CN111739588A

CN111739588A - Method and device for analyzing atmospheric pollutant source, storage medium and terminal

Info

Publication number: CN111739588A
Application number: CN202010567002.4A
Authority: CN
Inventors: 王帅; 周政男; 晏平仲; 林久人; 刘慧灵; 张潮; 秦东明; 陆涛
Original assignee: 3Clear Technology Co Ltd
Current assignee: 3Clear Technology Co Ltd
Priority date: 2020-06-19
Filing date: 2020-06-19
Publication date: 2020-10-02
Anticipated expiration: 2040-06-19
Also published as: CN111739588B

Abstract

The invention discloses an analysis method, a device, a storage medium and a terminal for atmospheric pollutant sources, wherein the method comprises the following steps: operating a second model according to the key parameter attributes determined by the first model, analyzing the atmospheric pollutant data, and generating an analysis file at least comprising the analysis result of the atmospheric pollutant source; therefore, by adopting the embodiment of the application, the key parameter attributes in the second model can be determined through the first model; the second model can be operated according to the key parameter attributes determined by the first model, the atmospheric pollutant data are automatically analyzed, and an analysis file at least comprising an atmospheric pollutant source analysis result is generated.

Description

Method and device for analyzing atmospheric pollutant source, storage medium and terminal

Technical Field

The invention relates to the technical field of computers, in particular to an analysis method, an analysis device, a storage medium and a terminal for an atmospheric pollutant source.

Background

VOCs (Volatile Organic Compounds) are a class of Organic pollutants that are ubiquitous and complex in composition in the atmosphere. The pollution is mainly reflected in two aspects, on one hand, most VOCs have toxicological characteristics and harm human health. On the other hand, some VOCs have stronger photochemical reaction activity and can carry out secondary conversion in the environment. The photochemical reaction of the compound is used for leading the process of photochemical smog, is important for the generation of ozone in cities and areas, and is one of important precursors for causing dust-haze weather. In conclusion, volatile organic compounds are one of the important causes for the formation of complex atmospheric pollution.

NAQPMS (Nested Air Quality Prediction System, Nested grid Air Quality Prediction mode) is a third generation Air Quality mode designed based on the concept of "one atmosphere". The NAQPMS comprehensively considers the processes of advection, diffusion, dry-wet sedimentation, chemical conversion and the like of atmospheric pollutants in the atmosphere. The online source tracking technology of the NAQPMS mode coupling pollution performs source classification and regional quality tracking on various physical and chemical processes from source emission, can track the source of pollutants, and quantitatively analyzes the contribution rate of the conveying process and regional pollution emission. The analysis of the numerical prediction mode such as NAQPMS needs to be based on a more detailed list of emission sources, so the analysis of the atmospheric pollutant source becomes the basis and precondition for the application of the numerical prediction mode.

In 1997, the Paatero publication paper proposed the operation of the PMF model. PMF (Positive matrix factorization) is a new analysis method developed on the basis of the factor analysis method and is rapidly popularized and used internationally. The method is mainly based on the chemical composition data of the particle sample of the environmental receptor site, and does not directly depend on the chemical composition spectrum data of a pollution source, so that the method has greater flexibility in application. The PMF is a multivariate factor analysis tool, which decomposes a sample data matrix containing a plurality of dates and different components into two matrixes, namely a source spectrum distribution matrix and a source contribution matrix, then determines the type of decomposed source according to the grasped source spectrum distribution information, and the number of the sources is also given according to the understanding of an analyst on pollution sources, and is not limited. After Paatero proposed the operation method of the PMF model, Paatero and Hopke continuously improved the PMF model, and EPAPMF software was introduced on the US EPA official website. Paatero also independently introduced PMF2 and PMF3 model software. Since the introduction of PMF software based on PMF models, it has played an important role in the process of resolving the source of pollutants.

The PMF model is one of source unknown receptor models, the source unknown receptor models do not need to know the quantity of sources and the information of component spectrums in advance, a large amount of data are measured on the same receptor, the data are analyzed, a plurality of factors are extracted, the factors are identified into different pollution source types in a one-to-one correspondence mode, therefore, the quantity of the sources and the component spectrums of the sources are obtained, and the contribution values of the pollution source types to the receptor are estimated. However, the process of analyzing the pollutant source through the PMF model to generate the corresponding analysis result is not only tedious, but also requires professional knowledge and operation skills of the operator.

At present, in the process of analyzing the pollutant source by using PMF software based on a PMF model, the manual experience is high in occupation ratio, and the result accuracy usually depends on the operation experience of an operator. Moreover, in the process of analyzing the pollutant source, the operator is required to adjust various parameters for many times. For a beginner, in the process of analyzing the pollutant source, various factors are difficult to identify, and therefore, a reasonable analysis result is difficult to obtain. After the initial analysis result is obtained, the initial analysis result cannot be adjusted by combining the pollutant information of different areas. In a word, the existing PMF software of the PMF model is used for analyzing pollutant sources in different areas, so that the process of obtaining analysis results is not only complicated, but also needs to invest a large amount of manpower, material resources and time, and the accuracy of the obtained analysis results cannot be ensured.

