A method and platform for regulating operation parameters of an air purifier

Abstract

The present invention discloses an operating parameter regulation method and platform for an air purifier, relating to the technical field of air purification. The method includes: obtaining real-time air detection data; conducting a purification demand evaluation to generate an air purification instruction; activating an air purification regulation model to obtain an air purification regulation plan; conducting a regulation prediction evaluation on the air purifier in the target space to obtain a purification regulation prediction evaluation result; determining whether the purification regulation prediction evaluation result meets the purification regulation prediction evaluation expectation; if not, generating an air purification regulation strategy; and controlling the air purifier according to the air purification regulation strategy. The technical problems in the prior art, such as the inflexible regulation of air purifiers and the inability to respond to changes in air quality in real time, resulting in low air purification efficiency and high energy consumption, are solved. The operating parameters of the air purifier are dynamically adjusted according to real-time air quality data, achieving the technical effect of improving air purification efficiency and reducing energy consumption.

Description

Technical Field

[0001] This application relates to the technical field of air purification, and particularly to a method and platform for regulating the operating parameters of an air purifier. Background Art

[0002] With the acceleration of the industrialization process in modern society and the continuous improvement of people's living standards, the problem of air pollution has become increasingly serious. As an important device for improving indoor air quality, air purifiers have been widely used in places such as homes, offices, shopping malls, and hospitals. Air purifiers remove harmful substances in the air, such as PM2.5, formaldehyde, bacteria, viruses, etc., through filters, activated carbon, etc. However, in the actual use process of air purifiers, affected by various factors, such as the real-time change of air quality, different space layouts, and the limitations of purifier performance, the traditional static operation mode is difficult to reasonably adjust its wind speed, filter efficiency, working mode, etc. according to the characteristics of the space, so as to improve the air purification efficiency and achieve the best air purification effect, and it is impossible to achieve the balance between purification efficiency and energy consumption. In practical applications, the excessive operation of the purifier not only wastes energy, but may also cause unnecessary noise and fluctuations in air quality.

[0003] Therefore, in the current related technologies, there are technical problems such as inflexible regulation of air purifiers and inability to respond to changes in air quality in real time, which in turn lead to low air purification efficiency and high energy consumption. Summary of the Invention

[0004] By providing a method and platform for regulating the operating parameters of an air purifier, this application solves the technical problems in the prior art that the regulation of air purifiers is not flexible enough and cannot respond to changes in air quality in real time, which in turn leads to low air purification efficiency and high energy consumption, and realizes dynamically adjusting the operating parameters of the air purifier according to real-time air quality data, achieving the technical effect of improving air purification efficiency and reducing energy consumption.

[0005] The present application provides a method for regulating operation parameters of an air purifier. The method includes: obtaining real-time air detection data of a target space; evaluating a purification requirement according to the real-time air detection data to generate an air purification instruction; activating an air purification regulation model based on the air purification instruction, and inputting the real-time air detection data into the air purification regulation model to obtain an air purification regulation plan; performing a regulation prediction evaluation on the air purifier in the target space according to the air purification regulation plan based on the real-time air detection data to obtain a purification regulation prediction evaluation result; determining whether the purification regulation prediction evaluation result meets the purification regulation prediction evaluation expectation; if the purification regulation prediction evaluation result does not meet the purification regulation prediction evaluation expectation, performing an optimization regulation on the air purification regulation plan according to the purification regulation prediction evaluation expectation to generate an air purification regulation strategy; and controlling the air purifier according to the air purification regulation strategy.

[0006] In a possible implementation manner, when performing a regulation prediction evaluation on the air purifier in the target space according to the air purification regulation plan to obtain a purification regulation prediction evaluation result, the following processing is further performed: performing a learning of a regulation evaluation record on the air purifier to establish a purification regulation prediction evaluation channel, where the purification regulation prediction evaluation channel includes an air purification quality prediction branch, a purification regulation energy consumption prediction branch, and a purification regulation noise prediction branch; inputting the real-time air detection data and the air purification regulation plan into the air purification quality prediction branch to obtain a predicted air purification quality coefficient; obtaining a purification regulation energy consumption prediction coefficient according to the purification regulation energy consumption prediction branch based on the real-time air detection data and the air purification regulation plan; inputting the real-time air detection data and the air purification regulation plan into the purification regulation noise prediction branch to obtain a purification regulation noise prediction coefficient; and outputting the predicted air purification quality coefficient, the purification regulation energy consumption prediction coefficient, and the purification regulation noise prediction coefficient as the purification regulation prediction evaluation result.

[0007] In a possible implementation, the air purifier is subjected to regulation evaluation record learning to establish a purification regulation prediction evaluation channel, and the following processing is also performed: retrieving the regulation evaluation records of the air purifier to obtain an air detection sample set, a purification regulation plan sample set, a purification quality evaluation sample set, a purification regulation energy consumption evaluation sample set, and a purification regulation noise evaluation sample set; performing integrated fusion learning based on the air detection sample set, the purification regulation plan sample set, and the purification quality evaluation sample set to establish the air purification quality prediction branch; performing integrated fusion learning based on the air detection sample set, the purification regulation plan sample set, and the purification regulation energy consumption evaluation sample set to establish the purification regulation energy consumption prediction branch; performing integrated fusion learning based on the air detection sample set, the purification regulation plan sample set, and the purification regulation noise evaluation sample set to generate the purification regulation noise prediction branch; and connecting the air purification quality prediction branch, the purification regulation energy consumption prediction branch, and the purification regulation noise prediction branch to generate the purification regulation prediction evaluation channel.

[0008] In a possible implementation, when performing integrated fusion learning based on the air detection sample set, the purification regulation plan sample set, and the purification quality evaluation sample set to establish the air purification quality prediction branch, the following processing is also performed: performing supervised training on P meta-learners based on the air detection sample set, the purification regulation plan sample set, and the purification quality evaluation sample set to obtain P air purification quality predictors, where P is a positive integer greater than 1; using the output data set of the P air purification quality predictors as input information and the purification quality evaluation sample set as output information to train the purification quality prediction fusion model; merging the P air purification quality predictors as parallel independent nodes to generate the air purification quality prediction model; and merging the input layer of the air purification quality prediction model and the purification quality prediction fusion model to generate the air purification quality prediction branch.

