Air conditioner and self-cleaning control method, device, storage medium and program product thereof

Abstract

The application provides an air conditioner and a self-cleaning control method, device, storage medium and program product thereof, and belongs to the field of energy-saving refrigeration and air conditioning equipment. The method comprises the following steps: acquiring the type and concentration of microorganisms in an indoor environment, and acquiring working condition data of the air conditioner; inputting the type and concentration of the microorganisms and the working condition data into a pre-trained prediction model to predict a microorganism proliferation curve in a future preset time; judging whether the microorganism concentration value will exceed a preset threshold in the future preset time according to the predicted microorganism proliferation curve in the future preset time; and if it is judged that the microorganism concentration value will exceed the preset threshold in the future preset time, performing self-cleaning of the air conditioner. The scheme provided by the application can avoid the problems of incomplete cleaning or overcleaning caused by the fact that the single microorganism detection quantity is not targeted for directional cleaning.

Description

Technical Field

[0001] This invention relates to the field of control, and more particularly to an air conditioner and its self-cleaning control method, device, storage medium and program product, belonging to energy-saving refrigeration and air conditioning equipment. Background Technology

[0002] With increasing health awareness, indoor air quality is receiving more and more attention. Air conditioners, as air handling equipment, are highly susceptible to the growth of mold, bacteria, viruses, and other microorganisms in their internal components such as evaporators and filters. This not only affects air quality but can also trigger respiratory illnesses, allergic reactions, and other health problems. Furthermore, if these microorganisms inside air conditioners are not cleaned promptly, they can lead to a decrease in cooling or heating capacity. Therefore, self-cleaning technology for air conditioners has become a key focus of industry research and development. However, many existing self-cleaning technologies focus on a uniform cleaning strategy, such as initiating the same cleaning procedure (e.g., strong ultraviolet irradiation) for all detected microorganisms, without targeted cleaning. This can lead to incomplete cleaning or over-cleaning, resulting in energy consumption issues. Summary of the Invention

[0003] The main objective of this invention is to overcome the deficiencies of the aforementioned related technologies and provide an air conditioner and its self-cleaning control method, device, storage medium, and program product, which belong to energy-saving refrigeration and air conditioning equipment, in order to solve the problem that the self-cleaning technology of air conditioners in the related technologies focuses on the detection of a single microorganism and does not perform targeted cleaning.

[0004] The present invention provides a self-cleaning control method for an air conditioner, comprising: acquiring the types and concentrations of microorganisms in an indoor environment, and acquiring the operating condition data of the air conditioner; inputting the acquired types and concentrations of microorganisms and the operating condition data into a pre-trained prediction model to predict the microbial proliferation curve within a preset time period; and determining whether the microbial concentration value will exceed a preset threshold within the preset time period based on the predicted microbial proliferation curve within the preset time period.

[0005] If it is determined that the concentration of microorganisms will exceed a preset threshold within a preset time in the future, the air conditioner will perform self-cleaning based on the identification of one or more types of microorganisms in the indoor environment.

[0006] Optionally, obtaining the types and concentrations of microorganisms in the indoor environment includes: collecting spectral data of microorganisms in the indoor environment; and inputting the acquired spectral data into a pre-trained recognition model to identify the types and concentrations of microorganisms in the indoor environment.

[0007] Optionally, if it is determined that the microbial concentration value will exceed a preset threshold within a preset time in the future, the self-cleaning of the air conditioner is performed, including: if it is determined that the microbial concentration value will exceed the preset threshold within a preset time in the future, and the current time period is within a preset period, then the self-cleaning is scheduled to be performed; if it is determined that the microbial concentration value will exceed the preset threshold within a preset time in the future, and the current time period is not within a preset period, then the self-cleaning is performed immediately.

[0008] Optionally, scheduling self-cleaning includes: determining the time for self-cleaning based on the predicted time when the microbial concentration value exceeds a preset threshold and the preset time period; and performing self-cleaning of the air conditioner when the determined time for self-cleaning arrives.

[0009] Optionally, the self-cleaning of the air conditioner is performed based on the identification of one or more types of microorganisms in the indoor environment, including: if only one type of microorganism is identified in the indoor environment, a first cleaning mode is executed; if two or more types of microorganisms are identified in the indoor environment, a second cleaning mode is executed; executing the first cleaning mode includes: performing a corresponding self-cleaning operation based on the identified types of microorganisms in the indoor environment; executing the second cleaning mode includes: calculating the risk weighted scores of the two or more identified microorganisms based on their concentrations and risk weights; determining the primary risk source among the two or more microorganisms based on their calculated risk weighted scores, wherein the microorganism with the highest risk weighted score is determined as the primary risk source; first performing self-cleaning on the determined primary risk source, then recalculating the risk weighted scores of other types of microorganisms among the two or more microorganisms, and performing self-cleaning based on the calculated risk weighted scores.

[0010] Optionally, it also includes: sending a linkage control command to the purification device in the environment through the gateway device to control the purification device to start purifying the air.

[0011] Optionally, the method further includes: before the purification device completes air purification, collecting the concentration of microorganisms in the indoor environment; calculating the concentration decrease rate of microorganisms in the indoor environment, and determining whether to extend the purification time of the purification device based on the concentration decrease rate; wherein, if the concentration decrease rate is less than a first preset decrease rate threshold, the purification time is extended by a preset time; if the concentration decrease rate is greater than a second preset decrease rate threshold, the purification device is turned off, and the air purification ends.

[0012] Optionally, the method further includes: after the air purification device has finished purifying the air, detecting the indoor ambient humidity; determining whether the indoor ambient humidity needs to be increased based on the detected indoor ambient humidity; if it is determined that the indoor ambient humidity needs to be increased, sending a linkage control command to the humidifier in the environment through the gateway device to control the humidifier to turn on and increase the indoor ambient humidity; wherein, if the detected indoor ambient humidity is lower than a first preset humidity threshold, it is determined that the indoor ambient humidity needs to be increased, and the humidifier is turned on; if the detected indoor ambient humidity is not lower than the first preset humidity threshold, it is determined that the indoor ambient humidity does not need to be increased; after the humidifier is turned on, if the detected indoor ambient humidity is higher than a second preset humidity threshold, the humidifier is turned off and humidification is stopped.

[0013] Optionally, the method further includes: after the self-cleaning of the air conditioner is completed, acquiring the concentration of microorganisms in the indoor environment again; calculating the microorganism removal rate before and after self-cleaning based on the acquired concentrations in the indoor environment before and after self-cleaning; determining whether the air conditioner filter needs to be cleaned based on whether the calculated microorganism removal rate reaches a preset removal rate threshold; wherein, if the calculated microorganism removal rate reaches the preset removal rate threshold, it is determined that the air conditioner filter does not need to be cleaned; if the calculated microorganism removal rate does not reach the preset removal rate threshold, it is determined that the air conditioner filter needs to be cleaned.

[0014] Optionally, it further includes: monitoring the pressure difference between the air inlet side and the air outlet side of the air conditioner's filter, and calculating the pressure difference attenuation rate between the air inlet side and the air outlet side of the filter; if the calculated pressure difference attenuation rate is greater than a preset attenuation rate threshold, then it is determined that the filter needs to be replaced.

[0015] Another aspect of the present invention provides a self-cleaning device for an air conditioner, comprising: an acquisition unit for acquiring the types and concentrations of microorganisms in an indoor environment and acquiring the operating condition data of the air conditioner; a prediction unit for inputting the types and concentrations of microorganisms acquired by the acquisition unit and the operating condition data into a pre-trained prediction model to predict a microbial proliferation curve within a preset future time period; a judgment unit for judging whether the microbial concentration value will exceed a preset threshold within a preset future time period based on the microbial proliferation curve predicted by the prediction unit; and an execution unit for executing the self-cleaning of the air conditioner if the judgment unit judges that the microbial concentration value will exceed the preset threshold within a preset future time period, based on the identification of one or more types of microorganisms in the indoor environment.

[0016] Optionally, the acquisition unit acquires the types and concentrations of microorganisms in the indoor environment by: collecting spectral data of microorganisms in the indoor environment; and inputting the acquired spectral data into a pre-trained recognition model to identify the types and concentrations of microorganisms in the indoor environment.

[0017] Optionally, if the judgment unit determines that the microbial concentration value will exceed a preset threshold within a preset time in the future, the execution unit performs self-cleaning of the air conditioner, including: if it is determined that the microbial concentration value will exceed the preset threshold within a preset time in the future, and the current time period is within a preset period, then schedule the self-cleaning; if it is determined that the microbial concentration value will exceed the preset threshold within a preset time in the future, and the current time period is not within a preset period, then immediately perform self-cleaning.

[0018] Optionally, the execution unit, based on the identification of one or more types of microorganisms in the indoor environment, schedules self-cleaning, including: determining the self-cleaning time based on the predicted time when the microorganism concentration value exceeds a preset threshold and the preset time period; and executing the self-cleaning of the air conditioner when the determined self-cleaning time arrives.

[0019] Optionally, the execution unit performs self-cleaning of the air conditioner, including: if only one type of microorganism is identified in the indoor environment, a first cleaning mode is executed; if two or more types of microorganisms are identified in the indoor environment, a second cleaning mode is executed; executing the first cleaning mode includes: performing a corresponding self-cleaning operation according to the identified types of microorganisms in the indoor environment; executing the second cleaning mode includes: calculating the risk weighted scores of the two or more microorganisms respectively based on the concentration and risk weight of the two or more identified microorganisms; determining the primary risk source among the two or more microorganisms based on the calculated risk weighted scores, wherein the microorganism with the highest risk weighted score is determined as the primary risk source; first performing self-cleaning on the determined primary risk source, then recalculating the risk weighted scores of other types of microorganisms among the two or more microorganisms, and performing self-cleaning based on the calculated risk weighted scores.

[0020] Optionally, it also includes: a control unit, used to send a linkage control command to the purification device in the environment through the gateway device, so as to control the purification device to start purifying the air.

