An air quality data processing method, device, equipment, medium and product

Abstract

The application discloses a kind of air quality data processing method, device, equipment, medium and product, it is related to computer technical field, the method includes: obtaining the original monitoring data set of target monitoring site, and exception event record;According to the event type and event time range of exception event record, determine the target processing identifier corresponding to each group of original monitoring data in original monitoring data set;According to the target processing identifier corresponding to each group of original monitoring data, each group of original monitoring data is corrected and handled, and the corrected monitoring data set is obtained;Effectiveness is judged to each group of corrected monitoring data in corrected monitoring data set, and determine effective monitoring data set;In the case where effective monitoring data set reaches preset effective condition, air quality is calculated based on effective monitoring data set, and the processing result of target monitoring site in target period is obtained.The method can improve the accuracy of air quality result.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, equipment, medium and product for processing air quality data. Background Technology

[0002] With the widespread deployment of environmental monitoring networks, automatic air quality monitoring systems continuously collect a large amount of monitoring data from various stations. This data is used to reflect the regional air quality status and provides data support for environmental management and pollution prevention.

[0003] Existing air quality data processing procedures mostly rely on basic data verification and routine cleaning operations. Monitoring data is screened and organized by setting preset thresholds, and then time-period average calculations and air quality index calculations are carried out based on the processed data.

[0004] This type of processing method lacks sufficient correlation analysis of the causes of data anomalies, resulting in insufficient accuracy of the final air quality output. Summary of the Invention

[0005] This application provides a method, apparatus, equipment, medium, and product for processing air quality data, which can improve the accuracy of air quality results.

[0006] To achieve the above objectives, this application adopts the following technical solution: In a first aspect, this application provides a method for processing air quality data, including: Obtain the raw monitoring data set of the target monitoring station within the target time period, as well as the abnormal event records associated with the target monitoring station within the target time period; wherein, the abnormal event records include the event type and the event time range corresponding to the event type; Based on the event type and time range of the abnormal event records, the target processing identifiers corresponding to each group of raw monitoring data in the raw monitoring data set are determined; among them, the target processing identifiers include anomaly removal, valid value replacement, invalid labeling, time period weighting, and dust impact deduction; Based on the target processing identifier corresponding to each group of original monitoring data, the original monitoring data of each group is corrected to obtain a set of corrected monitoring data. The validity of each set of modified monitoring data in the modified monitoring dataset is assessed to determine the valid monitoring dataset. When the effective monitoring data set meets the preset effective conditions, air quality is calculated based on the effective monitoring data set to obtain the processing results of the target monitoring station within the target time period. Based on the target processing identifier corresponding to each group of original monitoring data, the original monitoring data of each group are corrected to obtain a set of corrected monitoring data, including: For each set of raw monitoring data, if the target processing identifier corresponding to the set of raw monitoring data is anomaly removal, then the set of raw monitoring data is deleted from the set of raw monitoring data to obtain the corresponding corrected monitoring data. If the target processing identifier is valid value replacement, then the pollutant concentration values ​​in the original monitoring data of this group are replaced with the target valid data to obtain the corresponding corrected monitoring data; If the target processing identifier is invalid, then the original monitoring data of that group is retained and an invalid mark is added to it to obtain the corresponding corrected monitoring data; If the target processing identifier is time-weighted, then the pollutant concentration values ​​in the original monitoring data of this group are multiplied by a preset weighting coefficient to obtain the corresponding corrected monitoring data; If the target processing identifier is dust impact deduction, then the pollutant concentration values ​​in the original monitoring data of this group are processed by dust impact deduction to obtain the corresponding corrected monitoring data.

[0007] In some possible implementations, the target processing identifier corresponding to each group of raw monitoring data in the raw monitoring dataset is determined based on the event type and time range of the abnormal event record, including: Compare the monitoring time points corresponding to each group of original monitoring data in the original monitoring data set with the event time range; For each set of raw monitoring data, when the monitoring time point corresponding to the set of raw monitoring data falls within the event time range, the event type corresponding to the set of raw monitoring data is determined, and the candidate processing identifier corresponding to the set of raw monitoring data is determined based on the event type. When the monitoring time points of the same set of raw monitoring data fall within the event time ranges corresponding to two or more different event types, the target processing identifier is determined from multiple candidate processing identifiers according to the preset identifier priority rules.

[0008] In some possible implementations, the validity of each set of corrected monitoring data in the corrected monitoring dataset is determined to identify the valid monitoring dataset, including: For each set of corrected monitoring data, obtain the pollutant concentration values ​​and additional labels in that set of corrected monitoring data; Corrected monitoring data with an additional invalid label are identified as invalid monitoring data; Corrected monitoring data whose additional markers do not contain invalid markers are identified as valid monitoring data; Based on the effective monitoring data, determine the effective monitoring data set.

[0009] In some possible implementations, the method for determining whether a set of valid monitoring data meets the preset valid conditions is as follows: Based on the effective monitoring data set and the original monitoring data set, the number of effective monitoring data sets and the data effectiveness rate are determined; whereby the number of effective monitoring data sets is the total number of monitoring data sets included in the effective monitoring data set; and the data effectiveness rate is the ratio of the number of effective monitoring data sets to the total number of original monitoring data sets in the original monitoring data set. If the number of valid monitoring data sets is greater than the first threshold and the data validity rate is greater than the second threshold, the set of valid monitoring data is determined to meet the preset valid conditions.

[0010] In some possible implementations, air quality calculations are performed based on a valid set of monitoring data to obtain the processing results of the target monitoring station within the target time period, including: Obtain the pollutant type and pollutant concentration value from each valid monitoring data point in the valid monitoring data set; According to the pollutant type, the effective monitoring data set is divided into at least one effective data subset for each pollutant; wherein each effective data subset for each pollutant corresponds to one pollutant. For each subset of valid data for a pollutant, the average pollutant concentration during the target time period is calculated based on the pollutant concentration values ​​in the valid monitoring data within that subset of valid data. The air quality index is calculated based on the average value of each pollutant over a given time period. Based on the air quality index and the average values ​​of pollutants over different time periods, the processing results of the target monitoring stations during the target time period are obtained.