[0009] In a possible implementation, if the purification regulation prediction evaluation result does not meet the purification regulation prediction evaluation expectation, the air purification regulation scheme is optimized and regulated according to the purification regulation prediction evaluation expectation to generate an air purification regulation strategy, and the following processing is also performed: collecting the operation parameter constraint information of the air purifier, and establishing a purification regulation constraint domain; adjusting the air purification regulation scheme according to the purification regulation constraint domain to generate a purification adjustment scheme space; extracting a first purification adjustment scheme according to the purification adjustment scheme space; inputting the real-time air detection data and the first purification adjustment scheme into the purification regulation prediction evaluation channel to obtain a first adjustment scheme purification prediction result; determining whether the first adjustment scheme purification prediction result meets the purification regulation prediction evaluation expectation; if the first adjustment scheme purification prediction result meets the purification regulation prediction evaluation expectation, adding the first purification adjustment scheme to the air purification regulation strategy.

[0010] In a possible implementation, when determining whether the first adjustment scheme purification prediction result meets the purification regulation prediction evaluation expectation, the following processing is also performed: if the first adjustment scheme purification prediction result does not meet the purification regulation prediction evaluation expectation, eliminating the first purification adjustment scheme; extracting a second purification adjustment scheme according to the purification adjustment scheme space; inputting the real-time air detection data and the second purification adjustment scheme into the purification regulation prediction evaluation channel to obtain a second adjustment scheme purification prediction result; determining whether the second adjustment scheme purification prediction result meets the purification regulation prediction evaluation expectation; if the second adjustment scheme purification prediction result meets the purification regulation prediction evaluation expectation, adding the second purification adjustment scheme to the air purification regulation strategy; if the second adjustment scheme purification prediction result does not meet the purification regulation prediction evaluation expectation, eliminating the second purification adjustment scheme, and continuing to perform optimization iteration on the purification adjustment scheme space according to the purification regulation prediction evaluation expectation until the air purification regulation strategy is generated.

[0011] In a possible implementation, when evaluating the purification requirement according to the real-time air detection data to generate an air purification instruction, the following processing is also performed: evaluating the air quality of the target space according to the real-time air detection data to obtain a real-time air quality coefficient; evaluating the purification requirement of the real-time air quality coefficient according to the air quality constraint of the target space to generate an air purification requirement coefficient; determining whether the air purification requirement coefficient is greater than or equal to an air purification requirement threshold; if the air purification requirement coefficient is greater than or equal to the air purification requirement threshold, obtaining the air purification instruction.

[0012] The present application also provides an operating parameter regulation platform for an air purifier, including: a real-time air detection data acquisition module for acquiring real-time air detection data of a target space; a purification requirement evaluation module for evaluating purification requirements according to the real-time air detection data and generating an air purification instruction; an air purification regulation scheme acquisition module for activating an air purification regulation model based on the air purification instruction and inputting the real-time air detection data into the air purification regulation model to obtain an air purification regulation scheme; a regulation prediction evaluation module for performing a regulation prediction evaluation on the air purifier in the target space according to the air purification regulation scheme based on the real-time air detection data to obtain a purification regulation prediction evaluation result; a prediction evaluation result judgment module for judging whether the purification regulation prediction evaluation result meets the purification regulation prediction evaluation expectation; an air purification regulation strategy generation module for, if the purification regulation prediction evaluation result does not meet the purification regulation prediction evaluation expectation, performing an optimization regulation on the air purification regulation scheme according to the purification regulation prediction expectation to generate an air purification regulation strategy; and an air purifier control module for controlling the air purifier according to the air purification regulation strategy.

[0013] It is intended to obtain real-time air detection data through an operating parameter regulation method and platform for an air purifier proposed in the present application; perform a purification requirement evaluation to generate an air purification instruction; activate an air purification regulation model to obtain an air purification regulation scheme; perform a regulation prediction evaluation on the air purifier in the target space to obtain a purification regulation prediction evaluation result; judge whether the purification regulation prediction evaluation result meets the purification regulation prediction evaluation expectation; if not, generate an air purification regulation strategy; and control the air purifier according to the air purification regulation strategy. This solves the technical problems in the prior art that the regulation of air purifiers is not flexible enough and cannot respond to air quality changes in real time, resulting in low air purification efficiency and high energy consumption, and realizes dynamically adjusting the operating parameters of the air purifier according to real-time air quality data, achieving the technical effect of improving air purification efficiency and reducing energy consumption. Description of the Drawings

[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments of the present disclosure will be briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the platform according to the embodiments of the present application. It should be understood that the operations before or below do not necessarily need to be executed precisely in sequence. On the contrary, according to needs, they can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several operations can be removed from these processes.

[0015] Figure 1 It is a schematic flowchart of an operating parameter regulation method for an air purifier provided by an embodiment of the present application;

[0016] Figure 2 Schematic structural diagram of an operating parameter regulation platform for an air purifier provided by an embodiment of the present application.

[0017] Explanation of reference numerals: Real-time air detection data acquisition module 10, purification requirement evaluation module 20, air purification regulation plan acquisition module 30, regulation prediction evaluation module 40, prediction evaluation result judgment module 50, air purification regulation strategy generation module 60, air purifier control module 70. Detailed implementation manners

[0018] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the description. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the following specifically gives the detailed implementation manners of the present application.

[0019] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations on the present application. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present application.

[0020] In the following description, "some embodiments" are involved, which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. The terms "first / second" involved are only used to distinguish similar objects and do not represent a specific order for the objects. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, platform, product or server including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or modules not clearly listed or inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application.

[0021] An embodiment of the present application provides an operating parameter regulation method for an air purifier, as Figure 1 shown, the method includes:

[0022] Step S100, obtaining real-time air detection data of a target space.

[0023] Preferably, the air quality in the target space (such as indoor environments like rooms, offices, shopping malls, etc.) is monitored in real time through air quality monitoring devices (such as sensors, detection instruments, etc.), and relevant air parameter data is obtained, which usually includes but is not limited to the PM2.5 concentration, the concentration of particulate matter with a diameter less than or equal to 2.5 micrometers in the air, used to measure the fine particulate matter pollution level in the air; the CO2 concentration, the concentration of carbon dioxide in the air, used to evaluate the ventilation and freshness of the air; the TVOCs (total volatile organic compounds) concentration, the concentration of harmful gases in the air, such as formaldehyde, benzene, xylene, etc.; temperature and humidity, which directly affect air quality and comfort; and the oxygen concentration, the change in which has a greater impact on health. Through the data obtained by these sensors, the air purifier can evaluate the air quality in the target space in real time, and thus make intelligent adjustments to control the operating state of the purifier to optimize the air purification effect.

[0024] Step S200, evaluate the purification requirement according to the real-time air detection data, and generate an air purification instruction.