[0021] Optionally, it further includes: a data acquisition unit, configured to acquire the concentration of microorganisms in the indoor environment before the control unit controls the purification device to complete the air purification; a first determination unit, configured to calculate the concentration decrease rate of microorganisms in the indoor environment, and determine whether to extend the purification time of controlling the purification device to purify the air based on the concentration decrease rate; wherein, if the concentration decrease rate is less than a first preset decrease rate threshold, the purification time is extended by a preset time; the control unit is further configured to: if the concentration decrease rate is greater than a second preset decrease rate threshold, control the purification device to turn off, and the air purification ends.

[0022] Optionally, it further includes: a detection unit, configured to detect indoor ambient humidity after the air purification device has finished purifying the air; a second determination unit, configured to determine whether it is necessary to increase the indoor ambient humidity based on the indoor ambient humidity detected by the detection unit; wherein, if the detection unit detects that the indoor ambient humidity is lower than a first preset humidity threshold, it determines that it is necessary to increase the indoor ambient humidity and controls the humidifier to turn on; if the detection unit detects that the indoor ambient humidity is not lower than the first preset humidity threshold, it determines that it is not necessary to increase the indoor ambient humidity; the control unit is further configured to: if the determination unit determines that it is necessary to increase the indoor ambient humidity, send a linkage control command to the humidifier in the environment through the gateway device to control the humidifier to turn on and increase the indoor ambient humidity; after controlling the humidifier to turn on, if the detection unit detects that the indoor ambient humidity is higher than the second preset humidity threshold, it controls the humidifier to turn off and stop humidification.

[0023] Optionally, the acquisition unit is further configured to: acquire the concentration of microorganisms in the indoor environment again after the self-cleaning of the air conditioner is completed; the device further includes: a calculation unit, configured to calculate the microorganism removal rate before and after the self-cleaning based on the acquired concentrations in the indoor environment before and after the self-cleaning; and a third determination unit, configured to determine whether the air conditioner filter needs to be cleaned based on whether the microorganism removal rate calculated by the calculation unit reaches a preset removal rate threshold; wherein, if the microorganism removal rate calculated by the calculation unit reaches the preset removal rate threshold, it is determined that the air conditioner filter does not need to be cleaned; if the microorganism removal rate calculated by the calculation unit does not reach the preset removal rate threshold, it is determined that the air conditioner filter needs to be cleaned.

[0024] Optionally, it further includes: a monitoring unit, used to monitor the pressure difference between the air inlet side and the air outlet side of the air conditioner's filter, and calculate the pressure difference attenuation rate between the air inlet side and the air outlet side of the filter; and a fourth determining unit, used to determine that the filter needs to be replaced if the calculated pressure difference attenuation rate is greater than a preset attenuation rate threshold.

[0025] In another aspect, the present invention provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the methods described above.

[0026] In another aspect, the present invention provides an air conditioner, including a processor, a memory, and a computer program stored in the memory that can run on the processor, wherein the processor executes the program to implement the steps of any of the methods described above.

[0027] In another aspect, the present invention provides an air conditioner including any of the aforementioned self-cleaning control devices.

[0028] In another aspect, the present invention provides a computer program product, including a computer program that, when executed by a processor, implements the steps of any of the methods described above.

[0029] According to the technical solution of the present invention, by identifying the types and concentrations of microorganisms in the indoor environment and combining the operating data of the air conditioner, it is predicted whether the microorganism concentration value will exceed a preset threshold within a preset time in the future. If it is determined that the microorganism concentration value will exceed the preset threshold within a preset time in the future, self-cleaning is performed according to the identified microorganism types. This achieves the identification of different microorganism types, and different self-cleaning modes are executed according to whether the identification result is a single microorganism or multiple microorganisms. This avoids the problem of incomplete or over-cleaning caused by focusing on the detection quantity of a single microorganism without targeted cleaning, ensuring thorough sterilization, improving cleaning efficiency, and having an energy-saving effect.

[0030] According to the technical solution of the present invention, based on the multi-dimensional operating condition data of the air conditioner and the identified microbial types and concentrations, a predictive model is used to predict the microbial proliferation curve within a preset time period in the future. Based on the microbial proliferation curve, it is determined whether the microbial concentration value will exceed a preset threshold within the preset time period in the future. If it is predicted that the microbial proliferation will exceed the preset threshold within the preset time period in the future, the microbial proliferation situation can be predicted in advance. Furthermore, depending on whether the current time is within a preset time period, it is determined whether to schedule self-cleaning or to perform self-cleaning immediately. Based on the time when the microbial concentration value exceeds the preset threshold and the preset time period, the time for performing self-cleaning is determined, thereby enabling preventive self-cleaning.

[0031] According to the technical solution of the present invention, depending on whether the identified microorganisms are one or multiple, a dedicated cleaning mode (first cleaning mode) for cleaning specific microorganism types or a graded cleaning mode based on microorganism risk priority (second cleaning mode) is executed, which solves the problems of incomplete sterilization and energy consumption caused by over-sterilization, and ensures efficient and accurate cleaning results.

[0032] According to the technical solution of the present invention, the microbial species are identified by collecting spectral data of microorganisms and inputting it into a pre-trained identification model, thereby achieving the matching of a customized cleaning solution, avoiding over-sterilization caused by "treating bacteria with virus standards", and thus also having an energy-saving effect.

[0033] According to the technical solution of the present invention, when two or more microorganisms are identified, the main risk source is determined by calculating the risk weight score of each microorganism. Self-cleaning is first performed on the main risk source, and then the risk weight scores of other types of microorganisms are recalculated. Self-cleaning is then performed based on the calculated risk weight scores, thereby improving cleaning efficiency and ensuring thorough sterilization.

[0034] According to the technical solution of the present invention, after self-cleaning, a linkage control command is sent to the purification equipment in the environment through the gateway device to control the purification equipment to purify the air, avoiding the possibility that air conditioning spray and high-temperature heating may shake off some biofilm and enter the air, causing secondary pollution. The purification time is extended by calculating the concentration reduction rate before and after purification to avoid incomplete purification.

[0035] According to the technical solution of the present invention, after the air is purified, it is determined whether humidification is needed based on the indoor ambient humidity. If humidification is needed, a linkage control command is sent to the humidification device in the environment through the gateway device to control the humidification device to turn on and increase the indoor ambient humidity. This avoids the indoor environment from drying out due to self-cleaning by heating or other methods, which would affect user comfort. Humidification is stopped when the humidity reaches a certain value, thereby preventing the growth of microorganisms due to dampness.

[0036] According to the technical solution of the present invention, the microbial removal rate after the self-cleaning process is completed is calculated, and whether the air conditioner filter needs to be cleaned is determined based on whether the microbial removal rate reaches the removal rate threshold. Therefore, the present invention can further determine the cleanliness of the filter, thereby cleaning the filter in a timely manner and avoiding affecting the cleanliness of the indoor environment and the health of users.

[0037] According to the technical solution of the present invention, by monitoring the pressure difference between the air inlet side and the air outlet side of the filter and calculating the pressure difference attenuation rate, it is determined whether the filter needs to be replaced based on whether the pressure difference attenuation rate is greater than a preset attenuation rate threshold, so that the filter can be replaced in a timely manner to avoid affecting the cleanliness of the indoor environment and the health of users.

[0038] According to the technical solution of the present invention, the linkage purification equipment targets sterilization and the humidifier adjusts humidity, forming a closed loop of "cleaning → sterilization → humidity adjustment → feedback", which prevents environmental imbalance after cleaning and ensures continuous and stable air quality throughout the house. Attached Figure Description

[0039] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this invention, illustrate exemplary embodiments of the invention and are used to explain the invention, but do not constitute an undue limitation of the invention. In the drawings:

[0040] Figure 1 This is a schematic diagram of an embodiment of the self-cleaning control method for air conditioners provided by the present invention;

[0041] Figure 2 This is a schematic diagram of another embodiment of the self-cleaning control method for air conditioners provided by the present invention;

[0042] Figure 3 This is a system architecture diagram of the present invention;

[0043] Figure 4 This is a schematic diagram of a specific embodiment of the self-cleaning control method for air conditioners provided by the present invention;

[0044] Figure 5 This is a structural block diagram of an embodiment of the self-cleaning control device for an air conditioner provided by the present invention;

[0045] Figure 6 This is a structural block diagram of another embodiment of the self-cleaning control device for air conditioners provided by the present invention. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0047] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0048] Many air conditioner self-cleaning technologies focus on a uniform cleaning strategy, such as initiating the same cleaning program (e.g., strong ultraviolet irradiation) for all detected microorganisms, without targeted cleaning. This may lead to energy consumption problems due to incomplete or excessive cleaning of the system.

[0049] Furthermore, if the ambient humidity is too high or pathogens remain in the air after cleaning, the self-cleaning method of air conditioners operating in isolation has the problem of incomplete cleaning. It also lacks integration with external devices such as air purifiers, failing to achieve a closed-loop management system for "whole-house health." Therefore, there is an urgent need for an intelligent closed-loop system capable of targeted self-cleaning based on microbial species identification and multi-device linkage, enabling a paradigm shift from "passive cleaning" to "proactive prevention and control."

[0050] This invention provides a self-cleaning control method for air conditioners.

[0051] Figure 1 This is a schematic diagram of an embodiment of the self-cleaning control method for air conditioners provided by the present invention.

[0052] like Figure 1 As shown, according to an embodiment of the present invention, the self-cleaning control method of the air conditioner includes at least steps S110, S120, S130 and S140.

[0053] Step S110: Obtain the types and concentrations of microorganisms in the indoor environment, and obtain the operating data of the air conditioner.

[0054] In one specific implementation, spectral data of microorganisms in an indoor environment are collected; the acquired spectral data is input into a pre-trained recognition model to identify the types and concentrations of microorganisms in the indoor environment.

[0055] Specifically, spectral data of microorganisms in the indoor environment can be collected using a multispectral sensor. The multispectral sensor has a fluorescence excitation unit. By exciting microbial samples in the indoor environment, the multispectral sensor collects their reflectance or absorption spectral characteristics, i.e., spectral data.

[0056] In one specific embodiment, a multispectral sensor can be installed at the air conditioner return air vent to collect spectral data of microorganisms in the indoor environment. When air flows through the return air vent, the multispectral sensor integrated at the air conditioner return air vent excites the microorganisms in the air using a fluorescence excitation unit, and the multispectral sensor collects the reflectance or absorption spectral characteristics.

[0057] After preprocessing the collected spectral data (e.g., denoising and normalization), it is input into a pre-trained recognition model to identify the types and concentrations of microorganisms in the indoor environment. Specifically, the types of microorganisms may include at least one of molds, bacteria, and viruses.

[0058] The identification model can specifically be a convolutional neural network (CNN) model. That is, a pre-trained CNN model is used to identify the types of microorganisms. Based on the multispectral fluorescence excitation mechanism, different microorganisms have different cell wall components, metabolites, and nucleic acid structures, resulting in differences in the wavelengths (spectral characteristics) of their absorption and emission of fluorescence. For example, molds typically contain melanin or specific pigments, exhibiting unique emission peaks under specific ultraviolet excitation; the protein and nucleic acid structures of bacteria or viruses have characteristic absorption or scattering in specific wavelength bands. Therefore, a pre-trained CNN model can be used to identify the types of microorganisms. Specifically, labeled samples of spectral data (reflectance spectra or absorption spectra) of different types of microorganisms are obtained. The acquired spectral data labeled samples are then used to train the CNN model, resulting in an identification model for recognizing the types and concentrations of microorganisms.

[0059] The identification model has a classification branch and a regression branch. The classification branch is used to identify the species of microorganisms, and the regression branch is used to identify the concentration of each species. Spectral data is treated as a special type of image or time-series signal. Feature fingerprints are extracted through the classification branch of a convolutional neural network and mapped to different microbial categories. Feature fingerprints refer to the unique spectral waveform patterns of microorganisms. Different microorganisms exhibit unique absorption valleys or emission peaks under specific excitation light due to differences in cell wall composition, metabolites, and nucleic acid structure. Convolutional neural networks (such as lightweight CNNs) automatically filter out these discriminative local waveform features, i.e., feature fingerprints, by sliding the convolutional layers through the input spectrum. The selected spectral feature vectors are then quantitatively mapped to different microbial species labels through mathematical calculations. Specifically, the Convolutional Neural Network (CNN) extracts the feature fingerprints (such as peak positions and valley depths) of each microbial species from the spectral data; the feature fingerprints are converted into feature vectors and projected into the probability space composed of each microbial species. That is, if there are N types of microorganisms in the actual application scenario, they are projected into an N-dimensional probability space; then, normalization mapping is performed through an activation function (e.g., the softmax activation function) to obtain the probability value belonging to each species. The species with the highest probability value is selected as the recognition result. If the highest probability value is lower than a preset probability threshold or there are multiple species with probability values ​​exceeding the preset probability threshold, they are marked as two or more microorganisms coexisting.

[0060] The regression branch in the convolutional neural network can identify the concentration value of each microbial species and output the microbial species identifier, concentration value, and whether two or more microorganisms coexist. For example, 0 indicates the presence of a single microorganism, and 1 indicates the presence of two or more microorganisms.

[0061] The specific operating data may include: indoor ambient temperature, indoor ambient humidity, air conditioner usage status and operating time, and filter fan speed. Real-time data collection of current indoor ambient temperature, indoor ambient humidity, air conditioner usage status and operating time, and filter fan speed is implemented.

[0062] Step S120: The identified types and concentrations of the microorganisms and the acquired operating condition data are input into a pre-trained prediction model to predict the microbial proliferation curve within a preset time period.

[0063] Ambient temperature determines the reproduction rate of microorganisms by regulating the catalytic activity of intracellular enzymes. Microbial enzyme activity and reproduction rate have an exponential relationship, involving the growth rate constant, which accelerates exponentially with increasing temperature. Water activity is crucial for microbial survival; higher humidity leads to faster proliferation and a larger predicted growth slope. Air conditioning usage status (on / off state), long-term shutdown leading to filter dust accumulation (favorable for microbial growth), and longer air conditioning operation resulting in heavier filter loads are all input into the model as initial concentration baselines and disturbance factors. Filter velocity (air velocity = airflow / filter area) is used as an environmental feature input because it affects the deposition efficiency of microorganisms on the filter surface. Filter velocity determines the total amount of microorganisms passing through the return air vent per unit time and is used as a correction coefficient input into the model.

[0064] The prediction model is used to predict the microbial proliferation curve within a preset time period. The prediction model can be, for example, an LSTM (Long Short-Term Memory) network model.

[0065] The model architecture includes an input layer, a core layer, and an output layer. The input layer receives multidimensional environmental feature vectors from the past T time steps (e.g., sampling once every 5 minutes in 1 hour). The core layer adopts a gated recurrent unit structure and uses its memory unit to capture the time dependence of environmental parameters. The output layer directly regresses the concentration values ​​of each type of microorganism within a preset time in the future, thereby outputting the proliferation curves of each type of microorganism within the preset time in the future, i.e., the curves of microbial concentration change over time.

[0066] Step S130: Based on the predicted microbial proliferation curve within a preset future time period, determine whether the microbial concentration value will exceed a preset threshold within the preset future time period.

[0067] Step S140: If it is determined that the microbial concentration value will exceed the preset threshold within a preset time in the future, then the self-cleaning of the air conditioner is performed based on the identification of one or more types of microorganisms in the indoor environment.

[0068] Specifically, based on the predicted microbial proliferation curve within a preset future time period, it is determined whether the microbial concentration value will exceed a preset threshold within the preset future time period, i.e., whether it will exceed the standard. If it is determined that the microbial concentration value will not exceed the preset threshold within the preset future time period, the self-cleaning of the air conditioner will not be performed; if it is determined that the microbial concentration value will exceed the preset threshold within the preset future time period, the self-cleaning of the air conditioner will be performed.

[0069] If it is determined that the microbial concentration will exceed a preset threshold within a preset time period in the future, and the current time period is within a preset time period, then self-cleaning will be scheduled to be performed; if it is determined that the microbial concentration will exceed a preset threshold within a preset time period in the future, and the current time period is not within a preset time period, then self-cleaning will be performed immediately.

[0070] The preset time period can specifically be a non-core usage period. This preset time period can be determined based on a combination of user behavior data statistics (such as usage time analysis of smart home platforms) and human physiological patterns (sleep cycles), identifying time periods when the user is asleep, less active, has a low breathing rate, and is less sensitive to air disturbances, such as nighttime. For example, the period from 00:00 to 6:00 AM. Different users can be assigned different non-core time periods. Users can set their own non-core time periods, or the non-core time periods can be determined based on different users' historical behavior data (such as historical sleep time).

[0071] For example, the system determines whether the microbial concentration will exceed the limit within the next 12 hours. If it determines that the concentration will not exceed the limit, self-cleaning will not be triggered, and monitoring will continue. If it determines that the microbial concentration will exceed the limit, and this occurs during a non-core usage period, self-cleaning will be scheduled to perform to avoid disturbing users' rest during non-core periods. If this does not occur during non-core periods, cleaning will be triggered immediately. For example, if the prediction shows that the mold concentration will exceed 80 CFU / m³ within 8 hours, and the current time is during the non-core usage period of 00:00–6:00 AM, then self-cleaning will be scheduled.

[0072] The scheduled self-cleaning process includes: determining the self-cleaning time based on the predicted time when the microbial concentration value exceeds a preset threshold and the preset time period; and performing self-cleaning on the air conditioner when the determined self-cleaning time arrives. In one specific embodiment, if the predicted time when the microbial concentration value exceeds the preset threshold is not within the preset time period, the end time of the current preset time period is determined as the self-cleaning time; that is, self-cleaning is performed when the current time exceeds the preset time period. If the predicted time when the microbial concentration value exceeds the preset threshold is within the preset time period, self-cleaning is performed before the predicted time when the microbial concentration value exceeds the preset threshold. The self-cleaning is performed within a set duration before the predicted time when the microbial concentration value exceeds the preset threshold, where the set duration is a pre-set self-cleaning execution duration.

[0073] Specifically, cleaning instructions can be written into a task queue, and an execution time window can be determined. This is an intelligent scheduling strategy based on a time window, rather than a simple delayed execution. By calculating the overlap between the predicted time exceeding a preset threshold and non-core usage periods (preset periods), the execution time is determined, avoiding self-cleaning during non-core usage periods (preset periods) and thus preventing disruption to user rest.

[0074] For example, if it is predicted that the microbial concentration will exceed a preset threshold within 8 hours at a certain point in time, and the period after 8 hours falls within the non-core usage period of 00:00–6:00, then a cleaning task will be scheduled. If it does not fall within the non-core usage period, cleaning will be triggered immediately.

[0075] In one specific implementation, the air conditioner performs self-cleaning based on whether the identified indoor environment contains one or more types of microorganisms. Specifically, this may include: if the identified indoor environment contains only one type of microorganism, then a first cleaning mode is executed; if the identified indoor environment contains two or more types of microorganisms, then a second cleaning mode is executed.

[0076] The first cleaning mode, i.e., the dedicated cleaning mode, executes a corresponding self-cleaning operation based on the identified types of microorganisms in the indoor environment. Different types of microorganisms correspond to different self-cleaning operations. For example, for mold, high-temperature sterilization and / or ultraviolet sterilization are used for self-cleaning. Based on the principle that high temperature can destroy spore structure and ultraviolet light can inactivate residues, thus synergistically removing biofilm, the heating module can be activated for high-temperature heating (e.g., heating to 75°C for 15 minutes) to kill heat-resistant molds in conjunction with ultraviolet light. For viruses, ultraviolet light irradiation can be used to kill viruses. Based on the principle that ultraviolet light can directly destroy nucleic acids, ultraviolet light irradiation is activated for a certain period of time (e.g., 10 minutes) to inactivate viruses. For bacteria, ozone sterilization and / or plasma sterilization are used for self-cleaning. Ozone and plasma can penetrate cell membranes; for example, the ozone generator can be activated while the plasma generator is simultaneously turned on to clean bacteria. Preferably, after the self-cleaning is completed, the spray system is activated to rinse the surface of the evaporator and remove residual biofilm.

