CN110502997A - Method and relevant device are surveyed in agricultural insurance based on artificial intelligence - Google Patents
Method and relevant device are surveyed in agricultural insurance based on artificial intelligence Download PDFInfo
- Publication number
- CN110502997A CN110502997A CN201910665932.0A CN201910665932A CN110502997A CN 110502997 A CN110502997 A CN 110502997A CN 201910665932 A CN201910665932 A CN 201910665932A CN 110502997 A CN110502997 A CN 110502997A
- Authority
- CN
- China
- Prior art keywords
- insurance
- target
- agricultural
- accepting
- artificial intelligence
- 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 84
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 70
- 238000004611 spectroscopical analysis Methods 0.000 claims abstract description 84
- 230000003595 spectral effect Effects 0.000 claims abstract description 59
- 238000001228 spectrum Methods 0.000 claims abstract description 43
- 238000000701 chemical imaging Methods 0.000 claims abstract description 20
- 238000000605 extraction Methods 0.000 claims abstract description 18
- 238000010521 absorption reaction Methods 0.000 claims description 56
- 238000012549 training Methods 0.000 claims description 53
- 239000000523 sample Substances 0.000 claims description 48
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 29
- 229910001868 water Inorganic materials 0.000 claims description 27
- 239000000284 extract Substances 0.000 claims description 15
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 claims description 14
- 229930002875 chlorophyll Natural products 0.000 claims description 13
- 235000019804 chlorophyll Nutrition 0.000 claims description 13
- ATNHDLDRLWWWCB-AENOIHSZSA-M chlorophyll a Chemical compound C1([C@@H](C(=O)OC)C(=O)C2=C3C)=C2N2C3=CC(C(CC)=C3C)=[N+]4C3=CC3=C(C=C)C(C)=C5N3[Mg-2]42[N+]2=C1[C@@H](CCC(=O)OC\C=C(/C)CCC[C@H](C)CCC[C@H](C)CCCC(C)C)[C@H](C)C2=C5 ATNHDLDRLWWWCB-AENOIHSZSA-M 0.000 claims description 13
- 238000003860 storage Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 10
- 238000009499 grossing Methods 0.000 claims description 9
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 7
- 229910002092 carbon dioxide Inorganic materials 0.000 claims description 7
- 239000001569 carbon dioxide Substances 0.000 claims description 7
- 229910052760 oxygen Inorganic materials 0.000 claims description 7
- 239000001301 oxygen Substances 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 5
- 238000011478 gradient descent method Methods 0.000 claims description 4
- 210000005036 nerve Anatomy 0.000 claims description 3
- 238000002834 transmittance Methods 0.000 claims description 3
- 241000208340 Araliaceae Species 0.000 claims 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims 1
- 235000003140 Panax quinquefolius Nutrition 0.000 claims 1
- 235000008434 ginseng Nutrition 0.000 claims 1
- 239000000203 mixture Substances 0.000 claims 1
- 230000006870 function Effects 0.000 description 12
- 238000009313 farming Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 241000894007 species Species 0.000 description 5
- 238000012360 testing method Methods 0.000 description 4
- 240000008042 Zea mays Species 0.000 description 3
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 description 3
- 235000002017 Zea mays subsp mays Nutrition 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 235000005822 corn Nutrition 0.000 description 3
- 244000068988 Glycine max Species 0.000 description 2
- 235000010469 Glycine max Nutrition 0.000 description 2
- 240000007594 Oryza sativa Species 0.000 description 2
- 235000007164 Oryza sativa Nutrition 0.000 description 2
- 244000061456 Solanum tuberosum Species 0.000 description 2
- 235000002595 Solanum tuberosum Nutrition 0.000 description 2
- 241000209140 Triticum Species 0.000 description 2
- 235000021307 Triticum Nutrition 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000002633 protecting effect Effects 0.000 description 2
- 238000000985 reflectance spectrum Methods 0.000 description 2
- 235000009566 rice Nutrition 0.000 description 2
- 238000012271 agricultural production Methods 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- 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
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- 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
- 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
- G06V10/58—Extraction of image or video features relating to hyperspectral data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/194—Terrestrial scenes using hyperspectral data, i.e. more or other wavelengths than RGB
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Strategic Management (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Finance (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Accounting & Taxation (AREA)
- General Business, Economics & Management (AREA)
- Biomedical Technology (AREA)
- Marketing (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Mining & Mineral Resources (AREA)
- Human Resources & Organizations (AREA)
- Marine Sciences & Fisheries (AREA)
- Primary Health Care (AREA)
- Animal Husbandry (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Agronomy & Crop Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Development Economics (AREA)
- Technology Law (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention belongs to disaggregated model technical fields, a kind of agricultural insurance based on artificial intelligence is provided and surveys method and relevant device, this method comprises: surveying in task the geographical location information extracted wait survey target of accepting insurance from the agricultural insurance when receiving agricultural insurance and surveying task；According to the geographical location information, the airborne hyperspectral imaging spectrum system acquisition spectroscopic data wait survey target of accepting insurance is controlled；The spectroscopic data wait survey target of accepting insurance is pre-processed；From pretreated described wait survey in the spectroscopic data for accepting insurance target, the extraction spectral signature wait survey target of accepting insurance；The spectral signature wait survey target of accepting insurance is input in trained crop type identification model and is analyzed, it is described wait survey which kind of crops is target of accepting insurance belong to obtain, as surveying result.That the present invention realizes is convenient, efficient, quickly and accurately agricultural insurance is surveyed.
Description
Technical field
The present invention relates to disaggregated model technical fields more particularly to a kind of agricultural insurance based on artificial intelligence to survey method
And relevant device.