[0011] Secondly, this application provides an air quality data processing apparatus, comprising: The acquisition module is used to acquire the raw monitoring data set of the target monitoring station within the target time period, as well as the abnormal event records associated with the target monitoring station within the target time period; wherein, the abnormal event records include the event type and the event time range corresponding to the event type; The matching and judgment module is used to determine the target processing identifier corresponding to each group of original monitoring data in the original monitoring data set based on the event type and time range of the abnormal event records. The target processing identifier includes anomaly removal, valid value replacement, invalid labeling, time-based weighting, and dust impact deduction. Based on the target processing identifier corresponding to each group of original monitoring data, the module performs correction processing on each group of original monitoring data to obtain a corrected monitoring data set. Finally, it performs validity judgment on each group of corrected monitoring data in the corrected monitoring data set to determine the valid monitoring data set. The processing module is used to calculate the air quality based on the effective monitoring data set when the effective monitoring data set meets the preset effective conditions, and to obtain the processing results of the target monitoring station within the target time period. The matching and judgment module is also used to, for each set of original monitoring data, if the target processing identifier corresponding to the set of original monitoring data is anomaly removal, then delete the set of original monitoring data from the set of original monitoring data to obtain the corresponding corrected monitoring data; if the target processing identifier is valid value replacement, then replace the pollutant concentration values ​​in the set of original monitoring data with target valid data to obtain the corresponding corrected monitoring data; if the target processing identifier is invalid labeling, then retain the set of original monitoring data and add an invalid label to it to obtain the corresponding corrected monitoring data; if the target processing identifier is time-time weighting, then multiply the pollutant concentration values ​​in the set of original monitoring data by a preset weighting coefficient to obtain the corresponding corrected monitoring data; if the target processing identifier is dust impact deduction, then perform dust impact deduction processing on the pollutant concentration values ​​in the set of original monitoring data to obtain the corresponding corrected monitoring data.

[0012] Thirdly, this application provides a computing device, including a memory and a processor; The memory stores one or more computer programs, the one or more computer programs including instructions; when the instructions are executed by the processor, the computing device performs the method as described in any one of the first aspects.

[0013] Fourthly, this application provides a computer-readable storage medium for storing a computer program for performing the method as described in any one of the first aspects.

[0014] Fifthly, this application provides a computer program product comprising one or more computer instructions, wherein when the computer instructions are executed by a computer, the computer performs the method as described in any one of the first aspects.

[0015] As can be seen from the above technical solution, this application has at least the following beneficial effects: In this application, by acquiring the original monitoring data set of the target monitoring station within the target time period and simultaneously acquiring the abnormal event records related to the station within the same time period, a correspondence can be established between abnormal events and monitoring data. Then, a target processing identifier is determined for each set of original monitoring data based on the type and time range of the abnormal event. Based on the target processing identifier corresponding to each set of original monitoring data, the original monitoring data of each set is corrected to obtain a corrected monitoring data set. This application, by judging the validity of the corrected monitoring data and selecting a valid monitoring data set, and only when the valid monitoring data meets the preset validity conditions, performs air quality calculations. This ensures that the data involved in the calculation meets the requirements of quantity and efficiency, avoids calculations in the case of missing or invalid data, and improves the reliability of the air quality calculation process. Furthermore, based on the structured processing steps such as target processing identifiers, data validity judgment, and validity condition judgment, the entire process of monitoring data from collection, correction, screening to calculation is standardized. This unifies the data processing logic under different abnormal scenarios, making the air quality assessment results more consistent with the actual monitoring situation, and ultimately improving the accuracy of air quality results.

[0016] It should be understood that the descriptions of technical features, technical solutions, beneficial effects, or similar language in this application do not imply that all features and advantages can be achieved in any single embodiment. Rather, it is understood that the description of a feature or beneficial effect means that a specific technical feature, technical solution, or beneficial effect is included in at least one embodiment. Therefore, the descriptions of technical features, technical solutions, or beneficial effects in this specification do not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions, and beneficial effects described in this embodiment can be combined in any suitable manner. Those skilled in the art will understand that embodiments can be implemented without one or more specific technical features, technical solutions, or beneficial effects of a particular embodiment. In other embodiments, additional technical features and beneficial effects may be identified in specific embodiments that do not embody all embodiments. Attached Figure Description

[0017] Figure 1 An application environment diagram for an air quality data processing method provided in this application embodiment; Figure 2 A flowchart illustrating an air quality data processing method provided in this application embodiment; Figure 3 A structural diagram of an air quality data processing device provided in an embodiment of this application; Figure 4 This is a schematic diagram of a computing device provided in an embodiment of this application. Detailed Implementation

[0018] The terms "first," "second," and "third," etc., used in this application specification and accompanying drawings are used to distinguish different objects, not to limit a specific order.

[0019] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0020] This application provides a method for processing air quality data. To make the technical solution of this application clearer and easier to understand, the application scenarios of the technical solution of this application are described below with reference to the accompanying drawings. Figure 1 As shown, this figure is an application environment diagram provided by an embodiment of this application.

[0021] In this application environment, the server acts as the execution entity, receiving station and time period query instructions from the terminal, acquiring monitoring data and abnormal event records, completing the correction, validity judgment and index calculation of air quality data, and finally sending the final processing results back to the terminal for display and viewing.

[0022] To make the technical solution of this application clearer and easier to understand, the following describes a method for processing air quality data provided by an embodiment of this application, in conjunction with the above application scenarios. Figure 2 As shown, this figure is a schematic flowchart of an air quality data processing method provided in an embodiment of this application. The air quality data processing method includes: S201. Obtain the original monitoring data set of the target monitoring station within the target time period, as well as the abnormal event records associated with the target monitoring station within the target time period.

[0023] Target monitoring stations are designated air quality data collection points with fixed monitoring locations and standardized monitoring equipment, capable of continuously collecting air quality-related data at fixed time frequencies. The raw monitoring data set refers to the sum of all raw monitoring data directly collected and reported by the monitoring equipment of the target monitoring station within the target time period. This set contains multiple sets of raw monitoring data, each corresponding to a monitoring time point (i.e., sampling time point), including pollutant type, pollutant concentration value, and additional labels. Pollutant concentration values ​​differ at different monitoring time points; therefore, the content of each set of raw monitoring data is different, but the data structure is the same.

[0024] Anomaly event records refer to information on various events that occur within a target time period and may affect the authenticity or validity of monitoring data. Each anomaly event record must include at least the event type and the corresponding time range. Common event types include sandstorm impact events, site power outage events, equipment failure events, human interference events, and routine maintenance events. The event time range is the start time to the end time of the anomaly event, for example, the event time range is 2026-05-20 10:00 to 2026-05-20 15:00.

