Method for achieving indoor cleaning system benefits through generative artificial intelligence (AIGC)

Abstract

The invention discloses a method for achieving indoor cleaning system benefits through generative artificial intelligence (AIGC). The method comprises the steps that professional generation data of an indoor cleaning system are provided; providing user generation data of the indoor cleaning system; inputting professional generated data and user generated data through application program (APP) software, and storing the professional generated data and the user generated data to a storage center; providing a generative artificial intelligence (AIGC) model, and performing calculation, comparison and identification according to the professional generated data and the user generated data to generate automatic generated data; according to the method, integrated benefit correction is provided, learning and improvement of the automatically generated data are compared by integrating the automatically generated data and optimizing deep learning processing data correction, and a generative artificial intelligence (AIGC) model is guided to rapidly converge and regressively correct to the most correct automatically generated data, so that the benefits of the optimized indoor cleaning system are generated, and the indoor cleaning system is implemented.

Description

TECHNICAL FIELD

[0001] The present application relates to a method for achieving clean room ZAPClean room level requirements by detecting, positioning, and circulating and filtering air pollution in an indoor field using an indoor air cleaning system combined with artificial general intelligence (AIGC). BACKGROUND

[0002] Modern people pay more and more attention to the quality of the gas around them, such as carbon monoxide, carbon dioxide, volatile organic compounds (VOC), PM2.5, nitrogen monoxide, sulfur monoxide, and even particles contained in the gas, which can affect human health and even endanger life when exposed to the environment. Therefore, the quality of the environment gas has attracted the attention of countries. How to detect the quality of the gas to avoid and stay away from areas with poor gas quality is a current topic of interest. Indoor air quality is not easy to grasp. In addition to outdoor air quality, indoor air conditioning conditions and pollution sources are the main factors affecting indoor air quality. It is possible to intelligently and quickly detect indoor air pollution sources in various indoor fields, effectively remove indoor air pollution to form a clean and safe breathing gas state, and monitor indoor air quality at any time and anywhere. Therefore, an indoor air cleaning system is proposed to detect, locate, and circulate and filter air pollution in an indoor field. The entire system is configured with gas sensors and intelligent cloud to form an intelligent linkage system. Through communication transmission control instructions, the gas cleaning device is controlled to filter and process air pollution, so that the air pollution state in the indoor field can meet the clean room ZAPClean room level requirements.

[0003] In addition, how to implement the indoor air cleaning system in the indoor field to optimize the number, specification, and performance control of the cleaning device, reduce noise control implementation, and minimize the setting cost planning requires a large amount of data to verify and repeatedly experiment to calculate the optimal planning and setting. Such a system can be well applied to general indoor home life, which is the main topic of the present application. SUMMARY

[0004] The main purpose of the present application is to provide a method for achieving the benefits of an indoor cleaning system using artificial general intelligence (AIGC). By implementing an indoor air cleaning system in indoor home life combined with an artificial general intelligence module (AIGC), the method can plan an indoor air cleaning system with optimal number, specification, and performance control of the cleaning device, noise control implementation, and minimum setting cost planning. The system is applied to detect, locate, and circulate and filter air pollution in an indoor field to meet the clean room ZAPClean room level requirements.

[0005] To achieve the above object, the present application provides a method for generating artificial intelligence (AIGC) to realize the benefits of an indoor clean system, comprising: providing a professional generated data of an indoor clean system, the professional generated data including outdoor and indoor air pollution data of a building, indoor field data of the building, clean room level data, air clean system hardware specifications, and air clean system software specifications; providing a user generated data of the indoor clean system, the user generated data including indoor field parameter data of a user building, indoor field experimental measurement air pollution parameter data of the user building, and HVAC air exchange rate parameter data of the indoor field of the user building; providing an artificial intelligence (AIGC) model, calculating, comparing and identifying an automatically generated data by inputting the professional generated data and the user generated data, the automatically generated data including the number of optimized air cleaning hardware, the performance control of optimized air cleaning hardware, the control of noise reduction of optimized air cleaning hardware, the minimum initial setup cost information of the air clean system, and the minimum operating cost information of the air clean system; providing an integrated benefit correction, the automatically generated data generated by the artificial intelligence (AIGC) model is finally integrated to realize the generation of new real deep learning processing data correction to optimization, compare the learning and improvement of the automatically generated data, and assist in guiding the artificial intelligence (AIGC) model to quickly converge towards the correct use direction, and return to the most correct automatically generated data for correction to produce the optimized indoor clean system benefit to implement the indoor clean system. BRIEF DESCRIPTION OF DRAWINGS

[0006] Figure 1 is a schematic diagram of the method for generating artificial intelligence (AIGC) to realize the benefits of an indoor clean system of the present application.

[0007] Figure 2 is a schematic diagram of an indoor air clean system of the present application.

[0008] Figure 3 is a clean degree level distinction table of the indoor air clean system of the present application.