[0077] The second cleaning mode is a graded cleaning mode that identifies two or more microorganisms and performs cleaning according to the risk weighting of the two or more microorganisms. In one specific embodiment, executing the second cleaning mode includes steps S1 to S3.

[0078] Step S1: Calculate the risk weighted score of each of the two or more identified microorganisms based on their concentration and risk weight.

[0079] Different types of microorganisms correspond to different risk weights. For example, Table 1 shows the risk weights corresponding to molds, bacteria, and viruses, where the risk weights are represented by 1 to 10, with larger values ​​indicating higher risk weights.

[0080] Table 1

[0081]

[0082] The risk-weighted score for each of the two or more identified microorganisms can be calculated using the following formula:

[0083] Risk-weighted score = concentration × risk weight

[0084] Step S2: Based on the calculated risk weighted scores of the two or more microorganisms, determine the primary risk source among the two or more microorganisms, wherein the microorganism with the highest risk weighted score is determined as the primary risk source, and the other types of microorganisms are secondary risk sources.

[0085] Step S3: First, perform self-cleaning for the identified main risk source, then recalculate the risk weighting scores of other types of microorganisms among the two or more microorganisms, and perform self-cleaning based on the calculated risk weighting scores.

[0086] Specifically, a self-cleaning operation can be performed based on the type of microorganisms of the primary risk source. The specific execution method can be referred to the first cleaning mode described above, and will not be repeated here. After performing self-cleaning on the primary risk source, the risk weighting scores of other types of microorganisms among the two or more identified microorganisms are recalculated, and self-cleaning is performed based on the calculated risk weighting scores.

[0087] In one specific implementation, the risk weighting scores of other types of microorganisms are recalculated and summed to obtain the comprehensive risk value of the other types of microorganisms. If the comprehensive risk value is less than a preset safety threshold, it indicates that the comprehensive risk of the remaining microorganisms is within a safe range, and the cleaning task is terminated. Otherwise, a targeted cleaning plan is executed for the secondary risk source, that is, the corresponding self-cleaning operation is executed according to the type of microorganism.

[0088] In another specific implementation, the risk weighting scores of other types of microorganisms are recalculated, and it is determined whether the risk weighting score of each type of microorganism is less than the corresponding preset safety threshold (different types of microorganisms correspond to different preset safety thresholds). If the risk weighting score of each type of microorganism is less than the corresponding preset safety threshold, the cleaning task is terminated. If it is determined that there are microorganisms among other types of microorganisms with a risk weighting score greater than or equal to the corresponding preset safety threshold, a targeted cleaning plan is executed, that is, self-cleaning is performed on microorganisms with a risk weighting score greater than or equal to the corresponding preset safety threshold.

[0089] Considering that a single cleaning solution cannot avoid the energy consumption problem caused by over-sterilization—for example, if the highest-requirement cleaning method is started based on mold as the standard, it would be over-cleaning for viruses and bacteria, wasting energy and accelerating equipment aging—different self-cleaning operations are corresponding to different types of microorganisms. For example, for mold, high-temperature sterilization and / or ultraviolet sterilization are used for self-cleaning. Based on the principle that high temperature can destroy spore structure and ultraviolet light can inactivate residues, thus synergistically removing biofilm, high-temperature heating (e.g., heating to 75°C for 15 minutes) can be started, combined with ultraviolet light to kill heat-resistant mold. For viruses, ultraviolet irradiation can be used to kill viruses. Based on the principle that ultraviolet light can directly destroy nucleic acids, ultraviolet light (254nm) can be started for 10 minutes to inactivate viruses. For bacteria, ozone sterilization and / or plasma sterilization are used for self-cleaning. Ozone and plasma can penetrate cell membranes; for example, an ozone generator can be started while a plasma generator is turned on to clean bacteria. Preferably, after the self-cleaning is completed, a spray system is started to rinse the evaporator surface and remove residual biofilm.

[0090] Figure 2This is a schematic diagram of another embodiment of the self-cleaning control method for air conditioners provided by the present invention.

[0091] like Figure 2 As shown, according to another embodiment of the present invention, the self-cleaning control method of the air conditioner further includes step S150.

[0092] Step S150: Send a linkage control command to the purification device in the environment through the gateway device to control the purification device to start purifying the air.

[0093] Air conditioner self-cleaning mainly works in closed systems and is difficult to cover the entire room. Therefore, it can be linked with the purification equipment in the room for deep purification. In addition, the air conditioner spray and high temperature may shake off some biofilm into the air. If it is not adsorbed and inactivated by the purifier in time, it will cause secondary pollution.

[0094] In one specific embodiment, the purification device is controlled to purify the air based on the identified type of microorganism. If only one type of microorganism is identified in the indoor environment, and the identified microorganism is mold, the purification device is controlled to activate its filter and photocatalyst. If the identified microorganism is a virus or bacteria, the purification device is controlled to activate its plasma generator to capture aerosols and to activate ultraviolet sterilization (e.g., a UV-C band ultraviolet germicidal lamp, i.e., an ultraviolet band with a wavelength range of 200nm to 280nm, preferably 253.7nm) to kill viruses or bacteria.

[0095] For example, a linkage command can be sent to a smart gateway via a wireless communication module (such as a Wi-Fi module) to activate the air purifier for targeted sterilization and deep air purification. Targeted sterilization dynamically adjusts the purifier's cleaning strategy based on the identified microorganisms. If mold is identified, the focus is on physical interception and chemical degradation, controlling the purifier to activate the filter (e.g., a HEPA H13 filter) to physically intercept spores, while simultaneously controlling the photocatalytic device to decompose mycotoxins and spore proteins. If viruses / bacteria are identified, physical field forces and photochemical effects are used to rapidly inactivate active pathogens, instructing the purifier to activate the plasma module to actively capture tiny aerosols, and the UV-C lamp to directly destroy nucleic acids.

[0096] If two or more types of microorganisms are identified in the indoor environment, the full-function mode will be activated. Specifically, if multiple types coexist, the full-function mode will be activated, and the fan speed will be adjusted according to the concentration.

[0097] Optionally, before performing the self-cleaning of the air conditioner, if the self-cleaning is high-temperature heating or ultraviolet sterilization, the smart window is controlled to close; if the concentration of microorganisms fluctuates during the self-cleaning of the air conditioner, the smart window is controlled to open for ventilation; when the self-cleaning of the air conditioner is completed, the air conditioner is controlled to switch to ventilation mode, stop cooling or heating, open the fresh air duct, and control the fresh air system to start running for a preset time.

[0098] During the cleaning preparation period, if high-temperature heating or ultraviolet sterilization is detected, the smart window is instructed to close completely. During the cleaning execution period, if the sensor detects concentration fluctuations, the smart ventilation window is instructed to open to micro-ventilation mode, using the pressure difference between indoors and outdoors to create a weak airflow, accelerating the outward diffusion of the biofilm shell and preventing indoor sedimentation. During the cleaning end period, it is instructed to switch to ventilation mode and activate the fresh air system to run at full speed for a few minutes to quickly remove suspended particles and restore indoor air quality.

[0099] Optionally, the method further includes: before the purification device completes air purification, collecting the concentration of microorganisms and / or the concentration of particulate matter in the indoor environment; calculating the rate of decrease in the concentration of microorganisms and / or the rate of decrease in the concentration of particulate matter in the indoor environment, and determining whether to extend the purification time of the purification device in purifying the air based on the rate of decrease in the concentration of microorganisms and / or the rate of decrease in the concentration of particulate matter.

[0100] If the decrease rate of microbial concentration is less than a first preset decrease rate threshold and / or the decrease rate of particulate matter concentration is less than a third preset decrease rate threshold, the purification time is extended by a preset time; if the decrease rate of microbial concentration is greater than a second preset decrease rate threshold and / or the decrease rate of particulate matter concentration is greater than a fourth preset decrease rate threshold, the purification equipment is controlled to shut down, and the air purification ends.

[0101] Specifically, multispectral sensors at the air conditioner's return air vents collect microbial spectral data, which is then input into a pre-trained recognition model to identify microbial concentrations. Sensors within the purifier monitor suspended particles in real time, collecting particulate matter concentration data. This data is synchronized to an edge computing chip to remove noise interference. Using the multispectral data as the main axis, a continuous time-concentration sequence is generated and plotted in a two-dimensional coordinate system, yielding microbial concentration change curves and / or particulate matter concentration change curves. Based on these curves, it is determined whether to extend the purification time. For example, if the microbial concentration decrease rate is <50%, the current purification efficiency is deemed insufficient, and the purification operation time is automatically extended. If the microbial concentration decrease rate is >80%, the purification task is deemed complete, and the purification equipment is shut down to avoid over-operation.

[0102] Optionally, the method further includes: after the purification device has finished purifying the air, detecting the indoor ambient humidity; determining whether it is necessary to increase the indoor ambient humidity based on the detected indoor ambient humidity; if it is determined that it is necessary to increase the indoor ambient humidity, sending a linkage control command to the humidification device in the environment through the gateway device to control the humidification device to turn on and increase the indoor ambient humidity.

[0103] If the detected indoor humidity is below a first preset humidity threshold, it is determined that the indoor humidity needs to be increased, and the humidifier is turned on. If the detected indoor humidity is not below the first preset humidity threshold, it is determined that the indoor humidity does not need to be increased. After the humidifier is turned on, if the detected indoor humidity is above a second preset humidity threshold, the humidifier is turned off, and humidification stops. For example, if the detected indoor humidity is below 40%, the smart humidifier is then activated to gradually adjust the humidity to a comfortable range of 50%–60%; if the detected indoor humidity is above 60%, humidification stops to prevent the growth of microorganisms due to dampness.

[0104] Optionally, the method further includes: after the air conditioner completes its self-cleaning process, acquiring the microbial concentration in the indoor environment again; calculating the microbial removal rate before and after self-cleaning based on the acquired concentrations in the indoor environment before and after self-cleaning; and determining whether the air conditioner's filter needs cleaning based on whether the calculated microbial removal rate reaches a preset removal rate threshold. If the calculated microbial removal rate reaches the preset removal rate threshold, the air conditioner's filter is determined not to need cleaning; if the calculated microbial removal rate does not reach the preset removal rate threshold, the air conditioner's filter is determined to need cleaning. Optionally, if the air conditioner's filter is determined to need cleaning, a corresponding reminder message is issued.

[0105] Specifically, after the self-cleaning and linkage processes with the purification equipment have been performed, if the removal rate is still below standard, the most likely reason is that the biofilm is too thick or the filter is clogged. Therefore, after cleaning, the microbial spectral data in the indoor environment is collected again and input into a pre-trained recognition model to identify the types and concentrations of microorganisms in the indoor environment. The microbial removal rate before and after cleaning is calculated as follows: Removal rate = (Concentration before cleaning - Concentration after cleaning) / Concentration after cleaning × 100%. For example, if the mold concentration before cleaning is 120 CFU / m³ and the mold concentration after cleaning is 40 CFU / m³, then the removal rate is (120 - 40) / 120 × 100% = 66.7%. For example, according to industry standards such as GB / T 18883-2022 "Indoor Air Quality Standard", the removal rate threshold is set at 80%. If the removal rate does not reach the removal rate threshold, "Filter needs cleaning" is recorded, and a reminder is sent.

[0106] Optionally, the method further includes: monitoring the pressure difference between the air inlet side and the air outlet side of the filter screen of the air conditioner, and calculating the pressure difference attenuation rate between the air inlet side and the air outlet side of the filter screen; if the calculated pressure difference attenuation rate is greater than a preset attenuation rate threshold, it is determined that the filter screen needs to be replaced.

[0107] For example, monitor the pressure difference attenuation curve of the filter screen, install pressure difference sensors on the air inlet side and the air outlet side of the filter screen, collect the pressure difference values ΔP of the air inlet side and the air outlet side in real time, calculate the pressure difference attenuation slope ΔP / Δt, if the slope is greater than 0.5 Pa / day, it is determined that "the filter screen is clogged and needs to be replaced; if it is greater than 1 Pa / day, a reminder of 'the filter screen needs to be replaced' will be immediately pushed. The attenuation rate threshold can be given according to the pressure difference monitoring experiment of the air conditioner filter screen or industry standards.

[0108] S8: All data (concentrations before and after cleaning, equipment operation status, purifier operation duration, energy consumption, and humidifier adjustment curve) are uploaded to the cloud database for optimizing the recognition model and spectral library.

[0109] Figure 3 is the system architecture diagram of the present invention. As Figure 3 shown, the air conditioner return air inlet integrates a multi-spectral sensor, an edge computing chip, a temperature and humidity environment sensor, and a filter screen air velocity sensor. Inside the air conditioner main unit, there are an ultraviolet lamp, a heating module, an ozone generator, a plasma generation module, a spray system (including self-cleaning components), and a WiFi / Zigbee communication module. It is connected to the whole-house intelligent gateway through the communication module to achieve linkage control with the intelligent purifier and the intelligent humidifier, and upload the data before and after cleaning to the cloud database. Among them, the intelligent purifier is mainly used for targeted sterilization to deeply purify the air, and the intelligent humidifier is mainly used to control the humidity to avoid the growth of microorganisms due to humidity.

[0110] To clearly illustrate the technical solution of the present invention, the execution process of the self-cleaning control method of the air conditioner provided by the present invention will be described below with a specific embodiment.

[0111] Figure 4 is the method schematic diagram of a specific embodiment of the self-cleaning control method of the air conditioner provided by the present invention. As Figure 4As shown, air sample spectral data is acquired and preprocessed. A model is used to identify microbial species and concentrations, as well as whether multiple species coexist (0 / 1). Current ambient temperature and humidity, air conditioning usage status and duration, filter speed, and historical cleaning records are acquired and input along with the identified microbial species and concentrations into a prediction model (LSTM). The model outputs a microbial proliferation curve for a preset future time (e.g., 12 hours). It determines whether the microbial concentration will exceed the limit within this preset time. If it is determined that it will not exceed the limit, self-cleaning is not triggered, and monitoring continues. If it is determined that the microbial concentration will exceed the limit within the preset time, it is then determined whether the current period is a non-core usage period. If yes, cleaning will be scheduled; otherwise, cleaning will be triggered immediately. Based on the coexistence of multiple types of microorganisms, a self-cleaning strategy is generated. If the flag is 0, indicating that only one type of microorganism is identified, the first cleaning mode (dedicated cleaning mode) is executed. If the flag is 1, indicating that two or more types of microorganisms are identified, the second cleaning mode (tiered cleaning mode) is executed. The risk weighting score of each type of microorganism is calculated to determine the risk level, the air conditioner self-cleaning is initiated, and instructions are simultaneously sent to the smart gateway to start the purifier and humidifier. The removal rate before and after cleaning is calculated, the filter attenuation curve is monitored, the filter replacement cycle is determined, and the data is uploaded to the cloud for digitization, model optimization, and spectral library optimization.

[0112] The present invention also provides a self-cleaning control device.

[0113] Figure 5 This is a structural block diagram of an embodiment of the self-cleaning control device for air conditioners provided by the present invention. Figure 5 As shown, the self-cleaning control device 100 includes: an acquisition unit 110, a prediction unit 120, a judgment unit 130, and an execution unit 140.

[0114] The acquisition unit 110 is used to acquire the types and concentrations of microorganisms in the indoor environment and to acquire the operating data of the air conditioner.

[0115] In one specific implementation, spectral data of microorganisms in an indoor environment are collected; the acquired spectral data is input into a pre-trained recognition model to identify the types and concentrations of microorganisms in the indoor environment.

[0116] Specifically, spectral data of microorganisms in the indoor environment can be collected using a multispectral sensor. The multispectral sensor has a fluorescence excitation unit. By exciting microbial samples in the indoor environment, the multispectral sensor collects their reflectance or absorption spectral characteristics, i.e., spectral data.

[0117] In one specific embodiment, a multispectral sensor can be installed at the air conditioner return air vent to collect spectral data of microorganisms in the indoor environment. When air flows through the return air vent, the multispectral sensor integrated at the air conditioner return air vent excites the microorganisms in the air using a fluorescence excitation unit, and the multispectral sensor collects the reflectance or absorption spectral characteristics.

[0118] After preprocessing the collected spectral data (e.g., denoising and normalization), it is input into a pre-trained recognition model to identify the types and concentrations of microorganisms in the indoor environment. Specifically, the types of microorganisms may include at least one of molds, bacteria, and viruses.

[0119] The identification model can specifically be a convolutional neural network (CNN) model. That is, a pre-trained CNN model is used to identify the types of microorganisms. Based on the multispectral fluorescence excitation mechanism, different microorganisms have different cell wall components, metabolites, and nucleic acid structures, resulting in differences in the wavelengths (spectral characteristics) of their absorption and emission of fluorescence. For example, molds typically contain melanin or specific pigments, exhibiting unique emission peaks under specific ultraviolet excitation; the protein and nucleic acid structures of bacteria or viruses have characteristic absorption or scattering in specific wavelength bands. Therefore, a pre-trained CNN model can be used to identify the types of microorganisms. Specifically, labeled samples of spectral data (reflectance spectra or absorption spectra) of different types of microorganisms are obtained. The acquired spectral data labeled samples are then used to train the CNN model, resulting in an identification model for recognizing the types and concentrations of microorganisms.

[0120] The identification model has a classification branch and a regression branch. The classification branch is used to identify the species of microorganisms, and the regression branch is used to identify the concentration of each species. Spectral data is treated as a special type of image or time-series signal. Feature fingerprints are extracted through the classification branch of a convolutional neural network and mapped to different microbial categories. Feature fingerprints refer to the unique spectral waveform patterns of microorganisms. Different microorganisms exhibit unique absorption valleys or emission peaks under specific excitation light due to differences in cell wall composition, metabolites, and nucleic acid structure. Convolutional neural networks (such as lightweight CNNs) automatically filter out these discriminative local waveform features, i.e., feature fingerprints, by sliding the convolutional layers through the input spectrum. The selected spectral feature vectors are then quantitatively mapped to different microbial species labels through mathematical calculations. Specifically, the Convolutional Neural Network (CNN) extracts the feature fingerprints (such as peak positions and valley depths) of each microbial species from the spectral data; the feature fingerprints are converted into feature vectors and projected into the probability space composed of each microbial species. That is, if there are N types of microorganisms in the actual application scenario, they are projected into an N-dimensional probability space; then, normalization mapping is performed through an activation function (e.g., softmax activation function) to obtain the probability value belonging to each species. The species with the highest probability value is selected as the recognition result. If the highest probability value is lower than a preset probability threshold or there are multiple species with probability values ​​exceeding the preset probability threshold, they are marked as two or more microorganisms coexisting.

[0121] The regression branch in the convolutional neural network can identify the concentration value of each microbial species and output the microbial species identifier, concentration value, and whether two or more microorganisms coexist. For example, 0 indicates the presence of a single microorganism, and 1 indicates the presence of two or more microorganisms.

[0122] The specific operating data may include: indoor ambient temperature, indoor ambient humidity, air conditioner usage status and operating time, and filter fan speed. The system collects the current indoor ambient temperature, indoor ambient humidity, air conditioner usage status and operating time, and filter fan speed in real time.

[0123] The prediction unit 120 is used to input the microbial species and concentration and the operating condition data acquired by the acquisition unit into a pre-trained prediction model to predict the microbial proliferation curve within a preset time period in the future.

[0124] Ambient temperature determines the reproduction rate of microorganisms by regulating the catalytic activity of intracellular enzymes. Microbial enzyme activity and reproduction rate have an exponential relationship, involving the growth rate constant, which accelerates exponentially with increasing temperature. Water activity is crucial for microbial survival; higher humidity leads to faster proliferation and a larger predicted growth slope. Air conditioning usage status (on / off state), long-term shutdown leading to filter dust accumulation (favorable for microbial growth), and longer air conditioning operation resulting in heavier filter loads are all input into the model as initial concentration baselines and disturbance factors. Filter velocity (air velocity = airflow / filter area) is used as an environmental feature input because it affects the deposition efficiency of microorganisms on the filter surface. Filter velocity determines the total amount of microorganisms passing through the return air vent per unit time and is used as a correction coefficient input into the model.

[0125] The prediction model is used to predict the microbial proliferation curve within a preset time period. The prediction model can be, for example, an LSTM (Long Short-Term Memory) network model.

[0126] The model architecture includes an input layer, a core layer, and an output layer. The input layer receives multidimensional environmental feature vectors from the past T time steps (e.g., sampling once every 5 minutes in 1 hour). The core layer adopts a gated recurrent unit structure and uses its memory unit to capture the time dependence of environmental parameters. The output layer directly regresses the concentration values ​​of each type of microorganism within a preset time in the future, thereby outputting the proliferation curves of each type of microorganism within the preset time in the future, i.e., the curves of microbial concentration change over time.

[0127] The judgment unit 130 is used to determine whether the microbial concentration value will exceed a preset threshold within a preset time period based on the microbial proliferation curve predicted by the prediction unit. The execution unit 140, if the judgment unit determines that the microbial concentration value will exceed the preset threshold within a preset time period, executes the self-cleaning function of the air conditioner based on the identified types of microorganisms in the indoor environment being one or more.

[0128] Specifically, based on the predicted microbial proliferation curve within a preset future time period, it is determined whether the microbial concentration value will exceed a preset threshold within the preset future time period, i.e., whether it will exceed the standard. If it is determined that the microbial concentration value will not exceed the preset threshold within the preset future time period, the self-cleaning of the air conditioner will not be performed; if it is determined that the microbial concentration value will exceed the preset threshold within the preset future time period, the self-cleaning of the air conditioner will be performed.

[0129] If it is determined that the microbial concentration will exceed a preset threshold within a preset time period in the future, and the current time period is within a preset time period, then self-cleaning will be scheduled to be performed; if it is determined that the microbial concentration will exceed a preset threshold within a preset time period in the future, and the current time period is not within a preset time period, then self-cleaning will be performed immediately.

[0130] The preset time period can specifically be a non-core usage period. This preset time period can be determined based on a combination of user behavior data statistics (such as usage time analysis of smart home platforms) and human physiological patterns (sleep cycles), identifying time periods when the user is asleep, less active, has a low breathing rate, and is less sensitive to air disturbances, such as nighttime. For example, the period from 00:00 to 6:00 AM. Different users can be assigned different non-core time periods. Users can set their own non-core time periods, or the non-core time periods can be determined based on different users' historical behavior data (such as historical sleep time).

[0131] For example, the system determines whether the microbial concentration will exceed the limit within the next 12 hours. If it determines that the concentration will not exceed the limit, self-cleaning will not be triggered, and monitoring will continue. If it determines that the microbial concentration will exceed the limit, and this occurs during a non-core usage period, self-cleaning will be scheduled to occur to avoid disturbing users' rest during non-core periods. If this does not occur during non-core periods, cleaning will be triggered immediately. For example, if the prediction shows that the mold concentration will exceed 80 CFU / m³ within 8 hours, and the current time is during the non-core usage period of 00:00–6:00 AM, then self-cleaning will be scheduled.

[0132] The scheduled self-cleaning process includes: determining the self-cleaning time based on the predicted time when the microbial concentration value exceeds a preset threshold and the preset time period; and performing self-cleaning on the air conditioner when the determined self-cleaning time arrives. In one specific embodiment, if the predicted time when the microbial concentration value exceeds the preset threshold is not within the preset time period, the end time of the current preset time period is determined as the self-cleaning time; that is, self-cleaning is performed when the current time exceeds the preset time period. If the predicted time when the microbial concentration value exceeds the preset threshold is within the preset time period, self-cleaning is performed before the predicted time when the microbial concentration value exceeds the preset threshold. The self-cleaning is performed within a set duration before the predicted time when the microbial concentration value exceeds the preset threshold, where the set duration is a pre-set self-cleaning execution duration.

[0133] Specifically, cleaning instructions can be written into a task queue, and an execution time window can be determined—that is, an intelligent scheduling strategy based on a time window, rather than a simple delayed execution. The execution time is determined by calculating the overlap between the predicted time exceeding a preset threshold and non-core usage periods (preset periods).

[0134] For example, if it is predicted that the microbial concentration will exceed a preset threshold within 8 hours at a certain point in time, and the period after 8 hours falls within the non-core usage period of 00:00–6:00, then a cleaning task will be scheduled. If it does not fall within the non-core usage period, cleaning will be triggered immediately.

[0135] In one specific implementation, the air conditioner performs self-cleaning based on whether the identified indoor environment contains one or more types of microorganisms. Specifically, this may include: if the identified indoor environment contains only one type of microorganism, then a first cleaning mode is executed; if the identified indoor environment contains two or more types of microorganisms, then a second cleaning mode is executed.

[0136] The first cleaning mode, i.e., the dedicated cleaning mode, executes a corresponding self-cleaning operation based on the identified types of microorganisms in the indoor environment. Different types of microorganisms correspond to different self-cleaning operations. For example, for mold, high-temperature sterilization and / or ultraviolet sterilization are used for self-cleaning. Based on the principle that high temperature can destroy spore structure and ultraviolet light can inactivate residues, thus synergistically removing biofilm, the heating module can be activated for high-temperature heating (e.g., heating to 75°C for 15 minutes) to kill heat-resistant molds in conjunction with ultraviolet light. For viruses, ultraviolet light irradiation can be used to kill viruses. Based on the principle that ultraviolet light can directly destroy nucleic acids, ultraviolet light irradiation for a certain period of time (e.g., 10 minutes) is activated to inactivate viruses. For bacteria, ozone sterilization and / or plasma sterilization are used for self-cleaning. Ozone and plasma can penetrate cell membranes; for example, the ozone generator can be activated while the plasma generator is simultaneously turned on to clean bacteria. Preferably, after the self-cleaning is completed, the spray system is activated to rinse the surface of the evaporator and remove residual biofilm.

[0137] The second cleaning mode is a graded cleaning mode that identifies two or more microorganisms and performs cleaning according to the risk weighting of the two or more microorganisms. In one specific embodiment, executing the second cleaning mode includes steps S1 to S3.

[0138] Step S1: Calculate the risk weighted score of each of the two or more identified microorganisms based on their concentration and risk weight.

[0139] Different types of microorganisms correspond to different risk weights. For example, Table 1 shows the risk weights corresponding to molds, bacteria, and viruses, where the risk weights are represented by 1 to 10, with larger values ​​indicating higher risk weights.

[0140] Table 1

[0141]

[0142] The risk-weighted score for each of the two or more identified microorganisms can be calculated using the following formula:

[0143] Risk-weighted score = concentration × risk weight

[0144] Step S2: Based on the calculated risk weighted scores of the two or more microorganisms, determine the primary risk source among the two or more microorganisms, wherein the microorganism with the highest risk weighted score is determined as the primary risk source, and the other types of microorganisms are secondary risk sources.

[0145] Step S3: First, perform self-cleaning for the identified main risk source, then recalculate the risk weighting scores of other types of microorganisms among the two or more microorganisms, and perform self-cleaning based on the calculated risk weighting scores.

[0146] Specifically, a self-cleaning operation can be performed based on the type of microorganisms of the primary risk source. The specific execution method can be referred to the first cleaning mode described above, and will not be repeated here. After performing self-cleaning on the primary risk source, the risk weighting scores of other types of microorganisms among the two or more identified microorganisms are recalculated, and self-cleaning is performed based on the calculated risk weighting scores.

[0147] In one specific implementation, the risk weighting scores of other types of microorganisms are recalculated and summed to obtain the comprehensive risk value of the other types of microorganisms. If the comprehensive risk value is less than a preset safety threshold, it indicates that the comprehensive risk of the remaining microorganisms is within a safe range, and the cleaning task is terminated. Otherwise, a targeted cleaning plan is executed for the secondary risk source, that is, the corresponding self-cleaning operation is executed according to the type of microorganism.

[0148] In another specific implementation, the risk weighting scores of other types of microorganisms are recalculated, and it is determined whether the risk weighting score of each type of microorganism is less than the corresponding preset safety threshold (different types of microorganisms correspond to different preset safety thresholds). If the risk weighting score of each type of microorganism is less than the corresponding preset safety threshold, the cleaning task is terminated. If it is determined that there are microorganisms among other types of microorganisms with a risk weighting score greater than or equal to the corresponding preset safety threshold, a targeted cleaning plan is executed, that is, self-cleaning is performed on microorganisms with a risk weighting score greater than or equal to the corresponding preset safety threshold.

[0149] Considering that a single cleaning solution cannot avoid the energy consumption problem caused by over-sterilization—for example, if the highest-requirement cleaning method is started based on mold as the standard, it would be over-cleaning for viruses and bacteria, wasting energy and accelerating equipment aging—different self-cleaning operations are corresponding to different types of microorganisms. For example, for mold, high-temperature sterilization and / or ultraviolet sterilization are used for self-cleaning. Based on the principle that high temperature can destroy spore structure and ultraviolet light can inactivate residues, thus synergistically removing biofilm, high-temperature heating (e.g., heating to 75°C for 15 minutes) can be started, combined with ultraviolet light to kill heat-resistant mold. For viruses, ultraviolet irradiation can be used to kill viruses. Based on the principle that ultraviolet light can directly destroy nucleic acids, ultraviolet light (254nm) can be started for 10 minutes to inactivate viruses. For bacteria, ozone sterilization and / or plasma sterilization are used for self-cleaning. Ozone and plasma can penetrate cell membranes; for example, an ozone generator can be started while a plasma generator is turned on to clean bacteria. Preferably, after the self-cleaning is completed, a spray system is started to rinse the evaporator surface and remove residual biofilm.