[0025] Preferably, based on the real-time air quality data obtained from the target space, by analyzing and evaluating the current air pollution situation, it is determined whether to start the air purifier and how to adjust its operating parameters. Specifically, according to the air pollutant concentrations detected in real time (such as PM2.5, CO2, formaldehyde, etc.), the degree of air pollution is evaluated. For example, when the PM2.5 concentration is higher than a certain threshold, it indicates that the air pollution is relatively serious and an air purification instruction needs to be generated. In addition to pollutant concentrations, environmental factors such as temperature, humidity, and oxygen concentration are also evaluated. For example, if the indoor temperature is too high or the humidity is too low, the air purifier may need to adjust the wind speed or enable the humidification function. The purification requirement evaluation refers to judging whether there is a need for air purification according to the air quality evaluation result. For example, when certain harmful substances (such as formaldehyde or PM2.5) exceed the standard, it indicates that the current air quality is poor and the air purification function needs to be started. If multiple pollutants are detected, analyze which pollutant has the most serious impact on air quality, so as to set the purification priority, and then generate an air purification instruction, including the purifier start instruction (set to a suitable operating mode), the operating parameter adjustment instruction, that is, according to the types and concentrations of pollutants, instruct the purifier to adjust the wind speed, filtration method or other functions (such as enabling ozone disinfection, humidification, etc.) to ensure that it performs efficient purification work according to the actual air quality requirements to achieve the best purification effect.

[0026] Further, step S200 further includes step S210 of evaluating the air quality of the target space according to the real-time air detection data to obtain a real-time air quality coefficient; step S220 of evaluating the purification demand of the real-time air quality coefficient according to the air quality constraint of the target space to generate an air purification demand coefficient; step S230 of determining whether the air purification demand coefficient is greater than or equal to an air purification demand threshold; and step S240 of obtaining the air purification instruction if the air purification demand coefficient is greater than or equal to the air purification demand threshold.

[0027] Preferably, according to the obtained real-time air detection data of the target space (such as the concentrations of pollutants such as PM2.5, CO2, temperature and humidity, and formaldehyde), the air quality of the target space is evaluated, including comparing multiple air quality indicators (such as PM2.5 concentration, CO2 concentration, VOC content, etc.) with preset standards, and calculating a comprehensive air quality coefficient to reflect the overall current air quality. The larger the coefficient, the more serious the air pollution, and vice versa. According to the air quality constraint of the target space, the purification demand of the real-time air quality coefficient is evaluated, that is, the air quality coefficient is processed according to the predetermined air quality constraint to obtain an air purification demand coefficient, which represents the urgency or degree of air purification required. When the air quality coefficient is higher, the purification demand coefficient will also increase correspondingly, indicating a stronger air purification demand. Among them, the air quality constraint is the air quality standard or constraint in the purification demand evaluation, such as the maximum allowable PM2.5 concentration, the minimum comfortable temperature and humidity range, etc. Comparing the air purification demand coefficient with the air purification demand threshold to determine whether the purification condition is met. If the purification demand coefficient reaches or exceeds the air purification demand threshold, it indicates that the air quality has reached the level that needs to be purified, and a specific air purification instruction is generated. This instruction indicates the activation of the air purifier and appropriate adjustment according to the demand, which may include multiple control instructions, such as starting the air purifier; adjusting the purifier wind speed, mode (such as strong purification, quiet mode, etc.); starting specific filters or functions (such as HEPA filter, activated carbon filter, etc.); enabling other additional functions (such as humidification, negative ion function, etc.).

[0028] Step S300, based on the air purification instruction, activate the air purification control model and input the real-time air detection data into the air purification control model to obtain an air purification control scheme.

[0029] Preferably, the air purification instruction generated in the purification demand evaluation stage instructs the air purifier to start and adjust, and activates the air purification control model. The air purification control model is used to intelligently adjust the working state and parameters of the air purifier according to the air quality data and environmental conditions. Activating the control model means starting to make decisions and optimize parameters based on real-time data, rather than simply time-switch control. Instead, it intelligently adjusts the operating state of the air purifier. Then, the obtained real-time air detection data is input into the air purification control model. The air purification control model analyzes these data to determine the current air pollution situation, which pollutants have higher concentrations, and the air circulation, etc. For example, if the PM2.5 concentration is high, the model will analyze whether to adjust the wind speed or enable a more efficient filtration mode; if the temperature and humidity are too low, the model may enable the humidification function. Based on the input real-time air quality data, the control model generates a specific control plan, which includes how to adjust the operating parameters of the air purifier. For example, according to the air quality, the wind speed is adjusted to the strong mode or the low-speed mode; if the concentration of harmful gases in the air is high, the activated carbon filter is selected to adsorb harmful gases; if there are more particulate matters, the HEPA filter is enabled; according to the degree of air pollution, the purification time is extended or shortened; if the air humidity is low, the control plan may require starting the humidification function. Generally speaking, the air purifier no longer simply operates, but makes precise and efficient adjustments according to the changes in the environmental air quality to ensure that the air purifier always maintains the best working state to achieve the best air purification effect.

[0030] Step S400: Based on the real-time air detection data, conduct a control prediction evaluation on the air purifier in the target space according to the air purification control plan to obtain a purification control prediction evaluation result.

[0031] Preferably, according to the real-time air detection data and the air purification regulation plan, a regulation prediction evaluation is carried out on the air purifier in the target space, that is, the air purification regulation plan is used to predict the purification effect, energy consumption and noise situation of the air purifier in the current environment. Specifically, combined with the real-time air detection data, through the simulation and analysis of the purifier regulation plan, the improvement effect of the air purifier on the air quality under specific operations is estimated. This is a predictive calculation based on existing data and regulation strategies, that is, after simulating the operation of the purifier according to the current regulation plan (such as adjusting the wind speed, filter, humidification, etc.), the air quality, energy consumption and generated noise are predicted. For example, if the current PM2.5 concentration is relatively high, the regulation plan may require increasing the wind speed of the purifier and using a high-efficiency HEPA filter. On this basis, it is estimated how much the PM2.5 concentration will decrease within a certain period of time after this adjustment; if there is a relatively high concentration of formaldehyde in the target space, the regulation plan may require enabling the activated carbon filter, and the change trend of the formaldehyde concentration under the regulation plan is evaluated through simulation; and then the purification regulation prediction evaluation result is obtained, which describes the purification effect that the air purifier is expected to achieve according to the current regulation plan, such as the PM2.5 concentration is expected to be reduced to a certain level, the CO2 concentration is expected to reach the healthy standard range, the indoor temperature and humidity are restored to the comfortable range, or whether the concentration of other harmful gases (such as formaldehyde, TVOCs) decreases, whether the energy consumption decreases, and whether the noise decreases, etc. Through the regulation prediction evaluation, it is evaluated whether the regulation plan is effective and whether it needs to be further optimized to ensure that the air purifier can truly achieve the expected purification effect and control the corresponding energy consumption and noise situation.

