CN112801423A - Method and device for identifying abnormity of air quality monitoring data and storage medium - Google Patents
Method and device for identifying abnormity of air quality monitoring data and storage medium Download PDFInfo
- Publication number
- CN112801423A CN112801423A CN202110330428.2A CN202110330428A CN112801423A CN 112801423 A CN112801423 A CN 112801423A CN 202110330428 A CN202110330428 A CN 202110330428A CN 112801423 A CN112801423 A CN 112801423A
- Authority
- CN
- China
- Prior art keywords
- air quality
- data
- station
- monitoring
- target station
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 276
- 238000000034 method Methods 0.000 title claims abstract description 45
- 230000002159 abnormal effect Effects 0.000 claims abstract description 72
- 238000012549 training Methods 0.000 claims abstract description 25
- 230000005856 abnormality Effects 0.000 claims description 34
- 239000013598 vector Substances 0.000 claims description 22
- 235000019580 granularity Nutrition 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 10
- 230000002776 aggregation Effects 0.000 claims description 5
- 238000004220 aggregation Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000004364 calculation method Methods 0.000 description 7
- 239000003344 environmental pollutant Substances 0.000 description 7
- 231100000719 pollutant Toxicity 0.000 description 7
- 238000003908 quality control method Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/219—Managing data history or versioning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Business, Economics & Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The application discloses an anomaly identification method and device for air quality monitoring data and a storage medium, wherein the method comprises the following steps: determining a target site and a reference site of the target site, wherein the target site and the reference site are located in the same monitoring area; training an air quality prediction model of the target station by using first historical air quality data of the reference station and second historical air quality data of the target station in a first historical reference period; inputting first air quality monitoring data of the reference station in a period to be identified into the air quality prediction model to obtain air quality prediction data of the target station in the period to be identified; and identifying whether the target station has abnormal air quality monitoring or not according to the air quality prediction data and second air quality monitoring data of the target station in the period to be identified. The method is beneficial to improving the identification efficiency and accuracy of the abnormal site.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for identifying an anomaly of air quality monitoring data, and a storage medium.
Background
Nowadays, the environmental protection problem is increasingly highlighted, and large-scale and accurate observation data of conventional pollutants are important basis for measuring air quality and the basis of related research. The state control site is an air quality monitoring site deployed by the national ecological environment ministry, comprises four levels of country, province, city and county, and has the characteristics of multiple monitoring parameters, high precision and the like. However, abnormal observation data occurs inevitably due to instrument failure, harsh environment, and limitations of the monitoring method.
In the practical application process, the monitoring data is usually required to be audited and quality-controlled manually to remove abnormal observation data. The method can effectively remove abnormal data in atmospheric pollution monitoring. The method has the main defects of complexity, high labor and time consumption, difficulty in quickly obtaining a large amount of quality control data and limitation on quick application of the data. In addition, the quality control standards of different people have certain subjectivity and are difficult to be completely consistent, so that certain deviation can be introduced into the quality control data set.
Therefore, it is necessary to establish an objective quality control technical method with a unified standard, to automatically monitor the abnormal point locations of the data of the state control station, to effectively prevent the artificial counterfeiting and to efficiently manage the operation and maintenance of the state control station.
Disclosure of Invention
In view of this, the present application provides an anomaly identification method and apparatus for air quality monitoring data, and a storage medium, which are helpful for improving the identification efficiency and accuracy of an abnormal site and saving the labor cost.
According to one aspect of the application, an anomaly identification method for air quality monitoring data is provided, and comprises the following steps:
determining a target site and a reference site of the target site, wherein the target site and the reference site are located in the same monitoring area;
training an air quality prediction model of the target station by using first historical air quality data of the reference station and second historical air quality data of the target station in a first historical reference period;
inputting first air quality monitoring data of the reference station in a period to be identified into the air quality prediction model to obtain air quality prediction data of the target station in the period to be identified;
and identifying whether the target station has abnormal air quality monitoring or not according to the air quality prediction data and second air quality monitoring data of the target station in the period to be identified.
Optionally, the determining the target station and the reference station of the target station specifically includes:
determining a plurality of monitoring stations which are located in the same monitoring area with the target station according to the target station, wherein the monitoring stations comprise the target station and other monitoring stations;
acquiring historical air quality data of each monitored site in a second historical reference period, and respectively calculating the air quality similarity of the target site and each other monitored site;
and selecting N sites from the other monitoring sites as the reference sites according to the air quality similarity and the distance between the target site and each of the other monitoring sites, wherein N is greater than 2.
Optionally, before obtaining the historical air quality data of each monitored site in the second historical reference period, the method further includes:
if the number of the monitored stations is larger than N +1, the historical air quality data of each monitored station in the second historical reference period are obtained;
and if the number of the monitored sites is less than or equal to N +1, taking all other monitored sites in the monitored sites as the reference sites.
Optionally, the selecting, according to the air quality similarity and the distance between the target site and each of the other monitored sites, N sites from the other monitored sites as the reference site specifically includes:
normalizing the air quality similarity C and the distance D between the target station and each other monitoring station;
respectively calculating the matching degree Sim between the target station and each of the other monitoring stations according to the air quality similarity C and the distance D, wherein Sim =0.5 × D +0.5 × C;
and arranging the matching degrees of the other monitored sites in a descending order, and selecting the top N sites as the reference sites.
Optionally, the calculating the air quality similarity between the target site and each of the other monitored sites respectively specifically includes:
according to a plurality of preset time granularities, respectively carrying out aggregation processing on the historical air quality data of each other monitored station and the historical air quality data of the target station, and acquiring a first data characteristic vector of each other monitored station and a second data characteristic vector of the target station under any preset time granularity;
and respectively calculating the air quality similarity of each other monitoring station and the target station according to the first data characteristic vector and the second data characteristic vector.
Optionally, the second historical reference time interval is a time interval within a preset reference time interval range before the time interval to be identified, the preset reference time interval is greater than the time interval of the time interval to be identified, the time interval of the time interval to be identified includes one hour, the preset reference time interval includes one week, and the plurality of preset time granularities include at least one of a working day, a non-working day, a last 24 hours, and a last 72 hours.