[0150] Figure 6 This is a structural block diagram of another embodiment of the self-cleaning control device for air conditioners provided by the present invention. (See diagram below.) Figure 6 As shown, based on the above embodiments, the self-cleaning control device 100 further includes a control unit 150.

[0151] The control unit 150 is used to send linkage control commands to the purification equipment in the environment through the gateway device, so as to control the purification equipment to start purifying the air.

[0152] Air conditioner self-cleaning mainly works in closed systems and is difficult to cover the entire room. Therefore, it can be linked with the purification equipment in the room for deep purification. In addition, the air conditioner spray and high temperature may shake off some biofilm into the air. If it is not adsorbed and inactivated by the purifier in time, it will cause secondary pollution.

[0153] In one specific embodiment, the purification device is controlled to purify the air based on the identified type of microorganism. If only one type of microorganism is identified in the indoor environment, and the identified microorganism is mold, the purification device is controlled to activate its filter and photocatalyst. If the identified microorganism is a virus or bacteria, the purification device is controlled to activate its plasma generator to capture aerosols and to activate ultraviolet sterilization (e.g., a UV-C band ultraviolet germicidal lamp, i.e., an ultraviolet band with a wavelength range of 200nm to 280nm, preferably 253.7nm) to kill viruses or bacteria.

[0154] For example, a linkage command can be sent to a smart gateway via a wireless communication module (such as a Wi-Fi module) to activate the air purifier for targeted sterilization and deep air purification. Targeted sterilization dynamically adjusts the purifier's cleaning strategy based on the identified microorganisms. If mold is identified, the focus is on physical interception and chemical degradation, controlling the purifier to activate the filter (e.g., a HEPA H13 filter) to physically intercept spores, while simultaneously controlling the photocatalytic device to decompose mycotoxins and spore proteins. If viruses / bacteria are identified, physical field forces and photochemical effects are used to rapidly inactivate active pathogens, instructing the purifier to activate the plasma module to actively capture tiny aerosols, and the UV-C lamp to directly destroy nucleic acids.

[0155] If two or more types of microorganisms are identified in the indoor environment, the full-function mode will be activated. Specifically, if multiple types coexist, the full-function mode will be activated, and the fan speed will be adjusted according to the concentration.

[0156] Optionally, based on any of the above embodiments, the control unit 140 is further configured to: before performing the self-cleaning of the air conditioner, if the self-cleaning is high-temperature heating or ultraviolet sterilization, control the smart window to close; during the self-cleaning of the air conditioner, if the microbial concentration fluctuates, control the smart window to open for ventilation; when the self-cleaning of the air conditioner is completed, control the air conditioner to switch to ventilation mode, stop cooling or heating, open the fresh air duct, and control the fresh air system to start running for a preset time.

[0157] During the cleaning preparation period, if high-temperature heating or ultraviolet sterilization is detected, the smart window is instructed to close completely. During the cleaning execution period, if the sensor detects concentration fluctuations, the smart ventilation window is instructed to open to micro-ventilation mode, using the pressure difference between indoors and outdoors to create a weak airflow, accelerating the outward diffusion of the biofilm shell and preventing indoor sedimentation. During the cleaning end period, it is instructed to switch to ventilation mode and activate the fresh air system to run at full speed for a few minutes to quickly remove suspended particles and restore indoor air quality.

[0158] Optionally, based on any of the above embodiments, the device 100 further includes: a data acquisition unit and a first determination unit (not shown).

[0159] The data acquisition unit is used to acquire the concentration of microorganisms and / or particulate matter in the indoor environment before the control unit controls the purification equipment to complete the air purification; the first determination unit is used to calculate the rate of decrease of the concentration of microorganisms and / or the rate of decrease of the concentration of particulate matter in the indoor environment, and determine whether to extend the purification time of controlling the purification equipment to purify the air based on the rate of decrease of the concentration of microorganisms and / or the rate of decrease of the concentration of particulate matter.

[0160] Wherein, if the decrease rate of the microbial concentration is less than a first preset decrease rate threshold and / or the decrease rate of the particulate matter concentration is less than a third preset decrease rate threshold, the purification time is extended by a preset time; the control unit is further configured to: if the decrease rate of the microbial concentration is greater than a second preset decrease rate threshold and / or the decrease rate of the particulate matter concentration is greater than a fourth preset decrease rate threshold, control the purification equipment to shut down, and the air purification process ends.

[0161] Specifically, multispectral sensors at the air conditioner's return air vents collect microbial spectral data, which is then input into a pre-trained recognition model to identify microbial concentrations. Sensors within the purifier monitor suspended particles in real time, collecting particulate matter concentration data. This data is synchronized to an edge computing chip to remove noise interference. Using the multispectral data as the main axis, a continuous time-concentration sequence is generated and plotted in a two-dimensional coordinate system, yielding microbial concentration change curves and / or particulate matter concentration change curves. Based on these curves, it is determined whether to extend the purification time. For example, if the microbial concentration decrease rate is <50%, the current purification efficiency is deemed insufficient, and the purification operation time is automatically extended. If the microbial concentration decrease rate is >80%, the purification task is deemed complete, and the purification equipment is shut down to avoid over-operation.

[0162] Optionally, based on any of the above embodiments, the device 100 further includes: a detection unit and a second determination unit (not shown).

[0163] The detection unit is used to detect the indoor ambient humidity after the air purification device has finished purifying the air; the second determination unit is used to determine whether the indoor ambient humidity needs to be increased based on the indoor ambient humidity detected by the detection unit.

[0164] Specifically, if the detection unit detects that the indoor ambient humidity is lower than a first preset humidity threshold, it determines that the indoor ambient humidity needs to be increased and controls the humidifier to turn on; if the detection unit detects that the indoor ambient humidity is not lower than the first preset humidity threshold, it determines that the indoor ambient humidity does not need to be increased. The control unit is further configured to: if the second determining unit determines that the indoor ambient humidity needs to be increased, send a linkage control command to the humidifier in the environment through the gateway device to control the humidifier to turn on and increase the indoor ambient humidity; after controlling the humidifier to turn on, if the detection unit detects that the indoor ambient humidity is higher than the second preset humidity threshold, it controls the humidifier to turn off and stop humidification. For example, if the indoor ambient humidity is detected to be lower than 40%, the smart humidifier is then turned on to gradually adjust the ambient humidity to a comfortable range of 50%–60%; if the indoor ambient humidity is detected to be higher than 60%, humidification is stopped to prevent the growth of microorganisms due to dampness.

[0165] Optionally, based on any of the above embodiments, the device 100 further includes: a calculation unit and a third determination unit (not shown). The acquisition unit is further configured to: acquire the concentration of microorganisms in the indoor environment again after the self-cleaning of the air conditioner is completed; the calculation unit is configured to calculate the microorganism removal rate before and after the self-cleaning based on the acquired concentrations in the indoor environment before and after the self-cleaning; the third determination unit is configured to determine whether the air conditioner filter needs to be cleaned based on whether the microorganism removal rate calculated by the calculation unit reaches a preset removal rate threshold.

[0166] If the microbial removal rate calculated by the calculation unit reaches a preset removal rate threshold, it is determined that the air conditioner filter does not need cleaning; if the microbial removal rate calculated by the calculation unit does not reach the preset removal rate threshold, it is determined that the air conditioner filter needs cleaning. Optionally, it also includes a reminder unit, used to issue a corresponding reminder message if the third determining unit determines that the air conditioner filter needs cleaning.

[0167] Specifically, after the self-cleaning and linkage processes with the purification equipment have been performed, if the removal rate is still below standard, the most likely reason is that the biofilm is too thick or the filter is clogged. Therefore, after cleaning, the microbial spectral data in the indoor environment is collected again and input into a pre-trained recognition model to identify the types and concentrations of microorganisms in the indoor environment. The microbial removal rate before and after cleaning is calculated as follows: Removal rate = (Concentration before cleaning - Concentration after cleaning) / Concentration after cleaning × 100%. For example, if the mold concentration before cleaning is 120 CFU / m³ and the mold concentration after cleaning is 40 CFU / m³, then the removal rate is (120 - 40) / 120 × 100% = 66.7%. For example, according to industry standards such as GB / T 18883-2022 "Indoor Air Quality Standard", the removal rate threshold is set at 80%. If the removal rate does not reach the removal rate threshold, "Filter needs cleaning" is recorded, and a reminder is sent.

[0168] Optionally, based on any of the above embodiments, the device 100 further includes: a monitoring unit and a fourth determining unit (not shown). The monitoring unit is used to monitor the pressure difference between the air inlet side and the air outlet side of the air conditioner's filter, and calculate the pressure difference attenuation rate between the air inlet side and the air outlet side of the filter; the fourth determining unit is used to determine that the filter needs to be replaced if the calculated pressure difference attenuation rate is greater than a preset attenuation rate threshold.

[0169] For example, to monitor the filter's differential pressure decay curve, differential pressure sensors are installed on the air inlet and outlet sides of the filter to collect the real-time differential pressure value ΔP between the inlet and outlet sides. The differential pressure decay slope ΔP / Δt is calculated. If the slope is greater than 0.5 Pa / day, it is determined that "filter clogging is accelerating, and replacement is recommended"; if it is greater than 1 Pa / day, an immediate "filter needs replacement" reminder is sent. The decay rate threshold can be determined based on differential pressure monitoring experiments of air conditioning filters or industry standards.

[0170] The present invention also provides a storage medium corresponding to the self-cleaning control method of the air conditioner, wherein a computer program is stored thereon, and when the program is executed by a processor, it implements the steps of any of the aforementioned methods.

[0171] The present invention also provides an air conditioner corresponding to the self-cleaning control method of the air conditioner, comprising a processor, a memory, and a computer program stored in the memory that can run on the processor, wherein the processor executes the program to implement the steps of any of the aforementioned methods.

[0172] The present invention also provides an air conditioner corresponding to the self-cleaning control device of the air conditioner, including the self-cleaning control device of any of the aforementioned air conditioners.

[0173] The present invention also provides a computer program product corresponding to the self-cleaning control method of the air conditioner, comprising a computer program that, when executed by a processor, implements the steps of any of the aforementioned methods.

[0174] Accordingly, the solution provided by this invention constructs a full-link cleaning mode of "microbial species identification - proliferation prediction - cleaning according to species - multi-device linkage". It uses multispectral + convolutional neural network algorithms to overcome the limitations of single detection, realizes the classification and identification of mold, bacteria and viruses and matches them with exclusive self-cleaning solutions. Combining multi-dimensional data such as current environmental temperature and humidity, air conditioner usage status and running time, and filter wind speed, it uses LSTM algorithm to predict the microbial reproduction status in advance to trigger preventive cleaning. Based on the coexistence of multiple types of microorganisms (0 / 1), it executes the first cleaning mode and the second cleaning mode based on risk priority. At the same time, it links the air purifier and humidifier to form a cleaning closed loop based on the cleaning effect feedback. The data is uploaded to the cloud database to optimize the model and update the spectral library, thereby ensuring the cleaning effect and dynamically optimizing it to achieve efficient and adaptable whole-house cleaning.

[0175] This invention addresses the problems of existing air conditioning self-cleaning technologies, which often focus on detecting the number of single microorganisms, lack species identification for targeted cleaning, and suffer from passive cleaning timing and isolated equipment operation. By realizing microbial species identification, proliferation prediction, and multi-device collaborative linkage, this invention solves the problems of incomplete sterilization and energy consumption caused by over-sterilization, ensuring efficient and accurate cleaning results and providing an energy-saving refrigeration and air conditioning device.

[0176] The solution provided by this invention employs a multispectral + fluorescence + CNN algorithm to classify and identify mold, bacteria, and viruses, matching them with a customized cleaning plan. This avoids over-sterilization caused by treating bacteria with virus standards, improving cleaning efficiency and ensuring thorough sterilization. Based on an LSTM model that integrates multi-dimensional data on environment, operating conditions, and microorganisms, it predicts the proliferation trend within a preset time period and intelligently selects "real-time triggering" or "predictive triggering during non-core usage periods" to achieve proactive prevention and control, enhancing user experience. It also links with purification equipment for targeted sterilization and humidifiers for humidity adjustment, forming a closed loop of "cleaning → sterilization → humidity adjustment → feedback," preventing environmental imbalance after cleaning and ensuring continuous and stable air quality throughout the house.

[0177] The functions described herein can be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions can be stored as one or more instructions or codes on or transmitted via a computer-readable medium. Other examples and embodiments are within the scope and spirit of this invention and the appended claims. For example, due to the nature of software, the functions described above can be implemented using software executed by a processor, hardware, firmware, hardwired, or any combination thereof. Furthermore, the functional units can be integrated into a single processing unit, or each unit can exist physically separately, or two or more units can be integrated into a single unit.

[0178] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0179] The units described as separate components may or may not be physically separate. Similarly, the components of the control device may or may not be physical units; they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0180] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to related technologies, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0181] The above description is merely an embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of the claims of the present invention.

Claims

1. A self-cleaning control method for an air conditioner, characterized in that, include: The types and concentrations of microorganisms in the indoor environment are obtained, and the operating data of the air conditioner are also obtained; The obtained microbial species and concentration, along with the operating condition data, are input into a pre-trained prediction model to predict the microbial proliferation curve within a preset time period. Based on the predicted microbial proliferation curve within a preset future time period, determine whether the microbial concentration value will exceed the preset threshold within the preset future time period. If it is determined that the concentration of microorganisms will exceed a preset threshold within a preset time in the future, the air conditioner will perform self-cleaning based on the identification of one or more types of microorganisms in the indoor environment.

2. The method according to claim 1, characterized in that, Obtain the types and concentrations of microorganisms in the indoor environment, including: Collect spectral data of microorganisms in the indoor environment; The acquired spectral data is input into a pre-trained recognition model to identify the types and concentrations of microorganisms in the indoor environment.

3. The method according to claim 1, characterized in that, If it is determined that the microbial concentration will exceed a preset threshold within a preset time period, then the air conditioner's self-cleaning function is executed, including: If it is determined that the microbial concentration will exceed the preset threshold within a preset time in the future, and the current time period is within the preset time period, then a self-cleaning will be scheduled to be performed. If it is determined that the microbial concentration will exceed the preset threshold within a preset time period in the future, and the current time period is not within the preset time period, then self-cleaning will be performed immediately.

4. The method according to claim 3, characterized in that, Schedule a self-cleaning session, including: The self-cleaning time is determined based on the time when the predicted microbial concentration exceeds a preset threshold and the preset time period. The air conditioner performs self-cleaning when the predetermined self-cleaning time arrives.

5. The method according to any one of claims 1-4, characterized in that, Based on the identification of one or more types of microorganisms in the indoor environment, the air conditioner performs self-cleaning, including: If only one type of microorganism is identified in the indoor environment, then the first cleaning mode will be executed; If two or more types of microorganisms are identified in the indoor environment, the second cleaning mode will be executed. Execute the first cleaning mode, including: Based on the identified types of microorganisms in the indoor environment, perform corresponding self-cleaning operations; Execute the second cleaning mode, including: Based on the concentration and risk weight of the two or more identified microorganisms, calculate the risk weighted score for each of the two or more microorganisms. Based on the calculated risk weighted scores of the two or more microorganisms, the primary risk source among the two or more microorganisms is determined, wherein the microorganism with the highest risk weighted score is determined as the primary risk source; First, self-cleaning is performed on the identified primary risk source. Then, the risk weighting scores of other types of microorganisms among the two or more microorganisms are recalculated, and self-cleaning is performed based on the calculated risk weighting scores.

6. The method according to any one of claims 1-4, characterized in that, Also includes: The gateway device sends a linkage control command to the air purification device in the environment to control the air purification device to start purifying the air.

7. The method according to claim 6, characterized in that, Also includes: Before the purification equipment completes the air purification process, the concentration of microorganisms and / or particulate matter in the indoor environment is collected; the rate of decrease in the concentration of microorganisms and / or the rate of decrease in the concentration of particulate matter in the indoor environment is calculated; and based on the rate of decrease in the concentration of microorganisms and / or the rate of decrease in the concentration of particulate matter, it is determined whether to extend the purification time of the purification equipment. If the concentration decrease rate is less than a first preset decrease rate threshold, the purification time is extended by a preset time; if the concentration decrease rate is greater than a second preset decrease rate threshold, the purification equipment is turned off, and the air purification process ends.

8. The method according to claim 6, characterized in that, Also includes: After the air purification equipment has finished purifying the air, the indoor humidity is detected. Based on the measured indoor humidity, determine whether it is necessary to increase the indoor humidity. If it is determined that the indoor humidity needs to be increased, a linkage control command is sent to the humidification device in the environment through the gateway device to control the humidification device to turn on and increase the indoor humidity. If the indoor ambient humidity is detected to be lower than a first preset humidity threshold, it is determined that the indoor ambient humidity needs to be increased, and the humidifier is turned on; if the indoor ambient humidity is detected to be not lower than the first preset humidity threshold, it is determined that the indoor ambient humidity does not need to be increased; after the humidifier is turned on, if the indoor ambient humidity is detected to be higher than a second preset humidity threshold, the humidifier is turned off and humidification stops.

9. The method according to any one of claims 1-4, characterized in that, Also includes: After the air conditioner completes its self-cleaning process, the concentration of microorganisms in the indoor environment is measured again. Based on the concentrations obtained in the indoor environment before and after self-cleaning, the microbial removal rate before and after self-cleaning is calculated. Based on whether the calculated microbial removal rate reaches a preset removal rate threshold, it is determined whether the air conditioner filter needs to be cleaned. If the calculated microbial removal rate reaches a preset removal rate threshold, the air conditioner filter is determined not to need cleaning; if the calculated microbial removal rate does not reach the preset removal rate threshold, the air conditioner filter is determined to need cleaning.

10. The method according to any one of claims 1-4, characterized in that, Also includes: Monitor the pressure difference between the air inlet and outlet sides of the air conditioner's filter, and calculate the pressure difference attenuation rate between the air inlet and outlet sides of the filter. If the calculated differential pressure attenuation rate is greater than the preset attenuation rate threshold, then the filter needs to be replaced.

11. A self-cleaning control device for an air conditioner, characterized in that, include: The acquisition unit is used to acquire the types and concentrations of microorganisms in the indoor environment and to acquire the operating data of the air conditioner; The prediction unit is used to input the microbial species and concentration and the operating condition data obtained by the acquisition unit into a pre-trained prediction model to predict the microbial proliferation curve within a preset time period in the future. The judgment unit is used to determine whether the microbial concentration value will exceed a preset threshold within a preset time period based on the microbial proliferation curve predicted by the prediction unit. If the judgment unit determines that the microbial concentration value will exceed a preset threshold within a preset time in the future, the execution unit will perform the self-cleaning of the air conditioner based on the identification of one or more types of microorganisms in the indoor environment.

12. A storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the steps of the method according to any one of claims 1-10.

13. An air conditioner, characterized in that, It includes a processor, a memory, and a computer program stored in the memory that can run on the processor, wherein the processor executes the program to implement the steps of the method of any one of claims 1-10, or includes the self-cleaning control device as described in claim 11.

14. A computer program product, characterized in that, Includes a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1-10.

Images