Air purifier linkage outdoor air quality information control method and device

Abstract

This specification discloses a control method and device for an air purifier linked to outdoor air quality information. The scheme may include: acquiring outdoor air quality information in real time, the outdoor air quality information including at least the outdoor air quality index (AQI) and PM2.5 concentration; collecting indoor air quality parameters in real time, the indoor air quality parameters including at least indoor PM2.5 concentration, VOC concentration, and temperature; calculating an air purification demand index (AQDI) based on the outdoor air quality information and indoor air quality parameters; comparing the AQDI with a preset first threshold and a second threshold, and automatically switching the operating mode of the air purifier according to the comparison result; wherein the value of the first threshold is greater than the value of the second threshold, and the operating mode includes an internal circulation mode, an external circulation mode, and a pre-purification mode; recording historical operating data and user feedback, and dynamically adjusting the weight parameters in the AQDI calculation, as well as the first and second thresholds, through an adaptive learning algorithm.

Description

Technical Field

[0001] This application relates to the field of smart home technology, and in particular to a control method and device for linking an air purifier with outdoor air quality information. Background Technology

[0002] With air pollution becoming increasingly prominent, air purifiers have become key devices for improving indoor air quality. Current air purifier technologies generally employ automatic control schemes based on indoor environmental sensors, automatically adjusting the device's fan speed or operating mode by monitoring the real-time concentrations of pollutants such as PM2.5, VOCs, and CO2. While such schemes can respond to pollutants that have already entered the room, their control logic has significant limitations: it relies solely on indoor sensor data for decision-making, failing to incorporate the important influencing factor of outdoor air quality into the control system.

[0003] This control method, which relies solely on indoor sensor data, has several drawbacks. Specifically, the air purification response exhibits a significant lag. When a sudden outdoor pollution event occurs (such as smog, pollen transmission, or industrial emission peaks), pollutants first enter the room through gaps in doors and windows, causing indoor air quality to deteriorate. Only then does the purifier activate its purification program based on the pollution levels detected by the indoor sensors. This passive "pollute first, purify later" response model cannot effectively guarantee the continuous stability of indoor air quality. Summary of the Invention

[0004] This specification provides a control method and device for linking an air purifier with outdoor air quality information to solve at least one of the technical problems mentioned above.

[0005] To solve the above-mentioned technical problems, the embodiments in this specification are implemented as follows: According to a first aspect of the embodiments of this specification, a control method for an air purifier that is linked to outdoor air quality information is provided, comprising: Real-time acquisition of outdoor air quality information, including at least the outdoor air quality index (AQI) and PM2.5 concentration; Real-time collection of indoor air quality parameters, including at least indoor PM2.5 concentration, VOC concentration, and temperature; Based on the outdoor air quality information and indoor air quality parameters, the Air Quality Demand Index (AQDI) is calculated. The AQDI is compared with a preset first threshold and a second threshold, and the air purifier's operating mode is automatically switched according to the comparison result; wherein, the value of the first threshold is greater than the value of the second threshold, and the operating mode includes internal circulation mode, external circulation mode and pre-purification mode; Record historical operation data and user feedback, and dynamically adjust the weight parameters, the first threshold, and the second threshold in the AQDI calculation through an adaptive learning algorithm.

[0006] In some optional implementations, the real-time acquisition of outdoor air quality information includes: calling the city air quality data API through a network interface to acquire the outdoor air quality information at fixed time intervals, storing the data in a local cache and uploading it to the cloud; The real-time acquisition of indoor air quality parameters includes: collecting PM2.5 concentration, VOC concentration, CO2 concentration, and temperature and humidity data through indoor sensors, and performing noise filtering and standardization processing on the collected sensor data to generate a standardized indoor air quality index.

[0007] In some optional implementations, the formula for calculating the Air Quality Demand Index (AQDI) is: Among them, symbols Indicates the first weight, symbol Indicates the second weight, symbol Indicates the third weight, symbol Indicates the fourth weight; symbol Indicates the outdoor air quality index, symbol Indicates the reference safety value for outdoor air quality index, symbol Indicates the real-time indoor PM2.5 concentration, symbol Indicates the reference safety value for indoor PM2.5 concentration, symbol Indicates the real-time concentration of volatile organic compounds (VOCs) indoors, symbol [symbol missing]. Indicates the reference safety value for indoor VOC concentration, symbol This represents the temperature correction factor.

[0008] In some optional implementations, the automatic switching of the air purifier's operating mode based on the comparison results includes: When the AQDI is greater than the first threshold, the internal circulation mode is activated, and the air purifier is controlled to run at the first fan speed to achieve powerful purification, while a reminder to close the window is issued. When the AQDI is less than the second threshold, the external circulation mode is activated, and the air purifier is controlled to run at the second fan speed to achieve energy-saving ventilation. When the AQDI is between the second threshold and the first threshold, the fan speed is adjusted between the first fan speed setting and the second fan speed setting according to the difference between indoor and outdoor air quality. The operation mode switching also includes controlling the speed of the fan and the opening and closing status of the valves.