Background technique
Agricultural insurance, refer to insurance institution according to agricultural insurance contract, to insured people in agricultural production process because protecting
Property loss caused by the accidents such as the natural calamity that dangerous target is arranged undertakes the insurance activity of compensation insurance gold responsibility.Mesh
Before, in accepting insurance the stage for agricultural insurance, to avoid falseness from accepting insurance, insurance institution needs that the personnel of surveying is sent to survey, with core
The authenticity for the target of accepting insurance that argument guarantor provides also needs however, the mode for sending the personnel of surveying to be surveyed, takes time and effort
The cooperation of peasant household is wanted, difficulty is larger.
Summary of the invention
The main purpose of the present invention is to provide a kind of agricultural insurances based on artificial intelligence to survey method and relevant device,
It aims to solve the problem that the mode for sending the personnel of surveying to be surveyed, takes time and effort, it is also necessary to which the cooperation of peasant household, the biggish technology of difficulty are asked
Topic.
To achieve the above object, the present invention provides a kind of agricultural insurance based on artificial intelligence and surveys method, described to be based on
The agricultural insurance of artificial intelligence survey method the following steps are included:
When receiving agricultural insurance and surveying task, surveys in task and extracted wait survey target of accepting insurance from the agricultural insurance
Geographical location information；
According to the geographical location information, it is described wait survey target of accepting insurance to control the acquisition of airborne hyperspectral imaging spectrum system
Spectroscopic data；
The spectroscopic data wait survey target of accepting insurance is pre-processed；
From pretreated described wait survey in the spectroscopic data for accepting insurance target, the extraction light wait survey target of accepting insurance
Spectrum signature；
The spectral signature wait survey target of accepting insurance is input in trained crop type identification model and is carried out
Analysis, it is described wait survey which kind of crops is target of accepting insurance belong to obtain, as surveying result.
Optionally, the geographical location information is geographical coordinate,
It is described according to the geographical location information, control that the acquisition of airborne hyperspectral imaging spectrum system is described to accept insurance wait survey
The step of spectroscopic data of target includes:
Respectively on the four direction of the geographical coordinate, control airborne hyperspectral imaging spectrum system probe vertical to
Under, it is measured at the preset height wait survey target canopy of accepting insurance, records several spectrum in each direction, constitute institute
State the spectroscopic data wait survey target of accepting insurance.
Optionally, the pretreated step of spectroscopic data progress to described wait survey target of accepting insurance includes:
Smoothing denoising processing is carried out to the spectroscopic data wait survey target of accepting insurance using filtering fitting process；
From smoothing denoising, that treated is described wait survey in the spectroscopic data for accepting insurance target, rejects the strong absorption bands of water；
Average treatment is done wait survey the spectroscopic data for target of accepting insurance described in the strong absorption bands of water to eliminating.
Optionally, described from pretreated described wait survey in the spectroscopic data for accepting insurance target, it extracts described wait survey
The step of spectral signature for target of accepting insurance includes:
The pretreated spectrum number wait survey target of accepting insurance is analyzed using Spectroscopy differential method and continuum removal method
According to determine spectral signature region from the pretreated spectroscopic data wait survey target of accepting insurance；
Differential characteristics and Absorption Characteristics are extracted from the spectral signature region, obtain the Spectral Properties wait survey target of accepting insurance
Sign.
Optionally, the spectral signature region includes the region Lv Feng, the region Hong Gu, red border region, the suction of blue light region chlorophyll
Take-up, red light district chlorophyll absorption band, water weak absorbing band, water and the narrow absorption band of oxygen and water and carbon dioxide strong absorption band,
It is described to extract differential characteristics from the spectral signature region and the step of Absorption Characteristics includes:
Differential characteristics are extracted from the region Lv Feng, the region Hong Gu and the red border region；
From the blue light region chlorophyll absorption band, the red light district chlorophyll absorption band, the water weak absorbing band, the water
Absorption Characteristics are extracted with the narrow absorption band of oxygen and the water and carbon dioxide strong absorption band.
Optionally, described when receiving agricultural insurance and surveying task, surveyed in task from the agricultural insurance extract to
Before the step of surveying the geographical location information for target of accepting insurance, comprising:
The spectroscopic data of several crops is obtained, and the spectroscopic data of every kind of crops is pre-processed respectively；
Respectively from the spectroscopic data of pretreated every kind of crops, spectral signature is extracted as training sample, and root
Training sample set is constructed according to the training sample；
According to training sample set training crop type identification model, trained crop type identification mould is obtained
Type.
Optionally, described according to training sample set training crop type identification model, obtain trained farming
The step of species type identification model includes:
The training sample set is normalized；
The crop type identification model based on reverse transmittance nerve network BPNN is created, and initializes the farming species
The parameter of type identification model；
Training sample set after normalized is input in the crop type identification model, to output before obtaining
With reversed output；
Using gradient descent method, the crop type identification model is updated according to forward direction output and reversed output
Parameter obtains trained crop type identification model.
In addition, to achieve the above object, the present invention also provides the agricultural insurances based on artificial intelligence to survey device, the base
Surveying device in the agricultural insurance of artificial intelligence includes:
Acquisition module, for controlling described in the acquisition of airborne hyperspectral imaging spectrum system according to the geographical location information
Wait survey the spectroscopic data for target of accepting insurance；
Preprocessing module, for being pre-processed to the spectroscopic data wait survey target of accepting insurance；
Spectra feature extraction module, for extracting from pretreated described wait survey in the spectroscopic data for accepting insurance target
The spectral signature wait survey target of accepting insurance；
Analysis module is known for the spectral signature wait survey target of accepting insurance to be input to trained crop type
It is analyzed in other model, it is described wait survey which kind of crops is target of accepting insurance belong to obtain, as surveying result.
In addition, to achieve the above object, the present invention also provides a kind of agricultural insurances based on artificial intelligence to survey equipment, institute
It states the agricultural insurance based on artificial intelligence and surveys equipment and include processor, memory and be stored on the memory and can
The agricultural insurance exploration procedure based on artificial intelligence executed by the processor, wherein the agricultural based on artificial intelligence is protected
When dangerous exploration procedure is executed by the processor, realize that the step of method is surveyed in the above-mentioned agricultural insurance based on artificial intelligence such as
Suddenly.