[0032] Further, step S400 further includes step S410 of carrying out a regulation evaluation record learning on the air purifier and establishing a purification regulation prediction evaluation channel, where the purification regulation prediction evaluation channel includes an air purification quality prediction branch, a purification regulation energy consumption prediction branch, and a purification regulation noise prediction branch; step S420 of inputting the real-time air detection data and the air purification regulation plan into the air purification quality prediction branch to obtain a predicted air purification quality coefficient; step S430 of obtaining a purification regulation energy consumption prediction coefficient based on the real-time air detection data and the air purification regulation plan according to the purification regulation energy consumption prediction branch; step S440 of inputting the real-time air detection data and the air purification regulation plan into the purification regulation noise prediction branch to obtain a purification regulation noise prediction coefficient; step S450 of outputting the predicted air purification quality coefficient, the purification regulation energy consumption prediction coefficient, and the purification regulation noise prediction coefficient as the purification regulation prediction evaluation result.

[0033] Preferably, the regulation evaluation record learning of the air purifier refers to recording the regulation data (including air quality, energy consumption, noise, etc.) and the corresponding operation results (such as purification effect, energy consumption, noise level, etc.) of each operation of the air purifier, and learning these data, including continuously monitoring and recording the performance of the air purifier when implementing the regulation strategy, and gradually optimizing the regulation strategy, that is, improving the regulation strategy according to the learned historical data, so that the air purifier can always maintain an efficient and low-energy consumption operation state under different environmental conditions, thereby establishing a purification regulation prediction evaluation channel, which is an integrated prediction model for evaluating the performance of the air purifier when implementing the regulation strategy from multiple dimensions, including an air purification quality prediction branch, a purification regulation energy consumption prediction branch, and a purification regulation noise prediction branch. The air purification quality prediction branch is used to predict the purification effect of the air purifier under a specific regulation plan. By inputting real-time air detection data (such as PM2.5, CO2, formaldehyde concentration, etc.) and the regulation plan, the predicted air purification quality can be calculated; the purification regulation energy consumption prediction branch is used to predict the energy consumption of the air purifier when implementing the regulation plan. Based on the parameters set in the regulation plan (such as wind speed, mode, working time, etc.), this branch can calculate the power consumption of the purifier; the purification regulation noise prediction branch is used to predict the noise level of the air purifier under different regulation modes. By evaluating different operation modes (such as high wind speed mode, low wind speed mode) and air quality data, the change of the noise level can be predicted, and a low-noise working mode can be selected to improve the user's comfort.

[0034] Preferably, the real-time air detection data and the air purification control scheme are input into the air purification quality prediction branch to predict the purification effect that the air purifier can achieve, and then the predicted air purification quality coefficient is obtained, which represents the purification ability and effect of the air purifier on air pollution under the current control scheme. For example, how much the PM2.5 concentration is expected to decrease, or how much the concentrations of formaldehyde and TVOCs will drop; the real-time air detection data and the air purification control scheme are input into the purification control energy consumption prediction branch to predict the energy consumption performance of the purifier under this scheme, reflecting the energy consumption situation of the purifier in different working modes, and then the purification control energy consumption prediction coefficient is obtained, which represents the expected power or energy consumption of the air purifier under the given control scheme. For example, the strong mode may consume more electricity, while the low-speed mode is relatively energy-efficient; the real-time air data and the control scheme are input into the purification control noise prediction branch to predict the possible noise levels of the air purifier under different control schemes, and then the purification control noise prediction coefficient is obtained, which describes the noise level of the purifier under the given control scheme. For example, in the high wind speed mode, the air purifier may generate relatively loud noise, while in the low wind speed mode, the noise is relatively small. Finally, the predicted air purification quality coefficient, the purification control energy consumption prediction coefficient, and the purification control noise prediction coefficient are output as the purification control prediction evaluation result to ensure that while optimizing the air purification effect, the energy consumption and noise are minimized to provide a better user experience.

[0035] Further, step S410 further includes step S411 of retrieving the regulation evaluation records of the air purifier to obtain an air detection sample set, a purification regulation scheme sample set, a purification quality evaluation sample set, a purification regulation energy consumption evaluation sample set, and a purification regulation noise evaluation sample set; step S412 of performing integrated fusion learning based on the air detection sample set, the purification regulation scheme sample set, and the purification quality evaluation sample set to establish the air purification quality prediction branch; step S413 of performing integrated fusion learning based on the air detection sample set, the purification regulation scheme sample set, and the purification regulation energy consumption evaluation sample set to establish the purification regulation energy consumption prediction branch; step S414 of performing integrated fusion learning based on the air detection sample set, the purification regulation scheme sample set, and the purification regulation noise evaluation sample set to generate the purification regulation noise prediction branch; step S415 of connecting the air purification quality prediction branch, the purification regulation energy consumption prediction branch, and the purification regulation noise prediction branch to generate the purification regulation prediction evaluation channel.

[0036] Preferably, retrieve and obtain an air detection sample set, a purification control scheme sample set, a purification quality evaluation sample set, a purification control energy consumption evaluation sample set, and a purification control noise evaluation sample set from the historical regulation evaluation records of the air purifier. The air detection sample set contains air detection data at different times and environmental conditions in history, such as the concentration of pollutants like PM2.5, CO2, formaldehyde, temperature, and humidity. The purification control scheme sample set records various control schemes adopted by the air purifier under specific air quality conditions, such as wind speed adjustment, filter selection, operation mode setting, etc. The purification quality evaluation sample set records the evaluation results of the purification effect after the air purifier actually executes under a specific control scheme. For example, the PM2.5 concentration, VOC concentration, formaldehyde concentration, etc. before and after purification. The purification control energy consumption evaluation sample set records the energy consumption data of the air purifier under different purification control schemes. For example, the power consumption in the wind speed mode, the power consumption during the operation time, etc. The purification control noise evaluation sample set records the noise level data under different purification control schemes.