Disclosure of Invention

The embodiment of the application provides an analysis method and device for an atmospheric pollutant source, a storage medium and a terminal. The following presents a simplified summary in order to provide a basic understanding of some aspects of the disclosed embodiments. This summary is not an extensive overview and is intended to neither identify key/critical elements nor delineate the scope of such embodiments. Its sole purpose is to present some concepts in a simplified form as a prelude to the more detailed description that is presented later.

In a first aspect, an embodiment of the present application provides a method for resolving an atmospheric pollutant source, where the method includes:

acquiring atmospheric pollutant data of a preset area and extracting various factors for determining a first model according to the atmospheric pollutant data;

determining the first model according to the factors, wherein the first model is used for determining key parameter attributes in a second model, and the second model is a preset positive definite matrix factorization model;

and operating the second model according to the key parameter attributes determined by the first model, analyzing the atmospheric pollutant data, and generating an analysis file at least comprising an atmospheric pollutant source analysis result.

In a second aspect, an embodiment of the present application provides an apparatus for resolving an atmospheric pollutant source, the apparatus including:

the acquisition and extraction module is used for acquiring atmospheric pollutant data of a preset area and extracting various factors for determining the first model according to the atmospheric pollutant data;

the determining module is used for determining a first model according to the factors extracted by the obtaining and extracting module, the first model is used for determining key parameter attributes in a second model, and the second model is a preset positive definite matrix factorization model;

and the analysis module is used for operating the second model according to the key parameter attributes determined by the first model determined by the determination module, analyzing the atmospheric pollutant data and generating an analysis file at least comprising an atmospheric pollutant source analysis result.

In a third aspect, embodiments of the present application provide a computer storage medium storing a plurality of instructions adapted to be loaded by a processor and to perform the above-mentioned method steps.

In a fourth aspect, an embodiment of the present application provides a terminal, which may include: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to perform the above-mentioned method steps.

The technical scheme provided by the embodiment of the application can have the following beneficial effects:

in the embodiment of the application, the atmospheric pollutant data of a preset area and various factors in the atmospheric pollutant data are obtained; determining a first model according to various factors, wherein the first model is used for determining various key parameter attributes in a second model, and the second model is a preset positive definite matrix factorization model; and operating the second model according to the key parameter attributes determined by the first model, analyzing the atmospheric pollutant data, and generating an analysis file at least comprising the analysis result of the atmospheric pollutant source. The method and the device can determine the key parameter attributes in the second model through the first model; the second model can be operated according to the key parameter attributes determined by the first model, the atmospheric pollutant data are automatically analyzed, and an analysis file at least comprising an atmospheric pollutant source analysis result is generated.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.

Fig. 1 is a schematic flow chart of a method for resolving an atmospheric pollutant source according to an embodiment of the present disclosure;

FIG. 2 is a schematic flow chart of a method for resolving a source of an atmospheric pollutant in a specific application scenario in an embodiment of the present application;

fig. 3 is a schematic structural diagram of an apparatus for resolving an atmospheric pollutant source according to an embodiment of the present disclosure;

fig. 4 is a schematic structural diagram of a terminal according to an embodiment of the present application.

Detailed Description

The following description and the drawings sufficiently illustrate specific embodiments of the invention to enable those skilled in the art to practice them.

It should be understood that the described embodiments are only some embodiments of the invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the invention, as detailed in the appended claims.

In the description of the present invention, it is to be understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art. In addition, in the description of the present invention, "a plurality" means two or more unless otherwise specified. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.

Until now, the process of obtaining the analysis result by analyzing the atmospheric pollutant sources in different areas through the PMF software of the existing PMF model is not only complicated, but also needs a large amount of manpower, material resources and time, and the accuracy of the obtained analysis result cannot be ensured. Therefore, the present application provides an analysis method, an apparatus, a storage medium, and a terminal for atmospheric pollutant sources to solve the above problems in the related art. According to the technical scheme, the method comprises the steps of obtaining atmospheric pollutant data of a preset area and various factors in the atmospheric pollutant data; determining a first model according to various factors; operating a second model according to the key parameter attributes determined by the first model, analyzing the atmospheric pollutant data, and generating an analysis file at least comprising the analysis result of the atmospheric pollutant source; the method and the device can determine the key parameter attributes in the second model through the first model; the second model can be operated according to the key parameter attributes determined by the first model, the atmospheric pollutant data can be automatically analyzed, and the analysis file at least comprising the analysis result of the atmospheric pollutant source is generated.

The method for resolving the source of the atmospheric pollutants provided by the embodiments of the present application will be described in detail below with reference to fig. 1-2. The method for analyzing the atmospheric pollutant source can be realized by relying on a computer program and can be operated on an analyzing device of the atmospheric pollutant source. The computer program may be integrated into the application or may run as a separate tool-like application. The atmospheric pollutant source analysis device in the embodiment of the present application may be a user terminal, including but not limited to: personal computers, tablet computers, handheld devices, in-vehicle devices, wearable devices, computing devices or other processing devices connected to a wireless modem, and the like. The user terminals may be called different names in different networks, for example: user equipment, access terminal, subscriber unit, subscriber station, mobile station, remote terminal, mobile device, user terminal, wireless communication device, user agent or user equipment, cellular telephone, cordless telephone, Personal Digital Assistant (PDA), terminal equipment in a 5G network or future evolution network, and the like.