In addition, to achieve the above object, it is described computer-readable the present invention also provides a kind of computer readable storage medium
The agricultural insurance exploration procedure based on artificial intelligence is stored on storage medium, wherein the agricultural insurance based on artificial intelligence
When exploration procedure is executed by processor, the step of surveying method such as the above-mentioned agricultural insurance based on artificial intelligence is realized.
The present invention provides a kind of agricultural insurance based on artificial intelligence and surveys method and relevant device, when receiving agriculture guarantor
When task is surveyed in danger, the geographical location information that extracts wait survey accept insurance target is surveyed in task first from the agricultural insurance, then
According to the geographical location information of extraction, controls airborne hyperspectral imaging spectrum system and acquires wait survey target spectroscopic data of accepting insurance,
Pre-processing wait survey target spectroscopic data of accepting insurance to acquisition again, and extract from pretreated spectroscopic data wait survey
The spectral signature wait survey target of accepting insurance of extraction is input to trained crop type and known by the spectral signature for target of accepting insurance
It is analyzed in other model, to obtain wait survey which kind of crops is target of accepting insurance belong to, is based on instruction as surveying as a result, realizing
The crop type identification model perfected, which is treated, surveys target of accepting insurance and is analyzed, and can significantly improve the identification essence of crop type
Degree, realizes that convenient, efficient, quickly and accurately agricultural insurance is surveyed.
Detailed description of the invention
Fig. 1 is the hardware configuration that equipment is surveyed in the agricultural insurance based on artificial intelligence involved in the embodiment of the present invention
Schematic diagram；
Fig. 2 is that the present invention is based on the flow diagrams that method first embodiment is surveyed in the agricultural insurance of artificial intelligence；
Fig. 3 is that the present invention is based on the flow diagrams that method second embodiment is surveyed in the agricultural insurance of artificial intelligence；
Fig. 4 is that the present invention is based on the functional block diagrams that device first embodiment is surveyed in the agricultural insurance of artificial intelligence.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
The present embodiments relate to the agricultural insurance method of surveying based on artificial intelligence be mainly used in based on artificial intelligence
Equipment is surveyed in the agricultural insurance of energy, which surveys equipment and can be personal computer
The equipment having data processing function such as (personal computer, PC), server.
Referring to Fig.1, Fig. 1 is that equipment is surveyed in the agricultural insurance based on artificial intelligence involved in the embodiment of the present invention
Hardware structural diagram.In the embodiment of the present invention, it may include processor that equipment is surveyed in the agricultural insurance based on artificial intelligence
1001 (such as central processing unit Central Processing Unit, CPU), communication bus 1002, user interface 1003, net
Network interface 1004, memory 1005.Wherein, communication bus 1002 is for realizing the connection communication between these components；User connects
Mouth 1003 may include display screen (Display), input unit such as keyboard (Keyboard)；Network interface 1004 optionally may be used
To include standard wireline interface and wireless interface (such as Wireless Fidelity WIreless-FIdelity, WI-FI interface)；Memory
1005 can be high-speed random access memory (random access memory, RAM), be also possible to stable memory
(non-volatile memory), such as magnetic disk storage, memory 1005 optionally can also be independently of aforementioned processor
1001 storage device.It will be understood by those skilled in the art that hardware configuration shown in Fig. 1 is not constituted to limit of the invention
It is fixed, it may include perhaps combining certain components or different component layouts than illustrating more or fewer components.
With continued reference to Fig. 1, the memory 1005 in Fig. 1 as a kind of computer storage medium may include operating system,
Network communication module and agricultural insurance exploration procedure based on artificial intelligence.In Fig. 1, processor 1001 can call storage
The agricultural insurance exploration procedure based on artificial intelligence stored in device 1005, and execute various embodiments of the present invention offer based on people
Method is surveyed in the agricultural insurance of work intelligence.
The embodiment of the invention provides a kind of agricultural insurances based on artificial intelligence to survey method.
Referring to Fig. 2, Fig. 2 is the process signal that method first embodiment is surveyed the present invention is based on the agricultural insurance of artificial intelligence
Figure.
In the present embodiment, which surveys method and is looked by the agricultural insurance based on artificial intelligence
Equipment realization is surveyed, which, which surveys equipment, can be personal computer, server etc. with data
The equipment of processing function, the agricultural insurance based on artificial intelligence survey method the following steps are included:
Step S10 is surveyed in task from the agricultural insurance and is extracted wait survey when receiving agricultural insurance and surveying task
The geographical location information for target of accepting insurance；
The present embodiment carries out crop type identification to the target of accepting insurance that insured people provides using remote sensing technology, and realization is treated
Survey surveying for target of accepting insurance.Since traditional multispectral remote sensing is few by remote sensor wave band, spectral resolution is low, vegetation light
The influence for composing similitude, can not obtain higher crop type accuracy of identification, and hyperspectral technique then can be in numerous narrow-bands
Subtle SPECTRAL DIVERSITY between range detection crops, accurately distinguishes crop type, and the present embodiment utilizes UAV flight as a result,
Unmanned plane and its high light spectrum image-forming spectrometer of carrying (are defined as airborne hyperspectral imaging spectrum by high light spectrum image-forming spectrometer
System) acquire spectroscopic data wait survey target of accepting insurance.Specifically, it the agricultural insurance based on artificial intelligence need to be pre-established surveys and set
The standby communication connection between airborne hyperspectral imaging spectrum system, so that equipment pair is surveyed in the agricultural insurance based on artificial intelligence
Airborne hyperspectral imaging spectrum system is managed.
