CN112200456A - Enterprise environment influence evaluation method, device, equipment and computer storage medium - Google Patents

Enterprise environment influence evaluation method, device, equipment and computer storage medium Download PDF

Info

Publication number
CN112200456A
CN112200456A CN202011081311.7A CN202011081311A CN112200456A CN 112200456 A CN112200456 A CN 112200456A CN 202011081311 A CN202011081311 A CN 202011081311A CN 112200456 A CN112200456 A CN 112200456A
Authority
CN
China
Prior art keywords
enterprise
area
evaluated
current stage
type prediction
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202011081311.7A
Other languages
Chinese (zh)
Other versions
CN112200456B (en
Inventor
汪飙
侯鑫
邹冲
朱超杰
李世行
吴海山
殷磊
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
WeBank Co Ltd
Original Assignee
WeBank Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by WeBank Co Ltd filed Critical WeBank Co Ltd
Priority to CN202011081311.7A priority Critical patent/CN112200456B/en
Priority claimed from CN202011081311.7A external-priority patent/CN112200456B/en
Publication of CN112200456A publication Critical patent/CN112200456A/en
Priority to PCT/CN2021/102000 priority patent/WO2022073361A1/en
Application granted granted Critical
Publication of CN112200456B publication Critical patent/CN112200456B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • 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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/56—Extraction of image or video features relating to colour
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/13—Satellite images

Abstract

The invention discloses a method, a device, equipment and a computer storage medium for evaluating enterprise environment influence, wherein the method comprises the following steps: the method comprises the steps of obtaining remote sensing data corresponding to each enterprise area to be evaluated in the current stage, and constructing RGB images corresponding to the enterprise areas to be evaluated according to the remote sensing data; respectively inputting the RGB images corresponding to the enterprise areas to be evaluated into a land type prediction model, and outputting land type prediction results corresponding to the enterprise areas to be evaluated by the land type prediction model; and according to the land type prediction result corresponding to each enterprise area to be evaluated, evaluating the environmental impact corresponding to each enterprise area to be evaluated at the current stage. Compared with the prior art that environment medium data such as atmosphere around an enterprise are manually collected, the method and the system reduce the data collection cost and the difficulty of enterprise environment risk assessment through the remote sensing data corresponding to the enterprise area, and improve the objectivity of the enterprise environment risk assessment result by using the land type prediction model.