Referring to fig. 1, a flow chart of a method for analyzing an atmospheric pollutant source is provided in an embodiment of the present application. As shown in fig. 1, the method for resolving an atmospheric pollutant source according to the embodiment of the present application may include the following steps:

s101, obtaining atmospheric pollutant data of a preset area and extracting various factors for determining a first model according to the atmospheric pollutant data.

In this step, the predetermined area may be a region, such as Beijing, or a city region, such as Beijing Haisha. The range of the preset area is not particularly limited herein.

Atmospheric pollution data often corresponds to various types of atmospheric pollutants that contribute to atmospheric pollution. For example, when the type of the current atmospheric pollutant is volatile organic, then the atmospheric pollutant data is volatile organic data. When the current type of atmospheric pollutant is an automotive emissions source, then the atmospheric pollutant data is atmospheric pollutant data for the typical components OC, EC, Zn, Cu, Mn, Pb. The above are merely examples, and other types of atmospheric pollutant data are also possible, and are not described in detail herein.

In this step, the factors include at least a first factor corresponding to time, a second factor corresponding to the number of factors, and a third factor corresponding to the species. The above lists only common factors, and other factors may also be introduced according to different application scenarios, so as to determine each key parameter attribute in the second model through the first model.

It should be noted that, in this step, the extraction method for extracting the factors for determining the first model according to the atmospheric pollutant data is a conventional method, for example, common factors such as time, factor number, or species are extracted from a large amount of atmospheric pollutant data. The specific extraction method is not described herein again.

In this step, the second model is a predetermined positive definite matrix factorization model. The preset positive definite matrix factorization model provided by the embodiment of the application is different from a conventional positive definite matrix factorization model, and is a model obtained by improving the conventional positive definite matrix factorization model. The existing positive definite matrix factorization model is a method based on factor analysis, and has the advantages that a source fingerprint spectrum does not need to be measured, elements in a factorization matrix are not negative, data standard deviation can be utilized for optimization, and the like. The existing positive definite matrix factorization model is mainly used for source analysis of persistent toxic substances in atmospheric aerosol, soil and sediments, and the existing mature application models are PMF1.1, PMF2.0, PMF3.0 and the like.

In the scheme provided by the embodiment of the present application, after obtaining the key parameter attributes in the second model determined by the first model, the preset positive definite matrix factorization model can be automatically run, that is, the preset positive definite matrix factorization model is: and automatically operating the second model, analyzing the atmospheric pollutant data, and generating an analysis file at least comprising an atmospheric pollutant source analysis result. The first determining process for determining the key parameter attributes in the second model from the first model and the second analyzing process for automatically operating the preset positive definite matrix factorization model after obtaining the key parameter attributes in the second model determined by the first model are automatically completed without manual participation, so that a large amount of manpower and material resources are saved.

In addition, the key parameters determined by the first model and operated in the second model are often matched with the historical data of the atmospheric pollutants in the preset area. And inputting historical data of the atmospheric pollutants in the preset area into the first model, automatically configuring parameters through the first model, and obtaining and outputting various key parameters to be operated in the second model. And operating the second model according to the key parameter attributes corresponding to the key parameters determined by the first model, analyzing the atmospheric pollutant data, and generating an analysis file at least comprising the analysis result of the atmospheric pollutant source. The configuration process of each key parameter and the analysis process of the atmospheric pollutant data are automatically completed. Compared with the prior art, the analysis method provided by the embodiment of the disclosure avoids a complicated and complicated process of manually configuring each key parameter before analysis, so that the analysis efficiency is improved as a whole. According to statistics, compared with the existing analytic method, the analytic method of the atmospheric pollutant source provided by the embodiment of the disclosure can improve the analytic efficiency by 150%.

And S102, determining a first model according to the factors, wherein the first model is used for determining key parameter attributes in a second model, and the second model is a preset positive definite matrix factorization model.

In an embodiment of the disclosure, the first model is used to determine key parameter attributes of items in the second model. The parameter adjusting model of the first model is a conventional model, and all models capable of automatically adjusting various parameters can be applied to the method embodiment provided by the embodiment of the disclosure.

In this step, the key parameter attribute includes not only what each key parameter specifically refers to, for example, the key parameter may be time, the key parameter may also be factor number, the key parameter or species; the numerical range corresponding to the key parameter can also be referred to, which is specifically described as follows:

for example, the range of values corresponding to the first factor corresponding to time may be set to, 2020.5.1-2020.5.31, i.e.: statistics were made on the atmospheric pollutants data over the period of time 2020.5.1 to 2020.5.31.

For another example, the numerical range of the second factor corresponding to the number of factors may be set to 1-N according to the history data, where N is a positive integer greater than or equal to 2.