In the present embodiment, it can be based on manually in the relevant staff of accepting insurance the stage for agricultural insurance, insurance institution
The agricultural insurance of intelligence, which is surveyed in equipment, to be triggered corresponding agricultural insurance and surveys task, the agricultural insurance survey in task carry to
The geographical location information for target of accepting insurance is surveyed, which specifically can be geographical coordinate.When based on artificial intelligence
Agricultural insurance surveys equipment when receiving agricultural insurance and surveying task, surveys in task extracted wait survey from agricultural insurance first
The geographical coordinate for target of accepting insurance.
It is described wait survey to control the acquisition of airborne hyperspectral imaging spectrum system according to the geographical location information by step S20
The spectroscopic data for target of accepting insurance；
Later, based on the geographical coordinate wait survey target of accepting insurance, respectively on the four direction of the geographical coordinate, control
The probe vertical of airborne hyperspectral imaging spectrum system is downward, is surveyed at the preset height wait survey target canopy of accepting insurance
Amount, and several spectrum are recorded in each direction, constitute the spectroscopic data wait survey target of accepting insurance, wherein preset height can
It is also not construed as limiting with the spectrum quantity according to practical flexible setting, recorded in each direction.For example, can be respectively in the geography
The four direction of coordinate, the probe vertical for controlling airborne hyperspectral imaging spectrum system is downward, in distance wait survey target of accepting insurance
It is measured at 1-2 meters of canopy, records 5 spectrum in each direction, 20 spectrum are obtained, as wait survey target of accepting insurance
Spectroscopic data.
Step S30 pre-processes the spectroscopic data wait survey target of accepting insurance；
Since the spectroscopic data wave band wait survey target of accepting insurance of acquisition is more, data volume is big, information redundancy is serious, server
It needs to treat and surveys the spectroscopic data of target of accepting insurance and pre-processed, that is, is first right using Savitzky-Golay filtering fitting process
Wait survey target of accepting insurance spectroscopic data carry out smoothing denoising processing, then reject in the spectroscopic data wait survey target of accepting insurance by
Water vapor absorption influences strong wave band (1350~1400nm, 1800~1950nm, 2400~2500nm), finally treats to survey and hold
The spectroscopic data for protecting target does average treatment, i.e., by 20 spectrum averageds of acquisition.
Step S40 is extracted and described is accepted insurance wait survey from pretreated described wait survey in the spectroscopic data for accepting insurance target
The spectral signature of target；
After being pre-processed to the spectroscopic data of acquisition, from pretreated wait survey in the spectroscopic data for accepting insurance target
It extracts spectral signature (including differential characteristics and Absorption Characteristics).That is, first with Spectroscopy differential method and continuum removal method, to pre-
Some significant reflections and Absorption Characteristics in the spectroscopic data that treated wait survey target of accepting insurance are analyzed, from advance
Spectral signature region is determined in spectroscopic data after reason.Wherein, Spectroscopy differential method by mathematical simulation reflectance spectrum and is sought not
Same order fractional differentiation value extracts reflection and absorption peak parameter to determine spectrum bending point rapidly.In view of in practical application, single order
Differential is lower to noise-sensitive value, and the present embodiment uses single order Spectroscopy differential, and calculating formula is as follows:
Wherein, λiFor band wavelength, ρ ' (λi) it is wavelength XiFirst derivative.
Continuum removal method is that reflectance spectrum is absorbed to strong subband to convert, and amplifies its Absorption Characteristics, and
It is compared in common baseline, convenient for analyzing and extracting spectral absorption characteristics, the spectrum after being removed by continuum can be sought inhaling
Receipts depth (DEP), absorption characteristic parameters, the formula such as width (WID) and absorption area (AREA) are as follows:
DEP=1-CRmin
WID=λb-λa
ARER=DEPWID
Wherein, CRminFor minimum spectral reflectivity after continuum removal in an absorption paddy, λa、λbRespectively absorb starting point,
The wavelength value of terminal.
Using Spectroscopy differential method and continuum removal method, analyze pretreated wait survey the spectroscopic data for target of accepting insurance
Reflection and Absorption Characteristics, discovery is in Lv Feng, Hong Gu of visible light near infrared band, red side, blue light region chlorophyll absorption band, red
Light area chlorophyll absorption band, water weak absorbing band, water and the narrow absorption band of oxygen and water and carbon dioxide strong absorption band are identification farming
The dominant spectral features region of species type.From the green peak amplitude of green peak extracted region and Green edge, the red paddy of Cong Honggu extracted region
Red not care about one's appearance value and Red edge position are extracted from red border region in amplitude and the position Hong Gu, obtain six kinds of differential characteristics.From blue light region, leaf is green
Plain absorption band, red light district chlorophyll absorption band, water weak absorbing band, water and the narrow absorption band of oxygen and water and carbon dioxide strong absorption band
It is extracted respectively in (absorption band at five) and absorbs depth (DEP) and absorption area (AREA), obtain ten kinds of Absorption Characteristics.
The spectral signature wait survey target of accepting insurance is input to trained crop type and identifies mould by step S50
It is analyzed in type, it is described wait survey which kind of crops is target of accepting insurance belong to obtain, as surveying result.
From in the pretreated spectroscopic data for surveying target of accepting insurance extract spectral signature after, by 16 kinds of extraction
Spectral signature is input in trained crop type identification model and is analyzed.Wherein, crop type identification model has
Body is back propagation artificial neural network model (Back Propagation Neural Network) model, trained crops
Type identification model have preferable stability and predictive ability, prediction result only one.By 16 kinds of Spectral Properties of extraction
Sign is input in trained crop type identification model, and the crop type of crop type identification model output can be obtained
Coding, that is, determined wait survey which kind of crops is target of accepting insurance belong to, as surveying result.
Later, the target of accepting insurance for surveying result with insured people provides is compared, judges whether the two is consistent, if one
It causes, the target of accepting insurance for confirming that insured people provides is true.