[0009] In some optional implementations, the method further includes at least one of the following pre-purification triggering mechanisms: When the AQDI approaches but does not exceed the first threshold, the pre-purification mode is activated, and the fan and filter are started in advance to purify the air. When the outdoor air quality index changes abruptly, the pre-purification mode is automatically activated in advance to reduce the peak concentration of indoor pollutants.

[0010] In some optional implementations, the step of dynamically adjusting the weight parameters, the first threshold, and the second threshold in the AQDI calculation using an adaptive learning algorithm includes: Record the indoor and outdoor air quality data, actual operating mode, and subsequent indoor air quality improvement for each AQDI calculation; Collect user feedback on manual operations, including manually switching operating modes or manually closing windows; Based on recorded operational data and user feedback, machine learning algorithms are used to analyze the impact of various parameters on the purification effect under different environmental conditions, and the weight parameters, as well as the values ​​of the first and second thresholds, are adjusted accordingly.

[0011] In some alternative implementations, the value of the first threshold is automatically increased to trigger the switch from external circulation mode or pre-purification mode to internal circulation mode in advance, and the adjustment of the first threshold is triggered based on the user's manual closing of the window operation feedback.

[0012] In some alternative implementations, the method updates indoor and outdoor air quality data at fixed time intervals and recalculates the AQDI to determine whether to switch operating modes.

[0013] In some alternative implementations, the adaptive learning algorithm is implemented using cloud or local computing resources and continuously optimizes the control strategy based on historical operating data and user feedback.

[0014] According to a second aspect of the embodiments of this specification, a control device for linking an air purifier to outdoor air quality information is provided, comprising: An outdoor data acquisition module is used to acquire outdoor air quality information in real time, including at least the outdoor air quality index (AQI) and PM2.5 concentration. An indoor data acquisition module is used to collect indoor air quality parameters in real time, including at least indoor PM2.5 concentration, VOC concentration, and temperature. The joint assessment and decision-making module is used to calculate the Air Quality Demand Index (AQDI) based on the outdoor air quality information and indoor air quality parameters. The intelligent switching execution module is used to compare the AQDI with a preset first threshold and a second threshold, and automatically switch the operating mode of the air purifier according to the comparison result; wherein the value of the first threshold is greater than the value of the second threshold, and the operating mode includes internal circulation mode, external circulation mode and pre-purification mode; The adaptive learning module is used to record historical operation data and user feedback, and dynamically adjust the weight parameters, the first threshold and the second threshold in the AQDI calculation through an adaptive learning algorithm.

[0015] One embodiment of this specification can achieve at least the following beneficial effects: The technical solution of this application has several significant technical advantages, as detailed below: 1. The technical solution of this application combines the outdoor air quality information acquired through network connectivity with the air quality parameters monitored by indoor sensors. This allows air purification control decisions to comprehensively consider the combined impact of indoor and outdoor environments, thus avoiding the response lag problem caused by traditional solutions relying solely on indoor sensors. The Air Quality Demand Index (AQDI) is calculated based on indoor and outdoor data, and the operating mode is automatically switched accordingly. This joint assessment and intelligent switching mechanism enables predictive air purification control, activating corresponding protective measures before outdoor pollutants affect the indoor environment, effectively preventing pollutants from entering the room, and avoiding unnecessary energy consumption through accurate mode selection.

[0016] 2. The technical solution of this application records historical operating data and user feedback, and uses an adaptive learning algorithm to dynamically optimize control parameters. This allows the air purification control strategy to be continuously improved based on the actual usage environment and user habits. By analyzing historical operating effects and user operating preferences through machine learning, the weight parameters and mode switching thresholds in the AQDI calculation are automatically adjusted. This data-driven adaptive optimization mechanism enables personalized customization of the control strategy, allowing for continuous improvement in energy efficiency while ensuring air purification effects, and adapting to the usage needs of different regions, seasons, and users. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating a control method for linking an air purifier with outdoor air quality information, as provided in the embodiments of this specification. Figure 2 This is a schematic diagram of the structure of a control device for linking an air purifier with outdoor air quality information, as provided in the embodiments of this specification. Figure 3 yes Figure 2 A schematic diagram of the collaborative relationships among the modules in the control device that links the air purifier to outdoor air quality information. Figure 4 yes Figure 2 A schematic diagram of the signaling interaction of various modules in the control device that links the air purifier with outdoor air quality information. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of one or more embodiments of this specification clearer, the technical solutions of one or more embodiments of this specification 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 specification, and not all of them. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of one or more embodiments of this specification.

[0020] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another.

[0021] This application provides a control method for linking an air purifier with outdoor air quality information, such as... Figure 1 As shown, the method may include the following steps: Step 102: Acquire outdoor air quality information in real time, including at least the outdoor air quality index (AQI) and PM2.5 concentration.

[0022] In this step, during the real-time acquisition of outdoor air quality information, a city air quality data application interface can be called via a network interface to obtain parameters including the outdoor air quality index and fine particulate matter concentration at fixed time intervals. This acquisition process can be updated every 1 to 5 minutes to ensure the timeliness and accuracy of the outdoor air quality data. All acquired data is simultaneously stored in a local cache and uploaded to cloud storage. Among the acquired outdoor air quality information, the outdoor air quality index, as a quantitative indicator for comprehensively evaluating air pollution levels, can reflect the overall pollution degree of various pollutants, such as at least the outdoor air quality index (AQI) and PM2.5 concentration.