In a specific application scenario, the current factor number is 7. Specifically, the factor 1 is a volatile organic compound, wherein the volatile organic compound may be formaldehyde, acetaldehyde, or the like. Factor 2 represents the secondary inorganic aerosol source, and sulfate, nitrate, and ammonium salts are the main components of the factor. Factor 3 represents a source of coal, and is relatively high in OC, EC, Cl, Na, and some soil elements. The factor 4 represents an automotive emission source, and typical components of OC, EC, Zn, Cu, Mn, Pb, etc. are relatively high in content. Factor 5 is a source of fugitive dust which contains a large amount of crust elements such as Al, Fe, Mg, etc. Factor 6 is a source associated with metallurgical industry sources that contain higher proportions of Fe, Cr, Mn, etc. Factor 7 is another source, where OC, EC, Mn may be from chemical industry, cement industry, etc. OC, EC may be derived from biomass combustion.

The key parameter attribute may also be a species, for example, the factor 1 is a volatile organic compound, wherein the volatile organic compound may be formaldehyde, acetaldehyde, or the like. The above is merely an example, and the key parameter attribute may also introduce parameter attributes with other meanings according to requirements of different application scenarios, which is not described herein again.

The preset positive definite matrix factorization model in the scheme provided by the embodiment of the application can automatically run the preset positive definite matrix factorization model after obtaining each key parameter attribute in the second model determined by the first model, namely: and automatically operating the second model, analyzing the atmospheric pollutant data, and generating an analysis file at least comprising an atmospheric pollutant source analysis result.

In this step, the factors include at least a first factor corresponding to time, a second factor corresponding to the number of factors, and a third factor corresponding to the species. The above lists only common factors, and other factors may also be introduced according to different application scenarios to determine the first model, where the first model is used to determine key parameter attributes of each item in the second model, and the second model is a preset positive definite matrix factorization model.

In this step, determining the first model based on the factors includes the steps of:

obtaining historical data associated with the first factor, the second factor, and the third factor;

determining various historical key parameters and/or historical numerical value ranges corresponding to the various historical key parameters according to historical data;

and determining the first model according to various historical key parameters and/or historical numerical value ranges corresponding to various historical key parameters.

It should be noted that the historical data in this step may be historical data associated with any one of the first factor, the second factor, and the third factor, or may be historical data associated with all of the first factor, the second factor, and the third factor.

In this step, the first model is used to determine key parameter attributes of the items in the second model. The second model is a preset positive definite matrix factorization model. The preset positive definite matrix factorization model provided by the embodiment of the application is different from a conventional positive definite matrix factorization model, and is a model obtained by improving the conventional positive definite matrix factorization model. The preset positive definite matrix factorization model in the scheme provided by the embodiment of the application can automatically run the preset positive definite matrix factorization model after obtaining each key parameter attribute in the second model determined by the first model, namely: and automatically operating the second model, analyzing the atmospheric pollutant data, and generating an analysis file at least comprising an atmospheric pollutant source analysis result.

And S103, operating a second model according to the key parameter attributes determined by the first model, analyzing the atmospheric pollutant data, and generating an analysis file at least comprising the analysis result of the atmospheric pollutant source.

In the solution of the analytic method provided in the embodiment of the present disclosure, in addition to generating an analytic file including at least an atmospheric pollutant source analytic result, a table capable of viewing characteristic values may be generated, or a schematic diagram representing fitting results of the items may be generated, or factor confirmation may be performed according to the obtained factor-related data.

It should be noted that the feature values in the generated table are common feature values, and the meaning of each feature value is not specifically described here.

The fitting process for obtaining each fitting result is also a conventional method, and is not described herein again.

In addition, the process of performing factor confirmation according to the obtained factor-related data is also a conventional method, and is not described herein again. In practical applications, the factor used for factor confirmation may be a volatile organic compound, wherein the volatile organic compound may be formaldehyde, acetaldehyde, or the like. The factors used in the factor identification may also be automotive emissions sources, typical components of which are OC, EC, Zn, Cu, Mn, Pb, etc.

In practical applications, the factor used for factor confirmation may also be other factors, and specific possible factors may be referred to the same or related descriptions, and are not described herein again.

In one possible implementation, after generating the parsing file including at least the parsing result of the atmospheric pollutant source, the method further includes the following steps:

and according to the historical analysis data, identifying factors in the analysis result, and identifying each source in each factor within a preset sequencing range.

In this step, the preset sorting range may be adjusted according to the requirements of different application scenarios. For example, the preset sorting range may be configured to be 1, so that the source having the highest density and the highest weight value can be used as the identified source.

Conversely, the predetermined sorting range may be configured as 2 or wider, so that different sources under the same factor are listed in the order from high to low as much as possible. For example, the source having the highest concentration and the highest weight value is set as the source ranked the highest, and the other sources are ranked in order. Therefore, when the treatment scheme is specified according to the determined various sources, the treatment scheme aiming at the source with the most front sequence is preferentially selected, and the treatment effect is finally improved.

In practical application, in the process of identifying factors in an analysis result according to historical analysis data and identifying each source in each factor within a preset sequencing range, the preset sequencing range is often set to be 1 in order to improve analysis efficiency, that is: only the first source in the ranking of each factor is selected as the identified source. For example, when the current factor is a volatile organic compound, where the volatile organic compound only includes formaldehyde and acetaldehyde, and the concentration and the weight value of formaldehyde are respectively higher than the concentration and the weight value of acetaldehyde, the formaldehyde ranking is higher than that of acetaldehyde, and the set condition is: and when the first source in the sequence in the current factors is selected as the identified source, identifying that the first source in the sequence in the current factors is formaldehyde, and using the formaldehyde as the identified source.

In practical application, the value corresponding to the preset sorting range can be configured according to the requirements of different application scenarios, if the configuration of the preset sorting range is larger, the candidate sources corresponding to the current factor are richer, and the contribution rates of different sources under the same factor to the current pollution can be known in more detail, that is: the influence of different sources under the same factor on the current pollution. On the contrary, if the configuration of the preset sorting range is smaller, when the configuration of the preset sorting range is 1, it can be quickly determined that: which source contributes most to pollution based on the current factor. For example, when the current factor is a volatile organic compound, where the volatile organic compound includes only formaldehyde and acetaldehyde, and the concentration and the weight value of formaldehyde are respectively higher than the concentration and the weight value of acetaldehyde, the rank of formaldehyde is higher than that of acetaldehyde, and then the source in the first rank in the current factor is identified as formaldehyde, and formaldehyde is used as the identified source. Thus, it is finally possible to determine quickly and accurately: formaldehyde is the most highly contributing source when the current factor is a volatile organic. Therefore, when a pollution source in a predetermined area is treated, a treatment method capable of rapidly removing formaldehyde is preferably selected.

In a possible implementation manner, identifying factors in an analysis result according to historical analysis data, and identifying each source in each factor within a preset sequencing range includes the following steps:

determining preset conditions according to historical analysis data; the preset conditions are conditions for determining the weight value of each source in each factor, and in practical application, the preset conditions can be configured according to historical statistical results, and the preset conditions can also be configured according to historical experiences of users;

determining the weight value of each source in each factor according to preset conditions;

determining the ratio value of each source in each factor according to the component of each source, the concentration of each source and the weight value of each source in each factor;

and determining each source of which the ratio value in each factor is in a preset sequencing range according to the ratio value of each source in each factor and the mapping relation between the ratio value and each source.

In this step, the preset condition may be configured according to different application scenarios, and in the scheme provided in the embodiment of the present disclosure, the preset condition is not specifically limited.

For example, the current factor is a volatile organic, wherein the volatile organic includes acetaldehyde in addition to formaldehyde. In a specific application scenario, the ratio of the concentration of formaldehyde to the concentration of acetaldehyde is 3:1, and the ratio of the weight of formaldehyde to the weight of acetaldehyde is 4:1, so that the ratio of formaldehyde to acetaldehyde is 12: 1. And if the preset sorting range is that only the first source is selected as the source of the current factor in the current application scene, selecting the current formaldehyde as the only source which contributes to the volatile organic compounds in the preset area. In the subsequent treatment process of the atmospheric pollutant source, a treatment method capable of effectively eliminating formaldehyde pollution is selected.

In another application scenario, in the case that the preset sequencing range is 2 sources, both formaldehyde and acetaldehyde are used as the sources of the current factors. Most conditions of the application scene are the same as those of the previous application scene, and the only difference is that the preset sequencing range in the previous application scene is only used for selecting the only source contributing to the volatile organic compounds, but in the practical scene, formaldehyde and acetaldehyde can be selected. Formaldehyde contributes to volatile organic contamination and acetaldehyde is inferior. Thus, in order to eliminate the environmental pollution caused by the current factors, a treatment method capable of eliminating formaldehyde pollution is selected firstly, and then a treatment method capable of eliminating acetaldehyde pollution is selected.

In a possible implementation manner, after identifying factors in the parsing result according to the historical parsing data and identifying each source in each factor within a preset sorting range, the method further includes the following steps:

responding to a display instruction of a user, and displaying source associated information of each source in each factor within a preset sequencing range;

wherein the source association information comprises at least one of:

the method comprises the following steps of obtaining information of the ratio value of each factor in the total atmospheric pollutants, information of the name of each source corresponding to each factor and in a preset sequencing range, sequencing information of each source corresponding to each factor and in the preset sequencing range, and information of the ratio value of each source corresponding to each factor and in the preset sequencing range.

The above lists only common source association information, and may also introduce other source association relations for different application scenarios, which is not described herein again.

In this step, in response to a presentation instruction of a user, presenting the source association information of the sources within the preset sorting range in each factor includes the following steps:

responding to a display instruction of a user, and displaying the source associated information in a diagnostic spectrogram mode under the condition that the display mode information carried in the display instruction is the source associated information displayed in the diagnostic spectrogram mode; or,

responding to a display instruction of a user, and displaying the source correlation information in a linear regression display mode under the condition that the display mode information carried in the display instruction is the source correlation information displayed in the linear regression display mode; or,

and responding to a display instruction of a user, and displaying the source associated information in a display mode corresponding to the source component spectrum matrix and the source contribution matrix under the condition that the display mode information carried in the display instruction is the source associated information displayed in a display mode corresponding to the source component spectrum matrix and the source contribution matrix.

The above lists only common display modes, and other display modes may also be available, which are not described herein again.