This case provides a kind of agricultural insurance based on artificial intelligence and surveys method, surveys task when receiving agricultural insurance
When, the geographical location information that extracts wait survey accept insurance target is surveyed in task from the agricultural insurance first, then according to extraction
Geographical location information, control airborne hyperspectral imaging spectrum system are acquired wait survey target spectroscopic data of accepting insurance, then to acquisition
It is pre-processed wait survey target spectroscopic data of accepting insurance, and is extracted from pretreated spectroscopic data wait survey target of accepting insurance
Spectral signature, by the spectral signature wait survey target of accepting insurance of extraction be input in trained crop type identification model into
Row analysis, to obtain wait survey which kind of crops is target of accepting insurance belong to, as surveying as a result, realizing based on trained farming
Species type identification model, which is treated, surveys target of accepting insurance and is analyzed, and can significantly improve the accuracy of identification of crop type, realize
It is convenient, efficient, quickly and accurately agricultural insurance is surveyed.
Further, propose that the present invention is based on second that method is surveyed in the agricultural insurance of artificial intelligence based on first embodiment
Embodiment.The second embodiment of method is surveyed in agricultural insurance based on artificial intelligence and the agricultural insurance based on artificial intelligence is surveyed
The difference of the first embodiment of method is, before reference Fig. 3, the step S10, may include:
Step S60 obtains the spectroscopic data of several crops, and carries out respectively to the spectroscopic data of every kind of crops pre-
Processing；
It should be appreciated that in the present embodiment, before step S10, crop type identification model need to be trained in advance.Specifically
Ground acquires a large amount of spectroscopic datas of several common crops first, in the present embodiment, utilizes airborne hyperspectral imaging spectral
System surveys wheat, rice, corn, potato, six kinds of soybean, rape common crops canopy spectras, then respectively to every kind of farming
The spectrum of object is pre-processed, that is, using Savitzky-Golay filtering fitting process first to the spectrum respectively to every kind of crops
Smoothing denoising processing is carried out, then reject respectively is influenced strong wave band by water vapor absorption in the spectrum of every kind of crops, finally
Average treatment is done to the spectrum of every kind of crops respectively, i.e., respectively to the spectrum averaged of every kind of crops.
Step S70 extracts spectral signature as training sample respectively from the spectroscopic data of pretreated every kind of crops
This, and training sample set is constructed according to the training sample；
Further, in the way of extracting spectral signature in first embodiment, respectively from pretreated every kind of farming
The spectral signature of the spectral signature extracted region training data of the spectroscopic data of object constructs training sample set, such as:
Training sample set={ training sample 1, training sample 2, training sample 3, training sample 4, training sample 5, training sample
This 6 }
=spectral signature of wheat, and the spectral signature of corn, the spectral signature of rice, the spectral signature of corn, potato
Spectral signature, the spectral signature of soybean, the spectral signature of rape }
Step S80 obtains trained farming species according to training sample set training crop type identification model
Type identification model.
The process of training BPNN model is as follows:
A, each training sample that training sample is concentrated is normalized using normalized function premnmx, it will
Input of each training sample as BPNN model after normalization, corresponding crop type coding is as correct output；
B, BPNN model is created, sets BPNN model to three layers (input layers+hidden layer+output layer), input layer is set
Number of nodes (5 layers), node in hidden layer (being chosen as 17-25 layers), output layer number of nodes (1 layer), hidden layer transmission function
(tansig function), output layer transmission function (purelin function), training the number of iterations (being chosen as 20000 times), BPNN network
Middle learning efficiency (being chosen as 0.05), training objective minimal error (0.0001)；
C, initialize BPNN model parameter, the parameter include weight and biasing (biasing is considered as each neuron
Itself weight), that is, the weight of BPNN model and biasing are initialized as the random number from normal distribution (0,1)；
D, training is iterated using BPNN model of the traincgf method to building, that is, one training sample of input, to
Before find out the output of each hidden layer and output layer, then calculate the output of output layer and the deviation that correctly exports, that is, defeated
The error (measuring error size with least squares difference) of layer out indicates that the precision of model is higher since error is smaller, benefit
Weight and biasing are optimized with gradient descent method so that error becomes smaller, that is, reverse propagated error will specifically export
Layer obtains the reversed output of output layer, then will reversely export in conjunction with connection weight, as the reversed of hidden layer as input
Input, obtains the reversed output of hidden layer, and the reversed output for being then based on hidden layer calculates company, institute between input layer and hidden layer
The weight gradient reversed output of hidden layer (input of output layer multiplied by), after having a weight gradient gradient, so that it may update
The weight and biasing of BPNN model；
E, for each training sample, d process is recycled, until its error is less than or equal to previously positioned training objective minimum
Error has reached the number of iterations, can be obtained trained BPNN model.
In more implement, after BPNN model training is good, does not come into operation, but first detect trained immediately
The precision of BPNN model.Specifically, available preset verify data is verified from the spectral signature extracted region of verify data
The spectral signature building verifying sample set of data, each test specimens that test sample is concentrated using normalized function premnmx
Originally it is normalized, each sample for then concentrating the test sample after normalization is sequentially input to trained
In BPNN model, the crop type (namely prediction result) of trained BPNN model output is obtained.Later, according to reality
Crop type and the good BPNN model of prediction result training of judgement to every kind of crops identify whether it is accurate, if accurately,
Identification accurate quantity is added 1, then according to formula: the accuracy of identification=identification accurate quantity/corresponding crops of test sample collection
Type sum, calculates the accuracy of identification of trained BPNN model, then by the accuracy of identification of calculating and preset threshold (such as
80%) it is compared, if the accuracy of identification of trained BPNN model is greater than preset threshold, determines trained BPNN mould
The accuracy of identification of type meets condition, can come into operation.
In addition, the embodiment of the present invention, which also provides a kind of agricultural insurance based on artificial intelligence, surveys device.
It is that the present invention is based on the functional modules that device first embodiment is surveyed in the agricultural insurance of artificial intelligence referring to Fig. 4, Fig. 4
Schematic diagram.