Description

Enterprise environment influence evaluation method, device, equipment and computer storage medium
Technical Field
The invention relates to the field of enterprise environment risk assessment, in particular to an enterprise environment influence assessment method, device and equipment and a computer storage medium.
Background
In recent years, as environmental risk cognition in China is continuously deepened, the risk prevention and control range, the type and the fineness are gradually improved, especially, environmental risk control for the periphery of an enterprise is gradually concerned and paid attention, most of the existing environmental impact assessment methods for the periphery of the enterprise at home and abroad are developed for environmental risks for environmental media (such as water, gas, soil and the like) around the enterprise, but the environmental impact assessment methods need to accurately and manually acquire environmental media data of the atmosphere, the water, the soil and the like around the enterprise, so that the acquisition cost is high, the difficulty is overlarge when a plurality of enterprises related to one industry are assessed, the environmental impact assessment process is limited, and the environmental impact assessment result is not objective.
Disclosure of Invention
The invention provides an enterprise environment influence evaluation method, an enterprise environment influence evaluation device, enterprise environment influence evaluation equipment and a computer storage medium, and aims to reduce data acquisition cost and enterprise environment risk evaluation difficulty of enterprise environment risk evaluation and improve objectivity of an enterprise environment risk evaluation result.
In order to achieve the above object, the present invention provides an enterprise environmental impact assessment method, including:
the method comprises the steps of obtaining remote sensing data corresponding to each enterprise area to be evaluated in the current stage, and constructing RGB images corresponding to the enterprise areas to be evaluated according to the remote sensing data;
respectively inputting the RGB images corresponding to the enterprise areas to be evaluated into a land type prediction model, and outputting land type prediction results corresponding to the enterprise areas to be evaluated by the land type prediction model;
and according to the land type prediction result corresponding to each enterprise area to be evaluated, evaluating the environmental impact corresponding to each enterprise area to be evaluated at the current stage.
Preferably, the remote sensing data includes blue wave band data, green wave band data and red wave band data, and the step of constructing the RGB image corresponding to each enterprise to be evaluated according to the remote sensing data includes:
respectively carrying out normalization processing on the blue wave band data, the green wave band data and the red wave band data corresponding to each enterprise to be evaluated so as to obtain target blue wave band data, target green wave band data and target red wave band data corresponding to each enterprise to be evaluated;
and constructing an RGB image corresponding to each enterprise to be evaluated according to the target blue waveband data, the target green waveband data and the target red waveband data.
Preferably, before the step of inputting the RGB images corresponding to the enterprise areas to be evaluated into the land type prediction model, the method further includes:
acquiring training remote sensing data corresponding to a plurality of training enterprise areas, and constructing a training RGB image corresponding to each training enterprise area according to the training remote sensing data;
and acquiring an initial model, and training the initial model according to the training RGB image to obtain a land type prediction model.
Preferably, the step of training the initial model according to the training RGB image to obtain a land type prediction model comprises:
inputting the training RGB image into an initial model, and outputting a land type prediction result corresponding to the training RGB image by the initial model;
acquiring a real land type corresponding to the training RGB image, and calculating a loss function based on the real land type corresponding to the training RGB image and a land type prediction result corresponding to the training RGB image;
and updating the model parameters of the initial model in a gradient descending manner until the loss function converges or reaches a preset training iteration, and taking the model parameters corresponding to the loss function converging or reaching the preset training iteration as final model parameters to obtain a land type prediction model.
Preferably, the land type prediction result includes an industrial type prediction result and a resident type prediction result, and the step of evaluating the environmental impact corresponding to each enterprise area to be evaluated at the current stage according to the land type prediction result corresponding to each enterprise area to be evaluated includes:
acquiring the occupied area of the industrial area in the current stage and the occupied area of the resident area in the current stage corresponding to each enterprise area to be evaluated according to the industrial type prediction result and the resident type prediction result corresponding to each enterprise area to be evaluated in the current stage;
determining the occupation ratio of the industrial area and the occupation ratio of the residential area corresponding to each enterprise area to be evaluated at the current stage according to the occupation area of the industrial area at the current stage and the occupation area of the residential area at the current stage corresponding to each enterprise area to be evaluated at the current stage;
and according to the industrial area ratio and the residential area ratio corresponding to each enterprise area to be evaluated in the current stage, evaluating the environmental impact corresponding to each enterprise area to be evaluated.
Preferably, after the step of obtaining the floor area of the industrial area at the current stage and the floor area of the residential area at the current stage corresponding to each enterprise area to be evaluated, the method further includes:
acquiring the floor area of an industrial area of the last stage and the floor area of a residential area of the last stage corresponding to each enterprise area to be evaluated;
determining the change rate of the industrial area corresponding to each enterprise area to be evaluated at the current stage according to the occupied area of the industrial area at the current stage corresponding to each enterprise area to be evaluated and the occupied area of the industrial area at the previous stage;
determining the change rate of the residential areas corresponding to the enterprise areas to be evaluated at the current stage according to the occupied areas of the residential areas at the current stage and the occupied areas of the residential areas at the previous stage corresponding to the enterprise areas to be evaluated;
and evaluating the environmental impact corresponding to each enterprise area to be evaluated according to the industrial area change rate corresponding to each enterprise area to be evaluated in the current stage and the residential area change rate corresponding to each enterprise area to be evaluated in the current stage.
Preferably, the remote sensing data includes green band data, red band data and near-infrared band data, and after the step of obtaining the remote sensing data corresponding to each to-be-evaluated enterprise region at the current stage, the method further includes:
acquiring the water body index ratio and the water body index change rate corresponding to each enterprise area to be evaluated in the current stage according to the green wave band data and the near infrared wave band data corresponding to each enterprise area to be evaluated in the current stage;
acquiring the vegetation index proportion and the vegetation index change rate of each enterprise area to be evaluated at the current stage according to the red waveband data and the near infrared waveband data corresponding to each enterprise area to be evaluated at the current stage;
and evaluating the environmental impact corresponding to each enterprise area to be evaluated according to the water body index ratio, the water body index change rate, the vegetation index ratio and the vegetation index change rate corresponding to each enterprise area to be evaluated in the current stage.
In addition, to achieve the above object, the present invention further provides an enterprise environmental impact evaluation apparatus, including:
the construction module is used for acquiring remote sensing data corresponding to each enterprise area to be evaluated at the current stage and constructing an RGB image corresponding to each enterprise area to be evaluated according to the remote sensing data;
the prediction module is used for respectively inputting the RGB images corresponding to the enterprise areas to be evaluated into the land type prediction model and outputting land type prediction results corresponding to the enterprise areas to be evaluated by the land type prediction model;
and the evaluation module is used for evaluating the environmental impact corresponding to each enterprise area to be evaluated at the current stage according to the land type prediction result corresponding to each enterprise area to be evaluated.
In addition, in order to achieve the above object, the present invention further provides an enterprise environmental impact evaluation device, where the enterprise environmental impact evaluation device includes a processor, a memory, and an enterprise environmental impact evaluation program stored in the memory, and when the enterprise environmental impact evaluation program is executed by the processor, the steps of the enterprise environmental impact evaluation method are implemented.
In addition, to achieve the above object, the present invention further provides a computer storage medium, on which an enterprise environment influence assessment program is stored, and when the enterprise environment influence assessment program is executed by a processor, the method implements the steps of the enterprise environment influence assessment method.
Compared with the prior art, the invention discloses an enterprise environment influence evaluation method, device, equipment and computer storage medium, which are used for obtaining remote sensing data corresponding to each enterprise area to be evaluated at the current stage and constructing RGB images corresponding to the enterprise areas to be evaluated according to the remote sensing data; respectively inputting the RGB images corresponding to the enterprise areas to be evaluated into a land type prediction model, and outputting land type prediction results corresponding to the enterprise areas to be evaluated by the land type prediction model; and according to the land type prediction result corresponding to each enterprise area to be evaluated, evaluating the environmental impact corresponding to each enterprise area to be evaluated at the current stage. Compared with the prior art that environment medium data such as atmosphere, water, soil and the like around an enterprise are manually acquired, the method and the system have the advantages that the remote sensing data corresponding to the enterprise area are acquired, the data acquisition cost and the enterprise environment risk assessment difficulty of enterprise environment risk assessment are reduced, and the objectivity of the enterprise environment risk assessment result is improved by utilizing the land type prediction model.