Optionally, the reference site comprises a plurality of reference sites; the training of the air quality prediction model of the target station by using the first historical air quality data of the reference station and the second historical air quality data of the target station in the first historical reference period specifically includes:
respectively training an air quality prediction model matched with each reference station by using the first historical air quality data and the second historical air quality data of each reference station, so that the trained air quality prediction model can realize prediction of the air quality of the target station in the same time period based on the air quality monitoring data of the corresponding reference station;
correspondingly, the inputting the first air quality monitoring data of the reference station in the period to be identified into the air quality prediction model to obtain the air quality prediction data of the target station in the period to be identified specifically includes:
and respectively inputting the first air quality monitoring data of each reference station in the time period to be identified into a corresponding air quality prediction model to obtain a plurality of groups of air quality prediction data of the target station.
Optionally, before identifying whether an air quality monitoring abnormality exists at the target station according to the air quality prediction data and the second air quality monitoring data of the target station in the period to be identified, the method further includes:
determining a monitoring data confidence interval of the target station according to the multiple groups of air quality prediction data;
correspondingly, identifying whether the target station has an air quality monitoring abnormality according to the air quality prediction data and the second air quality monitoring data of the target station in the period to be identified specifically includes:
if the second air quality monitoring data of the target station is within the monitoring data confidence interval range, determining that the air quality monitoring of the target station is normal;
and if the second air quality monitoring data of the target station is out of the monitoring data confidence interval range, determining that the target station has abnormal air quality monitoring.
Optionally, the determining a monitoring data confidence interval of the target station according to the multiple sets of air quality prediction data specifically includes:
determining a monitoring data confidence interval of the target station and abnormal monitoring data intervals of a plurality of abnormal grades according to the plurality of groups of air quality prediction data;
correspondingly, if the second air quality monitoring data of the target station is out of the monitoring data confidence interval range, determining that the target station has an air quality monitoring abnormality, specifically including:
and if the second air quality monitoring data of the target station is in the range of any stage of abnormal monitoring data interval, determining that the target station has air quality monitoring abnormality, and determining the abnormal grade of the target station.
Optionally, the determining, according to the multiple sets of air quality prediction data, a monitoring data confidence interval of the target station and abnormal monitoring data intervals of multiple abnormal levels specifically includes:
obtaining a maximum value P of the plurality of sets of air quality prediction datamaxMinimum value PminAnd standard deviation Pσ；
Determining the confidence interval of the monitoring data as [ Pmin-Pσ , Pmax+Pσ]；
Determining the abnormal monitoring data interval of the first-level abnormality as Pmin-3Pσ , Pmin-Pσ) And (P)max+Pσ , Pmax+3Pσ]；
Determining the abnormal monitoring data interval of the second-level abnormality as (— infinity, P)min-3P) and (P)max+3Pσ , +∞)。
According to another aspect of the present application, there is provided an abnormality recognition apparatus for air quality monitoring data, including:
the system comprises a site determining module, a site determining module and a monitoring module, wherein the site determining module is used for determining a target site and a reference site of the target site, and the target site and the reference site are located in the same monitoring area;
the model training module is used for training an air quality prediction model of the target station by utilizing first historical air quality data of the reference station and second historical air quality data of the target station in a first historical reference time period;
the data prediction module is used for inputting first air quality monitoring data of the reference station in a period to be identified into the air quality prediction model to obtain air quality prediction data of the target station in the period to be identified;
and the abnormity identification module is used for identifying whether the target station has abnormal air quality monitoring according to the air quality prediction data and second air quality monitoring data of the target station in the period to be identified.
Optionally, the station determining module specifically includes:
the monitoring station selection unit is used for determining a plurality of monitoring stations which are positioned in the same monitoring area with the target station according to the target station, wherein the monitoring stations comprise the target station and other monitoring stations;
the similarity calculation unit is used for acquiring historical air quality data of each monitoring station in a second historical reference period and calculating the air quality similarity of the target station and each other monitoring station respectively;
and the first station selecting unit is used for selecting N stations from the other monitoring stations as the reference station according to the air quality similarity and the distance between the target station and each of the other monitoring stations, wherein N is greater than 2.
Optionally, the similarity calculation unit is specifically configured to, if the number of the monitored sites is greater than N +1, perform the obtaining of the historical air quality data of each monitored site in the second historical reference period;
the station determining module further includes: and the second site selection unit is used for taking all other monitored sites in the monitored sites as the reference sites if the number of the monitored sites is less than or equal to N + 1.
Optionally, the first station selecting unit is specifically configured to: normalizing the air quality similarity C and the distance D between the target station and each other monitoring station; respectively calculating the matching degree Sim between the target station and each of the other monitoring stations according to the air quality similarity C and the distance D, wherein Sim =0.5 × D +0.5 × C; and arranging the matching degrees of the other monitored sites in a descending order, and selecting the top N sites as the reference sites.
Optionally, the similarity calculation unit is specifically configured to: according to a plurality of preset time granularities, respectively carrying out aggregation processing on the historical air quality data of each other monitored station and the historical air quality data of the target station, and acquiring a first data characteristic vector of each other monitored station and a second data characteristic vector of the target station under any preset time granularity; and respectively calculating the air quality similarity of each other monitoring station and the target station according to the first data characteristic vector and the second data characteristic vector.
Optionally, the second historical reference time interval is a time interval within a preset reference time interval range before the time interval to be identified, the preset reference time interval is greater than the time interval of the time interval to be identified, the time interval of the time interval to be identified includes one hour, the preset reference time interval includes one week, and the plurality of preset time granularities include at least one of a working day, a non-working day, a last 24 hours, and a last 72 hours.