FIG. 2 is a schematic flow chart of a method for resolving a source of atmospheric pollutants in a specific application scenario in an embodiment of the present application; the steps of the analytical method for the source of atmospheric pollutants as shown in fig. 2 are as follows:

the method for analyzing the atmospheric pollutant source shown in fig. 2 includes two steps of automatic parameter adjustment and result display.

The step of automatically adjusting parameters comprises the following substeps, which are specifically described as follows:

acquiring atmospheric pollutant data of a preset area; in this embodiment, the atmospheric pollutant data is volatile organic compound data.

Data auditing is a conventional auditing method, and is not described herein again.

After the volatile organic compound data are acquired, the data are input into the PMF model, and parameters are adjusted before the PMF model runs the scheme. The factors comprise a first factor corresponding to time, a second factor corresponding to the number of factors and a third factor corresponding to the species, and the step of determining the first model according to the factors comprises the following steps:

determining each key parameter and/or a numerical range corresponding to each key parameter in the second model according to the first factor, the second factor and the third factor;

After each parameter is adjusted, the scheme is operated to generate an analysis file at least comprising the analysis result of the atmospheric pollutant source. In addition, the analysis file also comprises a first analysis result used for representing each characteristic value, a second analysis result used for representing each fitting result and a third analysis result used for factor confirmation.

After the analysis results are obtained, the factors are identified from the experience base. According to historical analysis data, identifying factors in analysis results, and identifying each source in each factor within a preset sequencing range comprises the following steps:

determining preset conditions according to historical analysis data;

It should be noted that, in the process of determining each key parameter attribute in the second model through the first model, the corresponding parameter file can be automatically generated, the data file and the uncertainty data file are input, and then the calculation program corresponding to the PMF model of the EPA is called to generate the result file.

The uncertainty data file is a file derived based on data generated by an uncertainty algorithm. The uncertainty algorithms in the embodiments disclosed in the present application are all conventional algorithms, for example, one conventional algorithm is selected below the detection line, and another conventional algorithm is selected above the detection line, so that the data processing process below the detection line can be effectively distinguished from the data processing process above the detection line. The uncertainty algorithm based on the adoption is a conventional algorithm, and is not described in detail herein.

The experience base in fig. 2 includes not only the pollution source types but also data such as local environmental data changes. The reference object is based on the data of the experience base, and the historical identification conditions for identifying the source can be restored, so that the resolution efficiency of the source of the atmospheric pollutants can be further improved. The statistical experimental result shows that the analytic method of the atmospheric pollutant source provided by the application can improve the analytic efficiency by 150% compared with the existing analytic method.

According to the method for analyzing the source of the atmospheric pollutant, the factor identification process adopts a factor identification model constructed by a factor identification algorithm. The construction of the factor recognition model based on the factor recognition algorithm is a conventional model construction method, and is not described herein again.

The factor identification algorithm in the embodiment of the present disclosure is explained as follows:

according to species information (including species frequently used by identification sources, percentage of identification sources in the past same time and the like) in an experience library uploaded by a user, calculating the relevance score of each source in each factor by using a TF-IDF (Term Frequency-Inverse Document Frequency) statistical method in combination with an EPA-PMF result file, and ranking according to the score high, wherein the score is higher, so that the factor is more likely to be the source. For example, if the same source is identified, the one with the highest score is taken as the best match. After the source is identified, the tracer species proportion of the identified source, the identified source and the like are stored in a database. Among them, TF-IDF (Term Frequency-Inverse Document Frequency) is a commonly used weighting technique for information retrieval and data mining. TF is Term Frequency (Term Frequency) and IDF is Inverse text Frequency index (Inverse Document Frequency).

In practical application, different correction factors are often introduced to correct the initial factor recognition algorithm to obtain a corrected factor recognition algorithm when preset areas are different. After the corrected factor identification algorithm is obtained, a corrected factor identification model is constructed based on the corrected factor identification algorithm in a conventional model construction method. Compared with the initial factor identification model, the modified factor identification model is more suitable for the characteristics of the atmospheric pollutants in the current region. The introduced correction factor is a conventional correction factor, and the method for correcting the initial factor identification algorithm by the correction factor is also a conventional method, which is not described herein again.

The step of displaying the result includes the following substeps, which are described in detail below:

responding to a display instruction of a user, and directly displaying the analysis result one by one; or,

responding to a display instruction of a user, and displaying the source associated information in a display mode corresponding to the source component spectrum matrix and the source contribution matrix under the condition that the display mode information carried in the display instruction is the source associated information displayed in a display mode corresponding to the source component spectrum matrix and the source contribution matrix; wherein, the F matrix is a spectrum matrix representing the source components, and the G matrix represents a source contribution matrix.

In the embodiment of the application, the atmospheric pollutant data of a preset area are obtained, and various factors for determining a first model are extracted according to the atmospheric pollutant data; determining a first model according to various factors, wherein the first model is used for determining various key parameter attributes in a second model, and the second model is a preset positive definite matrix factorization model; and operating the second model according to the key parameter attributes determined by the first model, analyzing the atmospheric pollutant data, and generating an analysis file at least comprising the analysis result of the atmospheric pollutant source. The method and the device can determine the key parameter attributes in the second model through the first model; the second model can be operated according to the key parameter attributes determined by the first model, the atmospheric pollutant data are automatically analyzed, and an analysis file at least comprising an atmospheric pollutant source analysis result is generated.