Drawings
Fig. 1 is a hardware configuration diagram of an enterprise environmental impact evaluation device according to embodiments of the present invention;
FIG. 2 is a flowchart illustrating a first embodiment of a method for assessing environmental impact of an enterprise according to the present invention;
FIG. 3 is twelve band data of a first embodiment of the enterprise environmental impact assessment method of the present invention;
FIG. 4 is a flowchart illustrating a second embodiment of a method for assessing environmental impact of an enterprise according to the present invention;
fig. 5 is a functional block diagram of the enterprise environmental impact evaluation device according to the first embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The enterprise environment influence evaluation equipment mainly related to the embodiment of the invention is network connection equipment capable of realizing network connection, and the enterprise environment influence evaluation equipment can be a server, a cloud platform and the like.
Referring to fig. 1, fig. 1 is a schematic diagram of a hardware structure of an enterprise environmental impact evaluation apparatus according to embodiments of the present invention. In this embodiment of the present invention, the enterprise environmental impact evaluation device may include a processor 1001 (e.g., a Central Processing Unit, CPU), a communication bus 1002, an input port 1003, an output port 1004, and a memory 1005. The communication bus 1002 is used for realizing connection communication among the components; the input port 1003 is used for data input; the output port 1004 is used for data output, the memory 1005 may be a high-speed RAM memory, or a non-volatile memory (non-volatile memory), such as a magnetic disk memory, and the memory 1005 may optionally be a storage device independent of the processor 1001. Those skilled in the art will appreciate that the hardware configuration depicted in FIG. 1 is not intended to be limiting of the present invention, and may include more or less components than those shown, or some components in combination, or a different arrangement of components.
With continued reference to FIG. 1, the memory 1005 of FIG. 1, which is one type of readable storage medium, may include an operating system, a network communication module, an application program module, and an enterprise environmental impact evaluation program. In fig. 1, the network communication module is mainly used for connecting to a server and performing data communication with the server; and processor 1001 may invoke the enterprise environmental impact evaluation program stored in memory 1005 and perform the following operations:
the method comprises the steps of obtaining remote sensing data corresponding to each enterprise area to be evaluated in the current stage, and constructing RGB images corresponding to the enterprise areas to be evaluated according to the remote sensing data;
respectively inputting the RGB images corresponding to the enterprise areas to be evaluated into a land type prediction model, and outputting land type prediction results corresponding to the enterprise areas to be evaluated by the land type prediction model;
and according to the land type prediction result corresponding to each enterprise area to be evaluated, evaluating the environmental impact corresponding to each enterprise area to be evaluated at the current stage.
Further, the processor 1001 may be further configured to call the enterprise environmental impact evaluation program stored in the memory 1005, and perform the following steps:
respectively carrying out normalization processing on the blue wave band data, the green wave band data and the red wave band data corresponding to each enterprise to be evaluated so as to obtain target blue wave band data, target green wave band data and target red wave band data corresponding to each enterprise to be evaluated;
and constructing an RGB image corresponding to each enterprise to be evaluated according to the target blue waveband data, the target green waveband data and the target red waveband data.
Further, the processor 1001 may be further configured to call the enterprise environmental impact evaluation program stored in the memory 1005, and perform the following steps:
acquiring training remote sensing data corresponding to a plurality of training enterprise areas, and constructing a training RGB image corresponding to each training enterprise area according to the training remote sensing data;
and acquiring an initial model, and training the initial model according to the training RGB image to obtain a land type prediction model.
Further, the processor 1001 may be further configured to call the enterprise environmental impact evaluation program stored in the memory 1005, and perform the following steps:
inputting the training RGB image into an initial model, and outputting a land type prediction result corresponding to the training RGB image by the initial model;
acquiring a real land type corresponding to the training RGB image, and calculating a loss function based on the real land type corresponding to the training RGB image and a land type prediction result corresponding to the training RGB image;
and updating the model parameters of the initial model in a gradient descending manner until the loss function converges or reaches a preset training iteration, and taking the model parameters corresponding to the loss function converging or reaching the preset training iteration as final model parameters to obtain a land type prediction model.
Further, the processor 1001 may be further configured to call the enterprise environmental impact evaluation program stored in the memory 1005, and perform the following steps:
acquiring the occupied area of the industrial area in the current stage and the occupied area of the resident area in the current stage corresponding to each enterprise area to be evaluated according to the industrial type prediction result and the resident type prediction result corresponding to each enterprise area to be evaluated in the current stage;
determining the occupation ratio of the industrial area and the occupation ratio of the residential area corresponding to each enterprise area to be evaluated at the current stage according to the occupation area of the industrial area at the current stage and the occupation area of the residential area at the current stage corresponding to each enterprise area to be evaluated at the current stage;
and according to the industrial area ratio and the residential area ratio corresponding to each enterprise area to be evaluated in the current stage, evaluating the environmental impact corresponding to each enterprise area to be evaluated.
Further, the processor 1001 may be further configured to call the enterprise environmental impact evaluation program stored in the memory 1005, and perform the following steps:
acquiring the floor area of an industrial area of the last stage and the floor area of a residential area of the last stage corresponding to each enterprise area to be evaluated;
determining the change rate of the industrial area corresponding to each enterprise area to be evaluated at the current stage according to the occupied area of the industrial area at the current stage corresponding to each enterprise area to be evaluated and the occupied area of the industrial area at the previous stage;
determining the change rate of the residential areas corresponding to the enterprise areas to be evaluated at the current stage according to the occupied areas of the residential areas at the current stage and the occupied areas of the residential areas at the previous stage corresponding to the enterprise areas to be evaluated;
and evaluating the environmental impact corresponding to each enterprise area to be evaluated according to the industrial area change rate corresponding to each enterprise area to be evaluated in the current stage and the residential area change rate corresponding to each enterprise area to be evaluated in the current stage.
Further, the processor 1001 may be further configured to call the enterprise environmental impact evaluation program stored in the memory 1005, and perform the following steps:
acquiring the water body index ratio and the water body index change rate corresponding to each enterprise area to be evaluated in the current stage according to the green wave band data and the near infrared wave band data corresponding to each enterprise area to be evaluated in the current stage;
acquiring the vegetation index proportion and the vegetation index change rate of each enterprise area to be evaluated at the current stage according to the red waveband data and the near infrared waveband data corresponding to each enterprise area to be evaluated at the current stage;
and evaluating the environmental impact corresponding to each enterprise area to be evaluated according to the water body index ratio, the water body index change rate, the vegetation index ratio and the vegetation index change rate corresponding to each enterprise area to be evaluated in the current stage.
Based on the structure, the invention provides various embodiments of the enterprise environment influence evaluation method.
Referring to fig. 2, fig. 2 is a flowchart illustrating a first embodiment of the enterprise environmental impact assessment method according to the present invention.
In this embodiment, the enterprise environmental impact assessment method is applied to an enterprise environmental impact assessment device, and the method includes:
step S10: the method comprises the steps of obtaining remote sensing data corresponding to each enterprise area to be evaluated in the current stage, and constructing RGB images corresponding to the enterprise areas to be evaluated according to the remote sensing data;
in this embodiment, it should be noted that, in the evaluation of the influence on the enterprise environment, most of the environmental medium data such as the atmosphere, water, soil and the like around the enterprise are manually collected for evaluation, but this method has high data collection cost and poor data representativeness, and the difficulty in evaluating a plurality of enterprises related to one industry is too high, so that the environmental influence evaluation result is not objective.