Optionally, the reference site comprises a plurality of reference sites;
the model training module is specifically configured to: respectively training an air quality prediction model matched with each reference station by using the first historical air quality data and the second historical air quality data of each reference station, so that the trained air quality prediction model can realize prediction of the air quality of the target station in the same time period based on the air quality monitoring data of the corresponding reference station;
accordingly, the data prediction module is specifically configured to: and respectively inputting the first air quality monitoring data of each reference station in the time period to be identified into a corresponding air quality prediction model to obtain a plurality of groups of air quality prediction data of the target station.
Optionally, the apparatus further comprises:
the interval determination module is used for determining a monitoring data confidence interval of the target station according to the multiple groups of air quality prediction data before identifying whether the target station has air quality monitoring abnormity according to the air quality prediction data and second air quality monitoring data of the target station in the period to be identified;
correspondingly, the abnormality identification module specifically includes:
a normal station identification unit, configured to determine that air quality monitoring of the target station is normal if second air quality monitoring data of the target station is within the monitoring data confidence interval range;
and the abnormal station identification unit is used for determining that the target station has air quality monitoring abnormality if the second air quality monitoring data of the target station is out of the monitoring data confidence interval range.
Optionally, the interval determining module is specifically configured to: determining a monitoring data confidence interval of the target station and abnormal monitoring data intervals of a plurality of abnormal grades according to the plurality of groups of air quality prediction data;
correspondingly, the abnormal site identification unit is specifically configured to: and if the second air quality monitoring data of the target station is in the range of any stage of abnormal monitoring data interval, determining that the target station has air quality monitoring abnormality, and determining the abnormal grade of the target station.
Optionally, the interval determining module is specifically configured to: obtaining a maximum value P of the plurality of sets of air quality prediction datamaxMinimum value PminAnd standard deviation Pσ(ii) a Determining the confidence interval of the monitoring data as [ Pmin-Pσ , Pmax+Pσ](ii) a Determining the abnormal monitoring data interval of the first-level abnormality as Pmin-3Pσ , Pmin-Pσ) And (P)max+Pσ , Pmax+3Pσ](ii) a Anomaly monitoring data zone for determining secondary anomaliesIs meta (— infinity, P)min-3P) and (P)max+3Pσ , +∞)。
According to yet another aspect of the present application, there is provided a storage medium having stored thereon a computer program which, when executed by a processor, implements the above-described abnormality identification method of air quality monitoring data.
According to yet another aspect of the present application, there is provided a computer device comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, the processor implementing the above-mentioned anomaly identification method for air quality monitoring data when executing the program.
By means of the technical scheme, according to the method and the device for identifying the abnormality of the air quality monitoring data and the storage medium, for a target station needing abnormality monitoring, matched reference stations are screened out in a monitoring area where the target station is located according to the air quality similarity and the spatial distance, so that corresponding models are trained by using historical air quality data of each reference station and the target station, the air quality data of the target station is predicted through the trained models, and whether the monitoring data of the target station are abnormal or not is identified according to the air quality prediction data. Compared with the mode of manually monitoring and identifying abnormal sites in the prior art, the method and the device can utilize historical monitoring data of reference sites which are located in the same monitoring area with the target sites to establish a model, so that air quality data of the target sites are predicted through the model, data support is provided for abnormal identification of the target sites, intelligent abnormal identification is conducted on the monitoring data of the target sites according to the air quality prediction data, the sites with obvious data abnormality can be found out more accurately, pollution conditions can be monitored better, and the atmospheric environment is controlled.
The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a schematic flow chart illustrating an anomaly identification method for air quality monitoring data according to an embodiment of the present application;
fig. 2 shows a schematic structural diagram of an anomaly identification device for air quality monitoring data according to an embodiment of the present application.
Detailed Description
The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
In this embodiment, a method for identifying an abnormality of air quality monitoring data is provided, as shown in fig. 1, the method includes:
the monitoring data of the target sites in any monitoring area are subjected to abnormal identification, the monitoring area comprises a plurality of monitoring sites, the target sites and reference sites corresponding to the target sites are contained in the monitoring sites, each monitoring site in the monitoring area monitors air quality parameters in a corresponding range, and the air quality parameters specifically can comprise PM2.5、S02、N02、CO、03、PM10And (4) carrying out concentration equalization.
In this embodiment of the application, to determine the reference station, optionally, step 101 may specifically include:
step 101-1, determining a plurality of monitoring stations which are located in the same monitoring area with the target station according to the target station, wherein the monitoring stations comprise the target station and other monitoring stations;
step 101-2, if the number of the monitoring stations is larger than N +1, acquiring historical air quality data of each monitoring station in a second historical reference period, and respectively calculating the air quality similarity of the target station and each other monitoring station; selecting N sites from the other monitoring sites as the reference sites according to the air quality similarity and the distance between the target site and each of the other monitoring sites, wherein N is greater than 2;
and 101-3, if the number of the monitored sites is less than or equal to N +1, taking all other monitored sites in the monitored sites as the reference sites.
In the above embodiment, the target site is a site that needs to be monitored for an anomaly, and after the target site is selected, a monitoring area where the target site is located may be determined first, and a reference site is selected from monitoring sites included in the monitoring area. In a specific application scenario, if the number of monitored sites included in the monitored area is less than or equal to N +1, all other monitored sites except for the target site in the monitored area are directly used as reference sites of the target site, taking N =5 as an example, if the monitored area includes 6 or less than 6 monitored sites, all other sites except the target site are used as reference sites. And if the number of the monitoring stations in the monitoring area is greater than N, screening 5 reference stations from other monitoring stations except the target station, wherein the reference station is a station with higher matching degree with the target station, and the matching degree can be considered from two aspects, namely the similarity of the air quality monitoring data and the spatial distance of the two stations, specifically, the second historical reference time period can be a latest week time period, taking the historical air quality data of the latest week of each monitoring station in the monitoring area, respectively calculating the air quality similarity of each other monitoring station and the target station, and further selecting the reference station by combining the air quality similarity and the spatial distance between each other monitoring station and the target station.
