CN116739189A - Transmission tracing method and device, storage medium and electronic equipment - Google Patents
Transmission tracing method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN116739189A CN116739189A CN202311015499.9A CN202311015499A CN116739189A CN 116739189 A CN116739189 A CN 116739189A CN 202311015499 A CN202311015499 A CN 202311015499A CN 116739189 A CN116739189 A CN 116739189A
- Authority
- CN
- China
- Prior art keywords
- transmission
- site
- data
- model
- 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.)
- Pending
Links
- 230000005540 biological transmission Effects 0.000 title claims abstract description 423
- 238000000034 method Methods 0.000 title claims abstract description 76
- 238000000547 structure data Methods 0.000 claims abstract description 27
- 238000004364 calculation method Methods 0.000 claims abstract description 24
- 238000012549 training Methods 0.000 claims description 41
- 238000012545 processing Methods 0.000 claims description 36
- 230000000903 blocking effect Effects 0.000 claims description 22
- 239000003344 environmental pollutant Substances 0.000 claims description 22
- 231100000719 pollutant Toxicity 0.000 claims description 22
- 238000005457 optimization Methods 0.000 claims description 12
- 230000002238 attenuated effect Effects 0.000 claims description 2
- 238000004590 computer program Methods 0.000 description 14
- 230000006870 function Effects 0.000 description 14
- 238000004891 communication Methods 0.000 description 10
- 239000000356 contaminant Substances 0.000 description 10
- 238000009792 diffusion process Methods 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 5
- 239000003570 air Substances 0.000 description 4
- 238000003915 air pollution Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000004088 simulation Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 230000002265 prevention Effects 0.000 description 3
- CBENFWSGALASAD-UHFFFAOYSA-N Ozone Chemical compound [O-][O+]=O CBENFWSGALASAD-UHFFFAOYSA-N 0.000 description 2
- RAHZWNYVWXNFOC-UHFFFAOYSA-N Sulphur dioxide Chemical compound O=S=O RAHZWNYVWXNFOC-UHFFFAOYSA-N 0.000 description 2
- 230000004913 activation Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000011109 contamination Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 239000013618 particulate matter Substances 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- MGWGWNFMUOTEHG-UHFFFAOYSA-N 4-(3,5-dimethylphenyl)-1,3-thiazol-2-amine Chemical compound CC1=CC(C)=CC(C=2N=C(N)SC=2)=C1 MGWGWNFMUOTEHG-UHFFFAOYSA-N 0.000 description 1
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 description 1
- 239000012080 ambient air Substances 0.000 description 1
- 229910002091 carbon monoxide Inorganic materials 0.000 description 1
- 230000010267 cellular communication Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000001311 chemical methods and process Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000013016 damping Methods 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- JCXJVPUVTGWSNB-UHFFFAOYSA-N nitrogen dioxide Inorganic materials O=[N]=O JCXJVPUVTGWSNB-UHFFFAOYSA-N 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000004062 sedimentation Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/907—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/909—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/042—Knowledge-based neural networks; Logical representations of neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/20—Identification of molecular entities, parts thereof or of chemical compositions
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/90—Programming languages; Computing architectures; Database systems; Data warehousing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Crystallography & Structural Chemistry (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Mathematical Physics (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Chemical & Material Sciences (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Medical Informatics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Entrepreneurship & Innovation (AREA)
- Library & Information Science (AREA)
- Remote Sensing (AREA)
- Operations Research (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Educational Administration (AREA)
Abstract
The invention provides a transmission tracing method, a transmission tracing device, a storage medium and electronic equipment, wherein the transmission tracing method comprises the following steps: based on the acquired site meteorological data of each site, respectively calculating transmission weight factors of corresponding sides of any two sites with transmission relations; constructing graph structure data based on the acquired site pollution data of each site and the transmission weight factors of each side, and calling a graph transmission model to carry out transmission calculation on the graph structure data to obtain the predicted pollution transmission concentration corresponding to each side; calculating a model loss value of the graph transmission model according to the predicted pollution transmission concentration corresponding to each side, optimizing model parameters in the graph transmission model according to the direction of reducing the model loss value, and constructing a target graph transmission model for predicting the transmission concentration, wherein the target graph transmission model realizes transmission tracing through predicting the transmission concentration. The embodiment of the invention can conveniently predict the transmission concentration between stations through the target graph transmission model and improve the service efficiency.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a transmission tracing method, a transmission tracing device, a storage medium, and an electronic device.
Background
At present, pollution tracing is an important premise of scientific prevention and control of atmospheric pollution, and the atmospheric pollution tracing can be roughly divided into macroscopic tracing and microscopic tracing; the macroscopic tracing refers to pollution transmission analysis between cities with large scale and large scale (hundred kilometers), and the microscopic tracing refers to pollution transmission analysis with medium scale and small scale (hundred meters), so that the pollution sources or the transportation conditions around the sites can be known. It should be noted that the spatial scale of the air pollution tracing is generally tens of kilometers to hundreds of kilometers, and the time scale is hours, days, months or years, so that the method is suitable for pollution tracing, prevention and control in larger scale and longer time period. With the promotion of the atmospheric pollution control process, local fine control of sites, such as differential control for pollution tracing of thousands of meters and hundreds of meters, has become a new trend and requirement; wherein, in the range of thousands of meters and hundreds of meters, the pollution diffusion time is about several minutes to tens of minutes.
In the prior art, the pollution tracing of the air pollution prevention and control field is mainly obtained by means of numerical mode simulation calculation, for example, the space-time distribution of emission sources and contribution rates is traced back through a dynamic mode, a specific emission source can be traced back by combining an emission source component analysis result and an emission source list, and synchronous tracing of a forecast result is realized; the source model method quantitatively describes the physical and chemical processes of atmospheric pollutants from a source to a receptor by using different scale numerical mode methods, and quantitatively estimates the contribution of different regions and different types of pollutant source emissions to pollutants in the ambient air. Currently, the air pollution tracing technology mainly comprises air quality models CMAQ, CMAX and CAMx-PSAT, and particulate matter pollution accurate tracing HYSPLIT (Hybrid Single-Particle Lagrangian Integrated Trajectory, a model for calculating air mass motion trail and simulating complex diffusion and sedimentation), large vortex simulation calculation and the like. Most models can only trace the pollution of large-scale areas, and a meteorological model WRF (the weather research and forecasting model, weather forecast mode) and an emission source model are required to support. Although the prior art can simulate the real air pollution transmission process, the problems of high operation difficulty, large calculation amount, long operation time, higher requirement on hardware resources, generally complex operation in business application and the like exist. Based on this, how to construct a target graph transmission model to predict the transmission concentration between sites conveniently by the target graph transmission model and to improve the business efficiency becomes a research hotspot.
Disclosure of Invention
In view of the above, the embodiments of the present invention provide a transmission tracing method, apparatus, storage medium, and electronic device, so as to solve the problems of large operation difficulty, large calculation amount, long calculation time, high requirement on hardware resources, and generally complicated operation in service application; correspondingly, the embodiment of the invention can construct the target graph transmission model so as to conveniently predict the transmission concentration between stations through the target graph transmission model, thereby realizing convenient transmission tracing and improving the service efficiency.
