Air purification method and device based on big data, electronic equipment and storage medium

Abstract

The invention provides an air purification method and device based on big data, electronic equipment and a storage medium, and relates to the technical field of data processing. The air purification method based on the big data comprises the steps that indoor air data detected by a plurality of air purifiers and environment sensing data detected by a plurality of associated sensors are obtained, and the actual air quality change trend is determined according to the indoor air data and the environment sensing data; according to the actual air quality change trend, the initial air pollutant concentration, the highest pollutant concentration and the air quality change attribute are determined, and the overall air quality in the current environment is determined according to the initial air pollutant concentration, the highest pollutant concentration and the air quality change attribute; according to the actual air quality change trend, the indoor air data and the environment sensing data, a pollution source and a corresponding pollution source type are determined; and according to the air influence data, the overall air quality, the pollution source and the pollution source type in the preset distance range, a target purification mode is determined.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to an air purification method, device, electronic device and storage medium based on big data. Background Art

[0002] With the development of science and technology, people's requirements for quality of life are gradually increasing, and products such as air purifiers that can effectively improve air cleanliness have emerged. In a relatively closed space, the release of air pollutants is characterized by persistence and uncertainty. Using an air purifier is one of the effective ways to improve indoor air quality, which is of great significance for protecting people's health and improving the quality of life. Air purifiers can be used in many fields such as home, medical, and industry.

[0003] In the related art, multiple sensors are generally set in the air purifier, and the concentration threshold of air pollutants is pre-set. When the concentration detected by the sensor exceeds the concentration threshold, the corresponding purification method is called to purify the air. However, the current air purification method is relatively simple, resulting in poor overall purification effect. Summary of the invention

[0004] The present application aims to provide an air purification method, device, electronic device and storage medium based on big data, which can improve the overall purification effect.

[0005] According to one aspect of the present application, a method for air purification based on big data is proposed, comprising: Acquire indoor air data detected by multiple air purifiers and environmental sensing data detected by multiple associated sensors, and determine the actual air quality change trend based on the indoor air data and environmental sensing data; Determine the initial air pollutant concentration, the maximum pollutant concentration and the air quality change attributes according to the actual air quality change trend, so as to determine the overall air quality in the current environment according to the initial air pollutant concentration, the maximum pollutant concentration and the air quality change attributes; Determine the pollution sources and corresponding pollution source types based on actual air quality change trends, indoor air data, and environmental sensor data; Determine the target purification method based on air impact data, overall air quality, pollution sources and pollution source types within a preset distance range.

[0006] According to some embodiments, determining the actual air quality change trend based on indoor air data and environmental sensor data includes: Determine a first change trend according to a preset statistical analysis method and indoor air data; Determine the model and the environmental sensor data according to the preset change trend, and determine a second change trend; According to the preset data check difference, the first change trend and the second change trend, the actual air quality change trend is determined.

[0007] According to some embodiments, determining the initial air pollutant concentration, the maximum pollutant concentration, and the air quality change attribute according to the actual air quality change trend includes: Get the key time points in the current environment; Extract pollutant concentration data corresponding to key time points from actual air quality change trends; According to a preset valid data selection method, the first valid data point in the pollutant concentration data is determined as the initial air pollutant concentration; Extract the highest pollutant concentration from the actual air quality change trend; Determine the attributes of air quality changes based on pollutant concentration data.

[0008] According to some embodiments, determining an air quality change attribute based on pollutant concentration data includes: Based on key time points, stage data analysis is performed on pollutant concentration data to determine the concentration change rate and concentration fluctuation information; The air quality change attributes are determined based on the preset attribute threshold, concentration change rate and concentration fluctuation information.

[0009] According to some embodiments, determining the overall air quality in the current environment according to the initial air pollutant concentration, the maximum pollutant concentration, and the air quality change attribute includes: Based on the preset air quality standards, initial air pollutant concentrations and maximum pollutant concentrations, determine the excess information of pollutant concentrations in the current environment; Determine the overall air quality based on the exceedance information and air quality change attributes.

[0010] According to some embodiments, further comprising: Get the location data and layout information of the current environment; Based on the layout information, determine the flow properties of different air pollutants; Set preset distance ranges based on location data and flow properties.

[0011] According to some embodiments, determining pollution sources and corresponding pollution source types based on actual air quality change trends, indoor air data, and environmental sensor data includes: According to the preset data analysis method, the actual air quality change trend, indoor air data and environmental sensor data are processed to determine the key characteristics and abnormal points of air quality changes; Determine the pollution sources and their basic source directions based on actual air quality change trends, key features and anomalies; Determine the type of pollution source based on the basic source direction and actual air quality change trend.