In the present embodiment, the agricultural insurance based on artificial intelligence surveys device and includes:
Geographical location information extraction module 10, for when receiving agricultural insurance and surveying task, from the agricultural insurance
The geographical location information extracted wait survey target of accepting insurance is surveyed in task；
Acquisition module 20, for controlling airborne hyperspectral imaging spectrum system and acquiring institute according to the geographical location information
State the spectroscopic data wait survey target of accepting insurance；
Preprocessing module 30, for being pre-processed to the spectroscopic data wait survey target of accepting insurance；
Spectra feature extraction module 40, for mentioning from pretreated described wait survey in the spectroscopic data for accepting insurance target
Take the spectral signature wait survey target of accepting insurance；
Analysis module 50, for the spectral signature wait survey target of accepting insurance to be input to trained crop type
It is analyzed in identification model, it is described wait survey which kind of crops is target of accepting insurance belong to obtain, as surveying result.
Wherein, each virtual functions module that device is surveyed in the above-mentioned agricultural insurance based on artificial intelligence is stored in shown in Fig. 1
Agricultural insurance based on artificial intelligence is surveyed in the memory 1005 of equipment, is looked into for realizing the agricultural insurance based on artificial intelligence
The institute for surveying program is functional；When each module is executed by processor 1001, realizes and mould is identified based on trained crop type
Type, which is treated, to be surveyed target of accepting insurance and is analyzed, and can be significantly improved the accuracy of identification of crop type, be realized convenient, efficient, fast
Speed, accurately agricultural insurance is surveyed.
Further, the acquisition module 20 includes:
Recording unit, in the four direction of the geographical coordinate, controlling airborne hyperspectral imaging spectrum respectively
The probe vertical of system is downward, measures at the preset height wait survey target canopy of accepting insurance, if recording in each direction
Dry spectrum constitutes the spectroscopic data wait survey target of accepting insurance.
Further, the preprocessing module 30 includes:
Smoothing denoising processing unit, for being carried out using filtering fitting process to the spectroscopic data wait survey target of accepting insurance
Smoothing denoising processing；
Culling unit rejects water for that treated to be described wait survey in the spectroscopic data for accepting insurance target from smoothing denoising
Strong absorption bands；
Average treatment unit, for being done wait survey the spectroscopic data for target of accepting insurance described in the strong absorption bands of water to eliminating
Average treatment.
Further, the Spectra feature extraction module 40 includes:
Determination unit, for analyzing pretreated described accept insurance wait survey using Spectroscopy differential method and continuum removal method
The spectroscopic data of target, to determine spectral signature region from the pretreated spectroscopic data wait survey target of accepting insurance；
Extraction unit obtains holding wait survey for extracting differential characteristics and Absorption Characteristics from the spectral signature region
Protect the spectral signature of target.
Further, the extraction unit includes:
First extracts subelement, for extracting differential from the region Lv Feng, the region Hong Gu and the red border region
Feature；
Second extracts subelement, is used for from the blue light region chlorophyll absorption band, the red light district chlorophyll absorption band, institute
It states water weak absorbing band, the water and the narrow absorption band of oxygen and the water and carbon dioxide strong absorption band extracts Absorption Characteristics.
Further, device is surveyed in the agricultural insurance based on artificial intelligence further include:
Module is obtained, for obtaining the spectroscopic data of several crops, and respectively to the spectroscopic data of every kind of crops
It is pre-processed；
Module is constructed, for from the spectroscopic data of pretreated every kind of crops, extracting spectral signature conduct respectively
Training sample, and training sample set is constructed according to the training sample；
Training module, for obtaining trained agriculture according to training sample set training crop type identification model
Agrotype identification model.
Further, the training module includes:
Normalized unit, each training sample for concentrating to the training sample are normalized；
Initialization unit, for creating the crop type identification model based on reverse transmittance nerve network BPNN, and just
The parameter of the beginningization crop type identification model；
Acquiring unit, for the training sample after normalized to be input in the crop type identification model,
To output and reversed output before obtaining；
Updating unit updates the crops according to forward direction output and reversed output for using gradient descent method
The parameter of type identification model obtains trained crop type identification model.
Wherein, the function realization that modules in device are surveyed in the above-mentioned agricultural insurance based on artificial intelligence is based on above-mentioned
It is corresponding that each step in embodiment of the method is surveyed in the agricultural insurance of artificial intelligence, function and realizes process here no longer one by one
It repeats.
In addition, the embodiment of the present invention also provides a kind of computer readable storage medium.
The agricultural insurance exploration procedure based on artificial intelligence is stored on computer readable storage medium of the present invention, wherein institute
When stating the agricultural insurance exploration procedure based on artificial intelligence and being executed by processor, such as the above-mentioned agricultural based on artificial intelligence is realized
The step of insurance survey method.
Wherein, the agricultural insurance exploration procedure based on artificial intelligence, which is performed realized method, can refer to base of the present invention
Each embodiment of method is surveyed in the agricultural insurance of artificial intelligence, details are not described herein again.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the system that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or system institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, method of element, article or system.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in one as described above
In storage medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that terminal device (it can be mobile phone,
Computer, server, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. method is surveyed in a kind of agricultural insurance based on artificial intelligence, which is characterized in that the agricultural based on artificial intelligence is protected
Danger survey method the following steps are included:
When receiving agricultural insurance and surveying task, the ground that extracts wait survey accept insurance target is surveyed in task from the agricultural insurance
Manage location information；
According to the geographical location information, the airborne hyperspectral imaging spectrum system acquisition light wait survey target of accepting insurance is controlled
Modal data；
The spectroscopic data wait survey target of accepting insurance is pre-processed；
From pretreated described wait survey in the spectroscopic data for accepting insurance target, the extraction Spectral Properties wait survey target of accepting insurance
Sign；
The spectral signature wait survey target of accepting insurance is input in trained crop type identification model and is analyzed,
It is described wait survey which kind of crops is target of accepting insurance belong to obtain, as surveying result.