[0025] The server sends a data query request to the ambient air automatic monitoring data service interface, using the unique identifier of the target monitoring station and the target time period as query conditions. It then extracts all raw sampling data that meet the conditions within the target time period from the monitoring data repository and sorts them according to the order of the monitoring time points to obtain the raw monitoring data set.

[0026] The server synchronously calls the abnormal event query interface, using the unique identifier of the target monitoring site and the target time period as search criteria, to traverse the abnormal event database and filter out abnormal event records that are associated with the target monitoring site and whose event time range overlaps with the target time period.

[0027] The server performs integrity checks on the acquired raw monitoring data set, such as verifying whether the number of data sets matches the theoretical number of sampling points that should be collected during the target time period. For time periods with missing data, the server sends a data replenishment command to the monitoring device to complete the missing data. The server can also perform deduplication and validity filtering on the acquired abnormal event records, removing duplicate reports, withdrawn or invalid reports, and retaining only valid abnormal event records, that is, event records that have been deduplicated and filtered, and that actually occurred and are compliant with information.

[0028] S202. Based on the event type and time range of the abnormal event record, determine the target processing identifier corresponding to each group of original monitoring data in the original monitoring data set.

[0029] The target processing identifier is the processing mark corresponding to each group of original monitoring data, including anomaly removal, valid value replacement, invalid labeling, time period weighting, and dust impact deduction.

[0030] One possible approach is to compare the monitoring time points corresponding to each group of raw monitoring data in the raw monitoring data set with the event time range; for each group of raw monitoring data, when the monitoring time point corresponding to the group of raw monitoring data falls within the event time range, the event type corresponding to the group of raw monitoring data is determined, and a candidate processing identifier corresponding to the group of raw monitoring data is determined based on the event type; when the monitoring time points of the same group of raw monitoring data simultaneously fall within the event time ranges corresponding to two or more different event types, the target processing identifier is determined from multiple candidate processing identifiers according to a preset identifier priority rule.

[0031] Candidate processing identifiers are processing markers initially determined based on event type. Identifier priority rules are preset priority orders among different candidate processing identifiers. For example, the identifier corresponding to sandstorm impact has a higher priority than the identifier corresponding to site power outage, and the identifier corresponding to equipment failure has a higher priority than the identifier corresponding to sandstorm impact.

[0032] It should be noted that each event type is pre-assigned a unique default processing identifier. For example, when the event type is a sandstorm impact event, the corresponding processing identifier is sandstorm impact deduction; when the event type is a site power outage event, the corresponding processing identifier is valid value replacement; when the event type is an equipment failure event, the corresponding processing identifier is invalid labeling; when the event type is a human interference event, the corresponding processing identifier is anomaly removal; and when the event type is a routine maintenance event, the corresponding processing identifier is time-weighted.

[0033] The server iterates through each set of raw monitoring data in the original monitoring data set according to the monitoring time points, reading the monitoring time point corresponding to each set of data. Simultaneously, the server retrieves all abnormal event records associated with the target monitoring site and extracts the event type and time range for each record. For a single set of raw monitoring data, the server verifies whether its monitoring time point falls within the time range of any abnormal event record. If the monitoring time point falls within a certain time range, the server identifies the abnormal event corresponding to that time range as the abnormal event for that set of raw monitoring data, and determines the processing identifier bound to that abnormal event as a candidate processing identifier for that set of raw monitoring data. If the monitoring time point does not fall within the time range of any abnormal event record, the server sets the processing identifier for that set of raw monitoring data to normal.

[0034] In actual monitoring, multiple abnormal events may occur simultaneously at the same monitoring time point, resulting in multiple candidate processing identifiers. Therefore, a priority order for these identifiers is pre-defined, from highest to lowest: anomaly removal, invalid labeling, dust impact deduction, valid value replacement, and time-period weighting. When a single set of raw monitoring data matches multiple candidate processing identifiers, the server selects the highest-priority candidate processing identifier according to the pre-defined priority order and designates it as the target processing identifier for that set of raw monitoring data. If a single set of raw monitoring data matches only one candidate processing identifier, that candidate processing identifier is directly designated as the target processing identifier for that set of raw monitoring data.

[0035] For example, a set of raw monitoring data was monitored at 10:00 AM on May 20, 2026. This time falls within the time interval of both a dust storm impact event and a power outage event. The priority of the identifier corresponding to the dust storm impact event is higher than that of the identifier corresponding to the power outage event. Therefore, the server selects the dust storm impact deduction corresponding to the dust storm impact event as the target processing identifier for this set of data.

[0036] After the server completes all matching and priority filtering, it will generate a corresponding target processing identifier for each set of raw monitoring data in the raw monitoring data set.

[0037] S203. Based on the target processing identifier corresponding to each group of original monitoring data, the original monitoring data of each group is corrected to obtain a set of corrected monitoring data.

[0038] For example, the server performs corresponding correction processing on each group of original monitoring data based on the target processing identifier, resulting in a corrected monitoring data set. The server iterates through each group of original monitoring data and performs the following operations based on its target processing identifier: For each set of raw monitoring data, if the target processing identifier for that set of raw monitoring data is "abnormal removal," then that set of raw monitoring data is deleted from the raw monitoring data set and not included in the corrected monitoring data set, resulting in the corresponding corrected monitoring data. The reason for removal can also be recorded in the operation log. The server continues to process the next set of data without performing any calculations or storing the removed data.

[0039] If the target processing identifier is valid value replacement, the pollutant concentration value in the original monitoring data set is replaced with the target valid data to obtain the corresponding corrected monitoring data. The server initiates the replacement value calculation process. The server reads the monitoring time point and pollutant type of the original monitoring data set and obtains the target valid data from a preset data source. The sources of the target valid data include three types: valid monitoring data of adjacent time periods at the same monitoring station, valid monitoring data of adjacent stations around the target station during the same period, and valid monitoring data of the current station during the same historical period. The server can use the inverse distance weighted average method to calculate the replacement value: if time interpolation is used, with the current monitoring time point as the center, a preset number of valid monitoring data of the same station and the same pollutant are queried forward and backward, with the weight being the reciprocal of the time distance between each data point and the current time point; if spatial interpolation is used, valid monitoring data of adjacent stations within a preset radius around the target station that are at the same monitoring time point are queried, with the weight being the reciprocal of the spatial distance between each adjacent station and the target station. The server writes the calculated replacement concentration value into the pollutant concentration value field of the original monitoring data set, overwriting the original value, and appends a replacement identifier to the additional tags.