According to an aspect of the present invention, there is provided a transmission tracing method, the method including:
acquiring site pollution data and site weather data of each site in a plurality of sites, wherein one site pollution data comprises target pollutant concentration of the corresponding site, and one site weather data comprises at least one weather data of the corresponding site;
based on the site meteorological data of each site, respectively calculating transmission weight factors of corresponding sides of any two sites with transmission relations, wherein the two sites with the transmission relations support the transmission of pollutants among the corresponding sites;
constructing graph structure data based on site pollution data of each site and transmission weight factors of each side, and calling a graph transmission model to carry out transmission calculation on the graph structure data to obtain predicted pollution transmission concentration corresponding to each side;
Calculating a model loss value of the graph transmission model according to the predicted pollution transmission concentration corresponding to each side, and optimizing model parameters in the graph transmission model according to the direction of reducing the model loss value so as to construct a target graph transmission model for predicting the transmission concentration, wherein the target graph transmission model realizes transmission tracing through predicting the transmission concentration.
According to another aspect of the present invention, there is provided a transmission tracing apparatus, the apparatus comprising:
an acquisition unit configured to acquire site pollution data and site weather data of each of a plurality of sites, one site pollution data including a target pollutant concentration of the corresponding site, and one site weather data including at least one weather data of the corresponding site;
the processing unit is used for respectively calculating transmission weight factors of corresponding sides of any two stations with transmission relations based on the station meteorological data of each station, and the two stations with the transmission relations support the pollutant to be transmitted between the corresponding stations;
the processing unit is further used for constructing graph structure data based on the site pollution data of each site and the transmission weight factors of each side, and calling a graph transmission model to carry out transmission calculation on the graph structure data to obtain the predicted pollution transmission concentration corresponding to each side;
The processing unit is further configured to calculate a model loss value of the graph transmission model according to the predicted pollution transmission concentration corresponding to each side, and optimize model parameters in the graph transmission model according to a direction of reducing the model loss value, so as to construct a target graph transmission model for predicting the transmission concentration, where the target graph transmission model realizes transmission tracing by predicting the transmission concentration.
According to another aspect of the invention there is provided an electronic device comprising a processor, and a memory storing a program, wherein the program comprises instructions which, when executed by the processor, cause the processor to perform the above mentioned method.
According to another aspect of the present invention there is provided a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the above mentioned method.
According to the method and the device for predicting the pollution transmission concentration, after the site pollution data and the site meteorological data of each site in the multiple sites are obtained, the transmission weight factors of the corresponding sides of any two sites with transmission relations are calculated respectively based on the site meteorological data of each site, so that the pollution transmission concentration can be predicted conveniently through the transmission weight factors, and the two sites with the transmission relations support the pollutant to be transmitted between the corresponding sites. Then, based on the site pollution data of each site and the transmission weight factors of each side, the graph structure data can be constructed, and the graph transmission model is called to carry out transmission calculation on the graph structure data, so that the predicted pollution transmission concentration corresponding to each side is obtained. Correspondingly, the model loss value of the graph transmission model can be calculated according to the predicted pollution transmission concentration corresponding to each side, and model parameters in the graph transmission model are optimized according to the direction of reducing the model loss value so as to construct a target graph transmission model for predicting the transmission concentration, and the target graph transmission model can realize transmission tracing through predicting the transmission concentration, so that the transmission concentration among stations is predicted conveniently through the target graph transmission model, the transmission tracing is realized conveniently, and the service efficiency is improved.
Drawings
Further details, features and advantages of the invention are disclosed in the following description of exemplary embodiments with reference to the following drawings, in which:
FIG. 1 shows a flow diagram of a transmission tracing method according to an exemplary embodiment of the invention;
FIG. 2 illustrates a schematic diagram of a contaminant transfer in accordance with an exemplary embodiment of the present invention;
FIG. 3 illustrates a flow diagram of another transmission tracing method according to an exemplary embodiment of the invention;
fig. 4 is a diagram showing calculation of a transmission weight factor according to an exemplary embodiment of the present invention;
fig. 5 shows a schematic block diagram of a transmission tracing device according to an exemplary embodiment of the invention;
fig. 6 shows a block diagram of an exemplary electronic device that can be used to implement an embodiment of the invention.
Detailed Description
Embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While the invention is susceptible of embodiment in the drawings, it is to be understood that the invention may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided to provide a more thorough and complete understanding of the invention. It should be understood that the drawings and embodiments of the invention are for illustration purposes only and are not intended to limit the scope of the present invention.
It should be understood that the various steps recited in the method embodiments of the present invention may be performed in a different order and/or performed in parallel. Furthermore, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the invention is not limited in this respect.
The term "including" and variations thereof as used herein are intended to be open-ended, i.e., including, but not limited to. The term "based on" is based at least in part on. The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments. Related definitions of other terms will be given in the description below. It should be noted that the terms "first," "second," and the like herein are merely used for distinguishing between different devices, modules, or units and not for limiting the order or interdependence of the functions performed by such devices, modules, or units.
It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those skilled in the art will appreciate that "one or more" is intended to be construed as "one or more" unless the context clearly indicates otherwise.
The names of messages or information interacted between the devices in the embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of such messages or information.
It should be noted that, the execution body of the transmission tracing method provided by the embodiment of the present invention may be one or more electronic devices, which is not limited in the present invention; the electronic device may be a terminal (i.e. a client) or a server, and when the execution body includes a plurality of electronic devices and the plurality of electronic devices include at least one terminal and at least one server, the transmission tracing method provided by the embodiment of the present invention may be executed jointly by the terminal and the server. Accordingly, the terminals referred to herein may include, but are not limited to: smart phones, tablet computers, notebook computers, desktop computers, smart watches, smart voice interaction devices, smart appliances, vehicle terminals, aircraft, and so on. The server mentioned herein may be an independent physical server, or may be a server cluster or a distributed system formed by a plurality of physical servers, or may be a cloud server that provides cloud services, cloud databases, cloud computing (cloud computing), cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network ), and basic cloud computing services such as big data and artificial intelligence platforms, and so on.
Based on the above description, the embodiments of the present invention propose a transmission tracing method, which may be executed by the above-mentioned electronic device (terminal or server); alternatively, the transmission tracing method may be performed by the terminal and the server together. For convenience of explanation, the following description will take the electronic device to execute the transmission tracing method as an example; as shown in fig. 1, the transmission tracing method may include the following steps S101-S104:
s101, site pollution data and site weather data of each site in a plurality of sites are acquired, wherein one site pollution data comprises target pollutant concentration of the corresponding site, and one site weather data comprises at least one weather data of the corresponding site.
Where target contaminant concentration refers to a concentration value of a target contaminant, and target contaminants include, but are not limited to: sulfur dioxide, carbon monoxide, and nitrogen dioxide, and the like; the invention is not limited in this regard. Accordingly, the at least one meteorological data includes, but is not limited to: wind direction, wind speed, temperature, pressure, humidity, atmospheric boundary layer height, solar radiation, and the like; the invention is not limited in this regard. Alternatively, when a site is available for data monitoring, the site may also be referred to as a monitoring site.