[0009] SYMBOL DESCRIPTION

[0010] A: indoor clean system

[0011] 1: storage center

[0012] 2: air quality detector

[0013] 3: application (APP) software

[0014] 4: artificial intelligence (AIGC) model

[0015] 5: gas cleaning device hardware

[0016] 5a: Fresh air machine

[0017] 5b: Total heat exchanger

[0018] 5c: Hood

[0019] 5d: Circulating filter device (FFU)

[0020] 5e: Negative pressure exhaust fan

[0021] 5f: Bathroom exhaust fan DETAILED DESCRIPTION

[0022] Embodiments embodying the features and advantages of the present application will be described in detail hereinafter. It should be understood that the present application can be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and fully convey the scope of the application to those skilled in the art.

[0023] Referring to Figure 1 The present application provides a method for generating an artificial intelligence generated content (AIGC) to achieve the benefits of an indoor clean system, comprising: providing a professional generated data of an indoor clean system, the professional generated data including outdoor and indoor air pollution data of a building, indoor field data of the building, clean room level data, air clean system hardware specifications, and air clean system software specifications; providing a user generated data of the indoor clean system, the user generated data including indoor field parameter data of a user building, indoor field experimental measurement air pollution parameter data of the user building, and heating ventilation air conditioning (HVAC) air exchange rate parameter data of the user building; providing an artificial intelligence generated content (AIGC) model 4, calculating, comparing, and identifying an automatically generated data by inputting the professional generated data and the user generated data, the automatically generated data including the number of optimized air clean hardware, the performance control of optimized air clean hardware, the control of noise reduction of optimized air clean hardware, the minimum initial setup cost information of the air clean system, and the minimum operating cost information of the air clean system; providing an artificial intelligence generated content (AIGC) model 4 integration benefit correction, the automatically generated data generated by the artificial intelligence generated content (AIGC) model 4 is finally integrated to achieve a new real deep learning processing data correction to the best, compare the learning and improvement of the automatically generated data, and assist in guiding the artificial intelligence generated content (AIGC) model 4 to quickly converge in the correct and useful direction, and return to the most correct automatically generated data to produce the best indoor clean system benefit to implement the indoor clean system.

[0024] As Figure 2As shown, the indoor air cleaning system A includes a storage center 1, an air quality detector 2, an application (APP) software 3, an artificial intelligence generated content (AIGC) model 4, and a gas cleaning device hardware 5.

[0025] The storage center 1 collects indoor cleaning system information data to form a big data database of professional generated data and user generated data. Notably, the indoor cleaning system information data refers to data applied for reference, such as spatial parameters of system implementation environment field, data parameters of air pollution detection, reference safety value parameters, clean room level comparison parameters, cleaning device software and hardware specifications, and control parameters, but not limited to, all system related research data, historical data, and other application data for generating AI machine learning model. The professional generated data includes outdoor and indoor air pollution specification data of buildings (such as air pollution properties, concentration safety values, etc.), indoor field space data of buildings (building size and proportion, use purpose function, environmental ventilation, temperature control comfort parameter, etc.), clean room level specification data (such as ZAP Clean room 1-12 level comparison table, such as Figure 3 ), and air cleaning system requirement software and hardware specifications (such as fan clean air output CADR, filter screen specifications, etc.). The user generated data includes user building indoor field air pollution data (such as real-time detection data of air quality detector 2, etc.), user building indoor field experimental measurement air pollution data (inspection unit detects actual air pollution data of user indoor field), and user building indoor field HVAC air exchange rate data (such as real-time detection of indoor and outdoor carbon dioxide comparison data of air quality detector 2, etc.).

[0026] The air quality detector 2 detects the air pollution output of the outdoor field and indoor field of the building and transmits the air pollution data to the storage center 1 through the Internet of Things to form a user generated data.

[0027] The application (APP) software 3 inputs related indoor cleaning system information data and transmits it to the storage center 1 for storage through the Internet of Things.