[0040] If the target processing identifier is invalid, the original monitoring data of that group will be retained and an invalid mark will be added to it. The data itself will not be modified in any way and will be directly included in the set of corrected monitoring data to be output.

[0041] If the target processing identifier is time-based weighting, the pollutant concentration values ​​in the original monitoring data set are multiplied by a preset weighting coefficient to obtain the corresponding corrected monitoring data. The weighting coefficient can be a preset fixed value or dynamically calculated based on the duration and severity of the abnormal event, and the minimum value of the coefficient is not less than 0.1. The server multiplies the original pollutant concentration values ​​by the weighting coefficient to obtain the weighted concentration values, overwriting the original values, and appends the weighted identifier and the weighting coefficient used to the additional tags.

[0042] The formula for calculating the weighting coefficient can be:

[0043] in, These are weighting coefficients, but the minimum value is 0.1. If the calculated... If it is less than 0.1, then directly... The value is 0.1; The baseline weighting coefficient is preset according to the event type, such as a baseline coefficient of 0.9 for routine maintenance. The duration of the abnormal event; The total duration of the target period. < ; The event severity factor, ranging from 0.5 to 1.0, reflects the strength of the impact of an abnormal event on monitoring data. In other words, the strength of the event's impact directly determines the specific value of this factor. For example, when the abnormal event is a routine site maintenance procedure, with equipment undergoing only routine checks and calibrations, and the impact on monitoring data is relatively minor, the event severity factor... It can be set to 0.9; when the abnormal event is a slight deviation in equipment parameters and has a moderate impact on the monitoring data, the event severity factor is [value missing]. It can be set to 0.7; when the abnormal event is a failure of equipment components and has a significant impact on the monitoring data, the event severity factor is [value missing]. It can be set to 0.5.

[0044] If the target processing flag is "dust impact deduction," the server performs dust impact deduction processing on the pollutant concentration values ​​in the original monitoring data to eliminate numerical interference caused by dusty weather, generating corrected pollutant concentration values, and adding a "dust impact deduction" flag to the data appendix. The dust impact deduction process can be as follows:

[0045] in, The corrected pollutant concentration; The original pollutant concentration was monitored. This represents the actual disturbance concentration of dust under the current operating conditions.

[0046] It is not a fixed value; it can be calculated by combining the background concentration of dust in the zoning standard with a real-time meteorological correction factor. The calculation formula is as follows:

[0047] in, The standard for dust background concentration in the zone; This is the wind speed correction factor. The higher the wind speed, the higher the value of the factor. It can be determined by referring to a table based on the real-time monitoring of hourly wind speed and the preset segmented wind speed interval. The wind direction correction factor has a higher value for the upwind direction of the dust storm. It can be determined by looking up a table based on the angle between the real-time monitored wind direction and the azimuth of the dust storm source area, which is matched with the preset wind direction interval.

[0048] To avoid negative values ​​in the concentration after deduction, the server applies three layers of boundary constraints to the initially calculated corrected concentration: (1) If the corrected pollutant concentration is less than 0, it is determined that the superimposed pollutant concentration caused by sand and dust interference is higher than the pollutant concentration obtained by the original monitoring (i.e. the original monitoring pollutant concentration). In this case, no sand and dust deduction will be performed, and the original pollutant concentration value will be retained. (2) If the corrected pollutant concentration is greater than or equal to 0 and less than the minimum detection limit for pollutants in the region, the corrected concentration shall be assigned the minimum detection limit for that pollutant; for example, pollutant PM 10 The corresponding minimum detection limit can be set to 5 μg / m 3 The minimum detection limit for pollutant SO2 can be set at 2 μg / m³. 3 The limit of detection for pollutant NO2 can be set to 2 μg / m³. 3 When negative values ​​are observed in the monitoring concentrations of various pollutants, the data validity shall be determined and the values ​​corrected according to the following standards: If the monitored concentration of pollutant SO2 is less than or equal to -14 μg / m³ 3 The data was deemed invalid; the SO2 concentration was -14 μg / m³. 3 Up to 0 μg / m 3 Within the range, a uniform value of 3 μg / m was assigned. 3 .

[0049] If the monitored concentration of pollutant NO2 is less than or equal to -10 μg / m³ 3 The data was deemed invalid; the NO2 monitoring concentration was below -10 μg / m³. 3 Up to 0 μg / m 3 Internally, a uniform value of 2μg / m 3 .

[0050] If the monitored concentration of pollutant O3 is less than or equal to -10 μg / m³ 3 The data is deemed invalid; if the ozone concentration of the pollutant is within -10 μg / m³, the data is deemed invalid. 3 Up to 0 μg / m 3 Within the range, a uniform value of 2μg / m is assigned. 3 .

[0051] If the monitored concentration of pollutant CO is less than or equal to -1 μg / m³ 3 The data was deemed invalid; the concentration of the pollutant carbon monoxide was within -1 μg / m³. 3 Up to 0 μg / m 3 Within the range, a uniform value of 0.3 μg / m is assigned. 3 .

[0052] If the pollutant is inhalable particulate matter (PM2.5) 10 ) and pollutants fine particulate matter (PM2.5) 2.5 The monitored concentration is less than or equal to -5 μg / m³. 3 The data is deemed invalid; if the monitored concentrations of inhalable particulate matter and fine particulate matter are within -5 μg / m³, the data is deemed invalid. 3 Up to 0 μg / m 3 Within the range, a uniform value of 2μg / m is assigned. 3 .

[0053] (3) If the corrected pollutant concentration is greater than or equal to the corresponding pollutant's minimum detection limit, the value shall be used directly as the final corrected concentration.

[0054] S204. Determine the validity of each set of corrected monitoring data in the corrected monitoring data set to determine the valid monitoring data set.

[0055] One possible approach is to obtain the pollutant concentration value and additional label in each set of corrected monitoring data; determine the corrected monitoring data with an invalid additional label as invalid monitoring data; determine the corrected monitoring data with an invalid additional label as valid monitoring data; and determine the set of valid monitoring data based on the valid monitoring data.

[0056] Invalid monitoring data are corrected monitoring data that are marked as invalid; they are not included in the valid monitoring data set and are not used in the calculation of the air quality index. Valid monitoring data are corrected monitoring data that are marked as valid but do not contain invalid markers (e.g., monitoring data marked as "valid," "replaced," or "weighted").

