Adaptive air purification method and system

Abstract

The present invention relates to an adaptive air purification method and system, belonging to the technical field of air purification. The method includes obtaining air quality monitoring data and obtaining an air quality level through the air quality judgment, and obtaining an air purification first control instruction according to the air quality level; obtaining a regional crowd flow recognition model through an improved Yolov8 algorithm according to a preset regional crowd flow video set; obtaining a regional crowd flow video, obtaining a regional crowd flow detection result through the regional crowd flow recognition model according to the regional crowd flow video, and obtaining regional crowd flow through Deepsort tracker statistics; obtaining an air purification second control instruction according to the regional crowd flow through regional crowd flow aggregation judgment; and jointly controlling the operating state of an air purifier according to the first air purification control instruction and the second air purification control instruction, realizing intelligent adjustment of the air purifier, improving purification efficiency, ensuring air quality in the region, reducing energy waste, and achieving energy conservation and emission reduction.

Description

Technical Field

[0001] The present invention belongs to the technical field of air purification, and in particular relates to an adaptive air purification method and system. Background Art

[0002] Existing air purification technologies mainly include filtration, adsorption, ionization, photocatalysis, etc. These technologies can purify indoor air to a certain extent, but they also have the following shortcomings: The disinfection function of traditional air purifiers is often fixed and cannot be adjusted according to actual needs. There is also a lack of an effective user avoidance mechanism, which may cause disinfectants to have adverse effects on human health. Traditional air purifiers usually require users to manually adjust the operating mode and cannot automatically adjust according to changes in indoor air quality. They are not convenient to use, and due to the lack of intelligent adjustment, air purifiers are often in a high-power operating state, resulting in high energy consumption. Existing air purifiers cannot respond in real time to air quality fluctuations caused by changes in pedestrian flow. Many air purifiers lack real-time monitoring and data display functions, and users cannot intuitively understand the indoor air quality status.

[0003] Therefore, there is an urgent need for an adaptive air purification method and system that can realize automatic adjustment of the air purifier through intelligent monitoring and control technology, thereby improving purification efficiency, reducing energy consumption, and providing a more comfortable and healthy indoor environment. Summary of the invention

[0004] In order to solve the above problems existing in the prior art, the present invention proposes an adaptive air purification method and system.

[0005] The purpose of the present invention can be achieved through the following technical solutions: An adaptive air purification method, comprising: Acquire air quality monitoring data, the air quality monitoring data includes PM 2.5 concentration, TVOC concentration, CO2 concentration; Obtain an air quality level through the air quality judgment according to the air quality monitoring data, and obtain a first air purification control instruction according to the air quality level; According to the preset regional crowd flow video set, the regional crowd flow recognition model is obtained by improving the Yolov8 algorithm; Obtain a regional crowd flow video, obtain a regional crowd flow detection result through the regional crowd flow recognition model according to the regional crowd flow video, and obtain the regional crowd flow through the Deepsort tracker according to the regional crowd flow detection result; According to the regional human flow, a second air purification control instruction is obtained by judging the regional human flow aggregation; The operating state of the air purifier is jointly controlled according to the first air purification control instruction and the second air purification control instruction.

[0006] Preferably, the obtaining of air quality monitoring data includes: deploying multiple sensor nodes to synchronously monitor air quality data in different areas, and averaging the air quality data collected by each sensor node to obtain the air quality monitoring data.

[0007] Preferably, obtaining an air quality level through the air quality judgment according to the air quality monitoring data, and obtaining a first air purification control instruction according to the air quality level includes: When PM 2.5 Concentration less than 35 μg / m 3 , TVOC concentration is less than 0.3mg / m 3 , when the CO2 concentration is less than 1000ppm, the air quality level is excellent; When PM 2.5 Concentration greater than 35 μg / m 3 And not more than 75μg / m 3 、TVOC concentration is greater than 0.3mg / m 3 And not more than 0.5mg / m 3 , when the CO2 concentration is less than 1000ppm, the air quality level is good air quality level; When PM 2.5 Concentration greater than 75 μg / m 3 Or TVOC concentration is greater than 0.5 mg / m 3 Or when the CO2 concentration exceeds 1000ppm, the air quality level is the air quality pollution level; When the air quality level is an excellent air quality level, an air purifier shutdown instruction is output; when the air quality level is a good air quality level, an air purifier low-speed operation instruction is output; when the air quality level is an air quality pollution level, an air purifier high-speed operation instruction is output.

[0008] Preferably, obtaining a regional crowd flow recognition model by improving the Yolov8 algorithm according to a preset regional crowd flow video set comprises: According to the preset area crowd flow video set, a preset area crowd flow video standard frame set is obtained by performing video frame quality enhancement processing; According to the preset regional crowd flow video standard frame set, the regional crowd flow recognition model is obtained through the improved Yolov8 algorithm training and testing.

[0009] Preferably, the step of obtaining a standard frame set of people flow videos in a preset area by performing video frame quality enhancement processing according to the people flow videos in the preset area comprises: Extracting a preset area crowd flow video frame set according to the preset area crowd flow video set; For the preset area crowd flow video frame set, each preset area crowd flow video frame image is processed by video frame quality enhancement to obtain the preset area crowd flow video standard frame set, and the video frame quality enhancement processing includes denoising, contrast enhancement, and illumination correction.

[0010] Preferably, the method of obtaining a regional crowd flow recognition model by training and testing the improved Yolov8 algorithm according to the preset regional crowd flow video standard frame set includes: The improved Yolov8 algorithm includes the integration of different pre-trained models, that is, using EfficientNet, ResNet, and MobileNet as basic networks respectively, independently training each Yolov8 model based on different Backbones, and fusing the prediction results through confidence averaging.

[0011] Preferably, the second air purification control instruction is obtained by judging the regional human flow based on the regional human flow aggregation, including: Preset area flow threshold; When the human flow in the area exceeds the preset human flow threshold, an air purifier low-speed operation instruction is output; when the human flow in the area drops below the preset human flow threshold, an air purifier shutdown instruction is output.

[0012] An adaptive air purification system, applying the adaptive air purification method as described above, comprises a data acquisition module, a first control instruction module, a second control instruction module, and a control module; The data acquisition module is used to obtain air quality monitoring data and regional human flow videos; The first control instruction module is used to obtain an air quality level through the air quality judgment according to the air quality monitoring data, and obtain a first air purification control instruction according to the air quality level; The second control instruction module is used to obtain a regional crowd flow detection result through the regional crowd flow recognition model according to the regional crowd flow video, obtain regional crowd flow through Deepsort tracker statistics according to the regional crowd flow detection result, and obtain a second air purification control instruction through regional crowd flow aggregation judgment according to the regional crowd flow; The control module is used to jointly control the operating state of the air purifier according to the first air purification control instruction and the second air purification control instruction.

[0013] An electronic device comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor implements the above-mentioned adaptive air purification method when executing the computer program.

[0014] A storage medium containing computer executable instructions, which are used to perform the above-mentioned adaptive air purification method when executed by a computer processor.

[0015] The beneficial effects of the present invention are: (1) By integrating air quality monitoring and regional human flow analysis, the operating status of the air purifier can be intelligently adjusted to make air purification more in line with actual needs, ensuring that stronger purification capabilities are provided in environments with high pollutant concentrations and large crowds, thereby improving purification efficiency and ensuring air quality in the area; at the same time, the operating power of the air purifier is increased only when necessary, reducing energy waste and achieving energy conservation and emission reduction.

[0016] (2) By setting up a user-friendly interface and remote control function, users can easily manage and monitor the air purifier. By acquiring air quality monitoring data through multiple sensors, the overall air quality of the area can be obtained.

[0017] (3) By detecting the microbial content, when the microbial content exceeds the preset microbial content, a sterilization instruction is sent to the terminal. After receiving the user's sterilization feedback instruction, the sterilization and disinfection operation is performed, which can confirm that the user has left or will not enter the area to be disinfected, thereby avoiding possible impacts on the user's health during the disinfection process, especially when chemical disinfectants are used. In addition, user feedback can also ensure that pets and plants are removed from the area before disinfection to avoid harm to them by disinfectants. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0019] Figure 1 The figure is a schematic flow chart of an adaptive air purification method of the present invention. DETAILED DESCRIPTION

[0020] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0021] See also Figure 1 , an adaptive air purification method, comprising: S1: Acquire air quality monitoring data, the air quality monitoring data includes PM 2.5concentration, TVOC concentration, CO2 concentration; S2: obtaining an air quality level through the air quality judgment according to the air quality monitoring data, and obtaining a first air purification control instruction according to the air quality level; S3: According to the preset regional crowd flow video set, the regional crowd flow recognition model is obtained by improving the Yolov8 algorithm; S4: obtaining a regional crowd flow video, obtaining a regional crowd flow detection result through the regional crowd flow recognition model according to the regional crowd flow video, and obtaining the regional crowd flow through statistics of the Deepsort tracker according to the regional crowd flow detection result; S5: Obtaining a second air purification control instruction according to the regional human flow through regional human flow aggregation judgment; S6: jointly controlling the operating state of the air purifier according to the first air purification control instruction and the second air purification control instruction.

[0022] In this embodiment, the acquisition of air quality monitoring data is specifically implemented by the following steps: By PM 2.5 Sensors to obtain PM 2.5 concentration; Obtain TVOC concentration through TVOC sensor; Get CO2 concentration through CO2 sensor; Specifically, multiple sensor nodes are deployed to synchronously monitor the air quality data of different areas, the air quality data collected by each sensor node is averaged to obtain air quality monitoring data, and the air quality monitoring data is uploaded to the terminal to display the current air quality in real time; at the same time, a microbial detector is added to detect the microbial content, and the microbial content includes bacterial content and virus content. When the microbial content exceeds the preset microbial content, a sterilization instruction is sent to the terminal. After receiving the user's sterilization feedback instruction, the sterilization control is turned on to perform sterilization and disinfection operations.

[0023] In this embodiment, the air quality level is obtained by judging the air quality according to the air quality monitoring data, and the first air purification control instruction is obtained according to the air quality level, which is specifically implemented by the following steps: S201: When PM 2.5 Concentration less than 35 μg / m 3 , TVOC concentration is less than 0.3mg / m 3 , when the CO2 concentration is less than 1000ppm, the air quality level is excellent; When PM 2.5 Concentration greater than 35 μg / m 3 And not more than 75μg / m 3、TVOC concentration is greater than 0.3mg / m 3 And not more than 0.5mg / m 3 , when the CO2 concentration is less than 1000ppm, the air quality level is good air quality level; When PM 2.5 Concentration greater than 75 μg / m 3 Or TVOC concentration is greater than 0.5 mg / m 3 Or when the CO2 concentration exceeds 1000ppm, the air quality level is the air quality pollution level.

[0024] S202: When the air quality level is an excellent air quality level, an air purifier shutdown instruction is output; when the air quality level is a good air quality level, an air purifier low-speed operation instruction is output; when the air quality level is an air quality pollution level, an air purifier high-speed operation instruction is output.

[0025] It should be noted that the first air purification control instruction includes an air purifier shutdown instruction, an air purifier low-speed operation instruction, and an air purifier high-speed operation instruction.

[0026] In this embodiment, the method of obtaining a regional crowd flow recognition model by improving the Yolov8 algorithm based on the preset regional crowd flow video set is specifically implemented by the following steps: S301: Obtaining a standard frame set of people flow videos in a preset area by performing video frame quality enhancement processing according to the people flow video set in the preset area; S301-1: extracting a preset area crowd flow video frame set according to the preset area crowd flow video set; S301-2: for the preset area crowd flow video frame set, each preset area crowd flow video frame image is processed by video frame quality enhancement to obtain a preset area crowd flow video standard frame set, wherein the video frame quality enhancement processing includes denoising, contrast enhancement, and illumination correction; Specifically, the noise of the video frame image of the crowd flow in the preset area is removed by median filtering; The contrast of the video frame image of the crowd flow in the preset area is enhanced by histogram equalization; Automatic white balance is used to correct the lighting of the video frames of people in the preset area.

[0027] S302: obtaining a regional crowd flow recognition model through training and testing of the improved Yolov8 algorithm according to the preset regional crowd flow video standard frame set; The improved Yolov8 algorithm includes the integration of different pre-trained models, that is, using EfficientNet, ResNet, and MobileNet as basic networks respectively, independently training each Yolov8 model based on different Backbones, and fusing the prediction results through confidence averaging.

[0028] In this embodiment, when the regional crowd flow detection result is a human label, the regional crowd flow detection result is input into the Deepsort tracker to perform regional crowd flow statistics, and the real-time regional crowd flow is obtained by accumulation.

[0029] In this embodiment, the second air purification control instruction is obtained according to the regional human flow through regional human flow aggregation judgment specifically implemented by the following steps: S501: preset the threshold of the flow of people in the area; S502: When the human flow in the area exceeds the preset human flow threshold, a low-speed operation instruction of the air purifier is output; when the human flow in the area drops below the preset human flow threshold, an air purifier shutdown instruction is output.

[0030] It should be noted that the second air purification control instruction includes an air purifier shutdown instruction and an air purifier low speed operation instruction.

[0031] An adaptive air purification system includes a data acquisition module, a first control instruction module, a second control instruction module, and a control module; The data acquisition module is used to obtain air quality monitoring data and regional human flow videos; The first control instruction module is used to obtain an air quality level through the air quality judgment according to the air quality monitoring data, and obtain a first air purification control instruction according to the air quality level; The second control instruction module is used to obtain a regional crowd flow detection result through the regional crowd flow recognition model according to the regional crowd flow video, obtain regional crowd flow through Deepsort tracker statistics according to the regional crowd flow detection result, and obtain a second air purification control instruction through regional crowd flow aggregation judgment according to the regional crowd flow; The control module is used to jointly control the operating state of the air purifier according to the first air purification control instruction and the second air purification control instruction.

[0032] The computer storage medium of the embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device.

[0033] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0034] The program code included on the computer readable medium can be transmitted with any appropriate medium, including but not limited to wireless, electric wire, optical cable, RF, etc., or any suitable combination of the above. The computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or their combinations, and the programming language includes object-oriented programming languages-such as Java, Smalltalk, C++, and also includes conventional procedural programming languages-such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0035] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. An adaptive air purification method, characterized in that: include: Acquire air quality monitoring data, the air quality monitoring data includes PM 2.5 concentration, TVOC concentration, CO2 concentration; Obtain an air quality level through the air quality judgment according to the air quality monitoring data, and obtain a first air purification control instruction according to the air quality level; According to the preset regional crowd flow video set, the regional crowd flow recognition model is obtained by improving the Yolov8 algorithm; Obtain a regional crowd flow video, obtain a regional crowd flow detection result through the regional crowd flow recognition model according to the regional crowd flow video, and obtain the regional crowd flow through the Deepsort tracker according to the regional crowd flow detection result; According to the regional human flow, a second air purification control instruction is obtained by judging the regional human flow aggregation; The operating state of the air purifier is jointly controlled according to the first air purification control instruction and the second air purification control instruction.

2. The adaptive air purification method according to claim 1, characterized in that: The obtaining of air quality monitoring data includes: deploying a plurality of sensor nodes to synchronously monitor air quality data of different areas, and taking an average value of the air quality data collected by each sensor node to obtain the air quality monitoring data.

3. The adaptive air purification method according to claim 1, characterized in that: The obtaining of an air quality level through the air quality judgment according to the air quality monitoring data, and obtaining a first air purification control instruction according to the air quality level comprises: When PM 2.5 Concentration less than 35 μg / m 3 , TVOC concentration is less than 0.3mg / m 3 , when the CO2 concentration is less than 1000ppm, the air quality level is excellent; When PM 2.5 Concentration greater than 35 μg / m 3 And not more than 75μg / m 3 、TVOC concentration is greater than 0.3mg / m 3 And not more than 0.5mg / m 3 , when the CO2 concentration is less than 1000ppm, the air quality level is good air quality level; When PM 2.5 Concentration greater than 75 μg / m 3 Or TVOC concentration is greater than 0.5 mg / m 3 Or when the CO2 concentration exceeds 1000ppm, the air quality level is the air quality pollution level; When the air quality level is an excellent air quality level, an air purifier shutdown instruction is output; when the air quality level is a good air quality level, an air purifier low-speed operation instruction is output; when the air quality level is an air quality pollution level, an air purifier high-speed operation instruction is output.

4. The adaptive air purification method according to claim 1, characterized in that: The method of obtaining a regional crowd flow recognition model by improving the Yolov8 algorithm based on a preset regional crowd flow video set includes: According to the preset area crowd flow video set, a preset area crowd flow video standard frame set is obtained by performing video frame quality enhancement processing; According to the preset regional crowd flow video standard frame set, the regional crowd flow recognition model is obtained through the improved Yolov8 algorithm training and testing.

5. The adaptive air purification method according to claim 4, characterized in that: The step of obtaining a standard frame set of people flow videos in a preset area by performing video frame quality enhancement processing according to the people flow videos in the preset area comprises: Extracting a preset area crowd flow video frame set according to the preset area crowd flow video set; For the preset area crowd flow video frame set, each preset area crowd flow video frame image is processed by video frame quality enhancement to obtain the preset area crowd flow video standard frame set, and the video frame quality enhancement processing includes denoising, contrast enhancement, and illumination correction.

6. The adaptive air purification method according to claim 4, characterized in that: The regional crowd flow recognition model obtained by training and testing the improved Yolov8 algorithm according to the preset regional crowd flow video standard frame set includes: The improved Yolov8 algorithm includes the integration of different pre-trained models, that is, using EfficientNet, ResNet, and MobileNet as basic networks respectively, independently training each Yolov8 model based on different Backbones, and fusing the prediction results through confidence averaging.

7. The adaptive air purification method according to claim 1, characterized in that: The second air purification control instruction is obtained by judging the regional human flow through regional human flow aggregation, including: Preset area flow threshold; When the human flow in the area exceeds the preset human flow threshold, an air purifier low-speed operation instruction is output; when the human flow in the area drops below the preset human flow threshold, an air purifier shutdown instruction is output.

8. An adaptive air purification system, using the adaptive air purification method according to any one of claims 1 to 7, characterized in that: It includes a data acquisition module, a first control instruction module, a second control instruction module, and a control module; The data acquisition module is used to obtain air quality monitoring data and regional human flow videos; The first control instruction module is used to obtain an air quality level through the air quality judgment according to the air quality monitoring data, and obtain a first air purification control instruction according to the air quality level; The second control instruction module is used to obtain a regional crowd flow detection result through the regional crowd flow recognition model according to the regional crowd flow video, obtain regional crowd flow through Deepsort tracker statistics according to the regional crowd flow detection result, and obtain a second air purification control instruction through regional crowd flow aggregation judgment according to the regional crowd flow; The control module is used to jointly control the operating state of the air purifier according to the first air purification control instruction and the second air purification control instruction.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that: When the processor executes the computer program, the adaptive air purification method as described in any one of claims 1-7 is implemented.

10. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are used to perform the adaptive air purification method as described in any one of claims 1-7 when executed by a computer processor.

Images