In the embodiment of the present invention, the acquisition modes of the site pollution data and the site meteorological data of each site may include, but are not limited to, the following several types:
the first acquisition mode is as follows: the electronic equipment can acquire the download links of the site pollution data and the site weather data of each site and download the site pollution data and the site weather data based on the download links according to the download links, so that the site pollution data and the site weather data downloaded based on the download links are used as the site pollution data and the site weather data of each site.
In the second acquisition mode, the electronic device stores site pollution data and site weather data of each site in at least one training data, so that the electronic device can select one training data from the at least one training data, and uses the site pollution data and the site weather data of each site in the selected training data as the acquired site pollution data and site weather data of each site.
The third acquisition mode is as follows: the electronic device may have a data acquisition component that may be used to acquire data from the storage device of each site, the electronic device may then obtain site pollution data and site weather data for each site from the storage device of each site via the data acquisition component, and so on.
S102, based on site meteorological data of each site, calculating transmission weight factors of corresponding sides of any two sites with transmission relations, wherein the two sites with the transmission relations support pollutants to be transmitted between the corresponding sites.
For example, assuming that the plurality of stations includes a station a, a station B, and a station C, and that there is a transmission relationship between the station a and the station B, and that there is a transmission relationship between the station a and the station C, and that there is no transmission relationship between the station B and the station C, the electronic device may calculate the transmission weight factors of the sides corresponding to the station a and the station B, and calculate the transmission weight factors of the sides corresponding to the station a and the station C.
S103, constructing graph structure data based on site pollution data of each site and transmission weight factors of each side, and calling a graph transmission model to carry out transmission calculation on the graph structure data to obtain predicted pollution transmission concentration corresponding to each side.
Wherein each edge (edge) is a directed edge, and any two corresponding edges of the stations with a transmission relationship may include at least one directed edge. For example, as shown in fig. 2, taking a site a and a site B as an example, the site a and the site B are two sites having a transmission relationship, and the corresponding edges of the site a and the site B may include two directed edges; in this case, for the site a, one of the directed edges of the sites a and B is the input edge of the site a (i.e., the directed edge indicated by the solid arrow between the sites a and B), the start point of the input edge is the site B, and the end point of the input edge is the site a; correspondingly, the other directed edge of the corresponding edges of the site a and the site B is the output edge of the site a (i.e., the directed edge indicated by the dotted arrow between the site a and the site B), the starting point of the output edge is the site a, and the end point of the output edge is the site B.
It should be noted that, the map structure data may include, but is not limited to, site data and edge data, and the site data includes, but is not limited to, site pollution data of each site, target weather data of each site, and the like, which is not limited in the present invention; wherein the target meteorological data for a site includes, but is not limited to: the temperature, pressure, humidity, atmospheric boundary layer height, solar radiation, etc. in the site meteorological data of the corresponding site are not limited in this regard. Accordingly, the above-mentioned edge data may include, but is not limited to, transmission weight factors of respective edges, and the edge data may be stored in the form of an adjacency matrix, may be stored in the form of an adjacency list, or the like; the invention is not limited in this regard.
S104, calculating a model loss value of the graph transmission model according to the predicted pollution transmission concentration corresponding to each side, optimizing model parameters in the graph transmission model according to the direction of reducing the model loss value, and constructing a target graph transmission model for predicting the transmission concentration, wherein the target graph transmission model realizes transmission tracing through predicting the transmission concentration.
Wherein the graph transmission model may refer to GNN (Graph Neutral Network, graph neural network), GCN (Graph Convolutional Network, graph convolution neural network), GAN (Graph Attention Network, graph intent network), and the like; the invention is not limited in this regard. It should be understood that the deep learning technology is more widely applied in the field of atmospheric environment, and further, the graph neural network technology in the deep learning technology can fully consider the association and the connection between nodes (i.e. sites), namely, the corresponding sides of any two sites with transmission relations can be better applied to the scenes of atmospheric pollution transmission, tracing and the like; the calculation of the graph transmission model mainly comprises a transmission part and an output part, wherein the transmission part is mainly used for combining neighbor nodes (namely stations with transmission relations) and side information (namely the station data and the side data) to obtain the state of the current node, and the output part can convert the characteristics and the state of the node into output vectors. It should be understood that the embodiment of the present invention may combine the directionality of the edges in the graph transmission model with the calculation of the pollution transmission concentration, so as to implement the calculation of the pollution transmission concentration between sites (such as cities), where the pollution transmission concentration may also be referred to as a pollution transmission amount, a pollution net transmission amount, or a pollution transmission contribution, etc.
It should be noted that the tag value (i.e., the true value) corresponding to each edge may be derived from the calculation result of the reference value pattern, and the tag value may be referred to as the reference contamination transmission concentration. Based on the above, when calculating the model loss value of the graph transmission model according to the predicted pollution transmission concentration corresponding to each side, the electronic device may call the reference numerical model, and calculate the reference pollution transmission concentration corresponding to each side based on the site pollution data and the site meteorological data of each site; and calculating a model loss value of the graph transmission model by adopting the difference value between the predicted pollution transmission concentration corresponding to each side and the reference pollution transmission concentration corresponding to the corresponding side.
In the embodiment of the invention, the electronic device may calculate root mean square error (rmsaloss) of the predicted pollution transmission concentration corresponding to each side and the reference pollution transmission concentration corresponding to the corresponding side by adopting formula 1.1, so as to obtain a model loss value of the graph transmission model:
1.1
Wherein,,L rmse for the model loss value, m is the number of edges, i is the ith edge of the m edges,y pred,i for the predicted contaminant transport concentration corresponding to the ith edge,y true,i the concentration is transmitted for the reference contamination corresponding to the ith side. Alternatively, the embodiment of the invention can also adopt the predicted pollution transmission concentration corresponding to each side, calculate the average absolute error with the difference value between the reference pollution transmission concentration corresponding to the corresponding side, so as to obtain the model loss value of the graph transmission model, and the like; the invention is not limited in this regard.
It should be noted that the large scale pollution tracing technology includes, but is not limited to: pollution source tracing techniques (e.g., PSAT (particulate source apportionment technology, particulate matter source identification technique), OSAT (ozone source apportionment technology, ozone source identification technique), etc.), air mass trajectory models, etc., small scale tracing techniques include, but are not limited to: small scale gaussian diffusion models (e.g., ADMS (Atmospheric Dispersion Modeling System, an atmospheric diffusion model), calpff (a gaussian mass diffusion model), etc.), lagrangian diffusion models, etc. Based on this, the reference numerical model may include, but is not limited to: pollution source tracing techniques, air mass trajectory models, gaussian diffusion models, lagrangian diffusion models, and the like; the invention is not limited in this regard.
For example, as shown in FIG. 2, at time T, the target contaminant concentration at site A may depend on the target contaminant concentration at site A at time T-1 and the sum of the contaminant transmission concentrations between site B, C, D and site A, where the target contaminant concentration at site A at time T-1 may be monitored by site A at time T-1 or by satellite telemetry at time T-1, and so on, and T is a positive integer. In the model optimization process (i.e., training process), a reference numerical model may be used to calculate reference pollution transmission concentrations (which may be used as tag values in the training process) between the station B, C, D and the station a, respectively, and obtain station pollution data and station weather data of each station corresponding to the time T-1, so as to form training data. In the prediction process, when the target pollutant concentration of each station at the time T is predicted, station pollution data and station meteorological data of each station corresponding to the time T-1 can be input into a target graph transmission model, so that the predicted pollutant transmission concentration between each station at the time T, namely the net transmission quantity of each station around the station, is calculated.