[0057] It should be noted that the server reads the corrected monitoring data set from memory or a temporary database. This set is stored in the form of an array or linked list. Each set of corrected monitoring data is a structure object, which includes at least the following fields: monitoring time point (timestamp), pollutant type (e.g., PM2.5). 2.5 PM 10 Pollutant concentration values ​​(floating-point type) for SO2, NO2, CO, O3, etc., and additional markers (string type, such as "valid", "replaced", "weighted", "invalid - equipment failure", etc.).

[0058] For example, the server reads a modified monitoring data set, where each set of data includes a monitoring time point, pollutant type, pollutant concentration value, and additional tags. The server iterates through each set of modified monitoring data, extracts the pollutant concentration value and additional tags, and determines the data validity according to the following rules: If the additional tags contain preset invalid keywords such as "invalid", "invalid - equipment failure", "awaiting manual review", or "abnormal removal", the data set is determined to be invalid monitoring data and the corresponding invalid reason is recorded; if the additional tags do not contain the above preset invalid keywords (e.g., the additional tags are "valid", "replaced", "weighted" or empty), the data set is determined to be valid monitoring data.

[0059] In special cases, the server uses a fallback logic. When the additional marker is empty or undefined, the server treats it as valid monitoring data by default and logs a warning. When the pollutant concentration value is zero, the server treats it as a non-empty value and continues to judge based on the additional marker. When both "valid" and "invalid" keywords appear in the additional marker, the server prioritizes judging it as invalid monitoring data, triggers an alarm, and prompts manual review.

[0060] After the traversal is complete, the server filters all valid monitoring data to form a valid monitoring data set. Invalid monitoring data is not included in this set and is not used in the air quality index calculation. The server then calculates the total number of data sets, the number of valid data sets, the number of invalid data sets, and the percentage of each type of invalidity. The statistical results are then generated into a structured log and written to the system monitoring database.

[0061] S205. When the effective monitoring data set meets the preset effective conditions, air quality is calculated based on the effective monitoring data set to obtain the processing results of the target monitoring station within the target time period.

[0062] A valid set of monitoring data meets the preset valid conditions, determined by the following methods: Based on the effective monitoring data set and the original monitoring data set, the number of effective monitoring data sets and the data effectiveness rate are determined; if the number of effective monitoring data sets is greater than the first threshold and the data effectiveness rate is greater than the second threshold, the effective monitoring data set is determined to have met the preset effective conditions.

[0063] The number of valid monitoring data sets is the total number of monitoring data sets included in the valid monitoring data set. The data effectiveness rate is the ratio of the number of valid monitoring data sets to the total number of original monitoring data sets in the original monitoring data set, usually expressed as a percentage. For example, the calculation formula is: Data effectiveness rate = Number of valid monitoring data sets ÷ Total number of original monitoring data sets × 100%.

[0064] Optionally, the data efficiency can be corrected by considering the importance of different pollutants, which can be expressed as:

[0065] in, The corrected data validity rate; n is the number of pollutant types; The data validity rate for pollutant class i is the ratio of the number of valid monitoring data sets for pollutant class i to the theoretical maximum number of data sets for that pollutant. The weighting coefficient for the i-th type of pollutant, such as PM2.5. 2.5 The weighting factor is 1.0, PM 10 The value is 0.9, and the others are 0.7. It is the largest weighting coefficient among all pollutants.

[0066] The first threshold is the minimum required number of valid monitoring data sets for a specific pollutant type. The first threshold can be set according to the characteristics of the pollutant and the evaluation criteria. For example, for PM2.5... 10 and PM 2.5 Because it is quite sensitive to air quality assessment, the corresponding first threshold can usually be set relatively high. Taking a 24-hour statistical period as an example, the minimum number of valid monitoring data sets per day is 22. For pollutants such as SO2, NO2, CO, and O3, the corresponding first threshold can be appropriately lowered, and the minimum number of valid monitoring data sets per day can be 18.

[0067] The concentration data of various pollutants must meet the minimum validity standards for the corresponding statistical periods: When conducting annual average statistics for sulfur dioxide, nitrogen dioxide, particulate matter (particle size ≤ 10 micrometers), particulate matter (particle size ≤ 2.5 micrometers), and nitrogen oxides, at least 324 daily average concentration values ​​must be retained throughout the year, at least 27 daily average concentration values ​​must be retained each month, and at least 25 daily average concentration values ​​must be retained in February; When conducting 24-hour average statistics for sulfur dioxide, nitrogen dioxide, carbon monoxide, particulate matter (particle size ≤ 10 micrometers), particulate matter (particle size ≤ 2.5 micrometers), and nitrogen oxides, at least 20 hours of average concentration values ​​or corresponding effective sampling time must be available each day; When conducting eight-hour average statistics for ozone, at least six hours of average concentration values ​​must be retained within each consecutive eight-hour statistical period; When conducting one-hour average statistics for sulfur dioxide, nitrogen dioxide, carbon monoxide, ozone, and nitrogen oxides, the effective sampling time of the instrument within a single hour must not be less than 45 minutes.

[0068] The second threshold is the minimum required value for data effectiveness set for a specific pollutant type. The second threshold is also set separately for each type of pollutant. For example, for PM2.5... 10 and PM 2.5 The second threshold can be set to 75%; for other pollutants, the second threshold can be set to 80%. When the data validity rate is greater than the second threshold, it indicates that the data quality within the target time period meets the calculation requirements.

[0069] One possible approach involves acquiring the pollutant type and concentration value from each valid monitoring data point in a valid monitoring data set; dividing the valid monitoring data set into at least one valid data subset for each pollutant type; each valid data subset for each pollutant corresponding to one pollutant; for each valid data subset for each pollutant, calculating the pollutant time-period average value for that pollutant within a target time period based on the pollutant concentration values ​​in the valid monitoring data within that subset; calculating the air quality index based on the pollutant time-period average values ​​for each pollutant; and obtaining the processing results of the target monitoring station within the target time period based on the air quality index and the pollutant time-period average values.

[0070] The pollutant time-period average is the average of all effective concentration values ​​of a certain pollutant within a target time period. For example, for PM2.5... 2.5 If there are 18 effective hourly concentration values ​​within the target time period, then PM 2.5 The average value of pollutants over a given period is equal to the arithmetic mean of these 18 values.

[0071] The Air Quality Index (AQI) is a dimensionless index used to quantitatively describe air quality, calculated based on the time-period average concentrations and concentration limits of various pollutants. For example, a piecewise linear interpolation method can be used to convert the concentrations of each pollutant into sub-indices, and the maximum value among these sub-indices is taken as the AQI.