[0012] According to one aspect of the present application, an air purification device based on big data is proposed, comprising: A change trend determination module is used to obtain indoor air data detected by multiple air purifiers and environmental sensing data detected by multiple associated sensors, and determine the actual air quality change trend based on the indoor air data and environmental sensing data; An air quality determination module, for determining the initial air pollutant concentration, the maximum pollutant concentration and the air quality change attribute according to the actual air quality change trend, so as to determine the overall air quality in the current environment according to the initial air pollutant concentration, the maximum pollutant concentration and the air quality change attribute; A type determination module is used to determine the pollution source and the corresponding pollution source type based on the actual air quality change trend, indoor air data and environmental sensor data; The purification method determination module is used to determine the target purification method based on the air impact data, overall air quality, pollution sources and pollution source types within a preset distance range.

[0013] Optionally, when determining the actual air quality change trend according to the indoor air data and the environmental sensor data, the change trend determination module is specifically used to: Determine a first change trend according to a preset statistical analysis method and indoor air data; Determine the model and the environmental sensor data according to the preset change trend, and determine a second change trend; According to the preset data check difference, the first change trend and the second change trend, the actual air quality change trend is determined.

[0014] Optionally, the air quality determination module is specifically used to determine the initial air pollutant concentration, the maximum pollutant concentration and the air quality change attribute according to the actual air quality change trend: Get the key time points in the current environment; Extract pollutant concentration data corresponding to key time points from actual air quality change trends; According to a preset valid data selection method, the first valid data point in the pollutant concentration data is determined as the initial air pollutant concentration; Extract the highest pollutant concentration from the actual air quality change trend; Determine the attributes of air quality changes based on pollutant concentration data.

[0015] Optionally, when the air quality determination module determines the air quality change attribute according to the pollutant concentration data, it is specifically used to: Based on key time points, stage data analysis is performed on pollutant concentration data to determine the concentration change rate and concentration fluctuation information; The air quality change attributes are determined based on the preset attribute threshold, concentration change rate and concentration fluctuation information.

[0016] Optionally, the air quality determination module is specifically used to determine the overall air quality in the current environment according to the initial air pollutant concentration, the maximum pollutant concentration and the air quality change attribute: Based on the preset air quality standards, initial air pollutant concentrations and maximum pollutant concentrations, determine the excess information of pollutant concentrations in the current environment; Determine the overall air quality based on the exceedance information and air quality change attributes.

[0017] Optionally, the air purification device based on big data further includes a range setting module, which is used to: Get the location data and layout information of the current environment; Based on the layout information, determine the flow properties of different air pollutants; Set preset distance ranges based on location data and flow properties.

[0018] Optionally, the type determination module is specifically used for: According to the preset data analysis method, the actual air quality change trend, indoor air data and environmental sensor data are processed to determine the key characteristics and abnormal points of air quality changes; Determine the pollution sources and their basic source directions based on actual air quality change trends, key features and anomalies; Determine the type of pollution source based on the basic source direction and actual air quality change trend.

[0019] According to one aspect of the present application, an electronic device is proposed, which includes: a processor; and a memory storing a computer program, wherein when the computer program is executed by the processor, the processor executes the air purification method based on big data as described above.

[0020] According to one aspect of the present application, a non-transitory computer-readable medium is provided, on which readable instructions are stored. When the instructions are executed by a processor, the processor executes the air purification method based on big data as described above.

[0021] It should be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the present application.

[0022] Through the above-mentioned embodiments provided by the present application, through big data analysis and machine learning technology, it is possible to accurately identify pollution sources and their types, so as to take targeted purification measures to effectively improve the air purification efficiency. It avoids the "one-size-fits-all" purification method in traditional air purification methods, and reduces unnecessary energy consumption and waste of purifiers. According to the actual air quality change trend and the change of pollution sources, the purification strategy is dynamically adjusted to ensure that the indoor air quality is always in good condition. Especially in the face of sudden pollution sources or a sharp deterioration in air quality, it can respond quickly and effectively protect the health of indoor personnel. By accurately identifying pollution sources and dynamically adjusting purification strategies, unnecessary energy consumption and emissions are avoided, which is in line with the green and low-carbon development concept. At the same time, intelligent air purification management also helps to improve people's environmental awareness and promote the formation of a green lifestyle. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0024] Figure 1 A flowchart of an air purification method based on big data provided in an embodiment of the present application; Figure 2 A block diagram of an air purification device based on big data provided in an embodiment of the present application; Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0026] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0027] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0028] Figure 1 This is a flow chart of an air purification method based on big data provided in an embodiment of the present application. The method of this embodiment can be applied to a purification analysis server. Figure 1 As shown, the method includes: step S10, step S11, step S12 and step S13.

[0029] In step S10, indoor air data detected by multiple air purifiers and environmental sensing data detected by multiple associated sensors are obtained, and the actual air quality change trend is determined based on the indoor air data and the environmental sensing data.

[0030] In this application, multiple air purifiers can be installed in the indoor area to be monitored, and associated sensors can also be set, such as weather station sensors for detecting temperature, humidity, wind speed, etc., light sensors, etc. These associated sensors can exchange information with the air purifier. Indoor air data can include PM2.5, PM10, carbon dioxide concentration, etc.

[0031] According to an example embodiment, the air purifier can detect indoor air data and then receive environmental sensing data detected and sent by the associated sensor. Data cleaning is performed on these data to remove invalid or abnormal data. The processed data can be modeled using a time series analysis method to predict the actual air quality change trend in the future.

[0032] In step S11, the initial air pollutant concentration, the maximum pollutant concentration and the air quality change attribute are determined according to the actual air quality change trend, so as to determine the overall air quality in the current environment according to the initial air pollutant concentration, the maximum pollutant concentration and the air quality change attribute.

[0033] In this application, the actual air quality change trend may include the initial air pollutant concentration, the maximum pollutant concentration, and the air quality change attribute, which may include relevant information of multiple pollutants. The air quality change attribute can be used to characterize the concentration change and change rate of different pollutants.

[0034] According to an example embodiment, the concentration at the beginning of the monitoring period can be used as the initial concentration, such as the concentration at 12 o'clock in the morning of the day. During the monitoring period, the highest concentration value can be used as the highest pollutant concentration of the pollutant. The rate of change of each pollutant concentration from the initial value to the highest value can be calculated in the following way: Change rate = (maximum concentration - initial concentration) / initial concentration * 100%.

[0035] Then, the data can be analyzed from a time series perspective to determine the trend of pollutant concentration changes, which can include rising, falling, and stable concentrations. Concentration thresholds for different pollutant concentrations can also be pre-set, and the rate of change, trend of change, and duration of exceeding the concentration threshold can be used as air quality change attributes.

[0036] The air quality standards set by the region can be obtained to determine the air quality levels of different pollutant concentrations. Based on this, weights are set in advance for the concentrations of various pollutants and the air quality change attributes to calculate the corresponding air quality levels. The initial air pollutant concentration, the maximum pollutant concentration, and the air quality change attributes can be directly matched to the overall air quality in the current environment, which can be reflected as a preset air quality level.

[0037] In step S12, the pollution sources and corresponding pollution source types are determined according to the actual air quality change trend, indoor air data and environmental sensor data.

[0038] In the present application, a reverse diffusion model can be pre-set, and the actual air quality change trend, indoor air data and environmental sensor data can be input into the model to output the location of the pollution source. Based on the pre-stored indoor layout diagram, the name of the specific pollution source corresponding to the pollution source location can be determined. Then, according to the characteristics of the preset pollution source, it can be compared with the actual indoor air data and environmental sensor data to match the corresponding pollution source type. In some implementations, the pollution source type can be divided according to the degree of harm, or it can be divided according to the harm to the residents.

[0039] In step S13, a target purification method is determined based on air impact data, overall air quality, pollution sources and pollution source types within a preset distance range.

[0040] In the present application, the preset distance range may be a range within a certain distance based on the center of the current location. The range may be set based on the location of the location, the surrounding environment, etc. The air impact data may be used to characterize air quality detection data within the preset distance range, including but not limited to the concentration of pollutants such as PM2.5.

[0041] The target purification method determination model can be pre-set, and the air impact data, overall air quality, pollution sources and pollution source types within the preset distance range are input into the model to directly output the target purification method. The target purification method includes the purification equipment to be called, the working order of the purification equipment, the working time, etc.

[0042] This application uses big data analysis and machine learning technology to accurately identify pollution sources and their types, so as to take targeted purification measures and effectively improve air purification efficiency. It avoids the "one-size-fits-all" purification method in traditional air purification methods and reduces unnecessary energy consumption and waste of purifiers. According to the actual air quality change trend and the change of pollution sources, the purification strategy is dynamically adjusted to ensure that the indoor air quality is always in good condition. Especially in the face of sudden pollution sources or a sharp deterioration in air quality, it can respond quickly and effectively protect the health of indoor personnel. By accurately identifying pollution sources and dynamically adjusting purification strategies, unnecessary energy consumption and emissions are avoided, which is in line with the green and low-carbon development concept. At the same time, intelligent air purification management also helps to improve people's environmental awareness and promote the formation of a green lifestyle.

[0043] According to some embodiments, a first change trend can be determined based on a preset statistical analysis method and indoor air data; a second change trend can be determined based on a preset change trend by determining a model and environmental sensor data; and an actual air quality change trend can be determined based on preset data check differences, the first change trend, and the second change trend.

[0044] In the present application, the preset data check difference can be used to represent the difference caused by the equipment difference of different acquisition devices of indoor air data and environmental sensor data.

[0045] According to an example embodiment, the pre-processed indoor air data can be analyzed according to a preset statistical analysis method (such as time series analysis, regression analysis, machine learning model, etc.). A first change trend of indoor air pollutant concentration is determined, which may be manifested as concentration rising, falling, or remaining relatively stable over time. A preset change trend determination model (which may be a prediction based on a physical model, a machine learning model, or an empirical formula) is used in combination with environmental sensor data to predict or infer possible external influences on indoor air quality, thereby forming a second change trend.

[0046] Based on the pre-stored device properties, identify and quantify the data deviation caused by the inherent differences (device differences) between the devices that acquire indoor air data and environmental sensor data. These differences may be caused by factors such as the device's measurement principle, accuracy, calibration status, installation location, etc.

[0047] A comprehensive analysis model may be established in advance, data inspection differences, a first change trend, and a second change trend may be input into the model, and the actual air quality change trend may be directly output.

[0048] This application determines the actual air quality change trend more accurately by integrating indoor air data and environmental sensor data, and can provide strong data support for indoor air purification decisions. Accurate purification decisions can ensure that purification equipment is started in time when air quality deteriorates, avoiding unnecessary energy consumption and waste of purification agents.

[0049] According to some embodiments, key time points in the current environment can be obtained; pollutant concentration data corresponding to the key time points can be extracted from the actual air quality change trend; according to a preset valid data selection method, the first valid data point in the pollutant concentration data is determined as the initial air pollutant concentration; the highest pollutant concentration is extracted from the actual air quality change trend; and the air quality change attributes are determined based on the pollutant concentration data.

[0050] In this application, key time points can be used to characterize the time points of events corresponding to sudden weather changes, special holidays, large-scale events, changes in traffic conditions, etc. The effective data selection method can be a pre-set method for selecting data that better reflects the changes in pollutant concentrations from a number of data, which can include methods such as data integrity check, data rationality judgment, data quality scoring, etc.

[0051] This can be done by obtaining important events or changes in the current environment, which can be obtained through public network platforms. By comparing the information of pre-set historical event points, the key time points corresponding to the current important events can be determined. In some implementations, a reasonable time window can be set for subsequent analysis based on the nature and possible impact of the key event. The time window should be long enough to include the air quality changes before and after the key event.

[0052] From the data set containing the actual air quality change trend, find the pollutant concentration data in the time period corresponding to the key time point. According to the preset valid data selection method, the extracted pollutant concentration data is screened. The first data point that meets all valid data selection criteria is determined as the initial air pollutant concentration.

[0053] In the actual air quality change trend, all pollutant concentration data are compared to find the data point with the highest concentration. In some implementations, if there are multiple maximum values, the most representative maximum pollutant concentration is further determined based on factors such as time sequence and duration. According to the pollutant concentration data, the trend of air quality changes is analyzed, including concentration increases, decreases, fluctuations, etc. The main analysis objects are the concentration changes before and after the key time points, and the difference between the maximum pollutant concentration and the initial air pollutant concentration. In some implementations, labels can be set for the main analysis objects, and then the labeled pollutant concentration data can be input into the preset attribute change determination model to directly output the corresponding air quality change attributes.

[0054] This application can accurately determine the initial air pollutant concentration by obtaining key time points in the current environment and extracting corresponding pollutant concentration data from the actual air quality change trend. By determining the initial air pollutant concentration, the starting point of indoor pollution can be accurately identified, providing key information for the timely start of air purification equipment. Extracting the highest pollutant concentration allows us to accurately grasp the severity of indoor pollution, so that we can adjust the air purification strategy in a targeted manner, such as increasing the operating power of the air purifier, shortening the purification cycle, etc., to effectively respond to pollution peaks. Extracting the highest pollutant concentration from the actual air quality change trend can intuitively show the extreme conditions of air quality during the monitoring period. This is crucial for assessing the extent of air quality deterioration and potential health risks.