[0037] Preferably, integrated fusion learning is a strategy of combining multiple models or multiple data sets for combined learning. By combining different types of data and evaluation criteria, the model can obtain more comprehensive information in multiple dimensions, thereby improving the accuracy and generalization ability of prediction. Specifically, by performing integrated fusion learning on the air detection sample set, the purification control scheme sample set, and the purification quality evaluation sample set, a branch model for predicting air purification quality is established, that is, the air purification quality prediction branch, with the goal of predicting the purification effect that the air purifier can achieve under a specific control scheme (such as the degree of reduction in PM2.5 concentration). By performing integrated fusion learning on the air detection sample set, the purification control scheme sample set, and the purification control energy consumption evaluation sample set, a branch model for predicting energy consumption is established, that is, the purification control energy consumption prediction branch, with the goal of evaluating the energy consumption performance of the purifier under different purification control schemes. By performing integrated fusion learning on the air detection sample set, the purification control scheme sample set, and the purification control noise evaluation sample set, a branch model for predicting noise is established, that is, the purification control noise prediction branch, with the goal of predicting the noise level of the air purifier under different control schemes. Finally, the three prediction branches (the air purification quality prediction branch, the purification control energy consumption prediction branch, and the purification control noise prediction branch) are connected together to form a purification control prediction and evaluation channel, which can simultaneously consider the air purification effect, energy efficiency, and noise level, and perform comprehensive evaluation according to different input data (such as air quality, control scheme) during operation, and optimize the scheme to achieve the best purification effect, the lowest energy consumption, and the minimum noise, improving the user experience and reducing resource waste.

[0038] Further, step S412 further includes step S412a of supervising and training P meta-learners based on the air detection sample set, the purification regulation scheme sample set, and the purification quality evaluation sample set to obtain P air purification quality predictors, where P is a positive integer greater than 1; step S412b of training a purification quality prediction fusion model with the output data set of the P air purification quality predictors as input information and the purification quality evaluation sample set as output information; step S412c of combining the P air purification quality predictors as parallel independent nodes to generate an air purification quality prediction model; and step S412d of combining the input layer of the air purification quality prediction model and the purification quality prediction fusion model to generate the air purification quality prediction branch.

[0039] Preferably, the method of meta-learning and ensemble learning is used to improve the prediction accuracy of the purification effect of the air purifier, including using multiple independent machine learning models (such as decision trees, neural networks, etc.) for prediction training, and finally combining their outputs to create an air purification quality prediction branch with stronger comprehensiveness and higher prediction performance. Specifically, a training prediction model is constructed based on P different meta-learners (such as decision trees, neural networks, support vector machines, etc.), and the P prediction models are supervised and trained using the air detection sample set, the purification regulation scheme sample set, and the purification quality evaluation sample set to learn how to map the input (such as real-time air detection data and regulation schemes) to the output (such as the evaluation result of the purification effect). Here, P represents the number of trained models, and P is a positive integer greater than 1, indicating that at least two models work simultaneously. Taking the output data set of the P predictors as the input and the real purification effect (purification quality evaluation sample set) as the output, the purification quality prediction fusion model is trained through the method of fusion learning, aiming to optimize the prediction accuracy by using the results of multiple predictors. For example, the purification quality prediction fusion model can reduce false predictions according to the strengths of each predictor and finally provide a more accurate prediction of the purification effect.

[0040] Preferably, the trained P air purification quality predictors are combined as independent parallel nodes. Each model independently gives a prediction result, and then these results are integrated in a certain way. For example, the voting method, weighted average method, etc. are used to combine the outputs of these predictors, and then an air purification quality prediction model is generated, which can comprehensively consider the results of multiple predictors and provide a final air purification quality prediction. Finally, by combining the input layers of the air purification quality prediction model and the purification quality prediction fusion model, the air purification quality prediction branch is generated. The air purification quality prediction branch will integrate all the trained models and data, be able to provide accurate air purification quality prediction, and provide data support for optimizing the operating parameters of the air purifier.

[0041] Step S500, determine whether the purification regulation prediction and evaluation result meets the purification regulation prediction and evaluation expectation.

[0042] Preferably, during the optimization process of the air purifier regulation strategy, the predicted purification effect is compared with the preset purification target (purification regulation prediction and evaluation expectation) to determine whether the current regulation plan is effective. Among them, the purification regulation prediction and evaluation expectation is the target value of air quality, energy efficiency, and noise preset based on actual needs and environmental conditions. For example, the air quality target is to reduce the PM2.5 concentration to a specific value (e.g., below 50 μg / m 3 ) or reduce the TVOCs concentration to the safe standard range; the energy efficiency target is to minimize energy consumption and optimize power usage while maintaining a good purification effect (e.g., reducing power consumption to meet a certain energy-saving standard); the noise target is to ensure that the operating noise of the purifier does not exceed a certain maximum value (e.g., below 40 dB) to ensure a comfortable experience for users.

[0043] Step S600, if the purification regulation prediction and evaluation result does not meet the purification regulation prediction and evaluation expectation, optimize and regulate the air purification regulation plan according to the purification regulation prediction and evaluation expectation to generate an air purification regulation strategy.

[0044] Preferably, if the purification regulation prediction and evaluation result does not meet the purification regulation prediction and evaluation expectation, for example, the purification effect is not ideal, the energy efficiency is too low, or the noise is too high, indicating that the current regulation plan needs to be optimized, then optimize and regulate the air purification regulation plan according to the purification regulation prediction and evaluation expectation. That is, when the prediction result does not reach the expectation, the current air purification regulation plan is adjusted and improved through a certain optimization method to make it as close as possible to or reach the predetermined target. For example, adjust the operating parameters (adjust the wind speed, filter type, working mode, etc.), optimize the energy efficiency (optimize the plan by reducing unnecessary energy consumption), reduce the noise (reduce the wind speed or select a quieter operating mode), change the purification mode (switch to a more powerful purification mode or change the filtration plan), and then generate an air purification regulation strategy, which integrates multiple effective parameters and operation steps, can balance other factors (such as energy efficiency, noise, etc.) while meeting the air purification requirements, and can include a combination of multiple regulation plans to dynamically adjust the working mode of the purifier according to the real-time air quality and other parameters to ensure that the air purifier can always maintain the best operating state in a changing environment.

[0045] Further, step S600 further includes step S610 of collecting the operation parameter constraint information of the air purifier and establishing a purification regulation constraint domain; step S620 of adjusting the air purification regulation scheme according to the purification regulation constraint domain to generate a purification adjustment scheme space; step S630 of extracting a first purification adjustment scheme according to the purification adjustment scheme space; step S640 of inputting the real-time air detection data and the first purification adjustment scheme into the purification regulation prediction and evaluation channel to obtain a first adjustment scheme purification prediction result; step S650 of determining whether the first adjustment scheme purification prediction result meets the purification regulation prediction and evaluation expectation; step S660 of, if the first adjustment scheme purification prediction result meets the purification regulation prediction and evaluation expectation, adding the first purification adjustment scheme to the air purification regulation strategy.