[0028] The artificial intelligence generated content (AIGC) model 4 can be one of OpenAI API artificial intelligence model, Azure artificial intelligence model, Gemini artificial intelligence model, AWS artificial intelligence model, IBM Watson artificial intelligence model. The professional generated data and user generated data stored in the storage center 1 are extracted by the artificial intelligence generated content (AIGC) model 4 through the Internet of Things to generate an automatically generated data by deep learning processing and analyzing data, such as Figure 1As shown, that is, the application (APP) software 3 input related indoor clean system information data, such as professional generated data including building outdoor, indoor air pollution specification data, building indoor field space data, clean room level specification data, air cleaning system hardware and software specifications and other information data, such as user generated data including user building indoor field air pollution data data, user building indoor field experimental measurement air pollution data data, user building indoor field HVAC air exchange rate data and other information data, stored in storage center 1 to form a large data database of air pollution data, through the application (APP) software 3 user input system demand optimization clean device quantity, specification layout, optimization performance control, noise reduction control implementation, and the minimum setting cost planning and other information, generated artificial intelligence (AIGC) model 4 can be based on the professional generated data and user generated data stored in storage center 1 to collect indoor clean system information data to generate. And deep learning processing and analysis of data to produce real and generated training discriminator comparison, get automatically generated data, such as the number of optimized air cleaning hardware, optimized air cleaning hardware performance control, optimized air cleaning hardware noise reduction control, air cleaning system minimum one-time setting cost information, air cleaning system minimum operating cost information and other information, while the generated artificial intelligence (AIGC) model 4 itself has a self-correcting analysis mechanism, providing generated artificial intelligence (AIGC) model 4 integration benefit correction, can be the generated artificial intelligence (AIGC) model 4 generated automatically generated data for the final integration evaluation, to predict the generation of new real deep learning processing data correction to the best, comparison of the authenticity of automatically generated data, and help guide the generated artificial intelligence (AIGC) model 4 quickly converge to the "correct" direction of use, regression correction to the most correct automatically generated data, so that the implementation of indoor air cleaning system can obtain the best pre-job layout and application optimization benefit through the combination of generated artificial intelligence platform, and truly obtain the required setting specification and cost of indoor air cleaning system, and then apply to indoor field detection, positioning, and circulating filtration of air pollution.

[0029] The above-mentioned gas cleaning device hardware 5 is arranged in the indoor field of the building. It is worth noting that the gas cleaning device hardware 5 can be one of the fresh air machine 5a, the total heat exchanger 5b, the exhaust hood 5c, the circulating filter device (FFU) 5d, the negative pressure exhaust fan 5e, and the bathroom exhaust fan 5f, but not limited to this. Each gas cleaning device hardware 5 includes at least one fan and at least one filter element. The gas cleaning device hardware 5 can be connected to the air pollution data collection device 2 through the Internet of Things

[0030] The receiving and computing center 1 intelligently selects and issues a control instruction based on the automatically generated data to regulate the operation of the fan of the gas purification device hardware 5, thereby diverting the air pollution circulating and filtered in the indoor area through the filter element, so that the air pollution status of the indoor area meets the clean room ZAPCleanroom 1-12 grade requirements.

[0031] In summary, the present invention uses a method for realizing the benefits of an indoor clean air system in indoor home life by combining a generative artificial intelligence (AIGC) model to plan an indoor air clean air system with the optimized number, specification layout, optimized performance control, noise reduction control implementation, and minimum setup cost planning of the clean equipment. In this way, before the implementation of the indoor air clean air system, the optimized pre-job layout and application optimization benefits can be obtained by combining the generative artificial intelligence platform, and the indoor air clean air system with the required setting specifications and costs can be truly obtained, and then applied to the indoor field to detect, locate, circulate and filter air pollution, and meet the clean room ZAPClean room level requirements, which has great industrial utilization value.

Claims

1. A method for achieving the benefit of an indoor clean system by using a generative artificial intelligence, comprising: providing a professional generative data of an indoor clean system, the professional generative data comprising outdoor and indoor air pollution data of a building, indoor field data of the building, clean room level data, air clean system hardware specifications, and air clean system software specifications; providing a user generative data of the indoor clean system, the user generative data comprising indoor field parameter data of a user building, indoor field experimental measurement air pollution parameter data of the user building, and HVAC air exchange rate parameter data of the user building; providing a generative artificial intelligence model, which is calculated, compared, and identified to generate an automatic generative data by inputting the professional generative data and the user generative data, the automatic generative data comprising the number of optimized air clean hardware, the performance control of optimized air clean hardware, the control of noise reduction of optimized air clean hardware, the minimum initial installation cost information of the air clean system, and the minimum operation cost information of the air clean system; providing an integrated benefit correction, the automatic generative data generated by the generative artificial intelligence model is finally integrated to achieve deep learning data correction to optimization, compare the learning and improvement of the automatic generative data, and assist in guiding the generative artificial intelligence (AIGC) model to quickly converge towards the correct direction of use, and return to the most correct automatic generative data to produce the best indoor clean system benefit implementation of the indoor clean system.

2. The method for achieving the benefit of an indoor clean system by using a generative artificial intelligence according to claim 1, wherein the generative artificial intelligence model comprises one of OpenAI API artificial intelligence model, Azure artificial intelligence model, Gemini artificial intelligence model, AWS artificial intelligence model, and IBM Watson artificial intelligence model.

3. The method for achieving the benefit of an indoor clean system by using a generative artificial intelligence according to claim 1, wherein the indoor clean system comprises a gas cleaning device hardware, and the gas cleaning device hardware specifications comprise air quality detector specifications, fresh air machine specifications, total heat exchanger specifications, circulating filter device specifications, mobile circulating filter device specifications, bathroom exhaust fan specifications, central control device (computer) specifications, negative pressure exhaust fan specifications, and filter element specifications.

4. The method for achieving the benefit of an indoor clean system by using a generative artificial intelligence according to claim 3, wherein the professional generative data comprises a clean room level specification data, and the clean room level specification data is ZAP Clean room 1-12 level specification. ​ ​

Images