Optionally, the "calculating the air quality similarity between the target site and each of the other monitored sites" in step 101-2 may specifically include: according to a plurality of preset time granularities, respectively carrying out aggregation processing on the historical air quality data of each other monitored station and the historical air quality data of the target station, and acquiring a first data characteristic vector of each other monitored station and a second data characteristic vector of the target station under any preset time granularity; and respectively calculating the air quality similarity of each other monitoring station and the target station according to the first data characteristic vector and the second data characteristic vector.
The second historical reference time interval is a time interval in a preset reference time interval range before the time interval to be identified, the preset reference time interval is greater than the time interval of the time interval to be identified, the time interval of the time interval to be identified comprises one hour, the preset reference time interval comprises one week, and the preset time granularity comprises at least one of working days, non-working days, the last 24 hours and the last 72 hours.
In the above embodiment, taking the period to be identified as the current hour, the preset reference time length as one week, and the second historical reference period as the last week, in a specific application scenario, the hourly pollutant concentration data (i.e., historical air quality data) of the last week of all monitored sites in the monitored area are taken, and are aggregated according to different time granularities into data feature vectors such as twenty-four hour working day concentration, twenty-four hour non-working day concentration, and twenty-four hour recent concentration, so as to distinguish a target site from data feature vectors of other sites.
Optionally, the step 101-2 of "selecting N sites as the reference sites among the other monitored sites" may specifically include: normalizing the air quality similarity C and the distance D between the target station and each other monitoring station; respectively calculating the matching degree Sim between the target station and each of the other monitoring stations according to the air quality similarity C and the distance D, wherein Sim =0.5 × D +0.5 × C; and arranging the matching degrees of the other monitored sites in a descending order, and selecting the top N sites as the reference sites.
In the above embodiment, the air quality similarity C and the distance D between the target site and each of the other monitoring sites are respectively normalized, and then the matching degree Sim between each of the other monitoring sites and the target site is respectively calculated, where the matching degree Sim is determined by performing weighted summation calculation on the air quality similarity C and the distance D, the weights may be all 0.5, or other weights may be set according to an actual situation, which is not limited herein, and after the matching degree Sim is calculated, N sites with higher matching degrees are selected from the other monitoring sites as reference sites.
in this embodiment of the application, after the reference station is determined, model training may be performed based on first historical air quality data corresponding to the reference station and second historical air quality data corresponding to the target station in a first historical reference period, where the first historical reference period may be the same as or different from a second historical reference period in this embodiment of the application, and taking the first historical reference period as an example, the air quality monitoring data of the target station and the reference station in the last week is taken, the first historical air quality data of any reference station is taken as an input, and the second historical air quality data of the target station is taken as an output, so as to perform model training, and specifically, a linear regression model may be established for training. In addition, it should be noted that the model can be established separately for different types of air quality parameters, such as PM for the reference site a and the target site2.5Air quality monitoring data establishment reference station A to PM of target station2.5A predictive model of the parameters.
103, inputting first air quality monitoring data of the reference station in a period to be identified into the air quality prediction model to obtain air quality prediction data of the target station in the period to be identified;
and 104, identifying whether the target station has abnormal air quality monitoring or not according to the air quality prediction data and second air quality monitoring data of the target station in the period to be identified.
In the embodiment of the application, after the model is trained successfully, the trained air quality prediction model is used for predicting the air quality data of the target station, specifically, the air quality monitoring data of the reference station within the period to be identified, namely, the first air quality monitoring data, can be input into the model to obtain the air quality prediction data of the target station, so that whether the air quality monitoring data (namely, the second air quality monitoring data) acquired by the target station is abnormal or not is judged according to the air quality prediction data.
In this embodiment of the application, optionally, step 102 may specifically include: respectively training an air quality prediction model matched with each reference station by using the first historical air quality data and the second historical air quality data of each reference station, so that the trained air quality prediction model can realize prediction of the air quality of the target station in the same time period based on the air quality monitoring data of the corresponding reference station;
correspondingly, step 103 may specifically include: and respectively inputting the first air quality monitoring data of each reference station in the time period to be identified into a corresponding air quality prediction model to obtain a plurality of groups of air quality prediction data of the target station.
In the above embodiment, when performing model training, training is performed on each reference station corresponding to a target station, taking 5 reference stations as an example, for a corresponding reference station a, using the latest week of air quality monitoring data of the reference station a as model input, using the latest week of air quality monitoring data of the target station as model output, performing model training, where the trained model can predict the air quality data of the target station at the same time interval by using the air quality monitoring data of the reference station a at a certain time interval, and multiple models correspond to multiple sets of air quality prediction data.
In this embodiment of the application, a reasonable range of the air quality monitoring data may be determined according to the multiple sets of air quality prediction data, so as to identify the abnormal data and the abnormal site, optionally, step 104 may further include: and determining a monitoring data confidence interval of the target station according to the multiple groups of air quality prediction data.
Accordingly, step 104 may include:
104-1, if the second air quality monitoring data of the target station is within the monitoring data confidence interval range, determining that the air quality monitoring of the target station is normal;
and step 104-2, if the second air quality monitoring data of the target station is out of the monitoring data confidence interval range, determining that the target station has abnormal air quality monitoring.
In the above embodiment, the detection data confidence interval of the target station may be determined based on multiple sets of air quality prediction data, so that when abnormal data identification is performed on the target station, as long as the second air quality monitoring data corresponding to the target station is in the confidence interval, the data may be considered normal and the station may be considered normal, otherwise, an abnormal situation may exist.
Optionally, according to the multiple sets of air quality prediction data, a monitoring data confidence interval of the target station and abnormal monitoring data intervals of multiple abnormal levels are determined. Wherein a maximum value P of the plurality of sets of air quality prediction data is obtainedmaxMinimum value PminAnd standard deviation Pσ(ii) a Determining the confidence interval of the monitoring data as [ Pmin-Pσ , Pmax+Pσ](ii) a Determining a primary exceptionThe abnormal monitoring data interval is [ P ]min-3Pσ , Pmin-Pσ) And (P)max+Pσ , Pmax+3Pσ](ii) a Determining the abnormal monitoring data interval of the second-level abnormality as (— infinity, P)min-3P) and (P)max+3Pσ , +∞)。
Correspondingly, step 104-2 may specifically include: and if the second air quality monitoring data of the target station is in the range of any stage of abnormal monitoring data interval, determining that the target station has air quality monitoring abnormality, and determining the abnormal grade of the target station.