[0046] Preferably, collect the operation parameter constraint information of the air purifier, such as wind speed, filter type, working time, etc. According to these constraint information, establish a purification regulation constraint domain to define which regulation schemes are acceptable. The purification regulation constraint domain is actually a parameter space that stipulates the allowable range of various operation parameters of the air purifier. For example, the wind speed must be between 0.5 m / s and 3 m / s; the filter selection can be HEPA or activated carbon, but both cannot be selected at the same time; the energy consumption cannot exceed a certain preset standard, etc. Based on the purification regulation constraint domain, preliminarily adjust the air purification regulation scheme of the air purifier, that is, within the range of the regulation constraint domain, consider all possible regulation schemes, and then generate a purification adjustment scheme space, which includes all combinations of regulation schemes that meet the constraint domain. Then randomly select one from the purification adjustment scheme space as the first purification adjustment scheme.

[0047] Preferably, input the first purification adjustment scheme and the real-time air detection data into the purification regulation prediction and evaluation channel to predict the purification effect that the scheme can achieve in the current environment, that is, obtain the first adjustment scheme purification prediction result (whether the scheme can achieve the expected air quality improvement effect), so as to determine whether the first adjustment scheme is effective. Then compare the first adjustment scheme purification prediction result with the purification regulation prediction and evaluation expectation. If the prediction result of the first adjustment scheme can meet the expectation (for example, the PM2.5 concentration drops below the expected value), it means that the scheme is effective, and add the scheme to the final air purification regulation strategy as one of the operation modes of the air purifier. Among them, the air purification regulation strategy includes multiple effective purification adjustment schemes, which are used to guide the working mode of the air purifier in different situations, so as to achieve the best air purification effect.

[0048] Further, step S650 further includes step S651. If the purification prediction result of the first adjustment plan does not meet the purification regulation prediction evaluation expectation, the first purification adjustment plan is eliminated; step S652, according to the purification adjustment plan space, a second purification adjustment plan is extracted; step S653, the real-time air detection data and the second purification adjustment plan are input into the purification regulation prediction evaluation channel to obtain the purification prediction result of the second adjustment plan; step S654, it is judged whether the purification prediction result of the second adjustment plan meets the purification regulation prediction evaluation expectation; step S655, if the purification prediction result of the second adjustment plan meets the purification regulation prediction evaluation expectation, the second purification adjustment plan is added to the air purification regulation strategy; step S656, if the purification prediction result of the second adjustment plan does not meet the purification regulation prediction evaluation expectation, the second purification adjustment plan is eliminated, and the purification adjustment plan space is continuously optimized and iterated according to the purification regulation prediction evaluation expectation until the air purification regulation strategy is generated.

[0049] Preferably, if the purification prediction result of the first adjustment plan does not meet the purification regulation prediction evaluation expectation, for example, the purification effect does not meet the standard, the energy efficiency is too low or the noise is too high, it is considered that this adjustment plan is inappropriate, then this plan is eliminated, and then a purification adjustment plan is randomly selected from the purification adjustment plan space as the second purification adjustment plan. Similarly, the real-time air detection data and the second purification adjustment plan are input into the purification regulation prediction evaluation channel to predict how much air quality improvement the second adjustment plan can bring, and then the purification prediction result of the second adjustment plan is generated. Then, it is judged whether the purification prediction result of the second adjustment plan meets the purification regulation prediction evaluation expectation, that is, the purification prediction result of the second adjustment plan is compared with the purification regulation prediction evaluation expectation. If the purification prediction result of the second adjustment plan meets the purification regulation prediction evaluation expectation, that is, it meets the predetermined air quality, energy efficiency, noise and other targets, it means that this plan is effective, and this plan is added to the air purification regulation strategy. If the purification prediction result of the second plan does not meet the expectation, then this plan is eliminated, and other plans are continuously selected from the purification adjustment plan space for further evaluation, and iterative optimization is carried out according to the result of each evaluation (whether it meets the expectation) until an air purification regulation strategy that meets the expected target is generated, which will include a variety of effective adjustment plans, comprehensively considering factors such as air quality, energy efficiency and noise to ensure the best operation of the air purifier.

[0050] Step S700, control the air purifier according to the air purification regulation strategy.

[0051] Preferably, the operating state of the air purifier is actually controlled and adjusted according to the air purification control strategy to achieve an optimized air purification effect. The core is to convert the theoretical control strategy into actual operation instructions to ensure that the air purifier operates efficiently in the actual environment. For example, the wind speed of the air purifier is adjusted according to the air quality and pollutant concentration; the air purifier is instructed to switch to a suitable filter type according to the control strategy; the operating mode of the air purifier (such as strong mode, energy-saving mode, automatic mode, etc.) is controlled, and the additional functions of the air purifier, such as humidification, dehumidification, negative ions, etc., are enabled or disabled according to the control strategy to optimize the air quality and meet the user comfort requirements.

[0052] In the foregoing, a method for regulating the operating parameters of an air purifier according to an embodiment of the present invention was described in detail. Next, a platform for regulating the operating parameters of an air purifier according to an embodiment of the present invention will be described with reference to Figure 1 In the foregoing, a method for regulating the operating parameters of an air purifier according to an embodiment of the present invention was described in detail. Next, a platform for regulating the operating parameters of an air purifier according to an embodiment of the present invention will be described with reference to Figure 2 Describe a platform for regulating the operating parameters of an air purifier according to an embodiment of the present invention.

[0053] A platform for regulating the operating parameters of an air purifier according to an embodiment of the present invention is used to solve the technical problems existing in the prior art, such as the inflexible regulation of air purifiers and the inability to respond to changes in air quality in real time, resulting in low air purification efficiency and high energy consumption. It realizes dynamically adjusting the operating parameters of the air purifier according to real-time air quality data, and achieves the technical effect of improving air purification efficiency and reducing energy consumption. A platform for regulating the operating parameters of an air purifier includes: a real-time air detection data acquisition module 10, a purification demand evaluation module 20, an air purification control scheme acquisition module 30, a regulation prediction evaluation module 40, a prediction evaluation result judgment module 50, an air purification control strategy generation module 60, and an air purifier control module 70.

[0054] The real-time air detection data acquisition module 10 is used to acquire real-time air detection data of the target space; the purification requirement evaluation module 20 is used to evaluate the purification requirement according to the real-time air detection data and generate an air purification instruction; the air purification regulation scheme acquisition module 30 is used to activate the air purification regulation model based on the air purification instruction, input the real-time air detection data into the air purification regulation model, and obtain an air purification regulation scheme; the regulation prediction evaluation module 40 is used to perform a regulation prediction evaluation on the air purifier in the target space according to the air purification regulation scheme based on the real-time air detection data, and obtain a purification regulation prediction evaluation result; the prediction evaluation result judgment module 50 is used to judge whether the purification regulation prediction evaluation result meets the purification regulation prediction evaluation expectation; the air purification regulation strategy generation module 60 is used to, if the purification regulation prediction evaluation result does not meet the purification regulation prediction evaluation expectation, perform an optimization regulation on the air purification regulation scheme according to the purification regulation prediction evaluation expectation, and generate an air purification regulation strategy; the air purifier control module 70 is used to control the air purifier according to the air purification regulation strategy.