The following are embodiments of the apparatus of the present invention that may be used to perform embodiments of the method of the present invention. For details which are not disclosed in the embodiments of the apparatus of the present invention, reference is made to the embodiments of the method of the present invention.

Referring to fig. 3, a schematic structural diagram of an atmospheric pollutant source analysis device according to an exemplary embodiment of the present invention is shown. The atmospheric pollutant source analysis device can be realized by software, hardware or a combination of the two to form all or part of the terminal. The device for analyzing the atmospheric pollutant source comprises an acquisition and extraction module 10, a determination module 20 and an analysis module 30.

Specifically, the obtaining and extracting module 10 is configured to obtain atmospheric pollutant data of a preset area and extract various factors for determining the first model according to the atmospheric pollutant data;

a determining module 20, configured to determine a first model according to the factors extracted by the obtaining and extracting module 10, where the first model is used to determine key parameter attributes in a second model, and the second model is a preset positive definite matrix factorization model;

and the analysis module 30 is configured to run the second model according to the key parameter attributes determined by the first model determined by the determination module 20, analyze the atmospheric pollutant data, and generate an analysis file at least including an atmospheric pollutant source analysis result.

Optionally, each factor includes a first factor corresponding to time, a second factor corresponding to the number of factors, and a third factor corresponding to the species, and the determining module 20 is specifically configured to:

determining various historical key parameters and/or numerical value ranges corresponding to the various historical key parameters according to historical data;

Optionally, the apparatus further comprises:

and an identification module (not shown in fig. 3) configured to, after the parsing module 30 generates a parsing file including at least the parsing result of the source of the atmospheric pollutant, identify factors in the parsing result according to the historical parsing data, and identify each source in each factor, where the source is within a preset sorting range.

Optionally, the identification module is specifically configured to:

determining preset conditions according to historical analysis data;

Optionally, the apparatus further comprises:

a display module (not shown in fig. 3) configured to, after the identification module identifies the factors in the analysis result according to the historical analysis data and identifies the sources in each factor within the preset sorting range, display, in response to a display instruction of a user, source association information of the sources in each factor within the preset sorting range;

the source correlation information displayed by the display module comprises at least one of the following items:

Optionally, the display module is specifically configured to:

It should be noted that, when the apparatus for analyzing an atmospheric pollutant source provided in the foregoing embodiment executes the method for analyzing an atmospheric pollutant source, only the division of the functional modules is taken as an example, and in practical applications, the functions may be distributed by different functional modules according to needs, that is, the internal structure of the device may be divided into different functional modules to complete all or part of the functions described above. In addition, the atmospheric pollutant source analysis device provided in the above embodiments and the atmospheric pollutant source analysis method embodiment belong to the same concept, and details of implementation processes thereof are referred to as method embodiments, and are not described herein again.

In the embodiment of the application, a determining module determines a first model according to various factors, wherein the first model is used for determining various key parameter attributes in a second model, and the second model is a preset positive definite matrix factorization model; and operating the second model according to the key parameter attributes determined by the first model determined by the determining module, analyzing the atmospheric pollutant data, and generating an analysis file at least comprising the analysis result of the atmospheric pollutant source. The method and the device can determine the key parameter attributes in the second model through the first model; the second model can be operated according to the key parameter attributes determined by the first model, the atmospheric pollutant data are automatically analyzed, and an analysis file at least comprising an atmospheric pollutant source analysis result is generated.

The present invention also provides a computer readable medium having stored thereon program instructions, which when executed by a processor, implement the method for resolving a source of atmospheric pollutants provided by the above-mentioned method embodiments.

The present invention also provides a computer program product containing instructions which, when run on a computer, cause the computer to perform the method for resolving a source of atmospheric pollutants as described in the various method embodiments above.

Please refer to fig. 4, which provides a schematic structural diagram of a terminal according to an embodiment of the present application. As shown in fig. 4, the terminal 1000 can include: at least one processor 1001, at least one network interface 1004, a user interface 1003, memory 1005, at least one communication bus 1002.

Wherein a communication bus 1002 is used to enable connective communication between these components.

The user interface 1003 may include a Display screen (Display) and a Camera (Camera), and the optional user interface 1003 may also include a standard wired interface and a wireless interface.

The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), among others.

Processor 1001 may include one or more processing cores, among other things. The processor 1001 interfaces various components throughout the electronic device 1000 using various interfaces and lines to perform various functions of the electronic device 1000 and to process data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 1005 and invoking data stored in the memory 1005. Alternatively, the processor 1001 may be implemented in at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). The processor 1001 may integrate one or more of a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a modem, and the like. Wherein, the CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for rendering and drawing the content required to be displayed by the display screen; the modem is used to handle wireless communications. It is understood that the modem may not be integrated into the processor 1001, but may be implemented by a single chip.

The Memory 1005 may include a Random Access Memory (RAM) or a Read-Only Memory (Read-Only Memory). Optionally, the memory 1005 includes a non-transitory computer-readable medium. The memory 1005 may be used to store an instruction, a program, code, a set of codes, or a set of instructions. The memory 1005 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the various method embodiments described above, and the like; the storage data area may store data and the like referred to in the above respective method embodiments. The memory 1005 may optionally be at least one memory device located remotely from the processor 1001. As shown in fig. 4, the memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, a user interface module, and an atmospheric pollutant source resolving application program.