[0072] The processing results are the air quality calculation results of the target monitoring stations during the target time period, including but not limited to: the time-period average value of each pollutant, air quality index, air quality level (such as excellent, good, lightly polluted, etc.), primary pollutant, and the number of exceedances. The processing results can be output in numerical, text, or report form.

[0073] For example, the server reads the valid monitoring data set and the raw monitoring data set from memory, and counts the number of valid monitoring data sets and the total number of raw monitoring data sets. The server calculates the data effectiveness rate, which is the ratio of the number of valid monitoring data sets to the total number of raw monitoring data sets. The server obtains a preset first threshold and a second threshold. For example, for PM... 10 and PM 2.5 The first threshold is set to 22 groups (taking hourly data as an example, the target period is 24 hours in total), and the second threshold is set to 75%; for SO2, NO2, CO, and O3, the first threshold is set to 18 groups, and the second threshold is set to 80%.

[0074] If the number of valid monitoring data sets is greater than the first threshold, and the data validity rate (or the corrected data validity rate) is greater than the second threshold, the server determines that the valid monitoring data set meets the preset valid conditions and continues to calculate the air quality; otherwise, the server determines that the current data quality does not meet the calculation requirements, terminates the subsequent calculation process, and outputs the corresponding prompt information (such as insufficient valid data, unable to calculate the air quality index).

[0075] After determining that the set of valid monitoring data meets the preset validity criteria, the server groups the valid monitoring data set according to pollutant type, grouping valid monitoring data belonging to the same pollutant type into the same valid pollutant data subset. For example, all pollutant types are PM2.5. 2.5 Effective monitoring data constitutes PM 2.5 Valid subset of data, all pollutant types are PM 10 Effective monitoring data constitutes PM 10 Valid data subsets, and so on. Each valid data subset corresponds to one pollutant.

[0076] For each valid subset of pollutant data, the server uses an arithmetic mean method to calculate the average pollutant concentration. This involves summing the pollutant concentration values ​​from all valid monitoring data within the subset, obtaining the total concentration, and then dividing this total by the number of data sets in that subset to obtain the average pollutant concentration over a given period. For example, assuming PM2.5... 2.5 The effective data subset contains 22 effective hourly concentration values, namely 35 μg / m³, 38 μg / m³, 42 μg / m³, etc. The server adds these 22 concentration values ​​to obtain the total concentration, then divides it by 22 to get the PM2.5 concentration. 2.5 The average value of pollutants during the period was 40 μg / m³.

[0077] The server calculates the air quality index based on the time-period average of each pollutant. The server can calculate the air quality index using the following sub-steps: The server retrieves the concentration limit standards for each pollutant, which are typically pre-stored in the server's configuration database, including the formulas for calculating the sub-index for each pollutant in different concentration ranges. For each pollutant, the server calculates its air quality sub-index using a linear interpolation method based on the concentration range of the pollutant's average concentration over a given time period.

[0078] The server compares the air quality indices of various pollutants and takes the maximum value as the air quality index. Simultaneously, the server identifies the pollutant corresponding to the air quality index as the primary pollutant for the current target time period.

[0079] For example, suppose PM 2.5 The air quality index was 110, PM2.5 10The air quality index is 95 for SO2, 30 for SO2, and 45 for NO2. Therefore, the air quality index is taken as the maximum value of 110, and the primary pollutant is PM2.5.

[0080] The server determines the air quality level for the target time period based on the calculated air quality index and a preset air quality index classification standard. In a specific example, the air quality index classification standard is as follows: 0 to 50 is excellent, 51 to 100 is good, 101 to 150 is lightly polluted, 151 to 200 is moderately polluted, 201 to 300 is heavily polluted, and greater than 300 is severely polluted.

[0081] The server also compares the average concentration of each pollutant over a given time period with the corresponding pollutant concentration limit standard to determine if there is any exceedance. If the average concentration of a pollutant over a given time period exceeds its concentration limit, the server records that the pollutant has exceeded the limit and indicates the multiple or specific value of the exceedance.

[0082] The server summarizes the results calculated above to form the processing results of the target monitoring station within the target time period. These processing results include, but are not limited to, the following: the time-period average value of each pollutant, air quality index, air quality level, primary pollutant, and the extent to which each pollutant exceeds the standard.

[0083] The server outputs the processing results in a structured data format (such as JSON or XML) and can simultaneously store them in a database for use in report generation, data display, or alarm push notifications. Furthermore, the server can push the processing results to terminal devices for viewing by operations and maintenance personnel or administrators.

[0084] Based on the above, the air quality data processing method acquires the original monitoring data set of the target monitoring station within the target time period and simultaneously acquires the records of abnormal events related to the station within the same time period. This establishes a correspondence between abnormal events and monitoring data. Then, based on the type and time range of the abnormal events, a target processing identifier is determined for each set of original monitoring data. Based on the target processing identifier corresponding to each set of original monitoring data, the original monitoring data is corrected to obtain a corrected monitoring data set. This application, by judging the validity of the corrected monitoring data and selecting a valid monitoring data set, and only when the valid monitoring data meets the preset validity conditions, performs air quality calculations. This ensures that the data involved in the calculation meets the requirements of quantity and efficiency, avoids calculations in the case of missing or invalid data, and improves the reliability of the air quality calculation process. Furthermore, based on the structured processing steps such as target processing identifiers, data validity judgment, and validity condition judgment, the entire process of monitoring data processing from collection, correction, screening to calculation is standardized. This unifies the data processing logic under different abnormal scenarios, making the air quality assessment results more consistent with the actual monitoring situation, and ultimately improving the accuracy of air quality results.

[0085] The above text combined Figures 1 to 2 The air quality data processing method provided in the embodiments of this application has been described in detail. The apparatus and equipment provided in the embodiments of this application will be described below with reference to the accompanying drawings.