[0023] Step 104: Collect indoor air quality parameters in real time, including at least indoor PM2.5 concentration, VOC concentration and temperature.

[0024] In this step, during the collection of indoor air quality parameters, a sensor array deployed indoors continuously monitors the concentration of fine particulate matter (PM2.5), volatile organic compounds (VOCs), and temperature. These sensors operate in real-time, continuously outputting current indoor environmental data, thus enabling timely capture of dynamic changes in indoor air quality. Specifically, the collected PM2.5 concentration reflects the degree of solid particulate pollution in the air, the VOC concentration characterizes the level of chemical gaseous pollutants, and the temperature parameter records the current thermal state of the environment.

[0025] Step 106: Calculate the Air Quality Demand Index (AQDI) based on the outdoor air quality information and indoor air quality parameters.

[0026] In this step of calculating the Air Quality Demand Index, a comprehensive evaluation method can be used to integrate and analyze outdoor air quality information and indoor air quality parameters. For example, a weighted calculation method can be used to comprehensively consider the impact of outdoor pollution levels, indoor pollutant concentrations, and ambient temperature on purification needs, ultimately generating a quantitative Air Quality Demand Index (AQDI).

[0027] Step 108: Compare the AQDI with a preset first threshold and a second threshold, and automatically switch the air purifier's operating mode according to the comparison result; wherein, the value of the first threshold is greater than the value of the second threshold, and the operating mode includes internal circulation mode, external circulation mode and pre-purification mode.

[0028] In this step, during the determination of the operating mode switch, the calculated air purification demand index is compared and analyzed with two preset thresholds. The first threshold is used as a higher critical value, and the second threshold is used as a lower critical value. These two thresholds form three different numerical ranges, each corresponding to a different level of air purification demand. This hierarchical judgment mechanism can provide a clear decision-making basis for the intelligent selection of the operating mode.

[0029] When the air purification demand index exceeds the first threshold, it indicates that both indoor and outdoor air quality are in a state that requires strong purification. At this time, the internal circulation mode is activated in conjunction with the pre-purification function. In this mode, the external ventilation valve is closed to prevent polluted outdoor air from entering the room, while the high-speed purification program is activated to quickly reduce the concentration of indoor pollutants and ensure that the cleanliness of indoor air is maintained in a poor air quality environment.

[0030] When the air purification demand index is below the second threshold, it indicates that both indoor and outdoor air quality are at a good level. At this time, the system switches to external circulation mode. In this mode, fresh outdoor air is introduced for natural ventilation by opening the external ventilation valve, while energy-saving ventilation is achieved by operating at a low speed. When the index is between the two thresholds, the system dynamically adjusts between the two modes based on the specific values ​​to ensure that the purification effect and energy consumption reach the optimal balance.

[0031] Step 110: Record historical operation data and user feedback, and dynamically adjust the weight parameters, the first threshold, and the second threshold in the AQDI calculation through an adaptive learning algorithm.

[0032] In this application's technical solution, a training dataset can be constructed during the adaptive learning process by continuously accumulating historical operation records and user operation feedback. These historical operation records can include the air quality parameters calculated each time, the corresponding air purification demand index value, and the actual operating mode used. User operation feedback mainly records intervention behaviors such as manually switching operating modes or closing windows. Based on the accumulated dataset, an adaptive learning algorithm can be further used to dynamically adjust the weight parameters, the first threshold, and the second threshold in the calculation of the air purification demand index. By analyzing the influence of each parameter on the actual purification effect under different environmental conditions, the allocation ratio of the weight coefficients is automatically optimized. Simultaneously, the specific values ​​of the two thresholds are continuously adjusted based on long-term operating results and user preferences. This technical solution allows the control strategy to continuously improve and better adapt to the actual usage environment.

[0033] This application's technical solution combines network-acquired outdoor air quality information with indoor sensor-monitored air quality parameters for joint analysis. This allows air purification control decisions to comprehensively consider the combined impact of indoor and outdoor environments, avoiding the response lag problem caused by traditional solutions relying solely on indoor sensors. The Air Quality Demand Index (AQDI) is calculated based on indoor and outdoor data, and the operating mode is automatically switched accordingly. This joint evaluation and intelligent switching mechanism enables predictive air purification control, activating corresponding protective measures before outdoor pollutants affect the indoor environment, effectively preventing pollutants from entering the room, and avoiding unnecessary energy consumption through accurate mode selection. Furthermore, this application's technical solution records historical operating data and user feedback, and uses adaptive learning algorithms to dynamically optimize control parameters, allowing the air purification control strategy to continuously improve based on the actual usage environment and user habits. By analyzing historical operating results and user operating preferences through machine learning, the weight parameters and mode switching thresholds in the AQDI calculation are automatically adjusted. This data-driven adaptive optimization mechanism enables personalized customization of the control strategy, continuously improving energy efficiency while ensuring air purification effectiveness, and adapting to the needs of different regions, seasons, and users.

[0034] Based on the technical solutions described above, this specification also provides some specific implementation schemes, which are described below.

[0035] In an optional embodiment, the real-time acquisition of outdoor air quality information may include: calling the city air quality data API through a network interface to acquire the outdoor air quality information at fixed time intervals, storing the data in a local cache and uploading it to the cloud; The real-time acquisition of indoor air quality parameters includes: collecting PM2.5 concentration, VOC concentration, CO2 concentration, and temperature and humidity data through indoor sensors, and performing noise filtering and standardization processing on the collected sensor data to generate a standardized indoor air quality index.

[0036] In an optional embodiment, the formula for calculating the Air Quality Demand Index (AQDI) is: In the optional embodiment, a multi-factor weighted calculation model that integrates indoor and outdoor environmental parameters is used to calculate the Air Quality Demand Index (AQDI). This model quantitatively assesses the impact of outdoor air pollution levels, indoor pollutant concentrations, and ambient temperature on purification efficiency, and finally outputs a normalized decision index. The specific calculation formula is as follows: Among them, symbols Indicates the first weight, symbol Indicates the second weight, symbol Indicates the third weight, symbol Indicates the fourth weight; symbol Indicates the outdoor air quality index, symbol Indicates the reference safety value for outdoor air quality index, symbol Indicates the real-time indoor PM2.5 concentration, symbol Indicates the reference safety value for indoor PM2.5 concentration, symbol Indicates the real-time concentration of volatile organic compounds (VOCs) indoors, symbol [symbol missing]. Indicates the reference safety value for indoor VOC concentration, symbol This represents the temperature correction factor.

[0037] The first term in the above formula is determined by the outdoor air quality index. Reference safety values ​​set by national air quality standards The ratio represents the severity of outdoor pollution relative to a safe baseline. The second and third items are determined by indoor PM2.5 concentration. and volatile organic compound concentration and their respective reference safety values , The ratio of the two values ​​objectively reflects the gap between the actual indoor pollution load and the ideal state.

[0038] Furthermore, in order to accurately assess the impact of environmental conditions on the purification effect, a temperature correction factor is introduced in the technical solution of this embodiment, and its calculation formula is as follows: This design is based on the actual impact mechanism of temperature on air purification efficiency, that is, when the ambient temperature... Deviation from the system's preset ideal operating temperature At that time, the filtration efficiency and airflow organization of the purification equipment will change accordingly. Here, β is an experimentally verified temperature influence coefficient. By introducing this correction term, the scheme can dynamically adjust the purification demand assessment according to actual temperature conditions, ensuring the accuracy of the assessment results under different temperature environments.

[0039] Weighting coefficient , , , All are values ​​between 0 and 1, and satisfy the following conditions: + + + The relationship is 1. In the initial settings, these weighting coefficients can be allocated according to the relative importance of each parameter's impact on indoor air quality. For example, in areas with severe industrial pollution, the weight of outdoor air quality (w1) can be appropriately increased, while in newly renovated environments, the weight of VOC concentration (w3) can be increased. The advantage of this calculation method is that it standardizes various parameters of different dimensions and ranges through ratio calculations, and then obtains a unified evaluation index through weighted summation. This not only reflects the current air quality status but also considers the impact of environmental conditions on the purification effect.

[0040] In an optional embodiment, automatically switching the air purifier's operating mode based on the comparison result may include: When the AQDI is greater than the first threshold, the internal circulation mode is activated, and the air purifier is controlled to run at the first fan speed to achieve powerful purification, while a reminder to close the window is issued. When the AQDI is less than the second threshold, the external circulation mode is activated, and the air purifier is controlled to run at the second fan speed to achieve energy-saving ventilation. When the AQDI is between the second threshold and the first threshold, the fan speed is adjusted between the first fan speed setting and the second fan speed setting according to the difference between indoor and outdoor air quality. The operation mode switching also includes controlling the speed of the fan and the opening and closing status of the valves.

[0041] In this embodiment, when the AQDI value exceeds the preset first threshold θ_high, it indicates that both indoor and outdoor air quality are at a poor level. The internal circulation mode should be activated immediately and the air purifier should be controlled to run at the first fan speed level, which corresponds to the maximum purification capacity of the device. The high-speed fan achieves powerful purification and will also actively remind the user to close the windows to effectively prevent the continuous intrusion of outdoor pollutants and form a closed purification environment.

[0042] When the AQDI value is below the second threshold θ_low, it indicates that both indoor and outdoor air quality have reached a good standard. At this time, switch to the external circulation mode and activate the second fan speed setting. This setting adopts a low-speed energy-saving operation strategy, which can reduce energy consumption while ensuring basic ventilation needs. Fresh outdoor air is introduced through valve control to achieve healthy circulation of indoor and outdoor air. This mode is suitable for ventilation needs when the air quality is good in spring and autumn, which can both keep the indoor air fresh and achieve rational use of energy.

[0043] When the AQDI value falls between the second threshold θ_low and the first threshold θ_high, the fan speed can be intelligently adjusted between the first and second fan speed settings based on the specific differences in indoor and outdoor air quality. This adjustment is based on real-time monitoring of the difference in indoor and outdoor parameters; the fan speed is appropriately increased when the indoor pollutant concentration is relatively high, and appropriately decreased when the outdoor air quality is better than the indoor air quality. Throughout the mode switching process, the fan speed control mechanism and the opening and closing status of the valves can be controlled synchronously to ensure a smooth transition between internal and external circulation modes, thereby achieving optimized control of purification efficiency and energy consumption balance.

[0044] In optional embodiments, the method may further include at least one of the following pre-purification triggering mechanisms: When the AQDI approaches but does not exceed the first threshold, the pre-purification mode is activated, and the fan and filter are started in advance to purify the air. When the outdoor air quality index changes abruptly, the pre-purification mode is automatically activated in advance to reduce the peak concentration of indoor pollutants.

[0045] In this embodiment, when the AQDI value is detected to be close to but not yet reached the first threshold θ_high, a pre-purification mode is activated for proactive intervention. This situation usually occurs during the critical window period when outdoor air quality continues to deteriorate but pollutants have not yet penetrated into the room in large quantities. By starting the fan and filter in advance to enter the pre-purification state, an effective purification barrier is established before the indoor pollutant concentration rises significantly, thereby avoiding the response lag problem of traditional control methods.

[0046] Another triggering scenario is for sudden changes in outdoor air quality. When real-time data monitoring detects a sharp increase in the outdoor air quality index within a short period, a so-called "abrupt change," the pre-purification mechanism is immediately activated. This abrupt change can be caused by sudden pollution events, such as industrial emission peaks, sandstorms, or sudden smog. By identifying abnormal fluctuations in the outdoor AQI, the pre-purification process is initiated before the indoor environment is significantly affected, effectively suppressing the formation of peak indoor pollutant concentrations.

[0047] The two pre-purification triggering mechanisms in this embodiment constitute a dual protection system: the triggering based on AQDI trends focuses on preventing gradual changes in pollution, while the triggering based on sudden changes in the outdoor air quality index focuses on responding to sudden pollution events. In actual operation, by continuously monitoring AQDI trends and outdoor air quality dynamics, the applicable triggering conditions can be intelligently determined, ensuring that the pre-purification function can be activated promptly under various pollution scenarios.

[0048] In an optional embodiment, dynamically adjusting the weight parameters, the first threshold, and the second threshold in the AQDI calculation using an adaptive learning algorithm may include: Record the indoor and outdoor air quality data, actual operating mode, and subsequent indoor air quality improvement for each AQDI calculation; Collect user feedback on manual operations, including manually switching operating modes or manually closing windows; Based on recorded operational data and user feedback, machine learning algorithms are used to analyze the impact of various parameters on the purification effect under different environmental conditions, and the weight parameters, as well as the values ​​of the first and second thresholds, are adjusted accordingly.

[0049] The technical solution of this embodiment will completely save the indoor and outdoor air quality data corresponding to each calculation of the air purification demand index. This data may include key parameters such as outdoor air quality index and fine particulate matter concentration, indoor fine particulate matter concentration, volatile organic compound concentration and temperature. It will also record the actual operating mode and its duration, and continuously track the subsequent improvement of indoor air quality, forming a complete chain for evaluating the operating effect.

[0050] Meanwhile, the technical solution of this embodiment records the timing and selected mode type when the user manually switches operating modes, as well as the user's manual window closing behavior. These manual operations reflect the user's direct judgment of the current environmental conditions and personalized needs, providing training samples for method optimization. This allows the control strategy to learn from actual usage scenarios and adjust in a direction that better meets user expectations. Based on the recorded operating data and user manual operation feedback, machine learning algorithms can be used for in-depth analysis. By analyzing the influence of various parameters on the actual purification effect under different environmental conditions, the weight parameters in the air purification demand index calculation formula can be automatically adjusted, making the calculation results more accurately reflect the actual purification needs. Furthermore, dynamically optimizing the values ​​of the first and second thresholds based on long-term operating results makes the mode switching timing more accurate. This continuous adaptive optimization process in the technical solution of this embodiment enables the control method to continuously improve its operating strategy, gradually increase air purification efficiency, and better adapt to users' personal preferences and usage habits.

[0051] In an optional embodiment, the value of the first threshold is automatically increased to trigger the switch from external circulation mode or pre-purification mode to internal circulation mode in advance, and the adjustment of the first threshold is triggered based on the user's manual window closing operation feedback.

[0052] In this embodiment, during the optimization of the control logic, when the user repeatedly performs the action of manually closing the window, a first threshold adjustment mechanism is automatically triggered. The principle behind this design is that the user's active window-closing behavior often indicates that outdoor air quality is beginning to deteriorate, or that the user has become more sensitive to the current air quality. This embodiment can promptly identify changes in the user's actual needs by capturing this behavioral characteristic. Specifically, after each recorded instance of the user manually closing the window, this event can be correlated with the current air quality parameters. When the user's window-closing operation occurs frequently under the same environmental conditions, the threshold adjustment program is activated, gradually increasing the value of the first threshold. This adjustment allows the switching from external circulation mode or pre-purification mode to internal circulation mode to be initiated earlier, ensuring that the change in operating mode is completed before the user perceives a change in air quality.