In the terminal 1000 shown in fig. 4, the user interface 1003 is mainly used as an interface for providing input for a user, and acquiring data input by the user; and the processor 1001 may be configured to invoke the parsing application of the atmospheric pollutant source stored in the memory 1005, and specifically perform the following operations:

determining a first model according to various factors, wherein the first model is used for determining various key parameter attributes in a second model, and the second model is a preset positive definite matrix factorization model;

and operating the second model according to the key parameter attributes determined by the first model, analyzing the atmospheric pollutant data, and generating an analysis file at least comprising the analysis result of the atmospheric pollutant source.

In one embodiment, the factors include a first factor corresponding to time, a second factor corresponding to a factor number, and a third factor corresponding to a species, and the processor 1001 specifically performs the following operations when determining the first model according to the factors:

determining each key parameter and/or a numerical range corresponding to each key parameter according to the first factor, the second factor and the third factor;

and determining the first model according to each key parameter and/or the numerical range corresponding to each key parameter.

In one embodiment, the processor 1001 further performs the following operations after the generating of the parse file including at least the parsing result of the source of the atmospheric pollutant:

In an embodiment, when the processor 1001 executes the parsing according to the history, identifies factors in the parsing result, and identifies each source in each factor within a preset sorting range, the following operations are specifically executed:

determining preset conditions according to historical analysis data;

In one embodiment, after performing the steps of parsing data according to the history, identifying factors in the parsing result, and identifying the sources in each factor within the preset sorting range, the processor 1001 further performs the following operations:

wherein the source association information comprises at least one of:

In an embodiment, when the processor 1001 executes the presentation instruction in response to the user and presents the source association information of each source in each factor within the preset sorting range, the following operations are specifically performed:

In the embodiment of the application, a first model is determined according to various factors, the first model is used for determining various key parameter attributes in a second model, and the second model is a preset positive definite matrix factorization model; and operating the second model according to the key parameter attributes determined by the first model, analyzing the atmospheric pollutant data, and generating an analysis file at least comprising the analysis result of the atmospheric pollutant source. The method and the device can determine the key parameter attributes in the second model through the first model; the second model can be operated according to the key parameter attributes determined by the first model, the atmospheric pollutant data are automatically analyzed, and an analysis file at least comprising an atmospheric pollutant source analysis result is generated.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a read-only memory or a random access memory.

The above disclosure is only for the purpose of illustrating the preferred embodiments of the present application and is not to be construed as limiting the scope of the present application, so that the present application is not limited thereto, and all equivalent variations and modifications can be made to the present application.

Claims

1. A method for resolving a source of atmospheric pollutants, the method comprising:

2. The method of claim 1, wherein the factors include a first factor corresponding to time, a second factor corresponding to a factor number, and a third factor corresponding to a species, and wherein determining the first model based on the factors includes:

determining various historical key parameters and/or historical numerical value ranges corresponding to the various historical key parameters according to the historical data;

and determining the first model according to the historical key parameters and/or the historical numerical value ranges corresponding to the historical key parameters.

3. The method of claim 1, wherein after the generating a parse file comprising at least the atmospheric pollutant source parse results, the method further comprises:

and according to historical analysis data, identifying factors in the analysis result, and identifying each source in each factor within a preset sequencing range.

4. The method of claim 3, wherein the identifying factors in the parsing result according to historical parsing data, and identifying the sources in each factor within a preset sequencing range comprises:

determining preset conditions according to historical analysis data;

5. The method of claim 4, wherein after identifying factors in the parsing result according to the historical parsing data and identifying respective sources in each factor within a preset ordering range, the method further comprises:

wherein the source association information comprises at least one of:

6. The method of claim 5, wherein presenting, in response to a presentation instruction from a user, the source association information of the respective sources within the preset ordering range in each factor comprises:

responding to a display instruction of a user, and displaying the source associated information in a diagnostic spectrogram mode under the condition that the display mode information carried in the display instruction is used for displaying the source associated information in the diagnostic spectrogram display mode; or,

responding to a display instruction of a user, and displaying the source correlation information in a linear regression display mode under the condition that the display mode information carried in the display instruction is that the source correlation information is displayed in the linear regression display mode; or,

responding to a display instruction of a user, and displaying the source associated information in a display mode corresponding to a source component spectrum matrix and a source contribution matrix under the condition that the display mode information carried in the display instruction is that the source associated information is displayed in a display mode corresponding to the source component spectrum matrix and the source contribution matrix.

7. An apparatus for resolving a source of atmospheric pollutants, the apparatus comprising:

8. The apparatus according to claim 7, wherein the factors include a first factor corresponding to time, a second factor corresponding to a factor number, and a third factor corresponding to a species, and the determining module is specifically configured to:

9. A computer storage medium, characterized in that it stores a plurality of instructions adapted to be loaded by a processor and to carry out the method steps according to any one of claims 1 to 6.

10. A terminal, comprising: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to perform the method steps of any of claims 1 to 6.