[0086] This application also provides an air quality data processing device, such as... Figure 3 As shown, this figure is a structural diagram of an air quality data processing device provided in an embodiment of this application. The device includes: The acquisition module 301 is used to acquire the original monitoring data set of the target monitoring station within the target time period, as well as the abnormal event records associated with the target monitoring station within the target time period; wherein, the abnormal event records include the event type and the event time range corresponding to the event type; The matching and judgment module 302 is used to determine the target processing identifier corresponding to each group of original monitoring data in the original monitoring data set based on the event type and time range of the abnormal event record; wherein, the target processing identifier includes anomaly removal, valid value replacement, invalid labeling, time period weighting, and dust impact deduction; according to the target processing identifier corresponding to each group of original monitoring data, the original monitoring data of each group is corrected to obtain a corrected monitoring data set; the validity of each group of corrected monitoring data in the corrected monitoring data set is judged to determine the valid monitoring data set; Processing module 303 is used to perform air quality calculations based on the effective monitoring data set when the effective monitoring data set meets the preset effective conditions, and to obtain the processing results of the target monitoring station within the target time period; The matching and judgment module 302 is further configured to, for each set of original monitoring data, if the target processing identifier corresponding to the set of original monitoring data is anomaly removal, delete the set of original monitoring data from the set of original monitoring data to obtain the corresponding corrected monitoring data; if the target processing identifier is valid value replacement, replace the pollutant concentration values ​​in the set of original monitoring data with target valid data to obtain the corresponding corrected monitoring data; if the target processing identifier is invalid labeling, retain the set of original monitoring data and add an invalid label to it to obtain the corresponding corrected monitoring data; if the target processing identifier is time-weighted, multiply the pollutant concentration values ​​in the set of original monitoring data by a preset weighting coefficient to obtain the corresponding corrected monitoring data; if the target processing identifier is dust impact deduction, perform dust impact deduction processing on the pollutant concentration values ​​in the set of original monitoring data to obtain the corresponding corrected monitoring data.

[0087] In some possible implementations, the matching and judgment module 302 is specifically used for: Compare the monitoring time points corresponding to each group of original monitoring data in the original monitoring data set with the event time range; For each set of raw monitoring data, when the monitoring time point corresponding to the set of raw monitoring data falls within the event time range, the event type corresponding to the set of raw monitoring data is determined, and the candidate processing identifier corresponding to the set of raw monitoring data is determined based on the event type. When the monitoring time points of the same set of raw monitoring data fall within the event time ranges corresponding to two or more different event types, the target processing identifier is determined from multiple candidate processing identifiers according to the preset identifier priority rules.

[0088] In some possible implementations, the matching and judgment module 302 is specifically used for: For each set of corrected monitoring data, obtain the pollutant concentration values ​​and additional labels in that set of corrected monitoring data; Corrected monitoring data with an additional invalid label are identified as invalid monitoring data; Corrected monitoring data whose additional markers do not contain invalid markers are identified as valid monitoring data; Based on the effective monitoring data, determine the effective monitoring data set.

[0089] In some possible implementations, processing module 303 is specifically used for: Based on the effective monitoring data set and the original monitoring data set, the number of effective monitoring data sets and the data effectiveness rate are determined; whereby the number of effective monitoring data sets is the total number of monitoring data sets included in the effective monitoring data set; and the data effectiveness rate is the ratio of the number of effective monitoring data sets to the total number of original monitoring data sets in the original monitoring data set. If the number of valid monitoring data sets is greater than the first threshold and the data validity rate is greater than the second threshold, the set of valid monitoring data is determined to meet the preset valid conditions.

[0090] In some possible implementations, processing module 303 is specifically used for: Obtain the pollutant type and pollutant concentration value from each valid monitoring data point in the valid monitoring data set; According to the pollutant type, the effective monitoring data set is divided into at least one effective data subset for each pollutant; wherein each effective data subset for each pollutant corresponds to one pollutant. For each subset of valid data for a pollutant, the average pollutant concentration during the target time period is calculated based on the pollutant concentration values ​​in the valid monitoring data within that subset of valid data. The air quality index is calculated based on the average value of each pollutant over a given time period. Based on the air quality index and the average values ​​of pollutants over different time periods, the processing results of the target monitoring stations during the target time period are obtained.

[0091] The air quality data processing apparatus according to the embodiments of this application can correspond to the execution of the method described in the embodiments of this application, and the other operations and / or functions of each module / unit of the air quality data processing apparatus are respectively for implementing Figure 2 For the sake of brevity, the corresponding processes of each method in the illustrated embodiments will not be described in detail here.

[0092] This application also provides a computing device. For example... Figure 4 As shown in the figure, this is a schematic diagram of a computing device provided in an embodiment of this application. The computing device 400 includes a bus 401, a processor 402, a communication interface 403, and a memory 404. The processor 402, the memory 404, and the communication interface 403 communicate with each other via the bus 401.

[0093] Bus 401 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0094] Processor 402 can be any one or more of the following processors: central processing unit (CPU), graphics processing unit (GPU), microprocessor (MP), or digital signal processor (DSP).

[0095] Communication interface 403 is used for communication with external devices.

[0096] Memory 404 may include volatile memory, such as random access memory (RAM). Memory 404 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0097] The memory 404 stores executable code, and the processor 402 executes the executable code to perform the aforementioned air quality data processing method.

[0098] Specifically, in achieving Figure 3 In the case of the illustrated embodiment, and Figure 3 When the modules or units of the air quality data processing device described in the embodiments are implemented by software, the following steps are performed: Figure 3 The software or program code required for the functions of each module / unit can be partially or entirely stored in memory 404. Processor 402 executes the program code corresponding to each unit stored in memory 404 to perform the aforementioned air quality data processing method.

[0099] This application also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium that a computing device can store, or a data storage device such as a data center containing one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive). The computer-readable storage medium includes instructions that instruct the computing device to perform the aforementioned air quality data processing method.

[0100] This application also provides a computer program product comprising one or more computer instructions. When the computer instructions are loaded and executed on a computing device, all or part of the processes or functions described in this application are generated.

[0101] The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, or data center to another website, computer, or data center via wired (e.g., coaxial cable, fiber optic) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0102] When the computer program product is executed by a computer, the computer performs any of the aforementioned methods for processing air quality data. The computer program product can be a software installation package; when any of the aforementioned methods for processing air quality data is required, the computer program product can be downloaded and executed on the computer.

[0103] The descriptions of the processes or structures corresponding to the above figures each have their own emphasis. For parts of a process or structure that are not described in detail, please refer to the relevant descriptions of other processes or structures.

[0104] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be covered within the scope of protection of this application.

Claims

1. A method for processing air quality data, characterized in that, The method includes: Obtain the raw monitoring data set of the target monitoring station within the target time period, as well as the abnormal event records associated with the target monitoring station within the target time period; wherein, the abnormal event records include the event type and the event time range corresponding to the event type; Based on the event type and time range of the abnormal event records, the target processing identifier corresponding to each group of original monitoring data in the original monitoring data set is determined; wherein, the target processing identifier includes anomaly removal, valid value replacement, invalid labeling, time period weighting, and dust impact deduction; Based on the target processing identifier corresponding to each group of original monitoring data, the original monitoring data of each group is corrected to obtain a set of corrected monitoring data. The validity of each set of corrected monitoring data in the corrected monitoring data set is determined to identify the valid monitoring data set. When the effective monitoring data set meets the preset effective conditions, air quality is calculated based on the effective monitoring data set to obtain the processing results of the target monitoring station within the target time period. Based on the target processing identifier corresponding to each group of original monitoring data, the original monitoring data of each group are corrected to obtain a set of corrected monitoring data, including: For each set of raw monitoring data, if the target processing identifier corresponding to the set of raw monitoring data is anomaly removal, then the set of raw monitoring data is deleted from the set of raw monitoring data to obtain the corresponding corrected monitoring data. If the target processing identifier is valid value replacement, then the pollutant concentration values ​​in the original monitoring data of this group are replaced with the target valid data to obtain the corresponding corrected monitoring data; If the target processing identifier is invalid, then the original monitoring data of that group is retained and an invalid mark is added to it to obtain the corresponding corrected monitoring data; If the target processing identifier is time-weighted, then the pollutant concentration values ​​in the original monitoring data of this group are multiplied by a preset weighting coefficient to obtain the corresponding corrected monitoring data; If the target processing identifier is dust impact deduction, then the pollutant concentration values ​​in the original monitoring data of this group are processed by dust impact deduction to obtain the corresponding corrected monitoring data.

2. The method according to claim 1, characterized in that, The step of determining the target processing identifier corresponding to each group of original monitoring data in the original monitoring data set based on the event type and event time range of the abnormal event records includes: The monitoring time points corresponding to each group of original monitoring data in the original monitoring data set are compared with the event time range; For each set of raw monitoring data, when the monitoring time point corresponding to the set of raw monitoring data falls within the event time range, the event type corresponding to the set of raw monitoring data is determined, and the candidate processing identifier corresponding to the set of raw monitoring data is determined based on the event type. When the monitoring time points of the same set of raw monitoring data fall within the event time ranges corresponding to two or more different event types, the target processing identifier is determined from multiple candidate processing identifiers according to the preset identifier priority rules.

3. The method according to claim 1, characterized in that, The step of determining the validity of each set of corrected monitoring data in the corrected monitoring data set to identify the valid monitoring data set includes: For each set of corrected monitoring data, obtain the pollutant concentration values ​​and additional labels in that set of corrected monitoring data; Corrected monitoring data with an additional invalid label are identified as invalid monitoring data; Corrected monitoring data whose additional markers do not contain invalid markers are identified as valid monitoring data; Based on the effective monitoring data, determine the effective monitoring data set.

4. The method according to claim 1, characterized in that, The method for determining whether a set of valid monitoring data meets the preset valid conditions is as follows: Based on the effective monitoring data set and the original monitoring data set, the number of effective monitoring data sets and the data effectiveness rate are determined; whereby the number of effective monitoring data sets is the total number of monitoring data sets included in the effective monitoring data set; and the data effectiveness rate is the ratio of the number of effective monitoring data sets to the total number of original monitoring data sets in the original monitoring data set. If the number of valid monitoring data sets is greater than a first threshold and the data validity rate is greater than a second threshold, the set of valid monitoring data is determined to have met the preset valid conditions.

5. The method according to claim 1, characterized in that, The air quality calculation based on the effective monitoring data set, to obtain the processing results of the target monitoring station within the target time period, includes: Obtain the pollutant type and pollutant concentration value from each valid monitoring data point in the valid monitoring data set; According to the pollutant type, the effective monitoring data set is divided into at least one subset of effective pollutant data; wherein each subset of effective pollutant data corresponds to one pollutant. For each subset of valid data for a pollutant, the average pollutant concentration during the target time period is calculated based on the pollutant concentration values ​​in the valid monitoring data within that subset of valid data. The air quality index is calculated based on the average value of each pollutant over a given time period. Based on the air quality index and the average values ​​of pollutants over different time periods, the processing results of the target monitoring stations during the target time period are obtained.

6. An air quality data processing device, characterized in that, The device includes: The acquisition module is used to acquire the raw monitoring data set of the target monitoring station within the target time period, as well as the abnormal event records associated with the target monitoring station within the target time period; wherein, the abnormal event records include the event type and the event time range corresponding to the event type; The matching and judgment module is used to determine the target processing identifier corresponding to each group of original monitoring data in the original monitoring data set based on the event type and time range of the abnormal event records. The target processing identifier includes anomaly removal, valid value replacement, invalid labeling, time-based weighting, and dust impact deduction. Based on the target processing identifier corresponding to each group of original monitoring data, the module performs correction processing on each group of original monitoring data to obtain a corrected monitoring data set. Finally, it performs validity judgment on each group of corrected monitoring data in the corrected monitoring data set to determine the valid monitoring data set. The processing module is used to calculate the air quality based on the effective monitoring data set when the effective monitoring data set meets the preset effective conditions, and to obtain the processing results of the target monitoring station within the target time period. The matching and judgment module is also used to, for each set of original monitoring data, if the target processing identifier corresponding to the set of original monitoring data is anomaly removal, then delete the set of original monitoring data from the set of original monitoring data to obtain the corresponding corrected monitoring data; if the target processing identifier is valid value replacement, then replace the pollutant concentration values ​​in the set of original monitoring data with target valid data to obtain the corresponding corrected monitoring data; if the target processing identifier is invalid labeling, then retain the set of original monitoring data and add an invalid label to it to obtain the corresponding corrected monitoring data; if the target processing identifier is time-time weighting, then multiply the pollutant concentration values ​​in the set of original monitoring data by a preset weighting coefficient to obtain the corresponding corrected monitoring data; if the target processing identifier is dust impact deduction, then perform dust impact deduction processing on the pollutant concentration values ​​in the set of original monitoring data to obtain the corresponding corrected monitoring data.

7. A computing device, characterized in that, Including memory and processor; The memory stores one or more computer programs, the one or more computer programs including instructions; when the instructions are executed by the processor, the computing device performs the method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program for performing the method as described in any one of claims 1 to 5.

9. A computer program product, characterized in that, The computer program product includes one or more computer instructions, which, when executed by a computer, perform the method as described in any one of claims 1 to 5.

Images