[0055] According to some embodiments, stage data analysis can be performed on pollutant concentration data based on key time points to determine the concentration change rate and concentration fluctuation information; and the air quality change attributes can be determined based on preset attribute thresholds, concentration change rate and concentration fluctuation information.

[0056] In this application, pollutant concentration data can be divided into different time periods or stages according to key time points (such as weather changes, traffic rush hours, special events, etc.). Ensure that the data of each stage can reflect the air quality conditions under a specific environment. For each stage, calculate the rate of change of pollutant concentration. This can be achieved by calculating the difference in concentration at the beginning and end of the stage, and then dividing it by the length of the stage. The rate of change can reflect how fast the air quality changes in a short period of time. In addition to the rate of change, the fluctuation of concentration in each stage can also be analyzed. Specifically, it can be measured by calculating indicators such as the standard deviation and coefficient of variation of the concentration. Fluctuation information helps to understand the slight changes in air quality in a stable state or the drastic fluctuations in an unstable state.

[0057] A series of attribute thresholds can be preset based on preset air quality standards and historical data analysis. These thresholds include thresholds for concentration change rate and concentration fluctuation range, which are used to determine the changing attributes of air quality. The calculated concentration change rate and concentration fluctuation information are compared with the preset attribute thresholds. Based on the comparison results, the changing attributes of air quality are determined, such as "significantly improved", "slightly improved", "remaining stable", "slightly deteriorated" or "significantly deteriorated".

[0058] This application can timely detect the trend of air quality deterioration through real-time monitoring and analysis of concentration change rate and fluctuation information, and provide timely warning information for the air purification process so that countermeasures can be taken. Long-term and continuous analysis of air quality change attributes can provide historical data for reference for the air purification process in the current environment.

[0059] According to some embodiments, the excess information of pollutant concentration in the current environment can be determined based on the preset air quality standard, the initial air pollutant concentration and the maximum pollutant concentration; the overall air quality can be determined based on the excess information and the air quality change attributes.

[0060] In this application, the concentration limits of various pollutants can be preset according to relevant international or domestic air quality standards. These standards usually include the concentration limits of different pollutants (such as PM2.5, PM10, NO2, SO2, O3, etc.) in different time periods (such as 24-hour average, 1-hour average, etc.).

[0061] For the initial air pollutant concentration and the maximum pollutant concentration, the excess multiples relative to the preset air quality standard can be calculated respectively. The excess multiples can be calculated using the following formula: Exceeding standard multiple = pollutant concentration / standard limit - 1.

[0062] If the calculation result is a positive number, it means that the pollutant concentration exceeds the standard; if it is a negative number or zero, it means that it does not exceed the standard. According to the calculation result of the excess multiple, determine which pollutants exceed the standard and the degree of excess. Exceeding standard information can include the type of pollutant that exceeds the standard, the excess multiple, and the duration of the excess.

[0063] The initial pollutant concentration, maximum pollutant concentration, and excess multiples can be input into the preset fuzzy logic system, and the fuzzy evaluation of the overall air quality (such as "excellent", "good", "lightly polluted", "moderately polluted", etc.) can be output according to the preset fuzzy rules and membership functions. The air quality evaluation is decomposed into multiple levels, such as the pollutant concentration layer, the excess information layer, the change trend layer, etc., and the overall air quality comprehensive score is calculated by comparing the relative importance of the elements at each level. The neural network model is trained using historical air quality data and preset evaluation results, and then the current initial pollutant concentration, maximum pollutant concentration, excess information, and air quality change attributes are input to output the predicted evaluation of the overall air quality, that is, the overall air quality.

[0064] This application can more comprehensively reflect the air quality conditions in the current environment and improve the accuracy of the evaluation by comprehensively considering the initial pollutant concentration, maximum pollutant concentration, exceeding standard information and air quality change trends.

[0065] According to some embodiments, the location data and layout information of the current environment may also be obtained; the flow properties of different air pollutants may be determined based on the layout information; and a preset distance range may be set based on the location data and the flow properties.

[0066] In this application, you can use satellite positioning systems such as GPS and Beidou, or wireless signal positioning technologies such as Wi-Fi and Bluetooth to obtain the geographical location data of the current environment (such as cities, industrial areas, residential areas, etc.), including longitude, latitude, altitude and other information. Through remote sensing satellite images, drone aerial photography, on-site surveys and other means, collect the layout information of the current environment, including topography, building distribution, road network, green space coverage, water distribution, etc. This information can be digitized through a geographic information system (GIS) to form a layout map or a three-dimensional model.

[0067] According to the physical and chemical properties of air pollutants, they are divided into different categories, such as particulate matter (PM2.5, PM10), gaseous pollutants (SO2, NOx, O3), heavy metals, etc. A flow property determination model can be established in advance to analyze the flow properties of different types of pollutants under specific layout conditions. In some implementations, a model can be established in combination with fluid mechanics and atmospheric diffusion theory, which can include the diffusion rate, diffusion direction, deposition rate, etc. of pollutants. The analysis results are organized into a database to record the flow properties of various types of pollutants under different layout conditions. The database may include information such as pollutant type, layout characteristics, flow property parameters (such as diffusion coefficient, wind direction and speed, deposition efficiency, etc.).

[0068] According to the location data and layout information of the current environment, the corresponding pollutant flow properties are retrieved from the flow property database. Based on the retrieved flow property parameters, combined with the degree of impact of air pollutants on human health and the environment, a preset distance range is set. This range can be one or more concentric circles, ellipses or other shaped areas, which are used to define the impact range under different pollution levels. In some implementations, the impact of changes in meteorological conditions (such as wind direction, wind speed, temperature, humidity, etc.) on the flow properties of pollutants can be considered to dynamically adjust the preset distance range. This can be achieved by real-time monitoring of meteorological data and real-time simulation using an atmospheric diffusion model.

[0069] By accurately identifying the flow path and diffusion range of pollutants, this application can more accurately deploy air purification equipment or take other air purification measures, which helps to improve air purification efficiency and reduce unnecessary waste of resources. By setting a reasonable preset distance range, potential high-pollution areas and sensitive points can be discovered and controlled in a timely manner. This helps reduce the impact of air pollution on public health and the environment and improve the quality of life of residents.

[0070] According to some embodiments, data processing can be performed on the actual air quality change trend, indoor air data and environmental sensor data according to a preset data analysis method to determine the key characteristics and abnormal points of air quality changes; the pollution source and the basic source direction of the pollution source can be determined based on the actual air quality change trend, key characteristics and abnormal points; the pollution source type can be determined based on the basic source direction and the actual air quality change trend.

[0071] In this application, the actual air quality change trend data is smoothed to remove noise, and methods such as moving average or Savitzky-Golay filtering can be used. Indoor air data and environmental sensor data are standardized to ensure that the data are comparable on the same scale. Key features are extracted from the preprocessed data using methods such as principal component analysis (PCA) or independent component analysis (ICA), which can reflect the main components of air quality changes. Time series analysis techniques such as autoregressive integrated moving average model (ARIMA) or long short-term memory network (LSTM) are used to identify trend terms, seasonal terms, and random terms in air quality change trends.

[0072] Statistical methods such as z-score or IQR (interquartile range) are used to detect anomalies in the data, which may indicate the presence of pollution sources or emergencies. In some implementations, machine learning algorithms such as Isolation Forest or Local Outlier Factor (LOF) can also be used for unsupervised anomaly detection to ultimately obtain key features and anomalies.

[0073] Match the extracted key features with the air quality change trend to identify the characteristic patterns related to the pollution source. Analyze the association between the abnormal points and the air quality change trend to determine whether the abnormal points are caused by the pollution source. Use the wind direction and wind speed information in the environmental sensor data, combined with the location and time of the abnormal points, to infer the basic source direction of the pollution source. In some implementations, geographic information system (GIS) data can be combined for more accurate spatial analysis.

[0074] According to the basic source direction, the characteristics of air quality change trend and the list of possible pollution sources (such as industrial emissions, traffic emissions, domestic emissions, etc.), a classification model such as decision tree or random forest is established. The actual air quality change trend, key characteristics and abnormal point information are input, and the type of pollution source is determined through the classification model.

[0075] This application can accurately locate indoor and surrounding pollution sources by comprehensively analyzing actual air quality change trends, indoor air data, and environmental sensor data, providing clear goals for indoor air purification. Targeted air purification strategies can be formulated based on the determined pollution source types and basic source directions. For example, for industrial emission pollution from outdoors, the filtration efficiency of the indoor ventilation system can be enhanced; for indoor living emissions, the frequency of use of air purifiers can be increased or the indoor layout can be optimized to reduce pollution sources. By accurately identifying the types and source directions of pollution sources, air purification resources can be allocated more effectively to avoid unnecessary waste. At the same time, measures taken against specific pollution sources can often improve indoor air quality more quickly.

[0076] The following describes an apparatus embodiment of the present application, which can be used to execute the method embodiment of the present application. For details not disclosed in the apparatus embodiment of the present application, reference can be made to the method embodiment of the present application.

[0077] Figure 2 This is a block diagram of an air purification device based on big data provided in an embodiment of the present application. Figure 2 As shown, the air purification device 200 based on big data includes a change trend determination module 201, an air quality determination module 202, a type determination module 203 and a purification method determination module 204.

[0078] The change trend determination module 201 is used to obtain indoor air data detected by multiple air purifiers and environmental sensing data detected by multiple associated sensors, and determine the actual air quality change trend based on the indoor air data and the environmental sensing data; The air quality determination module 202 is used to determine the initial air pollutant concentration, the maximum pollutant concentration and the air quality change attribute according to the actual air quality change trend, so as to determine the overall air quality in the current environment according to the initial air pollutant concentration, the maximum pollutant concentration and the air quality change attribute; A type determination module 203 is used to determine the pollution source and the corresponding pollution source type according to the actual air quality change trend, indoor air data and environmental sensor data; The purification mode determination module 204 is used to determine a target purification mode according to air impact data, overall air quality, pollution sources and pollution source types within a preset distance range.

[0079] Optionally, when determining the actual air quality change trend according to the indoor air data and the environmental sensor data, the change trend determination module 201 is specifically used to: Determine a first change trend according to a preset statistical analysis method and indoor air data; Determine the model and the environmental sensor data according to the preset change trend, and determine a second change trend; According to the preset data check difference, the first change trend and the second change trend, the actual air quality change trend is determined.

[0080] Optionally, the air quality determination module 202 is specifically used to: Get the key time points in the current environment; Extract pollutant concentration data corresponding to key time points from actual air quality change trends; According to a preset valid data selection method, the first valid data point in the pollutant concentration data is determined as the initial air pollutant concentration; Extract the highest pollutant concentration from the actual air quality change trend; Determine the attributes of air quality changes based on pollutant concentration data.

[0081] Optionally, when determining the air quality change attribute according to the pollutant concentration data, the air quality determination module 202 is specifically used to: Based on key time points, stage data analysis is performed on pollutant concentration data to determine the concentration change rate and concentration fluctuation information; The air quality change attributes are determined based on the preset attribute threshold, concentration change rate and concentration fluctuation information.

[0082] Optionally, the air quality determination module 202 is specifically used to: determine the overall air quality in the current environment according to the initial air pollutant concentration, the maximum pollutant concentration and the air quality change attribute; Based on the preset air quality standards, initial air pollutant concentrations and maximum pollutant concentrations, determine the excess information of pollutant concentrations in the current environment; Determine the overall air quality based on the exceedance information and air quality change attributes.

[0083] Optionally, the air purification device 200 based on big data further includes a range setting module 205, which is used to: Get the location data and layout information of the current environment; Based on the layout information, determine the flow properties of different air pollutants; Set preset distance ranges based on location data and flow properties.

[0084] Optionally, the type determination module 203 is specifically configured to: According to the preset data analysis method, the actual air quality change trend, indoor air data and environmental sensor data are processed to determine the key characteristics and abnormal points of air quality changes; Determine the pollution sources and their basic source directions based on actual air quality change trends, key features and anomalies; Determine the type of pollution source based on the basic source direction and actual air quality change trend.

[0085] The device performs functions similar to the method provided above. For other functions, please refer to the previous description and will not be repeated here.

[0086] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application, such as Figure 3 As shown, the electronic device 300 of this embodiment may include: a memory 301 and a processor 302 .

[0087] The memory 301 stores a computer program. When the computer program is executed by the processor 302, the processor 302 executes the method in the above embodiment.

[0088] The processor 302 and the memory 301 are connected, for example, via a bus.

[0089] Optionally, the electronic device 300 may further include a transceiver. It should be noted that in actual applications, the number of transceivers is not limited to one, and the structure of the electronic device 300 does not constitute a limitation on the embodiments of the present application.

[0090] The processor 302 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor 302 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0091] The bus may include a path to transmit information between the above components. The bus may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0092] The memory 301 can be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to these.

[0093] The memory 301 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 302. The processor 302 is used to execute the application code stored in the memory 301 to implement the contents shown in the above method embodiment.

[0094] The electronic devices include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0095] The electronic device of this embodiment can be used to execute the method of any of the above embodiments, and its implementation principle and technical effect are similar, which will not be described in detail here.

[0096] The present application also provides a non-transitory computer-readable storage medium having computer-readable instructions stored thereon. When the aforementioned instructions are executed by a processor, the processor executes the method in the above embodiment.

[0097] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

Claims

1. An air purification method based on big data, characterized in that: include: Acquire indoor air data detected by multiple air purifiers and environmental sensing data detected by multiple associated sensors, and determine the actual air quality change trend based on the indoor air data and the environmental sensing data; Determine an initial air pollutant concentration, a maximum pollutant concentration, and an air quality change attribute according to the actual air quality change trend, so as to determine the overall air quality in the current environment according to the initial air pollutant concentration, the maximum pollutant concentration, and the air quality change attribute; Determine pollution sources and corresponding pollution source types according to the actual air quality change trend, the indoor air data and the environmental sensor data; A target purification method is determined based on the air impact data within a preset distance range, the overall air quality, the pollution source and the type of the pollution source.

2. The method according to claim 1, characterized in that The determining, according to the indoor air data and the environmental sensor data, the actual air quality change trend comprises: Determining a first change trend according to a preset statistical analysis method and the indoor air data; Determine a second change trend according to a preset change trend determination model and the environmental sensor data; The actual air quality change trend is determined according to the preset data check difference, the first change trend and the second change trend.

3. The method according to claim 1, characterized in that Determining the initial air pollutant concentration, the maximum pollutant concentration and the air quality change attribute according to the actual air quality change trend includes: Obtain key time points in the current environment; Extracting pollutant concentration data corresponding to the key time point from the actual air quality change trend; According to a preset valid data selection method, the first valid data point in the pollutant concentration data is determined as the initial air pollutant concentration; Extracting the maximum pollutant concentration from the actual air quality change trend; The air quality change attribute is determined based on the pollutant concentration data.

4. The method according to claim 3, characterized in that Determining the air quality change attribute according to the pollutant concentration data includes: Based on the key time points, performing stage data analysis on the pollutant concentration data to determine concentration change rate and concentration fluctuation information; The air quality change attribute is determined according to a preset attribute threshold, the concentration change rate and the concentration fluctuation information.

5. The method according to claim 1, characterized in that: Determining the overall air quality in the current environment according to the initial air pollutant concentration, the maximum pollutant concentration, and the air quality change attribute includes: Based on a preset air quality standard, the initial air pollutant concentration and the maximum pollutant concentration, determining information on the excess of the pollutant concentration in the current environment; The overall air quality is determined according to the exceeding standard information and the air quality change attribute.

6. The method according to any one of claims 1 to 5, characterized in that: Also includes: Obtaining location data and layout information of the current environment; determining flow properties of different air pollutants based on the layout information; The preset distance range is set according to the position data and the flow property.

7. The method according to claim 1, characterized in that The determining of the pollution source and the corresponding pollution source type according to the actual air quality change trend, the indoor air data and the environmental sensor data includes: According to a preset data analysis method, data processing is performed on the actual air quality change trend, the indoor air data and the environmental sensor data to determine key features and abnormal points of air quality changes; Determine the pollution source and the basic source direction of the pollution source according to the actual air quality change trend, the key characteristics and the abnormal points; The pollution source type is determined according to the basic source direction and the actual air quality change trend.

8. An air purification device based on big data, characterized in that: include: A change trend determination module, used to obtain indoor air data detected by multiple air purifiers and environmental sensing data detected by multiple associated sensors, and determine the actual air quality change trend based on the indoor air data and the environmental sensing data; an air quality determination module, configured to determine an initial air pollutant concentration, a maximum pollutant concentration, and an air quality change attribute according to the actual air quality change trend, so as to determine the overall air quality in the current environment according to the initial air pollutant concentration, the maximum pollutant concentration, and the air quality change attribute; A type determination module, used to determine the pollution source and the corresponding pollution source type according to the actual air quality change trend, the indoor air data and the environmental sensor data; The purification mode determination module is used to determine the target purification mode according to the air impact data within a preset distance range, the overall air quality, the pollution source and the type of the pollution source.

9. An electronic device, characterized in that: include: processor; A memory storing a computer program, which, when executed by the processor, enables the processor to execute the air purification method based on big data as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that: Computer-readable instructions are stored thereon, and when the instructions are executed by a processor, the processor executes the air purification method based on big data as described in any one of claims 1-7.

Images