It should be noted that, when site pollution data and site weather data corresponding to a first time (e.g., T-1 time) are adopted (i.e., site pollution data and site weather data of each site corresponding to the first time), and predicted pollution transmission concentration between each site at a second time (e.g., T time) is calculated, the site weather data corresponding to the first time may be: the site weather data of each site at the second moment can also be: site weather data of each site at a first time, and so on; the invention is not limited in this regard.
It is understood that the pollution tracing fine quantitative analysis area contribution, industry contribution and key enterprise contribution can visually check the pollutant diffusion range, the influence area and the pollution diffusion track, and identify key areas and key enterprises, so that an emergency plan and a response mechanism under the extreme pollution weather condition are established for a management department for scientific pollution control, reference suggestions are provided for timely taking control measures, and technical support can be provided for joint defense joint control for coping with polluted weather and regional atmosphere pollution.
According to the method and the device for predicting the pollution transmission concentration, after the site pollution data and the site meteorological data of each site in the multiple sites are obtained, the transmission weight factors of the corresponding sides of any two sites with transmission relations are calculated respectively based on the site meteorological data of each site, so that the pollution transmission concentration can be predicted conveniently through the transmission weight factors, and the two sites with the transmission relations support the pollutant to be transmitted between the corresponding sites. Then, based on the site pollution data of each site and the transmission weight factors of each side, the graph structure data can be constructed, and the graph transmission model is called to carry out transmission calculation on the graph structure data, so that the predicted pollution transmission concentration corresponding to each side is obtained. Correspondingly, the model loss value of the graph transmission model can be calculated according to the predicted pollution transmission concentration corresponding to each side, and model parameters in the graph transmission model are optimized according to the direction of reducing the model loss value so as to construct a target graph transmission model for predicting the transmission concentration, and the target graph transmission model can realize transmission tracing through predicting the transmission concentration, so that the transmission concentration among stations is predicted conveniently through the target graph transmission model, the transmission tracing is realized conveniently, and the service efficiency is improved.
Based on the above description, the embodiment of the invention also provides a more specific transmission tracing method. Accordingly, the transmission tracing method may be performed by the above-mentioned electronic device (terminal or server); alternatively, the transmission tracing method may be performed by the terminal and the server together. For convenience of explanation, the following description will take the electronic device to execute the transmission tracing method as an example; referring to fig. 3, the transmission tracing method may include the following steps S301 to S305:
s301, site pollution data and site weather data of each site in a plurality of sites are acquired, wherein one site pollution data comprises target pollutant concentration of the corresponding site, and one site weather data comprises at least one weather data of the corresponding site.
It should be noted that the multiple sites may be all the built monitoring sites, may be part of the built monitoring sites, may also be any set sites (in this case, the multiple sites may include sites that do not support data monitoring), and so on; the invention is not limited in this regard.
S302, obtaining topographic data corresponding to each site, wherein the topographic data comprises site distances between any two sites in the plurality of sites.
The site distance between two sites may refer to a geographic distance (i.e., a geodesic distance) between two sites, or may refer to a euclidean distance between two sites, and so on; the invention is not limited in this regard. It should be noted that, since the geographic distance can better describe the actual interval between two sites, the geographic distance may be preferred as the site distance according to the embodiments of the present invention.
In the embodiment of the invention, the electronic equipment can determine the adjacent data corresponding to each site based on the topographic data, wherein the adjacent data is used for indicating the transmission relation of any two sites in the multiple sites; then, any two stations with transmission relations can be respectively determined from the plurality of stations according to the adjacent data. The transmission relationship may also be referred to as association or transmission possibility, that is, having a transmission relationship between two stations may refer to: the two stations have an association, and the two stations have no transmission relationship (i.e., no transmission relationship) may refer to: there is no association between the two sites. The adjacent data may be an adjacent matrix, an adjacent list, or the like, and the present invention is not limited thereto. The embodiment of the invention can fully consider the adjacent relation among the stations to reflect the transmission relation among the stations, so that the pollution transmission concentration among the stations can be better calculated based on the graph transmission model.
It should be appreciated that whether there is a transmission relationship between stations may depend on the station distance between stations, may depend on blocking information between stations, may depend on the station distance between stations and blocking information, and so on; the invention is not limited in this regard. The blocking information may also be referred to as mountain blocking effect or elevation data. Alternatively, the transmission relationship between stations may be non-directional, i.e. two stations with transmission relationship may transmit contaminants to each other, where any two stations with transmission relationship include two directed edges. Accordingly, the terrain data may also include blocking information between any two of the plurality of sites.
Specifically, for a third site and a fourth site in the multiple sites, if the site distance between the third site and the fourth site is smaller than the preset site distance, the electronic device may determine that a transmission relationship exists between the third site and the fourth site, and add a transmission identifier with the transmission relationship between the third site and the fourth site in the adjacent data; or if the blocking information between the third station and the fourth station is smaller than the preset blocking information, the electronic device can determine that the third station and the fourth station have a transmission relationship, and add a transmission identifier with the transmission relationship between the third station and the fourth station in the adjacent data; or if the site distance between the third site and the fourth site is smaller than the preset site distance and the blocking information between the third site and the fourth site is smaller than the preset blocking information, the electronic device may determine that the third site and the fourth site have a transmission relationship, and add a transmission identifier having a transmission relationship between the third site and the fourth site in the adjacent data.
The preset site distance may be 300 km or 500 km, which is not limited in the present invention. Correspondingly, the blocking information between two stations refers to mountain height information between two stations, and if mountain height information between two stations is greater than or equal to preset blocking information, the two stations do not have a transmission relationship; alternatively, the preset blocking information may be 1000 meters, or 1100 meters, which is not limited in the present invention.
In the embodiment of the invention, the transmission identifier can be a digital identifier (such as 1, etc.), or an alphabetical identifier (such as a, etc.), etc.; the invention is not limited in this regard. Correspondingly, when the third station and the fourth station do not have a transmission relation, the electronic device can add a no-transmission identifier which does not have a transmission relation between the third station and the fourth station in the adjacent data; the no-transmission identifier may be a numerical identifier (e.g. 0, etc.), or may be an alphabetical identifier (e.g. b, etc.), which is not limited in the present invention.
S303, based on site meteorological data and topographic data of each site, calculating transmission weight factors of corresponding sides of any two sites with transmission relations respectively.
Specifically, the site meteorological data of a site may include wind speed and wind direction of the corresponding site, two site corresponding sides having a transmission relationship include at least one directed side, and the transmission weight factors of the two site corresponding sides having a transmission relationship include: and a transmission weight factor corresponding to each of the at least one directed edge.
Based on the above, for a first directed edge related to the corresponding edge of the first site and the second site in the multiple sites, the electronic device may determine a direction of the first directed edge, where a starting point (i.e., a source node) of the first directed edge is the first site, an end point (i.e., a sink node) of the first directed edge is the second site, and a transmission relationship exists between the first site and the second site; and calculating angle information between the wind direction of the first site and the direction of the first directed edge by using a difference value between the direction of the first directed edge and the wind direction of the first site. The electronic device may then calculate a transmission weight factor for the first directed edge based on the angle information, the wind speed of the first site, and the site distance between the first site and the second site, the site distance between the first site and the second site being determined from the terrain data. It should be appreciated that the first directed edge is the output edge of the first station and is the input edge of the second station; wherein, first website and second website are: any two stations of the plurality of stations have a transmission relationship.
Specifically, the electronic device may calculate the transmission weight factor of the first directed edge according to equation 1.2:
1.2
Where v is the wind speed (i.e., wind speed value) of the source node (i.e., first site), d is the site distance between the first site and the second site,αis the angle information between the wind direction of the first station and the direction of the first directed edge, andα=|γ-β|,γin the direction of the first directed edge,βis the wind direction of the first site. Accordingly, the ReLU function is an activation function to take into account the effect of unidirectional transmissions from a first site to a second site. Alternatively, the activation function in calculating the transmission weight factor may be a Sigmoid function, etc., which is not limited in the present invention.
Exemplary, as shown in FIG. 4, assuming that the first site is site A and the second site is site B, the first directed edge is the edge of site A pointing to site B, the direction of the first directed edgeγFor angle value b, the wind direction of the first stationβIs the angle value a, in this case,angle information between the wind direction of the first station and the direction of the first directed edgeαIs the angle value c.
S304, constructing graph structure data based on site pollution data of each site and transmission weight factors of each side, and calling a graph transmission model to carry out transmission calculation on the graph structure data to obtain predicted pollution transmission concentration corresponding to each side.
It should be understood that the process of using the transmission weight factors of the respective sides to construct the graph structure data refers to: the process of integrating the transmission effect between each site into the graph structure refers to adding the attribute (i.e. the transmission weight factor) of each edge in the graph to the graph structure data. Wherein the set of edges may include each edge between stations having a transmission relationship among the plurality of stations.
By way of example, assume that the plurality of stations includes station a, station B, and station C, with a transmission relationship between station a and station B, with a transmission relationship between station a and station C, and with no transmission relationship between station B and station C; assuming that the corresponding sides of the sites a and B include the sides 1 and 2, and the corresponding sides of the sites a and C include the sides 3 and 4, the sides are the sides 1, 2, 3 and 4, respectively, and the side set formed by the sides includes the sides 1, 2, 3 and 4.
S305, calculating a model loss value of the graph transmission model according to the predicted pollution transmission concentration corresponding to each side, optimizing model parameters in the graph transmission model according to the direction of reducing the model loss value, and constructing a target graph transmission model for predicting the transmission concentration, wherein the target graph transmission model realizes transmission tracing through predicting the transmission concentration.
In the embodiment of the invention, the site pollution data and the site weather data of each site in the plurality of sites are obtained from a training data set, and one training data comprises the site pollution data and the site weather data of each site required by one-time model optimization. It should be noted that, the site pollution data of any site may be monitored by any site, may be monitored by a satellite remote sensing technology, may be generated by a mode simulation, etc., which is not limited in the present invention; accordingly, site weather data for any site may be monitored by the any site, may be obtained through FNL (Final Operational Global Analysis, a global re-analysis data), may be generated through a model simulation, and the like, which is not limited in this regard.
Based on this, the electronic device may acquire a training data set and traverse each training data in the training data set, such that site pollution data and site weather data for each site are acquired from the currently traversed training data; after each training data in the training data set is traversed, N times of optimization of model parameters in the graph transmission model are completed, wherein N is the number of training data in the training data set. Further, the electronic device may iterate the above steps, and if the iteration number reaches the preset iteration period, perform attenuation processing on the model parameters in the graph transmission model under the current system time, to obtain the graph transmission model after the attenuation processing; and continuing to perform model optimization on the graph transmission model after the attenuation treatment until convergence conditions are reached. It should be understood that the graph transmission model when the convergence condition is reached is the target graph transmission model; the reaching of the convergence condition may refer to that the iteration number reaches the preset iteration number, or may refer to that the model loss value is smaller than a preset threshold value, which is not limited by the present invention. Correspondingly, the preset iteration times can be 1000 times or 500 times, and the invention is not limited to the above; the preset threshold may be 0.01, 0.001, etc., which is not limited in the present invention.
Alternatively, the training data set may include at least one of the historical data sets, one of the historical data including, but not limited to: site pollution data and site meteorological data of each site at a historical moment, reference pollution transmission concentration corresponding to each side and the like, and the invention is not limited to the above; a historical time is a time prior to the current system time, and when site pollution data and site weather data of a site are monitored data, a historical time is a monitored time prior to the current system time. It should be noted that the history data set may include the history data at each history time in the past 5 years, and may also include the history data at each history time in the past 3 years, which is not limited in the present invention. Optionally, the historical data set may include a training data set and a test data set, and the electronic device may test the finally obtained target graph transmission model by using the test data set to obtain the test accuracy of the target graph transmission model.
Note that the preset iteration period may be 50, 60, or the like, which is not limited to the present invention. Correspondingly, when the iteration times reach a preset iteration period, the electronic equipment can carry out attenuation processing on model parameters in the graph transmission model under the current system time, and can effectively avoid the graph transmission model from reaching local convergence. For example, assuming that the preset iteration period is 50, the electronic device may perform attenuation processing when the iteration number reaches 50; when the iteration number reaches 100, the electronic equipment can carry out attenuation treatment; and, when the number of iterations reaches 150, the electronic device may perform decay processing, and so on. Optionally, when the electronic device performs attenuation processing, the electronic device may perform attenuation processing on model parameters in the graph transmission model under the current system time according to a preset attenuation weight; the preset damping weight may be 0.0005 or 0.006, which is not limited in the present invention.
In the embodiment of the present invention, the learning rate in the model optimization process may be initially 0.0001, or may be initially 0.001, which is not limited in the present invention. Correspondingly, the electronic equipment can optimize the model parameters in the graph transmission model by adopting an Adam method (Adaptive momentum, a self-adaptive momentum random optimization method), can also optimize the model parameters in the graph transmission model by adopting an adaGrad (an adaptive gradient algorithm), and the like; the invention is not limited in this regard.
After the target graph transmission model is obtained, the electronic equipment can acquire actual data (including real-time site pollution data and site meteorological data) of each site, and dynamically update a calculation result by adopting the actual data to obtain updated predicted pollution transmission concentration, so that real-time update of transmission tracing is realized; it should be appreciated that the dynamic update of the reference numerical model based on the emissions source list is slow and difficult, and the embodiments of the present invention may facilitate the dynamic update of the calculation results.
According to the embodiment of the invention, after the site pollution data and the site weather data of each site in the multiple sites are obtained and the topographic data corresponding to each site is obtained, the transmission weight factors of the corresponding sides of any two sites with transmission relations are calculated respectively based on the site weather data and the topographic data of each site; and then, constructing graph structure data based on site pollution data of each site and transmission weight factors of each side, and calling a graph transmission model to carry out transmission calculation on the graph structure data to obtain predicted pollution transmission concentration corresponding to each side. Furthermore, according to the predicted pollution transmission concentration corresponding to each side, a model loss value of the graph transmission model can be calculated, and model parameters in the graph transmission model are optimized according to the direction of reducing the model loss value, so that a target graph transmission model for predicting the transmission concentration is constructed, and the target graph transmission model realizes transmission tracing through predicting the transmission concentration. Therefore, the embodiment of the invention can combine the deep learning technology and integrate the atmospheric environmental domain knowledge into the graph transmission model for training, thereby training a set of multi-node and multi-relevance graph structure to quantify the pollution transmission concentration between stations (such as cities), thereby efficiently calculating the pollution transmission concentration, realizing convenient transmission tracing and improving the service efficiency.
Based on the description of the related embodiments of the transmission tracing method, the embodiments of the present invention further provide a transmission tracing device, where the transmission tracing device may be a computer program (including program code) running in an electronic device; as shown in fig. 5, the transmission tracing apparatus may include an acquisition unit 501 and a processing unit 502. The transmission tracing device may execute the transmission tracing method shown in fig. 1 or fig. 3, that is, the transmission tracing device may operate the above units:
an acquiring unit 501, configured to acquire site pollution data and site weather data of each site of a plurality of sites, where one site pollution data includes a target pollutant concentration of the corresponding site, and one site weather data includes at least one weather data of the corresponding site;
the processing unit 502 is configured to calculate, based on site meteorological data of each site, transmission weight factors of corresponding sides of any two sites with transmission relationships, where the two sites with transmission relationships support transmission of pollutants between the corresponding sites;
the processing unit 502 is further configured to construct graph structure data based on site pollution data of each site and transmission weight factors of each side, and call a graph transmission model to perform transmission calculation on the graph structure data, so as to obtain predicted pollution transmission concentrations corresponding to each side;
The processing unit 502 is further configured to calculate a model loss value of the graph transmission model according to the predicted pollution transmission concentration corresponding to each edge, and optimize model parameters in the graph transmission model according to a direction of reducing the model loss value, so as to construct a target graph transmission model for predicting the transmission concentration, where the target graph transmission model realizes transmission tracing by predicting the transmission concentration.
In one embodiment, when the processing unit 502 calculates the transmission weight factors of the corresponding sides of any two stations with transmission relations based on the station meteorological data of each station, the processing unit may be specifically configured to:
the method comprises the steps of obtaining topographic data corresponding to each site, wherein the topographic data comprises site distances between any two sites in the plurality of sites;
and respectively calculating transmission weight factors of corresponding sides of any two stations with transmission relations based on the station meteorological data and the topographic data of each station.
In another embodiment, the site meteorological data of one site includes wind speed and wind direction of the corresponding site, two site corresponding sides having a transmission relationship include at least one directed side, and the transmission weight factors of the two site corresponding sides having a transmission relationship include: a transmission weight factor corresponding to each of the at least one directed edge; the processing unit 502 may be specifically configured to, when calculating, based on the site meteorological data and the topographic data of the respective sites, transmission weight factors of corresponding sides of any two sites having a transmission relationship:
Determining the direction of a first directed edge related to a corresponding edge of a first site and a second site in the multiple sites, wherein the starting point of the first directed edge is the first site, the end point of the first directed edge is the second site, and a transmission relation exists between the first site and the second site;
calculating angle information between the wind direction of the first site and the direction of the first directed edge by adopting a difference value between the direction of the first directed edge and the wind direction of the first site;
and calculating a transmission weight factor of the first directed edge based on the angle information, the wind speed of the first site and the site distance between the first site and the second site, wherein the site distance between the first site and the second site is determined from the topographic data.
In another embodiment, the processing unit 502 may be further configured to:
determining adjacent data corresponding to each station based on the topographic data, wherein the adjacent data is used for indicating the transmission relation of any two stations in the plurality of stations;
and respectively determining any two stations with transmission relations from the plurality of stations according to the adjacent data.
In another embodiment, the topographic data further includes blocking information between any two sites of the multiple sites, and the processing unit 502 is further configured to, when determining, based on the topographic data, the adjacent data corresponding to each site:
for a third station and a fourth station in the plurality of stations, if the station distance between the third station and the fourth station is smaller than a preset station distance, determining that a transmission relationship exists between the third station and the fourth station, and adding a transmission identifier with the transmission relationship between the third station and the fourth station into the adjacent data; or,
if the blocking information between the third station and the fourth station is smaller than the preset blocking information, determining that a transmission relationship exists between the third station and the fourth station, and adding a transmission identifier with the transmission relationship between the third station and the fourth station into the adjacent data; or,
if the site distance between the third site and the fourth site is smaller than the preset site distance and the blocking information between the third site and the fourth site is smaller than the preset blocking information, determining that a transmission relationship exists between the third site and the fourth site, and adding a transmission identifier with the transmission relationship between the third site and the fourth site into the adjacent data.
In another embodiment, the processing unit 502 may be specifically configured to, when calculating the model loss value of the graph transmission model according to the predicted pollution transmission concentration corresponding to each edge:
invoking a reference numerical model, and calculating reference pollution transmission concentration corresponding to each side based on site pollution data and site meteorological data of each site;
and calculating a model loss value of the graph transmission model by adopting the difference value between the predicted pollution transmission concentration corresponding to each side and the reference pollution transmission concentration corresponding to the corresponding side.
In another embodiment, site pollution data and site weather data of each site in the plurality of sites are obtained from a training data set, and one training data includes site pollution data and site weather data of each site required for model optimization at a time; the acquisition unit 501 may be further configured to:
acquiring the training data set, and traversing each training data in the training data set so that the site pollution data and the site meteorological data of each site are acquired from currently traversed training data;
the processing unit 502 may also be configured to:
after traversing each training data in the training data set, completing N times of optimization on model parameters in the graph transmission model, wherein N is the number of training data in the training data set;
Iterating the steps, if the iteration times reach a preset iteration period, carrying out attenuation treatment on model parameters in the graph transmission model under the current system time to obtain an attenuated graph transmission model; and continuing to perform model optimization on the graph transmission model after the attenuation processing until convergence conditions are reached.
According to an embodiment of the present invention, each step involved in the method shown in fig. 1 or fig. 3 may be performed by each unit in the transmission tracing device shown in fig. 5. For example, step S101 shown in fig. 1 may be performed by the acquisition unit 501 shown in fig. 5, and steps S102 to S104 may each be performed by the processing unit 502 shown in fig. 5. As another example, step S301 shown in fig. 3 may be performed by the acquisition unit 501 shown in fig. 5, steps S302-S305 may each be performed by the processing unit 502 shown in fig. 5, and so on.
According to another embodiment of the present invention, each unit in the transmission tracing device shown in fig. 5 may be combined into one or several other units separately or all, or some (some) of the units may be further split into a plurality of units with smaller functions, which may achieve the same operation without affecting the implementation of the technical effects of the embodiments of the present invention. The above units are divided based on logic functions, and in practical applications, the functions of one unit may be implemented by a plurality of units, or the functions of a plurality of units may be implemented by one unit. In other embodiments of the present invention, any transmission tracing apparatus may also include other units, and in practical applications, these functions may also be implemented with assistance of other units, and may be implemented by cooperation of multiple units.
According to another embodiment of the present invention, a transmission tracing apparatus as shown in fig. 5 may be constructed by running a computer program (including program code) capable of executing the steps involved in the respective methods as shown in fig. 1 or 3 on a general-purpose electronic device such as a computer including a processing element such as a Central Processing Unit (CPU), a random access storage medium (RAM), a read only storage medium (ROM), and the like, and a storage element, and a transmission tracing method of an embodiment of the present invention is implemented. The computer program may be recorded on, for example, a computer storage medium, and loaded into and run in the above-described electronic device through the computer storage medium.
According to the method and the device for predicting the pollution transmission concentration, after the site pollution data and the site meteorological data of each site in the multiple sites are obtained, the transmission weight factors of the corresponding sides of any two sites with transmission relations are calculated respectively based on the site meteorological data of each site, so that the pollution transmission concentration can be predicted conveniently through the transmission weight factors, and the two sites with the transmission relations support the pollutant to be transmitted between the corresponding sites. Then, based on the site pollution data of each site and the transmission weight factors of each side, the graph structure data can be constructed, and the graph transmission model is called to carry out transmission calculation on the graph structure data, so that the predicted pollution transmission concentration corresponding to each side is obtained. Correspondingly, the model loss value of the graph transmission model can be calculated according to the predicted pollution transmission concentration corresponding to each side, and model parameters in the graph transmission model are optimized according to the direction of reducing the model loss value so as to construct a target graph transmission model for predicting the transmission concentration, and the target graph transmission model can realize transmission tracing through predicting the transmission concentration, so that the transmission concentration among stations is predicted conveniently through the target graph transmission model, the transmission tracing is realized conveniently, and the service efficiency is improved.
Based on the description of the method embodiment and the apparatus embodiment, the exemplary embodiment of the present invention further provides an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor. The memory stores a computer program executable by the at least one processor for causing the electronic device to perform a method according to an embodiment of the invention when executed by the at least one processor.
The exemplary embodiments of the present invention also provide a non-transitory computer readable storage medium storing a computer program, wherein the computer program, when executed by a processor of a computer, is for causing the computer to perform a method according to an embodiment of the present invention.
The exemplary embodiments of the invention also provide a computer program product comprising a computer program, wherein the computer program, when being executed by a processor of a computer, is for causing the computer to perform a method according to an embodiment of the invention.
Referring to fig. 6, a block diagram of an electronic device 600 that may be a server or a client of the present invention will now be described, which is an example of a hardware device that may be applied to aspects of the present invention. Electronic devices are intended to represent various forms of digital electronic computer devices, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 6, the electronic device 600 includes a computing unit 601 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 602 or a computer program loaded from a storage unit 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 may also be stored. The computing unit 601, ROM 602, and RAM 603 are connected to each other by a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
A number of components in the electronic device 600 are connected to the I/O interface 605, including: an input unit 606, an output unit 607, a storage unit 608, and a communication unit 609. The input unit 606 may be any type of device capable of inputting information to the electronic device 600, and the input unit 606 may receive input numeric or character information and generate key signal inputs related to user settings and/or function controls of the electronic device. The output unit 607 may be any type of device capable of presenting information and may include, but is not limited to, a display, speakers, video/audio output terminals, vibrators, and/or printers. Storage unit 608 may include, but is not limited to, magnetic disks, optical disks. The communication unit 609 allows the electronic device 600 to exchange information/data with other devices through a computer network, such as the internet, and/or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers and/or chipsets, such as bluetooth (TM) devices, wiFi devices, wiMax devices, cellular communication devices, and/or the like.
The computing unit 601 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 601 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above. For example, in some embodiments, the transmission tracing method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 600 via the ROM 602 and/or the communication unit 609. In some embodiments, the computing unit 601 may be configured to perform the transmission tracing method by any other suitable means (e.g., by means of firmware).
Program code for carrying out methods of the present invention may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
It is also to be understood that the foregoing is merely illustrative of the present invention and is not to be construed as limiting the scope of the invention, which is defined by the appended claims.
Claims (10)
1. The transmission tracing method is characterized by comprising the following steps of:
acquiring site pollution data and site weather data of each site in a plurality of sites, wherein one site pollution data comprises target pollutant concentration of the corresponding site, and one site weather data comprises at least one weather data of the corresponding site;
based on the site meteorological data of each site, respectively calculating transmission weight factors of corresponding sides of any two sites with transmission relations, wherein the two sites with the transmission relations support the transmission of pollutants among the corresponding sites;
constructing graph structure data based on site pollution data of each site and transmission weight factors of each side, and calling a graph transmission model to carry out transmission calculation on the graph structure data to obtain predicted pollution transmission concentration corresponding to each side;
Calculating a model loss value of the graph transmission model according to the predicted pollution transmission concentration corresponding to each side, and optimizing model parameters in the graph transmission model according to the direction of reducing the model loss value so as to construct a target graph transmission model for predicting the transmission concentration, wherein the target graph transmission model realizes transmission tracing through predicting the transmission concentration.
2. The method according to claim 1, wherein the calculating the transmission weight factors of the corresponding sides of any two stations having a transmission relationship based on the station meteorological data of the respective stations, respectively, includes:
the method comprises the steps of obtaining topographic data corresponding to each site, wherein the topographic data comprises site distances between any two sites in the plurality of sites;
and respectively calculating transmission weight factors of corresponding sides of any two stations with transmission relations based on the station meteorological data and the topographic data of each station.
3. The method of claim 2, wherein the site meteorological data for one site includes wind speed and wind direction for the respective site, the two site-corresponding sides having a transmission relationship include at least one directed side, and the transmission weight factors for the two site-corresponding sides having a transmission relationship include: a transmission weight factor corresponding to each of the at least one directed edge; the calculating the transmission weight factors of the corresponding sides of any two stations with transmission relations based on the station meteorological data and the topographic data of each station respectively comprises the following steps:
Determining the direction of a first directed edge related to a corresponding edge of a first site and a second site in the multiple sites, wherein the starting point of the first directed edge is the first site, the end point of the first directed edge is the second site, and a transmission relation exists between the first site and the second site;
calculating angle information between the wind direction of the first site and the direction of the first directed edge by adopting a difference value between the direction of the first directed edge and the wind direction of the first site;
and calculating a transmission weight factor of the first directed edge based on the angle information, the wind speed of the first site and the site distance between the first site and the second site, wherein the site distance between the first site and the second site is determined from the topographic data.
4. The method according to claim 2, wherein the method further comprises:
determining adjacent data corresponding to each station based on the topographic data, wherein the adjacent data is used for indicating the transmission relation of any two stations in the plurality of stations;
And respectively determining any two stations with transmission relations from the plurality of stations according to the adjacent data.
5. The method of claim 4, wherein the terrain data further comprises blocking information between any two sites of the plurality of sites, wherein the determining the adjacency data corresponding to each site based on the terrain data comprises:
for a third station and a fourth station in the plurality of stations, if the station distance between the third station and the fourth station is smaller than a preset station distance, determining that a transmission relationship exists between the third station and the fourth station, and adding a transmission identifier with the transmission relationship between the third station and the fourth station into the adjacent data; or,
if the blocking information between the third station and the fourth station is smaller than the preset blocking information, determining that a transmission relationship exists between the third station and the fourth station, and adding a transmission identifier with the transmission relationship between the third station and the fourth station into the adjacent data; or,
if the site distance between the third site and the fourth site is smaller than the preset site distance and the blocking information between the third site and the fourth site is smaller than the preset blocking information, determining that a transmission relationship exists between the third site and the fourth site, and adding a transmission identifier with the transmission relationship between the third site and the fourth site into the adjacent data.
6. The method according to any one of claims 1-5, wherein calculating a model loss value of the graph transmission model from the predicted pollution transmission concentration corresponding to each side comprises:
invoking a reference numerical model, and calculating reference pollution transmission concentration corresponding to each side based on site pollution data and site meteorological data of each site;
and calculating a model loss value of the graph transmission model by adopting the difference value between the predicted pollution transmission concentration corresponding to each side and the reference pollution transmission concentration corresponding to the corresponding side.
7. The method of any one of claims 1-5, wherein site pollution data and site weather data for each site of the plurality of sites are obtained from a training dataset, one training dataset comprising site pollution data and site weather data for each site required for one model optimization; the method further comprises the steps of:
acquiring the training data set, and traversing each training data in the training data set so that the site pollution data and the site meteorological data of each site are acquired from currently traversed training data;
After traversing each training data in the training data set, completing N times of optimization on model parameters in the graph transmission model, wherein N is the number of training data in the training data set;
iterating the steps, if the iteration times reach a preset iteration period, carrying out attenuation treatment on model parameters in the graph transmission model under the current system time to obtain an attenuated graph transmission model; and continuing to perform model optimization on the graph transmission model after the attenuation processing until convergence conditions are reached.
8. A transmission traceability device, the device comprising:
an acquisition unit configured to acquire site pollution data and site weather data of each of a plurality of sites, one site pollution data including a target pollutant concentration of the corresponding site, and one site weather data including at least one weather data of the corresponding site;
the processing unit is used for respectively calculating transmission weight factors of corresponding sides of any two stations with transmission relations based on the station meteorological data of each station, and the two stations with the transmission relations support the pollutant to be transmitted between the corresponding stations;
the processing unit is further used for constructing graph structure data based on the site pollution data of each site and the transmission weight factors of each side, and calling a graph transmission model to carry out transmission calculation on the graph structure data to obtain the predicted pollution transmission concentration corresponding to each side;
The processing unit is further configured to calculate a model loss value of the graph transmission model according to the predicted pollution transmission concentration corresponding to each side, and optimize model parameters in the graph transmission model according to a direction of reducing the model loss value, so as to construct a target graph transmission model for predicting the transmission concentration, where the target graph transmission model realizes transmission tracing by predicting the transmission concentration.
9. An electronic device, comprising:
a processor; and
a memory in which a program is stored,
wherein the program comprises instructions which, when executed by the processor, cause the processor to perform the method according to any of claims 1-7.
10. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311015499.9A CN116739189A (en) | 2023-08-14 | 2023-08-14 | Transmission tracing method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311015499.9A CN116739189A (en) | 2023-08-14 | 2023-08-14 | Transmission tracing method and device, storage medium and electronic equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116739189A true CN116739189A (en) | 2023-09-12 |
Family
ID=87910036
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311015499.9A Pending CN116739189A (en) | 2023-08-14 | 2023-08-14 | Transmission tracing method and device, storage medium and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116739189A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110363350A (en) * | 2019-07-15 | 2019-10-22 | 西华大学 | A kind of regional air pollutant analysis method based on complex network |
CN110687255A (en) * | 2019-10-21 | 2020-01-14 | 软通动力信息技术有限公司 | Air pollutant tracing method, device, equipment and storage medium |
CN113496310A (en) * | 2021-06-16 | 2021-10-12 | 国家超级计算深圳中心(深圳云计算中心) | Atmospheric pollutant prediction method and system based on deep learning model |
CN114154702A (en) * | 2021-11-25 | 2022-03-08 | 深圳中兴网信科技有限公司 | Pollutant concentration prediction method and device based on multi-granularity graph space-time neural network |
CN115438848A (en) * | 2022-08-29 | 2022-12-06 | 武汉大学 | PM based on deep mixed graph neural network 2.5 Long-term concentration prediction method |
-
2023
- 2023-08-14 CN CN202311015499.9A patent/CN116739189A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110363350A (en) * | 2019-07-15 | 2019-10-22 | 西华大学 | A kind of regional air pollutant analysis method based on complex network |
CN110687255A (en) * | 2019-10-21 | 2020-01-14 | 软通动力信息技术有限公司 | Air pollutant tracing method, device, equipment and storage medium |
CN113496310A (en) * | 2021-06-16 | 2021-10-12 | 国家超级计算深圳中心(深圳云计算中心) | Atmospheric pollutant prediction method and system based on deep learning model |
CN114154702A (en) * | 2021-11-25 | 2022-03-08 | 深圳中兴网信科技有限公司 | Pollutant concentration prediction method and device based on multi-granularity graph space-time neural network |
CN115438848A (en) * | 2022-08-29 | 2022-12-06 | 武汉大学 | PM based on deep mixed graph neural network 2.5 Long-term concentration prediction method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10830922B2 (en) | Air quality forecast by adapting pollutant emission inventory | |
US10636293B2 (en) | Uncertainty modeling in traffic demand prediction | |
US20220092418A1 (en) | Training method for air quality prediction model, prediction method and apparatus, device, program, and medium | |
Huang et al. | A bimodal Gaussian inhomogeneous Poisson algorithm for bike number prediction in a bike-sharing system | |
US20210341646A1 (en) | Weather parameter prediction model training method, weather parameter prediction method, electronic device and storage medium | |
CN112541302A (en) | Air quality prediction model training method, air quality prediction method and device | |
CN111797572A (en) | Urban accident disaster evolution simulation and risk prediction early warning method | |
CN114841437A (en) | Method and device for pre-evaluating contribution of emission source to air quality and electronic equipment | |
CN112001074B (en) | Method, device and storage medium for treating pollutants based on vegetation coverage | |
US10824777B2 (en) | Employing natural language processing to facilitate geospatial analysis | |
CN114239271A (en) | Atmospheric pollution early warning method, device and equipment | |
CN116738867B (en) | Unmanned aerial vehicle defense simulation method and system based on machine learning | |
CN116757506A (en) | Straw burning guiding method and device, storage medium and electronic equipment | |
CN116739189A (en) | Transmission tracing method and device, storage medium and electronic equipment | |
CN114565170A (en) | Pollutant tracing method and device, equipment, medium and product | |
CN114881472A (en) | Method, device and equipment for analyzing influence of motor vehicle exhaust on air quality | |
CN113723712B (en) | Wind power prediction method, system, equipment and medium | |
Lin et al. | Integrating ANFIS and Qt Framework to Develop a Mobile‐Based Typhoon Rainfall Forecasting System | |
CN114841438A (en) | Method and device for pre-evaluating influence of emission source on air quality and electronic equipment | |
CN113468244A (en) | Atmospheric environmental pollution source management system, method, electronic device and storage medium | |
CN107169088B (en) | User social relationship strength calculation method and system based on time-space interaction | |
CN118195282B (en) | Pollution control guiding method and device, storage medium and electronic equipment | |
Xue | Connected vehicle path planning and resource allocation in edge computing environment | |
Huu et al. | Wireless Sensor Network to Collect and Forecast Environment Parameters Using LSTM | |
CN118070982B (en) | Prediction method and device for selection of station passenger stairs in flood scene |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230912 |