It should be noted that the remote sensing technology proposed in this embodiment is a comprehensive technology for detecting and monitoring the resources and environment of the earth by detecting the electromagnetic wave radiation information on the earth surface from a remote sensing satellite far away from the ground through the remote sensing satellite, and then by transmission, processing, interpretation and analysis of the information. The aerial view is detected from a long distance in a high-altitude aerial view mode, the remote sensing images comprise multipoint remote sensing images, multispectral remote sensing images, multiple time periods and multiple heights, and multiple times of enhanced remote sensing information, continuous regional synchronous information of comprehensive systematicness, instantaneity or synchronism can be provided, and the aerial view is applied to the field of environmental science with great superiority. Remote sensing satellites have many uses, such as terrain detection, oil detection, atmospheric environment, and terrain detection, among others.
Specifically, the present embodiment determines the geographic location of each enterprise area to be evaluated and the central point of each enterprise area to be evaluated, and records the longitude and latitude coordinates (Lati, Loni) of the central point of each enterprise area to be evaluated; (i belongs to [1, N ]), then extending a preset range, such as a rectangular area range, around the central point of the enterprise area to be evaluated to obtain a rectangular area longitude and latitude range BOXi [ Loni-Lon _ bias, Lati-Lat _ bias, Loni + Lon _ bias, Lati + Lat _ bias ]; (i belongs to [1, N ]), wherein Lon _ bias and Lat _ bias are constants, and are not specifically limited, after the longitude and latitude range BOXi of the rectangular region is obtained, remote sensing data corresponding to the longitude and latitude range BOXi of the rectangular region corresponding to each enterprise region to be evaluated is obtained through a remote sensing satellite, as shown in FIG. 3, 12 waveband data corresponding to the longitude and latitude range BOXi of each rectangular region are obtained, namely, band 1-coastal aerosol waveband data with the central wavelength of 0.443 μm, band 2-blue waveband data with the central wavelength of 0.490 μm, band 3-green waveband data with the central wavelength of 0.560 μm, band 4-red waveband data with the central wavelength of 0.665 μm, band 5-vegetation red edge data with the central wavelength of 0.705 μm, band 6-red edge waveband data with the central wavelength of 0.740 μm, and red edge data with the central wavelength of 0.7 μm are obtained, Band 8-near infrared band data with the central wavelength of 0.842 mu m, band 8A-vegetation red edge band data with the central wavelength of 0.865 mu m, band 9-water vapor band data with the central wavelength of 0.945 mu m, band 10-short wave infrared band data with the central wavelength of 1.375 mu m, band 11-short wave infrared band data with the central wavelength of 1.610 mu m and band 12-short wave infrared band data with the central wavelength of 2.190 mu m, and after remote sensing data corresponding to each BOXi are obtained, RGB images corresponding to enterprise areas to be evaluated are constructed according to the remote sensing data.
Specifically, in step S10: the step of constructing the RGB image corresponding to each enterprise to be evaluated according to the remote sensing data comprises the following steps:
step S101: respectively carrying out normalization processing on the blue wave band data, the green wave band data and the red wave band data corresponding to each enterprise to be evaluated so as to obtain target blue wave band data, target green wave band data and target red wave band data corresponding to each enterprise to be evaluated;
step S102: and constructing an RGB image corresponding to each enterprise to be evaluated according to the target blue waveband data, the target green waveband data and the target red waveband data.
Specifically, in this step, blue band data RAWband2 with a center wavelength of 0.490 μm, green band data RAWband3 with a center wavelength of 0.560 μm, and red band data RAWband4 with a center wavelength of 0.665 μm corresponding to a rectangular region latitude and longitude range BOXi corresponding to each enterprise region to be evaluated are obtained through a remote sensing satellite, then normalization processing is respectively performed on the blue band data RAWband2, the green band data RAWband3, and the red band data RAWband 367 corresponding to each enterprise to be evaluated by a normalization method such as percentage truncation, so as to obtain target blue band data RAWband2_ s, target green band data RAWband3_ s, and target red band data RAWband4_ s, for example, the red band data RAWband3 is normalized by percentage truncation, so as to obtain normalized target red band data RAWband 84 — 84 RAWband 84 (rawmin — 827375) of normalized target red band data RAWband/or tband/or λ 25 and/or λ 42 and λ 80), the method comprises the steps that RAWband4_ min and RAWband4_ max are respectively the minimum value and the maximum value of RAWband4 data, and after target blue band data RAWband2_ s, target green band data RAWband3_ s and target red band data RAWband4_ s corresponding to each enterprise to be evaluated are obtained, the three data are respectively used as three different dimensions to construct RGB images [ RAWband4_ s, RAWband3_ s and RAWband2_ s ] corresponding to each enterprise to be evaluated.
Step S20: respectively inputting the RGB images corresponding to the enterprise areas to be evaluated into a land type prediction model, and outputting land type prediction results corresponding to the enterprise areas to be evaluated by the land type prediction model;
inputting an RGB image corresponding to an enterprise area to be evaluated into a land type prediction model, and then performing image segmentation processing on the RGB image by the land type prediction model, wherein the geographic area corresponding to the RGB image corresponding to the enterprise area to be evaluated comprises different land types such as an enterprise area, an industrial area around the enterprise, a residential area around the enterprise and the like, so as to divide the RGB image into a plurality of areas according to different area types, and labeling land type prediction results of the areas according to the land types of the areas, optionally labeling the land type prediction results of the areas by using labels, such as labeling the industrial area by using label 1, labeling the residential area by using label 2, labeling the company area by using label 3, optionally labeling the land type prediction results of the areas by using different colors, such as labeling the industrial area by using red, labeling the residential area by using red label, And marking residential areas with green colors, marking company areas with blue colors, and finally outputting land type prediction results corresponding to the enterprise areas to be evaluated by the land type prediction model.
Further, step S20: before the step of inputting the RGB images corresponding to each enterprise region to be evaluated into the land type prediction model, the method further includes:
step S201: acquiring training remote sensing data corresponding to a plurality of training enterprise areas, and constructing a training RGB image corresponding to each training enterprise area according to the training remote sensing data;
step S202: and acquiring an initial model, and training the initial model according to the training RGB image to obtain a land type prediction model.
In this step, a plurality of training data, that is, training remote sensing data corresponding to a plurality of training enterprise areas of known real land types, are obtained, and a training RGB image corresponding to each training enterprise area is constructed according to the training remote sensing data, where this step is the same as the step of constructing an RGB image corresponding to each enterprise to be evaluated according to the remote sensing data in step S10, and is not described herein again.
And then acquiring an initial model, and training the initial model according to the training RGB image to obtain a land type prediction model, wherein the initial model can be a convolutional neural network model, a deep learning model, a decision tree and the like.
Specifically, in step S202: the step of training the initial model according to the training RGB image to obtain a land type prediction model comprises:
step S202 a: inputting the training RGB image into an initial model, and outputting a land type prediction result corresponding to the training RGB image by the initial model;
step S202 b: acquiring a real land type corresponding to the training RGB image, and calculating a loss function based on the real land type corresponding to the training RGB image and a land type prediction result corresponding to the training RGB image;
step S202 c: and updating the model parameters of the initial model in a gradient descending manner until the loss function converges or reaches a preset training iteration, and taking the model parameters corresponding to the loss function converging or reaching the preset training iteration as final model parameters to obtain a land type prediction model.
In this step, before inputting the training RGB image into the initial model, the real land type is marked on the training RGB image by means of a vector diagram stored in the system or a manual marking method, for example, after obtaining the training RGB image corresponding to the maofu electromechanical technology limited company in anhui, the industrial area in the training RGB image is marked with red, the residential area in the training RGB image is marked with green, the company area in the training RGB image is marked with blue, the initial model parameters are randomly obtained, the training RGB image is input into the initial model, the initial model corresponding to the initial model parameters outputs the land type prediction result corresponding to the training RGB image, and then the loss function is calculated according to the real land type corresponding to the training RGB image and the land type prediction result corresponding to the training RGB image, wherein the loss function may be a common loss function for a task, in this embodiment, the cross entropy loss function is calculated based on the mini-batch.
Specifically, the gradient corresponding to each parameter in the initial model is calculated according to the cross entropy loss function, and each parameter is updated correspondingly according to the gradient of each parameter, that is, each parameter of the initial model is adjusted. Here, the process of updating the model parameters according to the cross entropy loss function is similar to the existing model parameter updating process, and is not described in detail here.
And judging whether the cross entropy loss function is converged, wherein the convergence condition is that the cross entropy loss function obtains a minimum value, if the cross entropy loss function is converged, stopping training, or the model parameter updating turn of the initial model reaches a preset training iteration turn, storing the last training parameter as a final model parameter, and obtaining a land type prediction model based on the final model parameter.
Otherwise, if the cross entropy loss function does not reach the convergence condition, continuing training: and continuously carrying out iterative updating until convergence, and finally obtaining the land type prediction model.
Step S30: and according to the land type prediction result corresponding to each enterprise area to be evaluated, evaluating the environmental impact corresponding to each enterprise area to be evaluated at the current stage.
In the step, after a land type prediction result corresponding to each enterprise area to be evaluated is output by a land type prediction model, according to the land type prediction result corresponding to each enterprise area to be evaluated, an industrial area proportion and a residential area proportion corresponding to each enterprise area to be evaluated in the current stage are obtained, so that enterprise land use corresponding to each enterprise area to be evaluated in the current stage is scored, and the influence of the enterprise areas of each enterprise area to be evaluated is evaluated.
According to the scheme, the remote sensing data corresponding to each enterprise area to be evaluated at the current stage is obtained, and RGB images corresponding to each enterprise area to be evaluated are constructed according to the remote sensing data; respectively inputting the RGB images corresponding to the enterprise areas to be evaluated into a land type prediction model, and outputting land type prediction results corresponding to the enterprise areas to be evaluated by the land type prediction model; and according to the land type prediction result corresponding to each enterprise area to be evaluated, evaluating the environmental impact corresponding to each enterprise area to be evaluated at the current stage. Compared with the prior art that environment medium data such as atmosphere, water, soil and the like around an enterprise are manually acquired, the method and the system have the advantages that the remote sensing data corresponding to the enterprise area are acquired, the data acquisition cost and the enterprise environment risk assessment difficulty of enterprise environment risk assessment are reduced, and the objectivity of the enterprise environment risk assessment result is improved by utilizing the land type prediction model.
A third embodiment of the present invention is proposed based on the second embodiment shown in fig. 2 described above. Fig. 4 is a schematic flow chart of a method for evaluating environmental impact of an enterprise according to a second embodiment of the present invention.
The step of evaluating the environmental impact corresponding to each enterprise area to be evaluated at the current stage according to the land type prediction result corresponding to each enterprise area to be evaluated comprises the following steps:
step S301: acquiring the occupied area of the industrial area in the current stage and the occupied area of the resident area in the current stage corresponding to each enterprise area to be evaluated according to the industrial type prediction result and the resident type prediction result corresponding to each enterprise area to be evaluated in the current stage;
step S302: determining the occupation ratio of the industrial area and the occupation ratio of the residential area corresponding to each enterprise area to be evaluated at the current stage according to the occupation area of the industrial area at the current stage and the occupation area of the residential area at the current stage corresponding to each enterprise area to be evaluated at the current stage;
step S303: and according to the industrial area ratio and the residential area ratio corresponding to each enterprise area to be evaluated in the current stage, evaluating the environmental impact corresponding to each enterprise area to be evaluated.
In the step, after obtaining land type prediction results corresponding to each enterprise area to be evaluated, wherein the land type prediction results comprise industrial type prediction results and residential type prediction results, obtaining industrial area occupation ratios and residential area occupation ratios corresponding to each enterprise area to be evaluated at the current stage according to the land type prediction results corresponding to each enterprise area to be evaluated, and specifically obtaining the industrial area occupation area F at the current stage corresponding to each enterprise area to be evaluated according to the industrial type prediction results and the residential type prediction results corresponding to each enterprise area to be evaluated at the current stageitAnd the occupied area R of the residential area at the current stageitWherein i ∈ [1, N ]]Then, the Sum of industrial area Sum _ F of N companies and the Sum of residential area Sum _ R of N companies are calculated, where Sum _ F is F1t+F2t+…+FNt；Sum_R＝R1t+R2t+…+RNtFinally, determining the industrial area proportion F corresponding to each enterprise area to be evaluated in the current stageitPro and residential area ratio RitPro, wherein Fit_pro＝Fit/Sum_F，Rit_pro＝Ritand/Sum _ R, and taking the industrial area ratio and the residential area ratio corresponding to each enterprise area to be evaluated at the current stage as the environmental impact corresponding to each enterprise area to be evaluatedAnd evaluating the factors so as to evaluate the environmental impact corresponding to each enterprise area to be evaluated at the current stage.
Further, the environmental impact evaluation factor in this implementation includes, in addition to the industrial area proportion and the residential area proportion corresponding to each enterprise area to be evaluated at the current stage, the industrial area change rate corresponding to each enterprise area to be evaluated at the current stage, the residential area change rate corresponding to each enterprise area to be evaluated at the current stage, the water body index proportion, the water body index change rate, the vegetation index proportion, the vegetation index change rate, and the like corresponding to each enterprise area to be evaluated at the current stage.
Specifically, after the step of obtaining the floor area of the industrial area in the current stage and the floor area of the residential area in the current stage corresponding to each enterprise area to be evaluated, the method further includes:
step S40 a: acquiring the floor area of an industrial area of the last stage and the floor area of a residential area of the last stage corresponding to each enterprise area to be evaluated;
step S40 b: determining the change rate of the industrial area corresponding to each enterprise area to be evaluated at the current stage according to the occupied area of the industrial area at the current stage corresponding to each enterprise area to be evaluated and the occupied area of the industrial area at the previous stage;
step S40 c: determining the change rate of the residential areas corresponding to the enterprise areas to be evaluated at the current stage according to the occupied areas of the residential areas at the current stage and the occupied areas of the residential areas at the previous stage corresponding to the enterprise areas to be evaluated;
step S40 d: and evaluating the environmental impact corresponding to each enterprise area to be evaluated according to the industrial area change rate corresponding to each enterprise area to be evaluated in the current stage and the residential area change rate corresponding to each enterprise area to be evaluated in the current stage.
In the step, the occupied area F of the last-stage industrial area corresponding to each enterprise area to be evaluated is obtainedikAnd the occupied area R of the residential area in the last stageikFor example, if the current stage is 2020 and9 months, the occupied floor of the industrial area corresponding to each enterprise area to be evaluated in 2020 and8 months or 2019 and9 months is obtainedAccumulating the occupied area of the residential area, and then determining the industrial area change rate F corresponding to each enterprise area to be evaluated at the current stagetkA rate and a residential area rate of change Rtk _ rate, wherein Ftk _ rate (F)it-Fik)/Fik；Rtk_rate＝(Rit-Rik)/RikAnd the change rate F of the industrial area corresponding to each enterprise area to be evaluated in the current stage is calculatedtkThe rate and the residential area change rate Rtk _ rate are used as environmental impact evaluation factors corresponding to each enterprise area to be evaluated so as to evaluate the environmental impact corresponding to each enterprise area to be evaluated at the current stage.
Specifically, after the step of obtaining the remote sensing data corresponding to each enterprise area to be evaluated at the current stage, the method further includes:
step S50 a: acquiring the water body index ratio and the water body index change rate corresponding to each enterprise area to be evaluated in the current stage according to the green wave band data and the near infrared wave band data corresponding to each enterprise area to be evaluated in the current stage;
step S50 b: acquiring the vegetation index proportion and the vegetation index change rate of each enterprise area to be evaluated at the current stage according to the red waveband data and the near infrared waveband data corresponding to each enterprise area to be evaluated at the current stage;
step S50 c: and evaluating the environmental impact corresponding to each enterprise area to be evaluated according to the water body index ratio, the water body index change rate, the vegetation index ratio and the vegetation index change rate corresponding to each enterprise area to be evaluated in the current stage.
In the step, the remote sensing data comprises green wave band data RAWband3 with a center wavelength of 0.560 μm, red wave band data RAWband4 with a center wavelength of 0.665 μm and near infrared wave band data RAWband8 with a center wavelength of 0.842 μm, after the steps of obtaining green wave band data RAWband3, red wave band data RAWband4 and near infrared wave band data RAWband8 corresponding to each enterprise area to be evaluated in the current stage, obtaining water body indexes NDWIt corresponding to each enterprise area to be evaluated in the current stage according to green wave band data RAWband3 and near infrared wave band data RAWband8 corresponding to each enterprise area to be evaluated in the current stage, wherein the NDWIt is obtained by the steps of obtaining water body indexes NDWIt of each enterprise area to be evaluated in the current stage (RAWband3-RAWband8)/(RAWband3+ Wband8) and obtaining water body indexes corresponding to be evaluated in the enterprise area to be evaluated in the current stage, and obtaining water body indexes corresponding to-WItWIt-WIt-on-by the first stage, obtaining water body indexes of water body indexes and obtaining water body indexes corresponding to-WItWIt-WIt ratio change, and taking the water body index ratio NDWIit _ pro and the water body index change rate NDWItk _ rate corresponding to each enterprise area to be evaluated in the current stage as the environment influence evaluation factor corresponding to each enterprise area to be evaluated so as to evaluate the environment influence corresponding to each enterprise area to be evaluated in the current stage. The step of calculating the water body index change rate NDWItk _ rate is the same as the step of calculating the industrial area change rate Ftk _ rate, and is not described herein again.
Further, according to red wave band data RAWband4 with the center wavelength of 0.665 μm and near infrared wave band data RAWband8 with the center wavelength of 0.842 μm corresponding to each enterprise area to be evaluated in the current stage, vegetation indexes NDVIit corresponding to each enterprise area to be evaluated in the current stage are obtained, wherein, NDVIit is (RAWband4-RAWband8)/(RAWband4+ RAWband8), further obtaining the vegetation index ratio NDVIit _ pro corresponding to each enterprise area to be evaluated at the current stage, and acquiring the vegetation index ratio NDVIjt _ pro of the last stage corresponding to each enterprise area to be evaluated, further obtaining the vegetation index change rate NDVItk _ rate according to NDVIit _ pro and NDVIjt _ pro, and the vegetation index ratio NDVIit _ pro and the vegetation index change rate NDVItk _ rate corresponding to each enterprise area to be evaluated in the current stage are used as environmental impact evaluation factors corresponding to each enterprise area to be evaluated so as to evaluate the environmental impact corresponding to each enterprise area to be evaluated in the current stage. The step of calculating the vegetation index change rate NDVItk _ rate is the same as the step of calculating the industrial area change rate Ftk _ rate, and is not repeated herein.
Based on the scheme, after 8-dimensional environmental impact assessment factors of industrial area proportion, residential area proportion, industrial area change rate, residential area change rate, water body index proportion, water body index change rate, vegetation index proportion and vegetation index change rate corresponding to each enterprise area to be assessed at the current stage are obtained, according to the 8-dimensional environmental impact assessment factors, environmental impact scoring is performed on each enterprise area to be assessed, and the objectivity of enterprise environmental risk assessment results is further improved.
In addition, the embodiment also provides an enterprise environmental impact evaluation device. Referring to fig. 5, fig. 5 is a functional module diagram of the enterprise environmental impact evaluation device according to the first embodiment of the present invention.
In this embodiment, the enterprise environmental impact evaluation device is a virtual device, and is stored in the memory 1005 of the enterprise environmental impact evaluation apparatus shown in fig. 1, so as to implement all functions of the enterprise environmental impact evaluation program: the system comprises a remote sensing data acquisition module, a data processing module and a data processing module, wherein the remote sensing data acquisition module is used for acquiring remote sensing data corresponding to each enterprise area to be evaluated in the current stage and constructing an RGB image corresponding to each enterprise area to be evaluated according to the remote sensing data; the system comprises a land type prediction model, a land type prediction model and a database, wherein the land type prediction model is used for inputting RGB images corresponding to enterprise areas to be evaluated into the land type prediction model respectively and outputting land type prediction results corresponding to the enterprise areas to be evaluated; and the method is used for evaluating the environmental impact corresponding to each enterprise area to be evaluated at the current stage according to the land type prediction result corresponding to each enterprise area to be evaluated.
Specifically, the enterprise environmental impact evaluation device includes:
the construction module 10 is configured to acquire remote sensing data corresponding to each enterprise area to be evaluated at the current stage, and construct an RGB image corresponding to each enterprise area to be evaluated according to the remote sensing data;
the prediction module 20 is configured to input the RGB images corresponding to the enterprise areas to be evaluated to the land type prediction model, and output a land type prediction result corresponding to each enterprise area to be evaluated by the land type prediction model;
and the evaluation module 30 is configured to evaluate the environmental impact corresponding to each to-be-evaluated enterprise area at the current stage according to the land type prediction result corresponding to each to-be-evaluated enterprise area.
Further, the building module is further configured to:
respectively carrying out normalization processing on the blue wave band data, the green wave band data and the red wave band data corresponding to each enterprise to be evaluated so as to obtain target blue wave band data, target green wave band data and target red wave band data corresponding to each enterprise to be evaluated;
and constructing an RGB image corresponding to each enterprise to be evaluated according to the target blue waveband data, the target green waveband data and the target red waveband data.
Further, the prediction module is further configured to:
acquiring training remote sensing data corresponding to a plurality of training enterprise areas, and constructing a training RGB image corresponding to each training enterprise area according to the training remote sensing data;
and acquiring an initial model, and training the initial model according to the training RGB image to obtain a land type prediction model.
Further, the prediction module is further configured to:
the receiving unit is used for receiving an instruction sent by the ground information center through a control system, executing a task according to the instruction and acquiring the local data, wherein the local data comprises image data;
and the preprocessing unit is used for preprocessing the local data to obtain local training data.
Further, the prediction module is further configured to:
inputting the training RGB image into an initial model, and outputting a land type prediction result corresponding to the training RGB image by the initial model;
acquiring a real land type corresponding to the training RGB image, and calculating a loss function based on the real land type corresponding to the training RGB image and a land type prediction result corresponding to the training RGB image;
and updating the model parameters of the initial model in a gradient descending manner until the loss function converges or reaches a preset training iteration, and taking the model parameters corresponding to the loss function converging or reaching the preset training iteration as final model parameters to obtain a land type prediction model.
Further, the evaluation module is further configured to:
acquiring the occupied area of the industrial area in the current stage and the occupied area of the resident area in the current stage corresponding to each enterprise area to be evaluated according to the industrial type prediction result and the resident type prediction result corresponding to each enterprise area to be evaluated in the current stage;
determining the occupation ratio of the industrial area and the occupation ratio of the residential area corresponding to each enterprise area to be evaluated at the current stage according to the occupation area of the industrial area at the current stage and the occupation area of the residential area at the current stage corresponding to each enterprise area to be evaluated at the current stage;
and according to the industrial area ratio and the residential area ratio corresponding to each enterprise area to be evaluated in the current stage, evaluating the environmental impact corresponding to each enterprise area to be evaluated.
Further, the evaluation module is further configured to:
acquiring the floor area of an industrial area of the last stage and the floor area of a residential area of the last stage corresponding to each enterprise area to be evaluated;
determining the change rate of the industrial area corresponding to each enterprise area to be evaluated at the current stage according to the occupied area of the industrial area at the current stage corresponding to each enterprise area to be evaluated and the occupied area of the industrial area at the previous stage;
determining the change rate of the residential areas corresponding to the enterprise areas to be evaluated at the current stage according to the occupied areas of the residential areas at the current stage and the occupied areas of the residential areas at the previous stage corresponding to the enterprise areas to be evaluated;
and evaluating the environmental impact corresponding to each enterprise area to be evaluated according to the industrial area change rate corresponding to each enterprise area to be evaluated in the current stage and the residential area change rate corresponding to each enterprise area to be evaluated in the current stage.
In addition, an embodiment of the present invention further provides a computer storage medium, where an enterprise environment influence assessment program is stored on the computer storage medium, and when the enterprise environment influence assessment program is executed by a processor, the steps of the enterprise environment influence assessment method are implemented, which is not described herein again.
Compared with the prior art, the enterprise environment influence assessment method, the enterprise environment influence assessment device, the enterprise environment influence assessment equipment and the computer storage medium are provided by the invention, and the method comprises the following steps: the method comprises the steps of obtaining remote sensing data corresponding to each enterprise area to be evaluated in the current stage, and constructing RGB images corresponding to the enterprise areas to be evaluated according to the remote sensing data; respectively inputting the RGB images corresponding to the enterprise areas to be evaluated into a land type prediction model, and outputting land type prediction results corresponding to the enterprise areas to be evaluated by the land type prediction model; and according to the land type prediction result corresponding to each enterprise area to be evaluated, evaluating the environmental impact corresponding to each enterprise area to be evaluated at the current stage. Compared with the prior art that environment medium data such as atmosphere, water, soil and the like around an enterprise are manually acquired, the method and the system have the advantages that the remote sensing data corresponding to the enterprise area are acquired, the data acquisition cost and the enterprise environment risk assessment difficulty of enterprise environment risk assessment are reduced, and the objectivity of the enterprise environment risk assessment result is improved by utilizing the land type prediction model.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for causing a terminal device to execute the method according to the embodiments of the present invention.
The above description is only for the preferred embodiment of the present invention and is not intended to limit the scope of the present invention, and all equivalent structures or flow transformations made by the present specification and drawings, or applied directly or indirectly to other related arts, are included in the scope of the present invention.

Claims (10)

1. An enterprise environmental impact assessment method, comprising:
the method comprises the steps of obtaining remote sensing data corresponding to each enterprise area to be evaluated in the current stage, and constructing RGB images corresponding to the enterprise areas to be evaluated according to the remote sensing data;
respectively inputting the RGB images corresponding to the enterprise areas to be evaluated into a land type prediction model, and outputting land type prediction results corresponding to the enterprise areas to be evaluated by the land type prediction model;
and according to the land type prediction result corresponding to each enterprise area to be evaluated, evaluating the environmental impact corresponding to each enterprise area to be evaluated at the current stage.
2. The method according to claim 1, wherein the remote sensing data comprises blue wave band data, green wave band data and red wave band data, and the step of constructing the RGB image corresponding to each enterprise to be evaluated according to the remote sensing data comprises the following steps:
respectively carrying out normalization processing on the blue wave band data, the green wave band data and the red wave band data corresponding to each enterprise to be evaluated so as to obtain target blue wave band data, target green wave band data and target red wave band data corresponding to each enterprise to be evaluated;
and constructing an RGB image corresponding to each enterprise to be evaluated according to the target blue waveband data, the target green waveband data and the target red waveband data.
3. The method according to claim 1, wherein the step of inputting the RGB images corresponding to the enterprise areas to be evaluated into the land type prediction model respectively further comprises:
acquiring training remote sensing data corresponding to a plurality of training enterprise areas, and constructing a training RGB image corresponding to each training enterprise area according to the training remote sensing data;
and acquiring an initial model, and training the initial model according to the training RGB image to obtain a land type prediction model.
4. A method according to claim 3, wherein the step of training the initial model from the training RGB image to obtain a land type prediction model comprises:
inputting the training RGB image into an initial model, and outputting a land type prediction result corresponding to the training RGB image by the initial model;
acquiring a real land type corresponding to the training RGB image, and calculating a loss function based on the real land type corresponding to the training RGB image and a land type prediction result corresponding to the training RGB image;
and updating the model parameters of the initial model in a gradient descending manner until the loss function converges or reaches a preset training iteration, and taking the model parameters corresponding to the loss function converging or reaching the preset training iteration as final model parameters to obtain a land type prediction model.
5. The method according to claim 1, wherein the land type prediction results comprise industrial type prediction results and resident type prediction results, and the step of evaluating the environmental impact corresponding to each to-be-evaluated enterprise area at the current stage according to the land type prediction results corresponding to each to-be-evaluated enterprise area comprises:
acquiring the occupied area of the industrial area in the current stage and the occupied area of the resident area in the current stage corresponding to each enterprise area to be evaluated according to the industrial type prediction result and the resident type prediction result corresponding to each enterprise area to be evaluated in the current stage;
determining the occupation ratio of the industrial area and the occupation ratio of the residential area corresponding to each enterprise area to be evaluated at the current stage according to the occupation area of the industrial area at the current stage and the occupation area of the residential area at the current stage corresponding to each enterprise area to be evaluated at the current stage;
and according to the industrial area ratio and the residential area ratio corresponding to each enterprise area to be evaluated in the current stage, evaluating the environmental impact corresponding to each enterprise area to be evaluated.
6. The method according to claim 5, wherein after the step of obtaining the current-stage industrial area floor space and the current-stage residential area floor space corresponding to each enterprise area to be evaluated, the method further comprises:
acquiring the floor area of an industrial area of the last stage and the floor area of a residential area of the last stage corresponding to each enterprise area to be evaluated;
determining the change rate of the industrial area corresponding to each enterprise area to be evaluated at the current stage according to the occupied area of the industrial area at the current stage corresponding to each enterprise area to be evaluated and the occupied area of the industrial area at the previous stage;
determining the change rate of the residential areas corresponding to the enterprise areas to be evaluated at the current stage according to the occupied areas of the residential areas at the current stage and the occupied areas of the residential areas at the previous stage corresponding to the enterprise areas to be evaluated;
and evaluating the environmental impact corresponding to each enterprise area to be evaluated according to the industrial area change rate corresponding to each enterprise area to be evaluated in the current stage and the residential area change rate corresponding to each enterprise area to be evaluated in the current stage.
7. The method according to any one of claims 1 to 6, wherein the remote sensing data comprises green wave band data, red wave band data and near infrared wave band data, and after the step of obtaining the remote sensing data corresponding to each enterprise region to be evaluated at the current stage, the method further comprises the following steps:
acquiring the water body index ratio and the water body index change rate corresponding to each enterprise area to be evaluated in the current stage according to the green wave band data and the near infrared wave band data corresponding to each enterprise area to be evaluated in the current stage;
acquiring the vegetation index proportion and the vegetation index change rate of each enterprise area to be evaluated at the current stage according to the red waveband data and the near infrared waveband data corresponding to each enterprise area to be evaluated at the current stage;
and evaluating the environmental impact corresponding to each enterprise area to be evaluated according to the water body index ratio, the water body index change rate, the vegetation index ratio and the vegetation index change rate corresponding to each enterprise area to be evaluated in the current stage.
8. An enterprise environmental impact assessment apparatus, comprising:
the construction module is used for acquiring remote sensing data corresponding to each enterprise area to be evaluated at the current stage and constructing an RGB image corresponding to each enterprise area to be evaluated according to the remote sensing data;
the prediction module is used for respectively inputting the RGB images corresponding to the enterprise areas to be evaluated into the land type prediction model and outputting land type prediction results corresponding to the enterprise areas to be evaluated by the land type prediction model;
and the evaluation module is used for evaluating the environmental impact corresponding to each enterprise area to be evaluated at the current stage according to the land type prediction result corresponding to each enterprise area to be evaluated.
9. An enterprise environmental impact assessment device, comprising a processor, a memory and an enterprise environmental impact assessment program stored in said memory, said enterprise environmental impact assessment program when executed by said processor implementing the steps of the enterprise environmental impact assessment method according to any one of claims 1-7.
10. A computer storage medium having stored thereon an enterprise environmental impact assessment program, the enterprise environmental impact assessment program when executed by a processor implementing the steps of the enterprise environmental impact assessment method according to any one of claims 1-7.
CN202011081311.7A 2020-10-10 2020-10-10 Enterprise environment influence assessment method, device, equipment and computer storage medium Active CN112200456B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202011081311.7A CN112200456B (en) 2020-10-10 Enterprise environment influence assessment method, device, equipment and computer storage medium
PCT/CN2021/102000 WO2022073361A1 (en) 2020-10-10 2021-06-24 Enterprise environment influence evaluation method, apparatus and device, and computer storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011081311.7A CN112200456B (en) 2020-10-10 Enterprise environment influence assessment method, device, equipment and computer storage medium

Publications (2)

Publication Number Publication Date
CN112200456A true CN112200456A (en) 2021-01-08
CN112200456B CN112200456B (en) 2024-04-30

Family

ID=

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022073361A1 (en) * 2020-10-10 2022-04-14 深圳前海微众银行股份有限公司 Enterprise environment influence evaluation method, apparatus and device, and computer storage medium

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150071528A1 (en) * 2013-09-11 2015-03-12 Digitalglobe, Inc. Classification of land based on analysis of remotely-sensed earth images
CN109581372A (en) * 2018-12-10 2019-04-05 北京航天泰坦科技股份有限公司 A kind of Remote Sensing Monitoring of Ecological Environment method
CN109784633A (en) * 2018-12-13 2019-05-21 重庆金融资产交易所有限责任公司 Device, method and the storage medium of business risk assessment
CN110991430A (en) * 2020-03-02 2020-04-10 中科星图股份有限公司 Ground feature identification and coverage rate calculation method and system based on remote sensing image

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150071528A1 (en) * 2013-09-11 2015-03-12 Digitalglobe, Inc. Classification of land based on analysis of remotely-sensed earth images
CN109581372A (en) * 2018-12-10 2019-04-05 北京航天泰坦科技股份有限公司 A kind of Remote Sensing Monitoring of Ecological Environment method
CN109784633A (en) * 2018-12-13 2019-05-21 重庆金融资产交易所有限责任公司 Device, method and the storage medium of business risk assessment
CN110991430A (en) * 2020-03-02 2020-04-10 中科星图股份有限公司 Ground feature identification and coverage rate calculation method and system based on remote sensing image

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022073361A1 (en) * 2020-10-10 2022-04-14 深圳前海微众银行股份有限公司 Enterprise environment influence evaluation method, apparatus and device, and computer storage medium

Also Published As

Publication number Publication date
WO2022073361A1 (en) 2022-04-14

Similar Documents

Publication Publication Date Title
Kakooei et al. Fusion of satellite, aircraft, and UAV data for automatic disaster damage assessment
Wallace et al. Non‐destructive estimation of above‐ground surface and near‐surface biomass using 3D terrestrial remote sensing techniques
US20160048925A1 (en) Method of determining structural damage using positive and negative tree proximity factors
Cihlar Land cover mapping of large areas from satellites: status and research priorities
Pindozzi et al. Using historical maps to analyze two hundred years of land cover changes: case study of Sorrento peninsula (south Italy)
US20190205287A1 (en) Method of modeling roof age of a structure
US20150317740A1 (en) Computer-implemented method for estimating insurance risk of a structure based on tree proximity
Mokroš et al. Early stage forest windthrow estimation based on unmanned aircraft system imagery
Young et al. Optimizing aerial imagery collection and processing parameters for drone‐based individual tree mapping in structurally complex conifer forests
Gazzea et al. Automated power lines vegetation monitoring using high-resolution satellite imagery
Mohd Zaki et al. Modelling above-ground live trees biomass and carbon stock estimation of tropical lowland Dipterocarp forest: integration of field-based and remotely sensed estimates
Bilous et al. Mapping growing stock volume and forest live biomass: a case study of the Polissya region of Ukraine
Leitão et al. From sample to pixel: multi‐scale remote sensing data for upscaling aboveground carbon data in heterogeneous landscapes
Qin et al. Synergistic application of geometric and radiometric features of LiDAR data for urban land cover mapping
Grunblatt et al. A GIS approach to desertification assessment and mapping
Ayrey et al. Ecologically-based metrics for assessing structure in developing area-based, enhanced forest inventories from LiDAR
Silva et al. treetop: A Shiny‐based application and R package for extracting forest information from LiDAR data for ecologists and conservationists
Lwin et al. Quantitative versus qualitative geospatial data in spatial modelling and decision making
CN112200456A (en) Enterprise environment influence evaluation method, device, equipment and computer storage medium
CN112200456B (en) Enterprise environment influence assessment method, device, equipment and computer storage medium
US20220292619A1 (en) Automated Property Inspections
US20220261713A1 (en) Computer Vision Systems and Methods for Detecting Power Line Hazards from Imagery
José-Silva et al. Improving the validation of ecological niche models with remote sensing analysis
CN113223155A (en) Distance prediction method, device, equipment and medium
Franceschi et al. Identifying treetops from aerial laser scanning data with particle swarming optimization

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant