CN112734579A - Accurate planting risk underwriting method based on satellite remote sensing technology - Google Patents
Accurate planting risk underwriting method based on satellite remote sensing technology Download PDFInfo
- Publication number
- CN112734579A CN112734579A CN202011550747.6A CN202011550747A CN112734579A CN 112734579 A CN112734579 A CN 112734579A CN 202011550747 A CN202011550747 A CN 202011550747A CN 112734579 A CN112734579 A CN 112734579A
- Authority
- CN
- China
- Prior art keywords
- area
- underwriting
- remote sensing
- insurance
- data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000005516 engineering process Methods 0.000 title claims abstract description 16
- 238000012544 monitoring process Methods 0.000 claims abstract description 45
- 238000012795 verification Methods 0.000 claims abstract description 14
- 238000001228 spectrum Methods 0.000 claims abstract description 4
- 230000003993 interaction Effects 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000004458 analytical method Methods 0.000 claims description 9
- 238000009826 distribution Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 238000003066 decision tree Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000005728 strengthening Methods 0.000 abstract description 2
- 241000209094 Oryza Species 0.000 description 15
- 235000007164 Oryza sativa Nutrition 0.000 description 15
- 235000009566 rice Nutrition 0.000 description 15
- 238000002310 reflectometry Methods 0.000 description 8
- 238000012937 correction Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- 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
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
- G06T2207/10036—Multispectral image; Hyperspectral image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Finance (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Agronomy & Crop Science (AREA)
- Evolutionary Biology (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Evolutionary Computation (AREA)
- Primary Health Care (AREA)
- Animal Husbandry (AREA)
- Tourism & Hospitality (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Technology Law (AREA)
- Geometry (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention provides a precise plant insurance underwriting method based on a satellite remote sensing technology, which comprises data acquisition and pretreatment, crop remote sensing monitoring, plotting and underwriting verification; the method introduces a remote sensing technology, forms a set of accurate insurance acceptance method based on the scale of the 'plot' based on multi-source and multi-spectrum remote sensing data, plot data and agricultural insurance acceptance data, forms agricultural insurance 'acceptance according to a graph', remarkably improves the insurance acceptance precision, assists in improving the insurance acceptance coverage, is beneficial to strengthening the management and control of the authenticity of the insurance acceptance, and improves the fine insurance acceptance level of the agricultural insurance.
Description
Technical Field
The invention belongs to the technical field of agricultural insurance, and particularly relates to a planting insurance accurate underwriting method based on a satellite remote sensing technology.
Background
China is a big agricultural country, in 2017, agricultural insurance provides risk guarantee for farmers of 2.13 million households, pays 334 million yuan of claim money, and 4737 million households benefit poor households and disaster-stricken farmers. Agricultural insurance compensation becomes an important capital source for farmers to recover production and rebuild disaster areas after disasters, and the insurance risk guarantee and economic compensation effect are increasingly prominent. However, with the expansion of the scale of agricultural insurance, agricultural insurance operations may face the need of investigation on the types, planting areas, risk characteristics, etc. of crops in the underwriting area before underwriting; when bearing insurance, it is difficult to accurately determine the position and the area of the land for bearing insurance, and the management and control of the risk of bearing insurance are difficult. In the insurance bidding process, due to the fact that the contract data collection is based on the multi-level summary from individuals to villages to towns, the phenomena which are not consistent with the real situation exist, such as false underwriting, false bid increasing, no best insurance, and the like, and insurance units need to be specified.
In recent years, a remote sensing technology provides a new means for large-area and objective monitoring of crops and the like, and provides a chance for monitoring the risk of agricultural insurance underwriting. How to apply the remote sensing technology to improve the objectivity, the fineness and the timeliness of the data of the insurance target becomes an important practical problem which needs to be solved urgently in agricultural insurance risk management. At present, the crop insurance application is developed through a remote sensing technology, and the main mode is to extract the crop planting distribution in a county-area range by using medium-high resolution satellite remote sensing and then compare the crop planting distribution with the underwriting statistical data of three-level administrative units of county and village. The remote sensing application method on the regional scale cannot accurately position the actual planting land of the applicant, and the refinement degree needs to be improved.
Disclosure of Invention
In order to overcome the defects in the prior art, the application provides a planting risk accurate underwriting method based on a satellite remote sensing technology.
Specifically, the invention provides a precise plant risk underwriting method based on a satellite remote sensing technology, which comprises the following steps:
s1 data acquisition and data preprocessing: the data comprises remote sensing image data, underwriting data and land parcel data;
s2 remote sensing monitoring of underwritten crops: analyzing image characteristics of underwritten crops and other crops in a target area by using remote sensing images of multiple periods, constructing a classification decision tree model based on spectrum and texture, and monitoring the spatial distribution and the remote sensing monitoring area of the underwritten crops;
upper graph labeled S3: constructing a man-machine interaction platform for collecting the position of a target, collecting the position of a land parcel of a large household, drawing an area, and associating with the information of a policy of the large household; preferably, the human-computer interaction platform is an APP client;
s4 underwriting: according to the insurance acceptance area, the drawing area and the remote sensing monitoring area of the major household, calculating the relative difference between the drawing area and the insurance acceptance area and the relative difference between the remote sensing monitoring area and the insurance acceptance area, and performing major household checking analysis;
the big household is a farmer whose bearing area is greater than or equal to a set value, and the set value can be adjusted arbitrarily according to actual needs, for example, the set value is 20 mu, 30 mu, 50 mu, 60 mu or 100 mu, and the like, and a specific value is set according to the requirements of an insurance company under normal conditions; in the present invention, it is preferable to mark farmers having a coverage area of 30 acres or more, or 40 acres, or 50 acres as big households.
In the past method, preferably, the remote sensing image data in S1 includes medium and high resolution images, such as sentinel No. 2, high score No. 1, high score No. 2, google image, and the like; wherein the resolution of the high-resolution image is better than 1 meter and comprises blue, green and red wave bands; the resolution of the medium-resolution image is superior to 16 meters and comprises blue, green, red and near-infrared wave bands;
the insurance underwriting data is provided by an agricultural insurance company and comprises information such as names of farmers/institutions, identification numbers/institution codes, the counties, towns, villages and insurance underwriting areas;
the land data is produced by an artificial intelligence technology or provides the certainty right data for the agricultural department.
Further, the data preprocessing in S1 includes performing radiometric calibration, orthometric correction, geometric fine correction, atmospheric correction, mosaic mosaicking, and the like on the remote sensing image data for monitoring and analysis, so that the remote sensing image meets the standard requirements for monitoring;
collecting the underwriting area of the underwriting data in three levels of county, town and village, screening farmers with the underwriting area larger than or equal to a set value, and marking the farmers as big households; the set value is selected as described above.
And processing the plot data to be overlapped with the region data, and adding village and town information to the plot.
Further, the remote sensing monitoring of the underwriting crops in the step S2 further comprises the steps of combining the monitored spatial distribution of the underwriting crops with the remote sensing monitoring area and the data of the plots, carrying out superposition analysis to obtain the planting plots of the underwriting crops, and carrying out area statistics in three levels of county, town and village.
Further, the step of drawing the target in S3, according to the specific flow of farmer identification and salesman drawing, constructs a target position collection human-computer interaction platform, preferably an APP client, collects the position of a field of a farmer (for example, a farmer with a coverage area greater than or equal to 50 mu), associates the position with the policy information of the farmer, and takes a picture to obtain evidence, and includes the following steps:
(S2-1) uploading the insurance policies of all major users through a human-computer interaction platform, wherein the human-computer interaction platform is preferably an APP client; the preferable insurance policy content comprises the name of the farmer house, the identity card number of the farmer house, the county, the town and the village where the farmer house is located and the insurance area information.
(S2-2) the co-insurer points out the planting position of the big household on the spot according to the high-definition satellite map of the target area, optionally including the information mastered by the co-insurer;
the service staff draws the insured land parcel of the major home according to the description and the appointed position of the co-insured person, the man-machine interaction platform (preferably an APP client) displays and records the position and the area of the land parcel in real time, and guides the co-insured person to correct the position and the area of the land parcel through the feedback of the area of the pattern spot; the area of the map spot can be fed back according to the difference between the area of the drawn land parcel and the underwriting area, so that the co-insurer can correct the position and the area of the land parcel by referring to the feedback of the area of the map spot;
finally, preferably, the insured land parcel of the major household is exported and stored in shp format.
Further, in the underwriting verification in S4, preferably, the plot drawn by the dao-home identification is matched with the planting result monitored by remote sensing through intersection correlation analysis, the rice planting plot in the drawn plot is derived, and each attribute field of the dao-home is assigned, and finally, the relative difference between the drawn area and the underwriting area and the relative difference between the remote sensing monitored area and the underwriting are calculated according to the underwriting area, the drawn area and the remote sensing monitored area of the dao-home, wherein the calculation formula is as follows:
relative differenceHZ-CB(area drawn-area guaranteed)/area guaranteed 100%,
relative differenceRS-CBThe remote sensing monitoring area-insurance area/insurance area is 100 percent,
the relative difference between the drawing area and the underwriting area and the relative difference between the remote sensing monitoring area and the underwriting are as follows:
drawing an area<The bearing area is as follows: relative differenceHZ-CB<-10％；
Drawing area ≈ underwriting area: relative difference of 10% or lessHZ-CB≤-10％；
Drawing area > underwriting area: relative differenceHZ-CB＞10％；
Remote sensing area of monitoring<The bearing area is as follows: relative differenceRS-CB<-10％；
The remote sensing monitoring area is approximately equal to the underwriting area: relative difference of 10% or lessRS-CB≤-10％；
Remote sensing monitoring area > underwriting area: relative differenceRS-CB＞10％。
Further, the analysis of the verification of the tenant in S4 includes:
if the drawing area is smaller than the underwriting area, the user is marked as a plot drawing error, and the step returns to S3 for re-pointing and drawing;
if the drawing area is approximately equal to the underwriting area and the remote sensing area is approximately equal to the underwriting area, the verification of the major account is passed;
if the drawing area is approximately equal to the underwriting area and the remote sensing area is smaller than the underwriting area, the large user has false underwriting or wrong identification and needs to check on site;
if the drawing area is larger than the underwriting area and the remote sensing area is approximately equal to the underwriting area, the verification of the major account is passed;
if the drawing area is larger than the underwriting area and the remote sensing area is larger than the underwriting area, the major account is not guaranteed to be the best;
if the drawing area is larger than the underwriting area and the remote sensing area is smaller than the underwriting area, the large user has false underwriting or wrong identification and needs to check on site;
in the above method, further, the method further includes step S5 of coverage rate underwriting and stock calculation, where the calculation formula is:
the coverage rate of the underwriting is the underwriting area/the remote sensing monitoring area multiplied by 100 percent
The expandable surface stock is the remote sensing monitoring area-the insurance area.
For the calculated three-level underwriting coverage rate and the extensible area stock of the county, town and village, if the underwriting coverage rate is 0, the village/town does not underwritten completely;
and if the coverage rate of the underwriting is 0-80%, the coverage rate of the underwriting of the village/town is insufficient, the village/town underwriting is not enough, the remaining underwriting area of the village/town is obtained by calculating the expandable surface stock, and the area where the village/town does not participate in the underwriting is obtained by combining the drawing pattern spot of the major household and the crop planting pattern spot monitored by remote sensing. The expandable surface stock and the un-participated area provide auxiliary support for the underwriting of expanding the surface according to the drawing;
if the coverage rate of underwriting is 80% -100%, the coverage rate of the village/town underwriting meets the requirement;
if the coverage rate of the underwriting is more than 100%, the village/town has false underwriting.
Thus, by looking at the underwriting coverage and the scalable inventory data, the remaining underwriting amount per town/village can be accurately known, as well as whether there is a false underwriting.
It should be clear that the "underwriting area" in the calculation formula mentioned in the present invention refers to the "underwriting area" in the underwriting data collected at S1, preferably, the underwriting area information of the farmers and/or institutions provided by the agricultural insurance company;
the remote sensing monitoring area is obtained by remote sensing monitoring of the insurance-bearing crops S2;
the drawing area indicates the planting position of a large household on site through an assistant and a maintainer according to a high-definition satellite map of a target area optionally comprising information mastered by the assistant and the maintainer; and drawing the insured plot of the major according to the description and the assigned position of the co-insurer by the salesman, and guiding the co-insurer to correct the planting position and the area through the feedback of the area of the pattern spots to obtain the drawn area.
In another aspect of the present invention, a human-computer interaction method for drawing a region for insurance coverage of a large user is further provided, which includes the following steps:
the method comprises the following steps that (1) an assistant insurer identifies the planting position of a large household on site according to a high-definition satellite map of a target area;
the service staff draws the insured plot of the major according to the description and the appointed position of the co-insured staff, the man-machine interaction platform (preferably an APP client) displays and records the position and the area of the plot in real time, and guides the co-insured staff to correct the planting position and the drawn area through the feedback of the area of the pattern spots;
and when the planting positions and the drawing areas provided by the co-insured member and the service member are basically consistent, exporting the insured land parcel of the large household, and storing the insured land parcel in a shp format.
The method provided by the invention forms a set of accurate insurance acceptance method based on the size of the 'plot' by introducing a remote sensing technology and based on multi-source and multi-spectrum remote sensing data, plot data and agricultural insurance acceptance data, forms 'per-map insurance acceptance' of the agricultural insurance, further improves the insurance acceptance precision and the promotion of the insurance acceptance coverage, is beneficial to strengthening the management and control of the authenticity of the insurance acceptance, and can obviously promote the fine insurance acceptance level of the agricultural insurance.
The method provided by the invention realizes the spatialization of the insurance target object, grasps the actual planting position and planting stock of the target, finds out the coverage rate of the insurance acceptance and the area of the surface capable of being expanded, and provides the auxiliary support of expanding the surface according to the drawing. And drawing a plot, an underwriting plot and comparing the remote sensing monitoring areas, thus realizing underwriting according to a graph and avoiding false underwriting.
Drawings
The technical solution of the present application is further explained below with reference to the drawings and the embodiments.
FIG. 1 is a flow chart of a planting risk accurate underwriting technology based on a satellite remote sensing technology;
FIG. 2 is a flow chart of human-computer interaction user insurance block assignment drawing.
Detailed Description
In order to more clearly illustrate the technical solutions and advantages of the present invention, the present invention is further described below with reference to examples, and it should be noted that the embodiments and features in the embodiments may be combined with each other in the present application without conflict.
Examples
The technical scheme of the invention is explained and explained below by taking the accurate underwriting of rice in Jinhu county as an example.
The implementation flow of this embodiment is shown in fig. 1, and the details of the implementation of each part are as follows.
Firstly, the remote sensing image in 6-8 months is used for identifying the planting area and the planting area of the rice, and the area is counted according to the town and the village. And (4) performing superposition analysis on the recognized rice and plot data to obtain a rice planting plot, and comparing and checking the rice planting plot with the result of the upper graph of the major account mark, namely the area of the major account covered plot to obtain the farmers who pass the checking and should not be fully protected and need to check on site. The method specifically comprises the following steps:
(1) data acquisition and preprocessing:
(1-1) data acquisition
The data comprises remote sensing satellite images of Jinhu county, administrative region demarcation lines, farmer insurance acceptance information and land parcel data.
The remote sensing image data comprises medium and high resolution images. The high-resolution image is high resolution No. 2, the resolution is 0.8 m, and blue, green and red wave bands are formed; the middle resolution image is high resolution No. 1, the resolution is 16 meters, the blue, green, red and near infrared wave bands are adopted, the image time phase is 7 months, the cloud cover is less than 10%, and the whole Jinhu county is covered.
The administrative region demarcation line comprises a town and village vector surface map layer;
the peasant household underwriting information comprises a name of a peasant household, an identity card number, the county, the town and the village where the peasant household underwriting information is located and an underwriting area;
the plot data comprises an authorized plot acquired by an agricultural department;
(1-2) data processing:
and carrying out operations such as radiometric calibration, orthorectification, geometric fine correction, atmospheric correction, mosaic splicing and the like on the remote sensing image, so that the remote sensing image meets the standard requirement of monitoring.
And (3) underwriting data processing: and summarizing the underwriting area of the underwriting data in three levels of county, town and village, screening farmers with the underwriting area of more than or equal to 50 mu, and marking the farmers as big households.
Land block data processing: adding village and town information to land parcel in superposition with region data
(2) Remote sensing monitoring of rice
A decision tree classification model is established by analyzing the spectral and textural features of the rice and other ground objects by using the remote sensing image in 7 months in 2020, and the planting distribution of the rice is extracted.
The specific process of rice identification comprises the following steps:
s1, calculating the NDVI of the image, setting the NDVI to be more than 0.6, and judging if the NDVI is true, then performing s 2; the NDVI is a normalized vegetation index, and the calculation formula is a ratio of the difference between the reflectivity of the near infrared band and the reflectivity of the red band to the sum of the reflectivity of the near infrared band and the reflectivity of the red band;
s2, setting the condition B4>0.28 and B2<0.1, if true, carrying out judgment of s 3; wherein, B4 is the reflectivity of near infrared band, B2 is the reflectivity of green band;
s3, setting the condition DVI >150, and if true, identifying the pixel as rice; wherein, DVI is a difference value vegetation index, and the calculation formula is the difference between the reflectivity of the blue band and the reflectivity of the green band;
s4 merging and deriving all rice pixels
And overlapping the identified rice pixel result with the right-confirming land parcel to obtain the rice planting land parcel data, and counting the rice planting land parcels in counties and towns.
(3) Drawing on large house label
According to the specific flow of farmer identification and salesman drawing, a target position acquisition APP client is constructed, the land position of a large household (farmer with the underwriting area of more than or equal to 50 mu) is acquired, and the land position is associated with the policy information of the large household, photographed and collected for evidence and the like.
As shown in fig. 2, firstly, the policy of all major households is uploaded on the APP client, and the policy content includes information of names of the farmers, identification numbers of the farmers, counties, towns, villages, insurance coverage and the like of the farmers.
Then, the co-insurer identifies the planting position of the big household on site according to the high-definition satellite map and the situation mastered by the co-insurer; and drawing the insured land parcel of the major house by the service staff through the description and the appointed position of the co-insurer, displaying and recording the position and the area of the land parcel in real time by the APP client, and guiding the co-insurer to correct the planting position and the area through the feedback of the area of the pattern spots.
And finally, exporting the insured land parcel of the major household and storing the insured land parcel in an shp format.
(4): underwriting verification
And finally, calculating the relative difference between the drawn area and the underwriting area and the relative difference between the remote sensing area and the underwriting according to the underwriting area, the drawn area and the remote sensing area of the major. The calculation formula is as follows:
relative difference HZ-CB (plotted area-guaranteed area)/guaranteed area 100%,
relative difference RS-CB (remote sensing monitoring area-insurance area)/insurance area 100%,
the relative difference between the drawing area and the underwriting area and the relative difference between the remote sensing monitoring area and the underwriting are as follows:
area < underwriting area: relative difference HZ-CB < -10%;
drawing area ≈ underwriting area: the relative difference HZ-CB is more than or equal to 10 percent and less than or equal to-10 percent;
drawing area > underwriting area: the relative difference HZ-CB is more than 10 percent;
remote sensing monitoring area < underwriting area: relative difference RS-CB < -10%;
the remote sensing monitoring area is approximately equal to the underwriting area: the relative difference RS-CB is more than or equal to 10 percent and less than or equal to-10 percent;
remote sensing monitoring area > underwriting area: the relative difference RS-CB was > 10%.
Underwriting verification analysis:
if the drawing area is smaller than the underwriting area, marking the user as a plot drawing error, and returning to perform re-pointing and drawing;
if the drawing area is approximately equal to the underwriting area and the remote sensing area is approximately equal to the underwriting area, the verification of the major account is passed;
if the drawing area is approximately equal to the underwriting area and the remote sensing area is smaller than the underwriting area, the large user has false underwriting or wrong identification and needs to check on site;
if the drawing area is larger than the underwriting area and the remote sensing area is approximately equal to the underwriting area, the verification of the major account is passed;
if the drawing area is larger than the underwriting area and the remote sensing area is larger than the underwriting area, the major account is not guaranteed to be the best;
if the drawing area is larger than the underwriting area and the remote sensing area is smaller than the underwriting area, the large user has false underwriting or wrong identification and needs to check on site;
and respectively counting the number of the users who are subjected to re-identification and drawing, pass verification, false underwriting or identification errors and are not subjected to complete underwriting and the underwriting area, and calculating the number of the users and the area to obtain the verification passing rate.
(5): coverage, scalable inventory calculation
And respectively calculating the underwriting coverage rate and the extensible inventory by utilizing the three-level summarized remote sensing monitoring area and underwriting area in county, town and village. The calculation formula is as follows:
the coverage rate of the underwriting is the underwriting area/the remote sensing area multiplied by 100 percent,
the expandable surface stock is the remote sensing area-the bearing area;
for the calculated three-level underwriting coverage rate of county and town and the expandable surface stock,
if the coverage rate of underwriting is 0, the village/town is not underwritten completely;
if the coverage rate of underwriting is 0-80%, the coverage rate of the village/town underwriting is insufficient, and the village/town underwriting is not fully underwritten; and calculating the expandable surface stock to obtain the residual sustainable area of the village/town, and combining the drawing pattern spots of the large household with the crop planting pattern spots monitored by remote sensing to obtain the area where the planting is not in insurance. The expandable surface stock and the un-participated area provide auxiliary support for the underwriting of expanding the surface according to the drawing;
if the coverage rate of underwriting is 80% -100%, the coverage rate of the village/town underwriting meets the requirement;
if the coverage rate of the underwriting is more than 100%, the village/town has false underwriting.
By the method, the spatialization of the insurance target object is realized, the actual planting position and the planting stock of the target object are mastered, the insurance coverage rate is found out, the area of the surface can be expanded, and the auxiliary support of expanding the surface according to the drawing is provided. And drawing a plot, an underwriting plot and comparing the remote sensing monitoring areas, thus realizing underwriting according to a graph and avoiding false underwriting.
In light of the foregoing description of the preferred embodiments according to the present application, it is to be understood that various changes and modifications may be made without departing from the spirit and scope of the invention. The technical scope of the present application is not limited to the contents of the specification, and must be determined according to the scope of the claims.
Claims (10)
1. A planting risk accurate underwriting method based on a satellite remote sensing technology is characterized by comprising the following steps:
s1 data acquisition and data preprocessing: the data comprises remote sensing image data, underwriting data and land parcel data;
s2 remote sensing monitoring of underwritten crops: analyzing image characteristics of underwritten crops and other crops in a target area by using remote sensing images of multiple periods, constructing a classification decision tree model based on spectrum and texture, and monitoring the spatial distribution and the remote sensing monitoring area of the underwritten crops;
upper graph labeled S3: constructing a man-machine interaction platform for collecting the position of a target, collecting the position of a land parcel of a large household, drawing an area, and associating with the information of a policy of the large household;
s4 underwriting: according to the insurance acceptance area, the drawing area and the remote sensing monitoring area of the major households, calculating the relative difference between the drawing area and the insurance acceptance area and the relative difference between the remote sensing monitoring area and the insurance acceptance area, and performing major household checking analysis;
the big household is a farmer with the insurance-bearing area larger than or equal to a set value;
preferably, the human-computer interaction platform in S3 is an APP client.
2. The method of claim 1, wherein the remotely sensed image data in S1 comprises medium and high resolution images, wherein the high resolution image has a resolution better than 1 meter, and comprises blue, green and red bands; the resolution of the medium-resolution image is superior to 16 meters and comprises blue, green, red and near-infrared wave bands;
the insurance underwriting data is provided by an agricultural insurance company and comprises a farmer/institution name, an identity card number/institution code, and information of a country, a town, a village and an underwriting area;
the land data is produced by an artificial intelligence technology or provides the certainty right data for the agricultural department.
3. The method according to claim 1, wherein the data preprocessing in S1 includes performing radiometric calibration, orthometric calibration, geometric fine calibration, atmospheric calibration, or mosaic stitching on the remote sensing image data to make the remote sensing image meet the standard requirements for monitoring;
collecting the underwriting area of the underwriting data in three levels of county, town and village, screening farmers with the underwriting area larger than or equal to a set value, and marking the farmers as big households;
and processing the plot data to be overlapped with the region data, and adding village and town information to the plot.
4. The method as claimed in claim 1, wherein the remote sensing monitoring of the insurance crops in S2 further comprises combining the monitored spatial distribution of the insurance crops with the data of the area and the plot, performing superposition analysis to obtain the planting plot of the insurance crops, and performing area statistics on the three levels of county, town and village.
5. The method according to claim 1, wherein the human-computer interaction platform for constructing location collection of targets, collecting the position of the land parcel of the large household, drawing the area, and associating with the information of the large household policy, in S3, comprises the following steps:
(S2-1) uploading the insurance policies of all the major users through the man-machine interaction platform;
(S2-2) the co-insurer points out the planting position of the big household on the spot according to the high-definition satellite map of the target area, optionally including the information mastered by the co-insurer; the service staff draws the insured land parcel of the major home according to the description and the appointed position of the co-insured person, the man-machine interaction platform displays and records the position and the area of the land parcel in real time, and the co-insured person is guided to correct the position and the area of the land parcel through the feedback of the area of the map spot;
preferably, the human-computer interaction platform is an APP client.
6. The method according to claim 5, wherein (S2-1) the policy contents include names of farmers, identification numbers of farmers, counties, towns, villages and insurance coverage information.
7. The method of claim 1, wherein the calculating of the relative difference between the mapped area and the underwriting area and the relative difference between the telemetrically monitored area and the underwriting in S4 is performed according to the following formula:
relative differenceHZ-CB(area drawn-area guaranteed)/area guaranteed 100%,
relative differenceRS-CBThe remote sensing monitoring area-insurance area/insurance area is 100 percent,
the relative difference between the drawing area and the underwriting area and the relative difference between the remote sensing monitoring area and the underwriting are as follows:
drawing an area<The bearing area is as follows: relative differenceHZ-CB<-10％；
Drawing area ≈ underwriting area: relative difference of 10% or lessHZ-CB≤-10％；
Drawing area > underwriting area: relative differenceHZ-CB＞10％；
Remote sensing area of monitoring<The bearing area is as follows: relative differenceRS-CB<-10％；
The remote sensing monitoring area is approximately equal to the underwriting area: relative difference of 10% or lessRS-CB≤-10％；
Remote sensing monitoring area > underwriting area: relative differenceRS-CB＞10％。
8. The method of claim 1, wherein the analysis of the account verification in S4 comprises:
if the drawing area is smaller than the underwriting area, the user is marked as a plot drawing error, and the step returns to S3 for re-pointing and drawing;
if the drawing area is approximately equal to the underwriting area and the remote sensing area is approximately equal to the underwriting area, the verification of the major account is passed;
if the drawing area is approximately equal to the underwriting area and the remote sensing area is smaller than the underwriting area, the large user has false underwriting or wrong identification and needs to check on site;
if the drawing area is larger than the underwriting area and the remote sensing area is approximately equal to the underwriting area, the verification of the major account is passed;
if the drawing area is larger than the underwriting area and the remote sensing area is larger than the underwriting area, the major account is not guaranteed to be the best;
if the drawing area is larger than the underwriting area and the remote sensing area is smaller than the underwriting area, the large user has false underwriting or wrong identification and needs to check on site.
9. The method of claim 1, further comprising S5 underwriting coverage, scalable inventory calculation, wherein the calculation formula is:
the coverage rate of the underwriting is the underwriting area/the remote sensing monitoring area multiplied by 100 percent
The expandable surface stock is the remote sensing monitoring area-the insurance area.
10. A human-computer interaction large-user insurance-bearing land block recognition drawing method is characterized by comprising the following steps:
the method comprises the following steps that an assistant insurer points out the planting position of a large household on site according to a high-definition satellite map of the underwriting crops in a target area;
the service staff draws the insured plot of the major according to the description and the identification site of the co-insured staff, displays and records the position and the area of the plot in real time, and guides the co-insured staff to correct the planting position and the drawn area through the feedback of the area of the pattern spots and the description of the image;
and when the planting positions and the drawing areas provided by the co-insured member and the service member are basically consistent, exporting the insured land parcel of the large household, and storing the insured land parcel in a shp format.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011550747.6A CN112734579A (en) | 2020-12-24 | 2020-12-24 | Accurate planting risk underwriting method based on satellite remote sensing technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011550747.6A CN112734579A (en) | 2020-12-24 | 2020-12-24 | Accurate planting risk underwriting method based on satellite remote sensing technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112734579A true CN112734579A (en) | 2021-04-30 |
Family
ID=75615230
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011550747.6A Pending CN112734579A (en) | 2020-12-24 | 2020-12-24 | Accurate planting risk underwriting method based on satellite remote sensing technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112734579A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113298666A (en) * | 2021-07-27 | 2021-08-24 | 太平财产保险有限公司 | Mobile operation platform system for financial insurance and agricultural insurance |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107861133A (en) * | 2017-10-23 | 2018-03-30 | 北斗卫星导航科技邢台有限公司 | Intelligent information system is protected in a kind of Big Dipper agriculture |
| CN107966709A (en) * | 2017-11-15 | 2018-04-27 | 成都天麒科技有限公司 | A kind of plant protection operation method based on laser radar mapping |
| CN109241922A (en) * | 2018-09-18 | 2019-01-18 | 安徽阡陌网络科技有限公司 | Guarantor's method is precisely tested in a kind of agricultural insurance based on remotely-sensed data and digital field |
| CN110930260A (en) * | 2019-10-30 | 2020-03-27 | 中国银行保险信息技术管理有限公司 | Block-level full-core full-verification method and device for planting industry insurance mark |
-
2020
- 2020-12-24 CN CN202011550747.6A patent/CN112734579A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107861133A (en) * | 2017-10-23 | 2018-03-30 | 北斗卫星导航科技邢台有限公司 | Intelligent information system is protected in a kind of Big Dipper agriculture |
| CN107966709A (en) * | 2017-11-15 | 2018-04-27 | 成都天麒科技有限公司 | A kind of plant protection operation method based on laser radar mapping |
| CN109241922A (en) * | 2018-09-18 | 2019-01-18 | 安徽阡陌网络科技有限公司 | Guarantor's method is precisely tested in a kind of agricultural insurance based on remotely-sensed data and digital field |
| CN110930260A (en) * | 2019-10-30 | 2020-03-27 | 中国银行保险信息技术管理有限公司 | Block-level full-core full-verification method and device for planting industry insurance mark |
Non-Patent Citations (2)
| Title |
|---|
| 中国保险信息技术管理有限责任公司战略规划部: "全国农险平台建设持续推进农业保险数据应用价值逐步显现", 金融电子化, no. 09, 15 September 2017 (2017-09-15) * |
| 于烨堃: ""3S"技术在黑龙江省农业保险中的应用现状及建议――以阳光农业相互保险公司为例", 中国市场, no. 35, 18 December 2019 (2019-12-18) * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113298666A (en) * | 2021-07-27 | 2021-08-24 | 太平财产保险有限公司 | Mobile operation platform system for financial insurance and agricultural insurance |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Newton | Forest ecology and conservation: a handbook of techniques | |
| Mondal et al. | A reporting framework for Sustainable Development Goal 15: Multi-scale monitoring of forest degradation using MODIS, Landsat and Sentinel data | |
| Meneguzzo et al. | Mapping trees outside forests using high-resolution aerial imagery: a comparison of pixel-and object-based classification approaches | |
| CN110930260B (en) | Block-level full-core full-verification method and device for planting industry insurance mark | |
| Wang et al. | Using GF-2 imagery and the conditional random field model for urban forest cover mapping | |
| Huang et al. | Using satellite imagery and deep learning to evaluate the impact of anti-poverty programs | |
| US20120288163A1 (en) | System for identifying sustainable geographical areas by remote sensing techniques and method thereof | |
| Kocur-Bera | Data compatibility between the Land and Building Cadaster (LBC) and the Land Parcel Identification System (LPIS) in the context of area-based payments: A case study in the Polish Region of Warmia and Mazury | |
| Schumacher et al. | Wall-to-wall tree type classification using airborne lidar data and CIR images | |
| Nagendra et al. | Technology Assessment Using Satellite Big Data Analytics for India's Agri-Insurance Sector | |
| Ardila et al. | Quantification of crown changes and change uncertainty of trees in an urban environment | |
| Aynekulu et al. | Review of methodologies for land degradation neutrality baselines: Sub-national case studies from Costa Rica and Namibia | |
| CN112734579A (en) | Accurate planting risk underwriting method based on satellite remote sensing technology | |
| Farag et al. | Quantifying urban landscape water conservation potential using high resolution remote sensing and GIS | |
| Naik et al. | Using geospatial technology to strengthen data systems in developing countries: The case of agricultural statistics in India | |
| González‐Orozco et al. | Taxonomic identification of Amazonian tree crowns from aerial photography | |
| Bernasconi et al. | Automatic extraction of land cover statistics from satellite imagery by deep learning | |
| Um | Comparative evaluation of forestry carbon baseline between North Korea and Mongolia from Google Earth | |
| Siljander et al. | A predictive modelling technique for human population distribution and abundance estimation using remote-sensing and geospatial data in a rural mountainous area in Kenya | |
| Walker et al. | Technical guidance on development of a REDD+ reference level | |
| Azzari et al. | Understanding the requirements for surveys to support satellite-based crop type mapping | |
| Dubovyk et al. | Object-based cropland degradation identification: a case study in Uzbekistan | |
| Li et al. | Performance of GEDI data combined with Sentinel-2 images for automatic labelling of wall-to-wall corn mapping | |
| Dinku et al. | Designing Index-Based Weather Insurance for Farmers in Adi Ha, Ethiopia: Report to OXFAM America, July 2009 | |
| Stephenson et al. | Compiling a land audit in large rural areas: Results from the methodology applied in the non-urban areas of the Matzikama municipal area |
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 |