[0053] The adjustment mechanism in this embodiment allows for a deep alignment between the control strategy and user habits. By optimizing thresholds based on actual user behavior feedback, the triggering conditions for mode switching can better match the individual user's sensitivity and preferences. For example, if a user is particularly sensitive to outdoor pollutants, their frequent window-closing will cause the first threshold to rise accordingly, allowing the internal circulation mode to be activated earlier when air quality is relatively good. This personalized adjustment effectively enhances the user experience and makes air purification control more aligned with actual usage needs.

[0054] In an optional embodiment, the method updates indoor and outdoor air quality data at fixed time intervals and recalculates the AQDI to determine whether to switch operating modes.

[0055] In this embodiment, indoor and outdoor air quality data are updated at fixed time intervals. Specifically, the latest outdoor air quality index, fine particulate matter concentration, and other parameters are acquired every minute, while indoor fine particulate matter concentration, volatile organic compound concentration, and temperature monitoring data are updated simultaneously. This periodic data update mechanism in this embodiment ensures the real-time nature and accuracy of environmental status assessment.

[0056] Within each update cycle, the air purification demand index is recalculated immediately upon obtaining the latest indoor and outdoor air quality data. Based on the newly calculated index value, the system automatically determines whether to switch operating modes. If the new index value does not match the current operating mode, the system will switch to the corresponding operating mode promptly based on a comparison with preset thresholds.

[0057] In an optional embodiment, the adaptive learning algorithm is implemented using cloud or local computing resources and continuously optimizes the control strategy based on historical operating data and user feedback.

[0058] In this embodiment, the adaptive learning process implementation architecture provides two computing paths: cloud-based and local. The cloud-based computing path utilizes the data processing capabilities of a remote server to perform in-depth analysis of collected historical operation records and user feedback information, making it suitable for scenarios requiring complex calculations and big data processing. The local computing path relies on the air purifier's own processing unit to complete the learning optimization, featuring rapid response and independence from network connectivity.

[0059] Regarding the continuous optimization mechanism, the technical solution in this embodiment continuously accumulates historical operational data, including air quality parameters, equipment operating status, and user operation records, and combines this with user feedback on the purification effect, using machine learning methods to continuously improve the control strategy. This continuous optimization process makes the calculation of the air purification demand index more accurate, and the judgment of the timing of operating mode switching more in line with the actual use environment, thereby continuously improving the air purification effect and energy utilization efficiency in long-term operation.

[0060] Based on the foregoing technical solutions, the present invention also provides a control device for linking an air purifier with outdoor air quality information. From a macroscopic perspective, this device may include the following modules: The outdoor data acquisition module 202 is used to acquire outdoor air quality information in real time, including at least the outdoor air quality index (AQI) and PM2.5 concentration. The indoor data acquisition module 204 is used to collect indoor air quality parameters in real time, including at least indoor PM2.5 concentration, VOC concentration and temperature. The joint assessment and decision-making module 206 is used to calculate the Air Quality Demand Index (AQDI) based on the outdoor air quality information and indoor air quality parameters. The intelligent switching execution module 208 is used to compare the AQDI with a preset first threshold and a second threshold, and automatically switch the operating mode of the air purifier according to the comparison result; wherein, the value of the first threshold is greater than the value of the second threshold, and the operating mode includes an internal circulation mode, an external circulation mode, and a pre-purification mode; The adaptive learning module 210 is used to record historical running data and user feedback, and dynamically adjust the weight parameters, the first threshold and the second threshold in the AQDI calculation through an adaptive learning algorithm.

[0061] Figure 3 yes Figure 2 This diagram illustrates the collaborative relationships between various modules in the control device that links an air purifier to outdoor air quality information. It showcases the complete architecture and workflow of the air purification system. The system first acquires outdoor environmental parameters such as the city's air quality index, PM2.5 concentration, and pollen concentration through the outdoor data acquisition module. Simultaneously, it monitors indoor PM2.5 concentration, VOC concentration, carbon dioxide concentration, and temperature and humidity data through the indoor data acquisition module. All collected data is aggregated into a joint evaluation and decision-making module for comprehensive analysis. This module calculates the air purification demand index based on indoor and outdoor environmental conditions and makes operational decisions. The intelligent switching execution module controls the fan operation status based on the decision results, switching between external and internal circulation modes, while simultaneously operating valves and sending reminders to users to open or close windows. The adaptive learning module continuously collects system operation data and optimizes control parameters through machine learning algorithms, forming a complete closed-loop control system from environmental perception and intelligent decision-making to execution feedback.

[0062] like Figure 4 As shown, Figure 4 yes Figure 2 A schematic diagram of the signaling interaction between various modules in the control device that links the air purifier to outdoor air quality information is shown below. Figure 4 This embodiment details the complete implementation process of an intelligent switching control method for linking an air purifier with outdoor air quality information, as well as the interaction relationships between its modules.

[0063] After system startup, the initialization process is executed first, during which each module completes parameter configuration and establishes communication connections. Once initialization is complete, the system enters a continuous operating loop with a fixed frequency of one minute, clearly indicated by the "loop" label in the diagram. At the beginning of each operating cycle, the outdoor data acquisition module first sends an API request to the city's air quality data source to obtain outdoor air quality information including the Air Quality Index (AQI) and PM2.5 concentration. The data source receives the request and returns the corresponding outdoor data, completing a full data request-response interaction. Simultaneously, the indoor data acquisition process is executed in parallel within the system, using a sensor array to monitor indoor PM2.5 concentration, VOC concentration, and temperature parameters in real time, forming complete indoor environmental status data.

[0064] After the data acquisition phase is completed, the outdoor data acquisition module uploads the acquired outdoor data to the joint assessment and decision-making module, while the indoor data acquisition module simultaneously uploads the collected indoor environmental parameters, achieving complete aggregation of indoor and outdoor data. Upon receiving all data, the joint assessment and decision-making module immediately initiates the Air Quality Demand Index (AQDI) calculation process. This calculation process strictly follows a preset weighted formula, comprehensively considering multiple parameters such as outdoor air quality index, indoor PM2.5 concentration, VOC concentration, and temperature correction factor, ultimately generating a quantified AQDI value. After calculation, the system enters the decision-making phase. The joint assessment and decision-making module compares the calculated AQDI with preset first threshold θ_high and second threshold θ_low, generating corresponding control commands based on the comparison results. As shown in the "alt" selection box in the figure, the system provides three independent execution paths: the first path is selected when AQDI is greater than θ_high, the second path is selected when AQDI is less than θ_low, and the third path is selected in other cases.

[0065] Upon receiving the control command, the intelligent switching execution module immediately performs the corresponding operating mode switching operation. When AQDI is greater than θ_high, the module simultaneously performs three operations: activating the internal circulation mode and controlling the fan to operate at high speed to ensure rapid filtration of pollutants; sending a reminder to the user to close the windows to prevent outdoor pollutants from continuing to enter the room; and activating the pre-purification function, forming a multi-layered protection mechanism. When AQDI is less than θ_low, the module switches to external circulation mode and operates the fan at low speed, achieving energy savings while ensuring basic ventilation needs. When AQDI is in an intermediate state, the module precisely adjusts the fan speed according to the specific value, achieving a smooth transition between high and low speeds to ensure the optimal balance between purification effect and energy consumption.

[0066] Throughout the control process, the system executes an asynchronous adaptive learning process in parallel, independent of the main control loop, as shown in the dedicated "Adaptive Learning Process" area in the diagram. The intelligent switching execution module reports the complete data package for each run, including indoor and outdoor environmental parameters, the actual control strategy adopted, equipment operating status records, and user operation feedback, to the adaptive learning module. This module uses machine learning algorithms to perform in-depth analysis of accumulated historical operating data, assessing the impact of various control parameters on the actual purification effect under different environmental conditions and establishing a parameter optimization model. Based on the analysis results, the system automatically adjusts the allocation ratio of weight coefficients w1-w4 in the AQDI calculation formula and optimizes the specific values ​​of the mode switching thresholds θ_high and θ_low. These optimized parameters are updated in real time to the joint evaluation and decision-making module through a feedback mechanism, enabling continuous improvement and refinement of the control strategy.

[0067] The periodic data acquisition, intelligent decision-making, accurate execution, and autonomous learning in this technical solution form a complete intelligent control closed loop. Each operating cycle is built upon historical experience, continuously improving the system's control accuracy and adaptability through parameter optimization. The system not only responds in real-time to changes in the indoor and outdoor environment but also learns user operating habits and preferences to gradually achieve personalized air purification services.

[0068] Those skilled in the art will understand that the modules in the apparatus of the embodiments can be distributed in the apparatus of the embodiments as described in the embodiments, or they can be located in one or more devices different from this embodiment with corresponding changes. The modules of the above embodiments can be combined into one module, or they can be further divided into multiple sub-modules.

[0069] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A control method for an air purifier linked to outdoor air quality information, characterized in that, The method includes the following steps: Real-time acquisition of outdoor air quality information, including at least the outdoor air quality index (AQI) and PM2.5 concentration; Real-time collection of indoor air quality parameters, including at least indoor PM2.5 concentration, VOC concentration, and temperature; Based on the outdoor air quality information and indoor air quality parameters, the Air Quality Demand Index (AQDI) is calculated. The formula for calculating the AQDI is as follows: ； Among them, symbols Indicates the first weight, symbol Indicates the second weight, symbol Indicates the third weight, symbol Indicates the fourth weight; symbol Indicates the outdoor air quality index, symbol Indicates the reference safety value for outdoor air quality index, symbol Indicates the real-time indoor PM2.5 concentration, symbol Indicates the reference safety value for indoor PM2.5 concentration, symbol Indicates the real-time concentration of volatile organic compounds (VOCs) indoors, symbol [symbol missing]. Indicates the reference safety value for indoor VOC concentration, symbol Indicates the temperature correction factor; The AQDI is compared with a preset first threshold and a second threshold, and the air purifier's operating mode is automatically switched according to the comparison result; wherein, the value of the first threshold is greater than the value of the second threshold, and the operating mode includes internal circulation mode, external circulation mode and pre-purification mode; Record historical operation data and user feedback, and dynamically adjust the weight parameters, the first threshold, and the second threshold in the AQDI calculation through an adaptive learning algorithm.

2. The control method for linking an air purifier with outdoor air quality information according to claim 1, characterized in that, The real-time acquisition of outdoor air quality information includes: calling the city air quality data API through a network interface to acquire the outdoor air quality information at fixed time intervals, storing the data in a local cache and uploading it to the cloud; The real-time acquisition of indoor air quality parameters includes: collecting PM2.5 concentration, VOC concentration, CO2 concentration, and temperature and humidity data through indoor sensors, and performing noise filtering and standardization processing on the collected sensor data to generate a standardized indoor air quality index.

3. The control method for linking an air purifier with outdoor air quality information according to claim 1, characterized in that, The automatic switching of the air purifier's operating mode based on the comparison results includes: When the AQDI is greater than the first threshold, the internal circulation mode is activated, and the air purifier is controlled to run at the first fan speed to achieve powerful purification, while a reminder to close the window is issued. When the AQDI is less than the second threshold, the external circulation mode is activated, and the air purifier is controlled to run at the second fan speed to achieve energy-saving ventilation. When the AQDI is between the second threshold and the first threshold, the fan speed is adjusted between the first fan speed setting and the second fan speed setting according to the difference between indoor and outdoor air quality. The operation mode switching also includes controlling the speed of the fan and the opening and closing status of the valves.

4. The control method for linking an air purifier with outdoor air quality information according to claim 1, characterized in that, The method also includes at least one of the following pre-purification triggering mechanisms: When the AQDI approaches but does not exceed the first threshold, the pre-purification mode is activated, and the fan and filter are started in advance to purify the air. When the outdoor air quality index changes abruptly, the pre-purification mode is automatically activated in advance to reduce the peak concentration of indoor pollutants.

5. The control method for linking an air purifier with outdoor air quality information according to claim 1, characterized in that, The step of dynamically adjusting the weight parameters, the first threshold, and the second threshold in the AQDI calculation using an adaptive learning algorithm includes: Record the indoor and outdoor air quality data, actual operating mode, and subsequent indoor air quality improvement for each AQDI calculation; Collect user feedback on manual operations, including manually switching operating modes or manually closing windows; Based on recorded operational data and user feedback, machine learning algorithms are used to analyze the impact of various parameters on the purification effect under different environmental conditions, and the weight parameters, as well as the values ​​of the first and second thresholds, are adjusted accordingly.

6. The control method for linking an air purifier with outdoor air quality information according to claim 5, characterized in that, The value of the first threshold is automatically increased to trigger the switch from external circulation mode or pre-purification mode to internal circulation mode in advance, and the adjustment of the first threshold is triggered based on the user's manual closing of the window operation feedback.

7. The control method for linking an air purifier with outdoor air quality information according to claim 1, characterized in that, The method updates indoor and outdoor air quality data at fixed time intervals and recalculates AQDI to determine whether to switch operating modes.

8. The control method for linking an air purifier with outdoor air quality information according to claim 1, characterized in that, The adaptive learning algorithm is implemented using cloud or local computing resources and continuously optimizes the control strategy based on historical operating data and user feedback.

9. A control device for linking an air purifier to outdoor air quality information, characterized in that, The device includes: An outdoor data acquisition module is used to acquire outdoor air quality information in real time, including at least the outdoor air quality index (AQI) and PM2.5 concentration. An indoor data acquisition module is used to collect indoor air quality parameters in real time, including at least indoor PM2.5 concentration, VOC concentration, and temperature. The joint assessment and decision-making module is used to calculate the Air Quality Demand Index (AQDI) based on the outdoor air quality information and indoor air quality parameters. The formula for calculating the AQDI is as follows: ； Among them, symbols Indicates the first weight, symbol Indicates the second weight, symbol Indicates the third weight, symbol Indicates the fourth weight; symbol Indicates the outdoor air quality index, symbol Indicates the reference safety value for outdoor air quality index, symbol Indicates the real-time indoor PM2.5 concentration, symbol Indicates the reference safety value for indoor PM2.5 concentration, symbol Indicates the real-time concentration of volatile organic compounds (VOCs) indoors, symbol [symbol missing]. Indicates the reference safety value for indoor VOC concentration, symbol Indicates the temperature correction factor; The intelligent switching execution module is used to compare the AQDI with a preset first threshold and a second threshold, and automatically switch the operating mode of the air purifier according to the comparison result; wherein the value of the first threshold is greater than the value of the second threshold, and the operating mode includes internal circulation mode, external circulation mode and pre-purification mode; The adaptive learning module is used to record historical operation data and user feedback, and dynamically adjust the weight parameters, the first threshold and the second threshold in the AQDI calculation through an adaptive learning algorithm.

Images