In the embodiment, the abnormal grade is divided into a first grade and a second grade, the first grade belongs to low-degree unreliability, the second grade belongs to high-degree unreliability, and after multiple groups of air quality prediction data of the target station are obtained by using multiple models, the maximum predicted value and the minimum value plus one-time standard deviation are taken as the upper limit and the lower limit of the confidence interval of the monitoring data. For the target station, the credibility of the target station and the monitoring data of the target station is determined according to the following standard, for example, if the pollutant concentration at the current hour corresponding to the target station (i.e. the second air quality monitoring data) is within the confidence interval of the monitoring data, the pollutant concentration at the current hour of the substation is considered to be credible, if the pollutant concentration at the current hour corresponding to the target station is outside the prediction confidence interval and within the standard deviation interval of the maximum predicted value and the minimum value plus or minus three times, the pollutant concentration at the current hour of the substation is considered to be low-degree unreliable, otherwise, the pollutant concentration at the hour of the substation is considered to be high-degree unreliable.
By applying the technical scheme of the embodiment, for the target station which needs to be abnormally monitored, the matched reference stations are screened out in the monitoring area where the target station is located according to the air quality similarity and the spatial distance, so that the corresponding models are trained by using the historical air quality data of each reference station and the target station, the air quality data of the target station is predicted through the trained models, and whether the monitoring data of the target station is abnormal or not is identified according to the air quality prediction data. Compared with the mode of manually monitoring and identifying abnormal sites in the prior art, the method and the device can utilize historical monitoring data of reference sites which are located in the same monitoring area as the target sites to establish a model, thereby predicting the air quality data of the target sites through the model, providing data support for abnormal identification of the target sites, intelligently identifying the abnormal monitoring data of the target sites according to the air quality prediction data, being beneficial to finding out sites with obvious data abnormality more accurately, monitoring pollution conditions better, managing atmospheric environment, saving labor cost and improving identification efficiency.
Further, as a specific implementation of the method in fig. 1, an embodiment of the present application provides an apparatus for identifying an abnormality of air quality monitoring data, as shown in fig. 2, the apparatus includes:
the system comprises a site determining module, a site determining module and a monitoring module, wherein the site determining module is used for determining a target site and a reference site of the target site, and the target site and the reference site are located in the same monitoring area;
the model training module is used for training an air quality prediction model of the target station by utilizing first historical air quality data of the reference station and second historical air quality data of the target station in a first historical reference time period;
the data prediction module is used for inputting first air quality monitoring data of the reference station in a period to be identified into the air quality prediction model to obtain air quality prediction data of the target station in the period to be identified;
and the abnormity identification module is used for identifying whether the target station has abnormal air quality monitoring according to the air quality prediction data and second air quality monitoring data of the target station in the period to be identified.
Optionally, the station determining module specifically includes:
the monitoring station selection unit is used for determining a plurality of monitoring stations which are positioned in the same monitoring area with the target station according to the target station, wherein the monitoring stations comprise the target station and other monitoring stations;
the similarity calculation unit is used for acquiring historical air quality data of each monitoring station in a second historical reference period and calculating the air quality similarity of the target station and each other monitoring station respectively;
and the first station selecting unit is used for selecting N stations from the other monitoring stations as the reference station according to the air quality similarity and the distance between the target station and each of the other monitoring stations, wherein N is greater than 2.
Optionally, the similarity calculation unit is specifically configured to, if the number of the monitored sites is greater than N +1, perform the obtaining of the historical air quality data of each monitored site in the second historical reference period;
the station determining module further includes: and the second site selection unit is used for taking all other monitored sites in the monitored sites as the reference sites if the number of the monitored sites is less than or equal to N + 1.
Optionally, the first station selecting unit is specifically configured to: normalizing the air quality similarity C and the distance D between the target station and each other monitoring station; respectively calculating the matching degree Sim between the target station and each of the other monitoring stations according to the air quality similarity C and the distance D, wherein Sim =0.5 × D +0.5 × C; and arranging the matching degrees of the other monitored sites in a descending order, and selecting the top N sites as the reference sites.
Optionally, the similarity calculation unit is specifically configured to: according to a plurality of preset time granularities, respectively carrying out aggregation processing on the historical air quality data of each other monitored station and the historical air quality data of the target station, and acquiring a first data characteristic vector of each other monitored station and a second data characteristic vector of the target station under any preset time granularity; and respectively calculating the air quality similarity of each other monitoring station and the target station according to the first data characteristic vector and the second data characteristic vector.
Optionally, the second historical reference time interval is a time interval within a preset reference time interval range before the time interval to be identified, the preset reference time interval is greater than the time interval of the time interval to be identified, the time interval of the time interval to be identified includes one hour, the preset reference time interval includes one week, and the plurality of preset time granularities include at least one of a working day, a non-working day, a last 24 hours, and a last 72 hours.
Optionally, the reference site comprises a plurality of reference sites;
the model training module is specifically configured to: respectively training an air quality prediction model matched with each reference station by using the first historical air quality data and the second historical air quality data of each reference station, so that the trained air quality prediction model can realize prediction of the air quality of the target station in the same time period based on the air quality monitoring data of the corresponding reference station;
accordingly, the data prediction module is specifically configured to: and respectively inputting the first air quality monitoring data of each reference station in the time period to be identified into a corresponding air quality prediction model to obtain a plurality of groups of air quality prediction data of the target station.
Optionally, the apparatus further comprises:
the interval determination module is used for determining a monitoring data confidence interval of the target station according to the multiple groups of air quality prediction data before identifying whether the target station has air quality monitoring abnormity according to the air quality prediction data and second air quality monitoring data of the target station in the period to be identified;
correspondingly, the abnormality identification module specifically includes:
a normal station identification unit, configured to determine that air quality monitoring of the target station is normal if second air quality monitoring data of the target station is within the monitoring data confidence interval range;
and the abnormal station identification unit is used for determining that the target station has air quality monitoring abnormality if the second air quality monitoring data of the target station is out of the monitoring data confidence interval range.
Optionally, the interval determining module is specifically configured to: determining a monitoring data confidence interval of the target station and abnormal monitoring data intervals of a plurality of abnormal grades according to the plurality of groups of air quality prediction data;
correspondingly, the abnormal site identification unit is specifically configured to: and if the second air quality monitoring data of the target station is in the range of any stage of abnormal monitoring data interval, determining that the target station has air quality monitoring abnormality, and determining the abnormal grade of the target station.
Optionally, the interval determining module is specifically configured to: obtaining a maximum value P of the plurality of sets of air quality prediction datamaxMinimum value PminAnd standard deviation Pσ(ii) a Determining the confidence interval of the monitoring data as [ Pmin-Pσ , Pmax+Pσ](ii) a Determining the abnormal monitoring data interval of the first-level abnormality as Pmin-3Pσ , Pmin-Pσ) And (P)max+Pσ , Pmax+3Pσ](ii) a Determining the abnormal monitoring data interval of the second-level abnormality as (— infinity, P)min-3P) and (P)max+3Pσ , +∞)。
It should be noted that other corresponding descriptions of the functional units related to the abnormality identification device for air quality monitoring data provided in the embodiment of the present application may refer to corresponding descriptions in the methods in fig. 1 to fig. 2, and are not described herein again.
Based on the method shown in fig. 1, correspondingly, the embodiment of the present application further provides a storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the method for identifying an abnormality of the air quality monitoring data shown in fig. 1.
Based on such understanding, the technical solution of the present application may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.), and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the implementation scenarios of the present application.
Based on the method shown in fig. 1 and the virtual device embodiment shown in fig. 2, in order to achieve the above object, the present application further provides a computer device, which may specifically be a personal computer, a server, a network device, and the like, where the computer device includes a storage medium and a processor; a storage medium for storing a computer program; a processor for executing a computer program to implement the above-described anomaly identification method for air quality monitoring data as shown in fig. 1.
Optionally, the computer device may also include a user interface, a network interface, a camera, Radio Frequency (RF) circuitry, sensors, audio circuitry, a WI-FI module, and so forth. The user interface may include a Display screen (Display), an input unit such as a keypad (Keyboard), etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (e.g., a bluetooth interface, WI-FI interface), etc.
It will be appreciated by those skilled in the art that the present embodiment provides a computer device architecture that is not limiting of the computer device, and that may include more or fewer components, or some components in combination, or a different arrangement of components.
The storage medium may further include an operating system and a network communication module. An operating system is a program that manages and maintains the hardware and software resources of a computer device, supporting the operation of information handling programs, as well as other software and/or programs. The network communication module is used for realizing communication among components in the storage medium and other hardware and software in the entity device.
Through the description of the above embodiment, those skilled in the art can clearly understand that the present application can be implemented by software plus a necessary general hardware platform, and also can be implemented by hardware, for a target station that needs to be monitored for an anomaly, a matched reference station is screened out in a monitoring area where the target station is located according to the air quality similarity and the spatial distance, so that a corresponding model is trained by using historical air quality data of each reference station and the target station, the air quality data of the target station is predicted by the trained model, and whether the monitoring data of the target station is abnormal or not is identified according to the air quality prediction data. Compared with the mode of manually monitoring and identifying abnormal sites in the prior art, the method and the device can utilize historical monitoring data of reference sites which are located in the same monitoring area as the target sites to establish a model, so that air quality data of the target sites are predicted through the model, data support is provided for abnormal identification of the target sites, intelligent abnormal identification is conducted on the monitoring data of the target sites according to the air quality prediction data, the sites with obvious data abnormality can be found out more accurately, pollution conditions are monitored better, and the atmospheric environment is controlled.
Those skilled in the art will appreciate that the figures are merely schematic representations of one preferred implementation scenario and that the blocks or flow diagrams in the figures are not necessarily required to practice the present application. Those skilled in the art will appreciate that the modules in the devices in the implementation scenario may be distributed in the devices in the implementation scenario according to the description of the implementation scenario, or may be located in one or more devices different from the present implementation scenario with corresponding changes. The modules of the implementation scenario may be combined into one module, or may be further split into a plurality of sub-modules.
The above application serial numbers are for description purposes only and do not represent the superiority or inferiority of the implementation scenarios. The above disclosure is only a few specific implementation scenarios of the present application, but the present application is not limited thereto, and any variations that can be made by those skilled in the art are intended to fall within the scope of the present application.
Claims (13)
1. An anomaly identification method for air quality monitoring data is characterized by comprising the following steps:
determining a target site and a reference site of the target site, wherein the target site and the reference site are located in the same monitoring area;
training an air quality prediction model of the target station by using first historical air quality data of the reference station and second historical air quality data of the target station in a first historical reference period;
inputting first air quality monitoring data of the reference station in a period to be identified into the air quality prediction model to obtain air quality prediction data of the target station in the period to be identified;
and identifying whether the target station has abnormal air quality monitoring or not according to the air quality prediction data and second air quality monitoring data of the target station in the period to be identified.
2. The method according to claim 1, wherein the determining the target station and the reference station of the target station specifically comprises:
determining a plurality of monitoring stations which are located in the same monitoring area with the target station according to the target station, wherein the monitoring stations comprise the target station and other monitoring stations;
acquiring historical air quality data of each monitored site in a second historical reference period, and respectively calculating the air quality similarity of the target site and each other monitored site;
and selecting N sites from the other monitoring sites as the reference sites according to the air quality similarity and the distance between the target site and each of the other monitoring sites, wherein N is greater than 2.
3. The method of claim 2, wherein prior to obtaining historical air quality data for each monitored site within the second historical reference period, the method further comprises:
if the number of the monitored stations is larger than N +1, the historical air quality data of each monitored station in the second historical reference period are obtained;
and if the number of the monitored sites is less than or equal to N +1, taking all other monitored sites in the monitored sites as the reference sites.
4. The method according to claim 2, wherein the selecting N stations among the other monitored stations as the reference station according to the air quality similarity and the distance between the target station and each of the other monitored stations specifically comprises:
normalizing the air quality similarity C and the distance D between the target station and each other monitoring station;
respectively calculating the matching degree Sim between the target station and each of the other monitoring stations according to the air quality similarity C and the distance D, wherein Sim =0.5 × D +0.5 × C;
and arranging the matching degrees of the other monitored sites in a descending order, and selecting the top N sites as the reference sites.
5. The method according to claim 2, wherein the calculating the air quality similarity between the target site and each of the other monitored sites respectively comprises:
according to a plurality of preset time granularities, respectively carrying out aggregation processing on the historical air quality data of each other monitored station and the historical air quality data of the target station, and acquiring a first data characteristic vector of each other monitored station and a second data characteristic vector of the target station under any preset time granularity;
and respectively calculating the air quality similarity of each other monitoring station and the target station according to the first data characteristic vector and the second data characteristic vector.
6. The method of claim 5, wherein the second historical reference time period is a time period within a preset reference time period range before the time period to be identified, the preset reference time period is greater than the time period of the time period to be identified, the time period of the time period to be identified comprises one hour, the preset reference time period comprises one week, and the plurality of preset time granularities comprise at least one of a working day, a non-working day, a last 24 hours, and a last 72 hours.
7. The method of claim 1, wherein the reference site comprises a plurality; the training of the air quality prediction model of the target station by using the first historical air quality data of the reference station and the second historical air quality data of the target station in the first historical reference period specifically includes:
respectively training an air quality prediction model matched with each reference station by using the first historical air quality data and the second historical air quality data of each reference station, so that the trained air quality prediction model can realize prediction of the air quality of the target station in the same time period based on the air quality monitoring data of the corresponding reference station;
correspondingly, the inputting the first air quality monitoring data of the reference station in the period to be identified into the air quality prediction model to obtain the air quality prediction data of the target station in the period to be identified specifically includes:
and respectively inputting the first air quality monitoring data of each reference station in the time period to be identified into a corresponding air quality prediction model to obtain a plurality of groups of air quality prediction data of the target station.
8. The method of claim 7, wherein before identifying whether an air quality monitoring anomaly exists at the target station based on the air quality prediction data and second air quality monitoring data of the target station during the period to be identified, the method further comprises:
determining a monitoring data confidence interval of the target station according to the multiple groups of air quality prediction data;
correspondingly, identifying whether the target station has an air quality monitoring abnormality according to the air quality prediction data and the second air quality monitoring data of the target station in the period to be identified specifically includes:
if the second air quality monitoring data of the target station is within the monitoring data confidence interval range, determining that the air quality monitoring of the target station is normal;
and if the second air quality monitoring data of the target station is out of the monitoring data confidence interval range, determining that the target station has abnormal air quality monitoring.
9. The method according to claim 8, wherein the determining a confidence interval of the monitoring data of the target station according to the plurality of sets of air quality prediction data specifically comprises:
determining a monitoring data confidence interval of the target station and abnormal monitoring data intervals of a plurality of abnormal grades according to the plurality of groups of air quality prediction data;
correspondingly, if the second air quality monitoring data of the target station is out of the monitoring data confidence interval range, determining that the target station has an air quality monitoring abnormality, specifically including:
and if the second air quality monitoring data of the target station is in the range of any stage of abnormal monitoring data interval, determining that the target station has air quality monitoring abnormality, and determining the abnormal grade of the target station.
10. The method according to claim 9, wherein the determining a monitoring data confidence interval of the target station and abnormal monitoring data intervals of a plurality of abnormal levels according to the plurality of sets of air quality prediction data specifically comprises:
obtaining a maximum value P of the plurality of sets of air quality prediction datamaxMinimum value PminAnd standard deviation Pσ；
Determining the confidence interval of the monitoring data as [ Pmin-Pσ , Pmax+Pσ]；
Determining the abnormal monitoring data interval of the first-level abnormality as Pmin-3Pσ , Pmin-Pσ) And (P)max+Pσ , Pmax+3Pσ]；
Determining the abnormal monitoring data interval of the second-level abnormality as (— infinity, P)min-3P) and (P)max+3Pσ , +∞)。
11. An abnormality recognition device for air quality monitoring data, characterized by comprising:
the system comprises a site determining module, a site determining module and a monitoring module, wherein the site determining module is used for determining a target site and a reference site of the target site, and the target site and the reference site are located in the same monitoring area;
the model training module is used for training an air quality prediction model of the target station by utilizing first historical air quality data of the reference station and second historical air quality data of the target station in a first historical reference time period;
the data prediction module is used for inputting first air quality monitoring data of the reference station in a period to be identified into the air quality prediction model to obtain air quality prediction data of the target station in the period to be identified;
and the abnormity identification module is used for identifying whether the target station has abnormal air quality monitoring according to the air quality prediction data and second air quality monitoring data of the target station in the period to be identified.
12. A storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method of any of claims 1 to 10.
13. A computer device comprising a storage medium, a processor and a computer program stored on the storage medium and executable on the processor, characterized in that the processor implements the method of any one of claims 1 to 10 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110330428.2A CN112801423B (en) | 2021-03-29 | 2021-03-29 | Method and device for identifying abnormity of air quality monitoring data and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110330428.2A CN112801423B (en) | 2021-03-29 | 2021-03-29 | Method and device for identifying abnormity of air quality monitoring data and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112801423A true CN112801423A (en) | 2021-05-14 |
| CN112801423B CN112801423B (en) | 2021-07-20 |
Family
ID=75815877
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110330428.2A Active CN112801423B (en) | 2021-03-29 | 2021-03-29 | Method and device for identifying abnormity of air quality monitoring data and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112801423B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115184556A (en) * | 2022-07-13 | 2022-10-14 | 蔡文斯 | Abnormal value monitoring method and system of air quality data and alarm terminal equipment |
| CN117577227A (en) * | 2024-01-16 | 2024-02-20 | 北京市生态环境监测中心 | PM2.5 point location high value identification method, system, equipment and medium |
| CN117609792A (en) * | 2024-01-18 | 2024-02-27 | 北京英视睿达科技股份有限公司 | Water quality prediction model training method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104200104A (en) * | 2014-09-04 | 2014-12-10 | 浙江鸿程计算机系统有限公司 | Fine granularity air pollutant concentration area estimation method based on spatial characteristics |
| CN108268901A (en) * | 2018-01-25 | 2018-07-10 | 中国环境监测总站 | A kind of algorithm that environmental monitoring abnormal data is found based on dynamic time warping distance |
| CN109657842A (en) * | 2018-11-27 | 2019-04-19 | 平安科技（深圳）有限公司 | The prediction technique and device of air pollutant concentration, electronic equipment |
| CN109685246A (en) * | 2018-11-13 | 2019-04-26 | 平安科技（深圳）有限公司 | Environmental data predictor method, device and storage medium, server |
| US20190325334A1 (en) * | 2018-04-23 | 2019-10-24 | National Chung-Shan Institute Of Science And Technology | Method for predicting air quality with aid of machine learning models |
| CN111340288A (en) * | 2020-02-25 | 2020-06-26 | 武汉墨锦创意科技有限公司 | Urban air quality time sequence prediction method considering space-time correlation |
-
2021
- 2021-03-29 CN CN202110330428.2A patent/CN112801423B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104200104A (en) * | 2014-09-04 | 2014-12-10 | 浙江鸿程计算机系统有限公司 | Fine granularity air pollutant concentration area estimation method based on spatial characteristics |
| CN108268901A (en) * | 2018-01-25 | 2018-07-10 | 中国环境监测总站 | A kind of algorithm that environmental monitoring abnormal data is found based on dynamic time warping distance |
| US20190325334A1 (en) * | 2018-04-23 | 2019-10-24 | National Chung-Shan Institute Of Science And Technology | Method for predicting air quality with aid of machine learning models |
| CN109685246A (en) * | 2018-11-13 | 2019-04-26 | 平安科技（深圳）有限公司 | Environmental data predictor method, device and storage medium, server |
| CN109657842A (en) * | 2018-11-27 | 2019-04-19 | 平安科技（深圳）有限公司 | The prediction technique and device of air pollutant concentration, electronic equipment |
| CN111340288A (en) * | 2020-02-25 | 2020-06-26 | 武汉墨锦创意科技有限公司 | Urban air quality time sequence prediction method considering space-time correlation |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115184556A (en) * | 2022-07-13 | 2022-10-14 | 蔡文斯 | Abnormal value monitoring method and system of air quality data and alarm terminal equipment |
| CN117577227A (en) * | 2024-01-16 | 2024-02-20 | 北京市生态环境监测中心 | PM2.5 point location high value identification method, system, equipment and medium |
| CN117577227B (en) * | 2024-01-16 | 2024-04-16 | 北京市生态环境监测中心 | PM2.5 point location high value identification method, system, equipment and medium |
| CN117609792A (en) * | 2024-01-18 | 2024-02-27 | 北京英视睿达科技股份有限公司 | Water quality prediction model training method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112801423B (en) | 2021-07-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112801423B (en) | Method and device for identifying abnormity of air quality monitoring data and storage medium | |
| US10628292B2 (en) | Methods and systems for predicting estimation of project factors in software development | |
| US9679243B2 (en) | System and method for detecting platform anomalies through neural networks | |
| TWI385492B (en) | A system for maintaining and analyzing manufacturing equipment and method therefor | |
| US20190204818A1 (en) | Data collection system, abnormality detection method, and gateway device | |
| CN111174370A (en) | Fault detection method and device, storage medium and electronic device | |
| CN113486584B (en) | Method and device for predicting equipment failure, computer equipment and computer readable storage medium | |
| CN110211121B (en) | Method and device for pushing model | |
| JP2018013348A (en) | Hammering testing system and hammering testing method | |
| CN112817814A (en) | Abnormity monitoring method, system, storage medium and electronic device | |
| CN114385869A (en) | Method and device for detecting data abnormity, storage medium and computer equipment | |
| CN116756522B (en) | Probability forecasting method and device, storage medium and electronic equipment | |
| CN112783744A (en) | Data detection method, device, equipment and storage medium | |
| CN107517474B (en) | Network analysis optimization method and device | |
| CN110991867A (en) | Marketing resource adjustment method and device based on gross benefit rate influence factor | |
| US20220417106A1 (en) | Computerized system and method for an improved self organizing network | |
| CN112398706B (en) | Data evaluation standard determining method and device, storage medium and electronic equipment | |
| CN114938339A (en) | Data processing method and related device | |
| CN113361811A (en) | Method, system, device and computer readable storage medium for predicting operation state | |
| CN114124460A (en) | Industrial control system intrusion detection method and device, computer equipment and storage medium | |
| CN113487087A (en) | Method and device for predicting service life of equipment, computer equipment and computer-readable storage medium | |
| US11985048B2 (en) | Computerized system and method for an improved self organizing network | |
| CN116453437B (en) | Display screen module testing method, device, equipment and storage medium | |
| CN115795323B (en) | Malignant load identification method, equipment and storage medium | |
| CN117407774B (en) | Traffic data processing method and system based on artificial intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 100071 Beijing Fengtai Auto Museum West Road No. 8 Courtyard 1 Building 6 Floor 606 Patentee after: Beijing Yingshi Ruida Technology Co.,Ltd. Address before: 100071 Beijing Fengtai Auto Museum West Road No. 8 Courtyard 1 Building 6 Floor 606 Patentee before: BEIJING INSIGHTS VALUE TECHNOLOGY Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder |