lighting device is off, the lighting device is controlled to set the real-time on / off state of the lighting device to on, and the lighting value of the lighting device is set to D2;

[0116] If the real-time on / off state of the lighting device is on, the lighting device is controlled to adjust the lighting value of the lighting device to D2';

[0117] For example:

[0118] The system determines that the meeting scene of a conference room is a discussion scene. At this time, the real-time switch status of the lighting equipment in the conference room is off; the system calculates that the real-time difference between the inside and outside of the conference room is greater than or equal to the third threshold, and further calculates the demonstration lighting value D2=A of the conference room. e -A s / 2, controls the lighting device to turn on with the lighting value D2.

[0119] According to the above technical solution, step S3 includes the following:

[0120] S3-4. When the conference scene is a video conference scene, the real-time on / off state of the lighting device is off, and the real-time difference between the inside and outside of the conference room is greater than or equal to a third threshold, use the image sensor of the conference room to obtain a facial image of the person indoors, and use a face detection algorithm to extract the facial contour in the facial image, convert the facial image into a grayscale image, and calculate the average grayscale value of all pixels in the area enclosed by the facial contour in the facial image as the average facial light intensity of the corresponding person indoors;

[0121] Currently, face detection algorithms such as those based on OpenCV, Haar cascade classifiers, MTCNN, or deep learning are already very mature. Existing technologies can extract facial contours from facial images.

[0122] S3-4-1. Calculate the average of the facial light intensities of all people in the room, denoted as E; set a fourth threshold, denoted as F;

[0123] If E<F, then use the formula: D3=D min +δ×(FE), calculate the video conferencing lighting value of the conference room, where D3 represents the video conferencing lighting value of the conference room and δ represents the adjustment coefficient;

[0124] If E≥F, then use the formula: D3=D min +δ×(EF), calculate the video conferencing lighting value of the conference room;

[0125] Dynamically adjust the lighting value of the video conferencing scene based on the difference between the real-time average facial light intensity and the set threshold to ensure uniform lighting, avoid uncomfortable light intensity or shadows, and improve video conferencing quality;

[0126] S3-4-2. Extract the video conferencing lighting values ​​of all conference rooms from the database, and calculate the average value of the video conferencing lighting values ​​of all conference rooms, which is recorded as D3';

[0127] S3-4-3. The lighting control scheme for video conferencing lighting values ​​is as follows:

[0128] If the real-time on / off state of the lighting device is off, the lighting device is controlled to set the real-time on / off state of the lighting device to on, and the lighting value of the lighting device is set to D3;

[0129] If the real-time on / off state of the lighting device is on, the lighting device is controlled to adjust the lighting value of the lighting device to D3'.

[0130] See also Figure 2 , an AI-based environmental lighting control data analysis system, which includes an information acquisition module, an environmental feature judgment module and a lighting control module;

[0131] The information acquisition module is used to collect and store the environmental data of the conference room; the environmental feature judgment module is used to judge the current conference scene based on real-time environmental data; and the lighting control module is used to adjust the switch status and lighting value of the lighting equipment according to the conference scene.

[0132] According to the above technical solution, the information collection module includes a conference room information unit and a lighting equipment information unit;

[0133] The conference room information unit is used to collect the indoor light intensity value, outdoor light intensity value, noise intensity, number of people indoors and screen light intensity value of the conference room in real time through sensors, and store the environmental data in the database to ensure that the system can continuously update the environmental status; the lighting equipment information unit is used to monitor and record the switch status and lighting value of the lighting equipment in real time to ensure that the system can dynamically adjust according to real-time data.

[0134] According to the above technical solution, the environmental feature judgment module includes an environmental feature calculation unit and a meeting scene judgment unit;

[0135] The environmental feature calculation unit is used to calculate the internal and external difference value, screen impact value and meeting activity value as environmental features based on the real-time environmental data of the conference room; the meeting scene judgment unit is used to judge the current meeting scene based on the environmental features.

[0136] According to the above technical solution, the lighting control module includes a solution generation unit and a dynamic control unit;

[0137] The solution generation unit is used to generate corresponding lighting control solutions for different conference scenes; the dynamic control unit is used to dynamically control the lighting equipment.

[0138] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0139] Finally, it should be noted that the above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein with equivalents. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. An AI-based ambient lighting control data analysis method, characterized by: The method comprises the following steps: S1. Set up sensors in the conference room to collect and store environmental data of the conference room through the sensors; extract the real-time environmental data records of the conference room and calculate the real-time environmental characteristics of the conference room; S2. Determine the conference scene of the conference room based on the real-time environmental characteristics of the conference room, where the conference scene includes a non-meeting scene, a discussion scene, a demonstration scene, and a video conference scene; S3. When the meeting scene is a non-meeting scene, obtain the real-time on / off status of the lighting equipment and generate a lighting control plan for the non-meeting scene; when the meeting scene is a discussion scene, calculate the discussion lighting value of the conference room based on the real-time environmental data records of the conference room, and generate a lighting control plan for the discussion scene; when the meeting scene is a demonstration scene, calculate the demonstration lighting value of the conference room based on the real-time environmental data records of the conference room, and generate a lighting control plan for the demonstration scene; when the meeting scene is a video conference scene, use the image sensor of the conference room to obtain facial images of people in the room, calculate the average facial light intensity of people in the room, and calculate the video conference lighting value of the conference room in combination with the minimum lighting value of the lighting equipment, and generate a lighting control plan for the video conference scene; control the lighting equipment according to the lighting control plan; Step S2 includes the following: S2-1. If the real-time number of people in the conference room is zero, the conference scene of the conference room is no meeting scene; S2-2. If the real-time number of people in the conference room is not zero and the real-time conference activity value of the conference room is greater than or equal to the first threshold, the conference scene of the conference room is a discussion scene; S2-3. If the real-time number of people in the conference room is not zero, the real-time conference activity value of the conference room is less than the first threshold, and the real-time screen impact value of the conference room is greater than or equal to the second threshold; Use the image sensor in the conference room to obtain real-time screen images, and use the face detection algorithm to analyze whether a face is detected in the real-time screen image; When no face is detected in the real-time screen image, the meeting scene in the conference room is a demonstration scene; When a face is detected in the real-time screen image, the conference scene in the conference room is a video conference scene.

2. The AI-based ambient lighting control data analysis method according to claim 1, characterized in that: The step S1 includes the following: S1-1. Each time the sensors installed in the conference room collect data, a record of the conference room environment data is generated and stored in the database. The environmental data record includes the indoor light intensity value, the outdoor light intensity value, the number of people in the room, the noise intensity, and the screen light intensity value; S1-2, the environmental characteristics include the difference between the inside and outside, the screen impact value and the meeting activity value; extract the real-time environmental data records of the conference room from the database, and use the formula: A1=|A e -A o |, calculate the real-time difference between the inside and outside of the conference room, where A1 represents the real-time difference between the inside and outside of the conference room, and A e Indicates the real-time indoor light intensity value of the conference room, A o Indicates the real-time outdoor light intensity value of the conference room; According to the real-time indoor light intensity value and screen light intensity value of the conference room, use the formula: A2=A s / A e , calculate the real-time screen impact value of the conference room, where A2 represents the real-time screen impact value of the conference room, A s Indicates the real-time screen light intensity value of the conference room; According to the real-time number of people in the conference room and the noise intensity, the formula is: B=α×N 2 +β×ln(C) to calculate the real-time meeting activity value of the conference room, where B represents the real-time meeting activity value of the conference room, α represents the number of people weight, N represents the real-time number of people in the conference room, β represents the noise weight, and C represents the real-time noise intensity of the conference room.

3. The AI-based ambient lighting control data analysis method according to claim 2, characterized in that: The step S3 includes the following: S3-1. When the conference scene is a non-conference scene, extract the real-time switch status of the lighting equipment and the real-time environmental data record of the conference room from the database, where the real-time switch status includes on and off; The lighting control solution for non-meeting scenes is as follows: If the real-time on / off state of the lighting device is on, the lighting device is controlled to set the real-time on / off state of the lighting device to off; If the real-time on / off state of the lighting device is off, the real-time number of people in the conference room is obtained by using the sensor of the conference room. When the real-time number of people in the conference room obtained by the sensor is not zero, and the real-time difference between the inside and outside of the conference room is greater than or equal to the third threshold, the lighting device is controlled to set the real-time on / off state of the lighting device to on, and the lighting value of the lighting device is set to D min Among them, D min Indicates the minimum lighting value of the lighting device; when the real-time number of people in the conference room obtained by the sensor is not zero, and the real-time difference between the inside and outside of the conference room is less than the third threshold, the lighting device is not controlled; S3-2, when the conference scene is a discussion scene, the real-time on / off state of the lighting equipment is off, and the real-time inside / outside difference value of the conference room is greater than or equal to the third threshold, according to the real-time indoor light intensity value A of the conference room e And the real-time outdoor light intensity value A of the conference room o , using the formula: D1=(A e +A o ) / 2+ΔA, calculate the discussion lighting value of the conference room, where D1 represents the discussion lighting value of the conference room and ΔA represents the lighting compensation value; Extract the discussion lighting values ​​of all conference rooms from the database, and calculate the average value of the discussion lighting values ​​of all conference rooms, which is recorded as D1'; The lighting control scheme for the discussion scenario is as follows: If the real-time on / off state of the lighting device is off, the lighting device is controlled to set the real-time on / off state of the lighting device to on, and the lighting value of the lighting device is set to D1; If the real-time on / off state of the lighting device is on, the lighting device is controlled to adjust the lighting value of the lighting device to D1'.

4. The AI-based ambient lighting control data analysis method according to claim 3, characterized in that: The step S3 includes the following: S3-3, when the conference scene is a demonstration scene, the real-time on / off state of the lighting equipment is off, and the real-time inside / outside difference value of the conference room is greater than or equal to the third threshold, according to the real-time indoor light intensity value A of the conference room e And the real-time screen light intensity value A of the conference room s , using the formula: D2=max{0,A e -A s / 2}, calculate the demonstration lighting value of the conference room, where D2 represents the demonstration lighting value of the conference room, max{0, A e -A s / 2} means between 0 and A e -A s / 2 select the maximum value; S3-3-1. Extract the demonstration lighting values ​​of all conference rooms from the database, and calculate the average value of the demonstration lighting values ​​of all conference rooms, which is recorded as D2'; S3-3-2. The lighting control scheme for the demonstration scene is as follows: If the real-time on / off state of the lighting device is off, the lighting device is controlled to set the real-time on / off state of the lighting device to on, and the lighting value of the lighting device is set to D2; If the real-time on / off state of the lighting device is on, the lighting device is controlled to adjust the lighting value of the lighting device to D2'.

5. The AI-based ambient lighting control data analysis method according to claim 4, characterized in that: The step S3 includes the following: S3-4. When the conference scene is a video conference scene, the real-time on / off state of the lighting device is off, and the real-time difference between the inside and outside of the conference room is greater than or equal to a third threshold, use the image sensor of the conference room to obtain a facial image of the person indoors, and use a face detection algorithm to extract the facial contour in the facial image, convert the facial image into a grayscale image, and calculate the average grayscale value of all pixels in the area enclosed by the facial contour in the facial image as the average facial light intensity of the corresponding person indoors; S3-4-1. Calculate the average of the facial light intensities of all people in the room, denoted as E; set a fourth threshold, denoted as F; If E<F, then use the formula: D3=D min +δ×(FE), calculate the video conferencing lighting value of the conference room, where D3 represents the video conferencing lighting value of the conference room and δ represents the adjustment coefficient; If E≥F, then use the formula: D3=D min +δ×(EF), calculate the video conferencing lighting value of the conference room; S3-4-2. Extract the video conferencing lighting values ​​of all conference rooms from the database, and calculate the average value of the video conferencing lighting values ​​of all conference rooms, which is recorded as D3'; S3-4-3. The lighting control scheme for video conferencing lighting values ​​is as follows: If the real-time on / off state of the lighting device is off, the lighting device is controlled to set the real-time on / off state of the lighting device to on, and the lighting value of the lighting device is set to D3; If the real-time on / off state of the lighting device is on, the lighting device is controlled to adjust the lighting value of the lighting device to D3'.

6. An AI-based ambient lighting control data analysis system, comprising: The system includes an information acquisition module, an environmental feature judgment module and a lighting control module; The information acquisition module is used to collect and store the environmental data of the conference room; the environmental feature judgment module is used to judge the current conference scene based on real-time environmental data; and the lighting control module is used to adjust the switch status and lighting value of the lighting equipment according to the conference scene.

7. The AI-based ambient lighting control data analysis system according to claim 6, characterized in that: The information collection module includes a conference room information unit and a lighting equipment information unit; The conference room information unit is used to collect the indoor light intensity value, outdoor light intensity value, noise intensity, number of people in the room and screen light intensity value of the conference room in real time through sensors, and store the environmental data in the database to ensure that the system can continuously update the environmental status; The lighting equipment information unit is used to monitor and record the switch status and lighting value of the lighting equipment in real time, ensuring that the system can be dynamically adjusted according to real-time data.

8. The AI-based ambient lighting control data analysis system according to claim 6, characterized in that: The environmental feature judgment module includes an environmental feature calculation unit and a meeting scene judgment unit; The environmental feature calculation unit is used to calculate the internal and external difference value, the screen impact value and the meeting activity value as environmental features based on the real-time environmental data of the conference room; The conference scene judgment unit is used to judge the current conference scene according to environmental characteristics.

9. The AI-based ambient lighting control data analysis system according to claim 6, characterized in that: The lighting control module includes a scheme generation unit and a dynamic control unit; The solution generation unit is used to generate corresponding lighting control solutions for different conference scenes; the dynamic control unit is used to dynamically control the lighting equipment.

Images