2. method is surveyed in the agricultural insurance based on artificial intelligence as described in claim 1, which is characterized in that the geographical location
Information is geographical coordinate,
It is described according to the geographical location information, it is described wait survey target of accepting insurance to control the acquisition of airborne hyperspectral imaging spectrum system
Spectroscopic data the step of include:
Respectively on the four direction of the geographical coordinate, the probe vertical for controlling airborne hyperspectral imaging spectrum system is downward,
It is measured at the preset height wait survey target canopy of accepting insurance, records several spectrum in each direction, described in composition
Wait survey the spectroscopic data for target of accepting insurance.
3. method is surveyed in the agricultural insurance based on artificial intelligence as claimed in claim 2, which is characterized in that it is described to it is described to
The spectroscopic data for surveying target of accepting insurance carries out pretreated step and includes:
Smoothing denoising processing is carried out to the spectroscopic data wait survey target of accepting insurance using filtering fitting process；
From smoothing denoising, that treated is described wait survey in the spectroscopic data for accepting insurance target, rejects the strong absorption bands of water；
Average treatment is done wait survey the spectroscopic data for target of accepting insurance described in the strong absorption bands of water to eliminating.
4. method is surveyed in the agricultural insurance based on artificial intelligence as claimed in claim 3, which is characterized in that described from pretreatment
Afterwards described wait survey in the spectroscopic data for target of accepting insurance, the step of extracting the spectral signature wait survey target of accepting insurance packet
It includes:
The pretreated spectroscopic data wait survey target of accepting insurance is analyzed using Spectroscopy differential method and continuum removal method, with
Spectral signature region is determined from the pretreated spectroscopic data wait survey target of accepting insurance；
Differential characteristics and Absorption Characteristics are extracted from the spectral signature region, obtain the spectral signature wait survey target of accepting insurance.
5. method is surveyed in the agricultural insurance based on artificial intelligence as claimed in claim 4, which is characterized in that the spectral signature
Region includes that the region Lv Feng, the region Hong Gu, red border region, blue light region chlorophyll absorption band, red light district chlorophyll absorption band, water are weak
Absorption band, water and the narrow absorption band of oxygen and water and carbon dioxide strong absorption band,
It is described to extract differential characteristics from the spectral signature region and the step of Absorption Characteristics includes:
Differential characteristics are extracted from the region Lv Feng, the region Hong Gu and the red border region；
From the blue light region chlorophyll absorption band, the red light district chlorophyll absorption band, the water weak absorbing band, the water and oxygen
Narrow absorption band and the water and carbon dioxide strong absorption band extract Absorption Characteristics.
6. method is surveyed in the agricultural insurance based on artificial intelligence as described in claim 1, which is characterized in that described to receive
When task is surveyed in agricultural insurance, is surveyed in task from the agricultural insurance and extract the geographical location information wait survey target of accepting insurance
Before step, comprising:
The spectroscopic data of several crops is obtained, and the spectroscopic data of every kind of crops is pre-processed respectively；
Respectively from the spectroscopic data of pretreated every kind of crops, spectral signature is extracted as training sample, and according to institute
State training sample building training sample set；
According to training sample set training crop type identification model, trained crop type identification model is obtained.
7. method is surveyed in the agricultural insurance based on artificial intelligence as claimed in claim 6, which is characterized in that described according to
Training sample set trains crop type identification model, and the step of obtaining trained crop type identification model includes:
The training sample set is normalized；
The crop type identification model based on reverse transmittance nerve network BPNN is created, and initializes the crop type and knows
The parameter of other model；
Training sample set after normalized is input in the crop type identification model, to output and instead before obtaining
To output；
Using gradient descent method, the ginseng of the crop type identification model is updated according to forward direction output and reversed output
Number, obtains trained crop type identification model.
8. device is surveyed in a kind of agricultural insurance based on artificial intelligence, which is characterized in that the agricultural based on artificial intelligence is protected
Danger surveys device and includes:
Geographical location information extraction module, for surveying and appointing from the agricultural insurance when receiving agricultural insurance and surveying task
The geographical location information wait survey target of accepting insurance is extracted in business；
Acquisition module, for it is described to be checked to control the acquisition of airborne hyperspectral imaging spectrum system according to the geographical location information
Survey the spectroscopic data for target of accepting insurance；
Preprocessing module, for being pre-processed to the spectroscopic data wait survey target of accepting insurance；
Spectra feature extraction module, for from pretreated described wait survey in the spectroscopic data for accepting insurance target, described in extraction
Wait survey the spectral signature for target of accepting insurance；
Analysis module identifies mould for the spectral signature wait survey target of accepting insurance to be input to trained crop type
It is analyzed in type, it is described wait survey which kind of crops is target of accepting insurance belong to obtain, as surveying result.
9. equipment is surveyed in a kind of agricultural insurance based on artificial intelligence, which is characterized in that the agricultural based on artificial intelligence is protected
Danger survey equipment include processor, memory and be stored on the memory and can be executed by the processor based on
The agricultural insurance exploration procedure of artificial intelligence, wherein the agricultural insurance exploration procedure based on artificial intelligence is by the processor
When execution, the step of method is surveyed in the agricultural insurance based on artificial intelligence as described in any one of claims 1 to 7 is realized.