[0055] Next, the specific configuration of the regulation prediction evaluation module 40 will be described in detail. The regulation prediction evaluation module 40 may further include: performing a regulation evaluation record learning on the air purifier to establish a purification regulation prediction evaluation channel, where the purification regulation prediction evaluation channel includes an air purification quality prediction branch, a purification regulation energy consumption prediction branch, and a purification regulation noise prediction branch; inputting the real-time air detection data and the air purification regulation scheme into the air purification quality prediction branch to obtain a predicted air purification quality coefficient; obtaining a purification regulation energy consumption prediction coefficient according to the purification regulation energy consumption prediction branch based on the real-time air detection data and the air purification regulation scheme; inputting the real-time air detection data and the air purification regulation scheme into the purification regulation noise prediction branch to obtain a purification regulation noise prediction coefficient; and outputting the predicted air purification quality coefficient, the purification regulation energy consumption prediction coefficient, and the purification regulation noise prediction coefficient as the purification regulation prediction evaluation result.

[0056] Next, the specific configuration of the regulation prediction and evaluation module 40 will be further described in detail. The regulation prediction and evaluation module 40 may further include: retrieving the regulation evaluation records of the air purifier to obtain an air detection sample set, a purification regulation scheme sample set, a purification quality evaluation sample set, a purification regulation energy consumption evaluation sample set, and a purification regulation noise evaluation sample set; performing integrated fusion learning based on the air detection sample set, the purification regulation scheme sample set, and the purification quality evaluation sample set to establish the air purification quality prediction branch; performing integrated fusion learning based on the air detection sample set, the purification regulation scheme sample set, and the purification regulation energy consumption evaluation sample set to establish the purification regulation energy consumption prediction branch; performing integrated fusion learning based on the air detection sample set, the purification regulation scheme sample set, and the purification regulation noise evaluation sample set to generate the purification regulation noise prediction branch; connecting the air purification quality prediction branch, the purification regulation energy consumption prediction branch, and the purification regulation noise prediction branch to generate the purification regulation prediction and evaluation channel.

[0057] Next, the specific configuration of the regulation prediction and evaluation module 40 will be further described in detail. The regulation prediction and evaluation module 40 may further include: supervising and training P meta-learners based on the air detection sample set, the purification regulation scheme sample set, and the purification quality evaluation sample set to obtain P air purification quality predictors, where P is a positive integer greater than 1; using the output data set of the P air purification quality predictors as input information and the purification quality evaluation sample set as output information to train the purification quality prediction fusion model; merging the P air purification quality predictors as parallel independent nodes to generate the air purification quality prediction model; merging the input layer of the air purification quality prediction model and the purification quality prediction fusion model to generate the air purification quality prediction branch.

[0058] Next, the specific configuration of the air purification regulation strategy generation module 60 will be described in detail. The air purification regulation strategy generation module 60 may further include: collecting the operation parameter constraint information of the air purifier to establish a purification regulation constraint domain; adjusting the air purification regulation scheme according to the purification regulation constraint domain to generate a purification adjustment scheme space; extracting a first purification adjustment scheme according to the purification adjustment scheme space; inputting the real-time air detection data and the first purification adjustment scheme into the purification regulation prediction and evaluation channel to obtain a first adjustment scheme purification prediction result; determining whether the first adjustment scheme purification prediction result meets the purification regulation prediction and evaluation expectation; if the first adjustment scheme purification prediction result meets the purification regulation prediction and evaluation expectation, adding the first purification adjustment scheme to the air purification regulation strategy.

[0059] Next, the specific configuration of the air purification regulation strategy generation module 60 will be further described in detail. The air purification regulation strategy generation module 60 may further include: if the purification prediction result of the first adjustment plan does not meet the purification regulation prediction evaluation expectation, eliminating the first purification adjustment plan; extracting a second purification adjustment plan according to the purification adjustment plan space; inputting the real-time air detection data and the second purification adjustment plan into the purification regulation prediction evaluation channel to obtain a purification prediction result of the second adjustment plan; determining whether the purification prediction result of the second adjustment plan meets the purification regulation prediction evaluation expectation; if the purification prediction result of the second adjustment plan meets the purification regulation prediction evaluation expectation, adding the second purification adjustment plan to the air purification regulation strategy; if the purification prediction result of the second adjustment plan does not meet the purification regulation prediction evaluation expectation, eliminating the second purification adjustment plan, and continuing to optimize and iterate the purification adjustment plan space according to the purification regulation prediction evaluation expectation until the air purification regulation strategy is generated.

[0060] Next, the specific configuration of the purification requirement evaluation module 20 will be described in detail. The purification requirement evaluation module 20 may further include: evaluating the air quality of the target space according to the real-time air detection data to obtain a real-time air quality coefficient; performing a purification requirement evaluation on the real-time air quality coefficient according to the air quality constraint of the target space to generate an air purification requirement coefficient; determining whether the air purification requirement coefficient is greater than or equal to an air purification requirement threshold; if the air purification requirement coefficient is greater than or equal to the air purification requirement threshold, obtaining the air purification instruction.

[0061] The operation parameter regulation platform of an air purifier provided by an embodiment of the present invention can execute an air purifier operation parameter regulation method provided by any embodiment of the present invention, and has function modules and beneficial effects corresponding to the execution of the method.

[0062] Although various references are made to certain modules in the platform according to embodiments of the present application, any number of different modules can be used and run on a user terminal and / or a server. The various units and modules included are only divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0063] The above specific embodiments do not constitute a limitation to the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present application shall be included within the protection scope of the present application.

Claims

1. A method for regulating operating parameters of an air purifier, characterized in that, The method includes: Obtaining real-time air detection data of the target space; Evaluating the purification requirement according to the real-time air detection data to generate an air purification instruction; Based on the air purification instruction, activating an air purification regulation model and inputting the real-time air detection data into the air purification regulation model to obtain an air purification regulation plan; Based on the real-time air detection data, performing a regulation prediction evaluation on the air purifier in the target space according to the air purification regulation plan to obtain a purification regulation prediction evaluation result; Judging whether the purification regulation prediction evaluation result meets the purification regulation prediction evaluation expectation; If the purification regulation prediction evaluation result does not meet the purification regulation prediction evaluation expectation, performing an optimization regulation on the air purification regulation plan according to the purification regulation prediction evaluation expectation to generate an air purification regulation strategy; Controlling the air purifier according to the air purification regulation strategy; Among them, based on the real-time air detection data, performing a regulation prediction evaluation on the air purifier in the target space according to the air purification regulation plan to obtain a purification regulation prediction evaluation result, including: Performing a regulation evaluation record learning on the air purifier to establish a purification regulation prediction evaluation channel, where the purification regulation prediction evaluation channel includes an air purification quality prediction branch, a purification regulation energy consumption prediction branch, and a purification regulation noise prediction branch; Inputting the real-time air detection data and the air purification regulation plan into the air purification quality prediction branch to obtain a predicted air purification quality coefficient; Based on the real-time air detection data and the air purification regulation plan, obtaining a purification regulation energy consumption prediction coefficient according to the purification regulation energy consumption prediction branch; Inputting the real-time air detection data and the air purification regulation plan into the purification regulation noise prediction branch to obtain a purification regulation noise prediction coefficient; Outputting the predicted air purification quality coefficient, the purification regulation energy consumption prediction coefficient, and the purification regulation noise prediction coefficient as the purification regulation prediction evaluation result; Performing a regulation evaluation record learning on the air purifier to establish a purification regulation prediction evaluation channel, including: Retrieving a regulation evaluation record of the air purifier to obtain an air detection sample set, a purification regulation plan sample set, a purification quality evaluation sample set, a purification regulation energy consumption evaluation sample set, and a purification regulation noise evaluation sample set; Performing an integrated fusion learning according to the air detection sample set, the purification regulation plan sample set, and the purification quality evaluation sample set to establish the air purification quality prediction branch; Performing an integrated fusion learning according to the air detection sample set, the purification regulation plan sample set, and the purification regulation energy consumption evaluation sample set to establish the purification regulation energy consumption prediction branch; Performing an integrated fusion learning according to the air detection sample set, the purification regulation plan sample set, and the purification regulation noise evaluation sample set to generate the purification regulation noise prediction branch; Connecting the air purification quality prediction branch, the purification regulation energy consumption prediction branch, and the purification regulation noise prediction branch to generate the purification regulation prediction evaluation channel; Among them, integrated fusion learning is performed based on the air detection sample set, the purification regulation scheme sample set, and the purification quality evaluation sample set to establish the air purification quality prediction branch, including: Supervisedly training P meta-learners based on the air detection sample set, the purification regulation scheme sample set, and the purification quality evaluation sample set to obtain P air purification quality predictors, where P is a positive integer greater than 1; Using the output data set of the P air purification quality predictors as input information and the purification quality evaluation sample set as output information to train the purification quality prediction fusion model; Merging the P air purification quality predictors as parallel independent nodes to generate an air purification quality prediction model; Merging the input layer of the air purification quality prediction model and the purification quality prediction fusion model to generate the air purification quality prediction branch.

2. The operating parameter regulation method of an air purifier according to claim 1, characterized in that, If the purification regulation prediction evaluation result does not meet the purification regulation prediction evaluation expectation, perform optimization regulation on the air purification regulation scheme according to the purification regulation prediction evaluation expectation to generate an air purification regulation strategy, including: Collect the operation parameter constraint information of the air purifier to establish a purification regulation constraint domain; Adjust the air purification regulation scheme according to the purification regulation constraint domain to generate a purification adjustment scheme space; Extract a first purification adjustment scheme according to the purification adjustment scheme space; Input the real-time air detection data and the first purification adjustment scheme into the purification regulation prediction evaluation channel to obtain a purification prediction result of the first adjustment scheme; Judge whether the purification prediction result of the first adjustment scheme meets the purification regulation prediction evaluation expectation; If the purification prediction result of the first adjustment scheme meets the purification regulation prediction evaluation expectation, add the first purification adjustment scheme to the air purification regulation strategy.

3. The operating parameter regulation method of an air purifier according to claim 2, characterized in that, Judging whether the purification prediction result of the first adjustment scheme meets the purification regulation prediction evaluation expectation includes: If the purification prediction result of the first adjustment scheme does not meet the purification regulation prediction evaluation expectation, eliminate the first purification adjustment scheme; Extract a second purification adjustment scheme according to the purification adjustment scheme space; Input the real-time air detection data and the second purification adjustment scheme into the purification regulation prediction evaluation channel to obtain a purification prediction result of the second adjustment scheme; Judge whether the purification prediction result of the second adjustment scheme meets the purification regulation prediction evaluation expectation; If the purification prediction result of the second adjustment scheme meets the purification regulation prediction evaluation expectation, add the second purification adjustment scheme to the air purification regulation strategy; If the purification prediction result of the second adjustment scheme does not meet the purification regulation prediction evaluation expectation, eliminate the second purification adjustment scheme, and continue to perform optimization iteration on the purification adjustment scheme space according to the purification regulation prediction evaluation expectation until the air purification regulation strategy is generated.

4. The operating parameter regulation method of an air purifier according to claim 1, characterized in that, Generate an air purification instruction according to the real-time air detection data, including: Evaluate the air quality of the target space according to the real-time air detection data to obtain a real-time air quality coefficient; Evaluate the purification demand of the real-time air quality coefficient according to the air quality constraint of the target space, and generate an air purification demand coefficient; Determine whether the air purification demand coefficient is greater than or equal to the air purification demand threshold; If the air purification demand coefficient is greater than or equal to the air purification demand threshold, obtain the air purification instruction.

5. An operating parameter regulation platform for an air purifier, characterized in that, The platform is used to implement the operation parameter regulation method of an air purifier according to any one of claims 1 to 4. The platform includes: A real-time air detection data acquisition module, which is used to acquire real-time air detection data of the target space; A purification demand evaluation module, which is used to evaluate the purification demand according to the real-time air detection data and generate an air purification instruction; An air purification regulation scheme acquisition module, which is used to activate an air purification regulation model based on the air purification instruction, input the real-time air detection data into the air purification regulation model, and obtain an air purification regulation scheme; A regulation prediction evaluation module, which is used to perform a regulation prediction evaluation on the air purifier in the target space according to the air purification regulation scheme based on the real-time air detection data, and obtain a purification regulation prediction evaluation result; A prediction evaluation result judgment module, which is used to judge whether the purification regulation prediction evaluation result meets the purification regulation prediction evaluation expectation; An air purification regulation strategy generation module, which is used to optimize the air purification regulation scheme according to the purification regulation prediction evaluation expectation if the purification regulation prediction evaluation result does not meet the purification regulation prediction evaluation expectation, and generate an air purification regulation strategy; An air purifier control module, which is used to control the air purifier according to the air purification regulation strategy.

Images