10. a kind of computer readable storage medium, which is characterized in that be stored on the computer readable storage medium based on people
The agricultural insurance exploration procedure of work intelligence, wherein the agricultural insurance exploration procedure based on artificial intelligence is executed by processor
When, realize the step of method is surveyed in the agricultural insurance based on artificial intelligence as described in any one of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910665932.0A CN110502997A (en) | 2019-07-23 | 2019-07-23 | Method and relevant device are surveyed in agricultural insurance based on artificial intelligence |
| PCT/CN2020/098926 WO2021012898A1 (en) | 2019-07-23 | 2020-06-29 | Artificial intelligence-based agricultural insurance surveying method and related device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910665932.0A CN110502997A (en) | 2019-07-23 | 2019-07-23 | Method and relevant device are surveyed in agricultural insurance based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110502997A true CN110502997A (en) | 2019-11-26 |
Family
ID=68586657
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910665932.0A Pending CN110502997A (en) | 2019-07-23 | 2019-07-23 | Method and relevant device are surveyed in agricultural insurance based on artificial intelligence |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110502997A (en) |
| WO (1) | WO2021012898A1 (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021012898A1 (en) * | 2019-07-23 | 2021-01-28 | 平安科技（深圳）有限公司 | Artificial intelligence-based agricultural insurance surveying method and related device |
| CN117315492A (en) * | 2023-11-29 | 2023-12-29 | 中国平安财产保险股份有限公司 | Planting risk early warning method, system, equipment and medium based on unmanned aerial vehicle technology |
| CN117538658A (en) * | 2023-11-16 | 2024-02-09 | 深圳市美信检测技术股份有限公司 | Artificial intelligence fault positioning method and device based on infrared spectrum and thermal imaging |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113222039B (en) * | 2021-05-24 | 2023-09-05 | 中国平安财产保险股份有限公司 | Training method, device, equipment and medium for remote sensing image target exploration model |
| CN114694043A (en) * | 2022-03-30 | 2022-07-01 | 中国人民解放军空军军医大学 | Ground wounded person identification method, device and medium of airborne multispectral multi-domain preferred features under complex scene |
| CN114550108B (en) * | 2022-04-26 | 2022-07-08 | 广东省农业科学院植物保护研究所 | Spodoptera frugiperda identification and early warning method and system |
| CN117523433B (en) * | 2023-11-27 | 2024-04-19 | 广东华茂高科种业有限公司 | Chlorophyll content monitoring method for rice in different growth periods |
| CN117689481B (en) * | 2024-02-04 | 2024-04-19 | 国任财产保险股份有限公司 | Natural disaster insurance processing method and system based on unmanned aerial vehicle video data |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107169018A (en) * | 2017-04-06 | 2017-09-15 | 河南云保遥感科技有限公司 | A kind of agricultural insurance is surveyed, loss assessment system and its implementation |
| CN109063660A (en) * | 2018-08-09 | 2018-12-21 | 成都天地量子科技有限公司 | A kind of crop recognition methods based on multispectral satellite image |
| US20180373932A1 (en) * | 2016-12-30 | 2018-12-27 | International Business Machines Corporation | Method and system for crop recognition and boundary delineation |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090164256A1 (en) * | 2007-12-20 | 2009-06-25 | International Business Machines | Device, system, and method of collaborative insurance |
| CN107909492A (en) * | 2017-11-30 | 2018-04-13 | 河南云保遥感科技有限公司 | It is a kind of to survey damage identification method using the agricultural insurance of machine learning techniques |
| CN108053325A (en) * | 2017-11-30 | 2018-05-18 | 河南云保遥感科技有限公司 | A kind of agricultural insurance damage identification method based on crops remote sensing technology |
| CN110502997A (en) * | 2019-07-23 | 2019-11-26 | 平安科技（深圳）有限公司 | Method and relevant device are surveyed in agricultural insurance based on artificial intelligence |
-
2019
- 2019-07-23 CN CN201910665932.0A patent/CN110502997A/en active Pending
-
2020
- 2020-06-29 WO PCT/CN2020/098926 patent/WO2021012898A1/en active Application Filing
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180373932A1 (en) * | 2016-12-30 | 2018-12-27 | International Business Machines Corporation | Method and system for crop recognition and boundary delineation |
| CN107169018A (en) * | 2017-04-06 | 2017-09-15 | 河南云保遥感科技有限公司 | A kind of agricultural insurance is surveyed, loss assessment system and its implementation |
| CN109063660A (en) * | 2018-08-09 | 2018-12-21 | 成都天地量子科技有限公司 | A kind of crop recognition methods based on multispectral satellite image |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021012898A1 (en) * | 2019-07-23 | 2021-01-28 | 平安科技（深圳）有限公司 | Artificial intelligence-based agricultural insurance surveying method and related device |
| CN117538658A (en) * | 2023-11-16 | 2024-02-09 | 深圳市美信检测技术股份有限公司 | Artificial intelligence fault positioning method and device based on infrared spectrum and thermal imaging |
| CN117315492A (en) * | 2023-11-29 | 2023-12-29 | 中国平安财产保险股份有限公司 | Planting risk early warning method, system, equipment and medium based on unmanned aerial vehicle technology |
| CN117315492B (en) * | 2023-11-29 | 2024-04-02 | 中国平安财产保险股份有限公司 | Planting risk early warning method, system, equipment and medium based on unmanned aerial vehicle technology |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021012898A1 (en) | 2021-01-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110502997A (en) | Method and relevant device are surveyed in agricultural insurance based on artificial intelligence | |
| Xue et al. | Significant remote sensing vegetation indices: A review of developments and applications | |
| Dash et al. | Assessing very high resolution UAV imagery for monitoring forest health during a simulated disease outbreak | |
| Yang et al. | Unmanned aerial vehicle remote sensing for field-based crop phenotyping: current status and perspectives | |
| CN105352895B (en) | High-spectrum remote sensing data vegetation information extraction method | |
| Zheng et al. | Retrieving leaf area index (LAI) using remote sensing: theories, methods and sensors | |
| Delalieux et al. | Hyperspectral indices to diagnose leaf biotic stress of apple plants, considering leaf phenology | |
| CN107037001A (en) | A kind of corn monoploid seed discrimination method based on near-infrared spectrum technique | |
| CN109598306A (en) | Hyperspectral image classification method based on SRCM and convolutional neural networks | |
| Zhang et al. | Extraction of tree crowns damaged by Dendrolimus tabulaeformis Tsai et Liu via spectral-spatial classification using UAV-based hyperspectral images | |
| CN104215591A (en) | Damage-free visible-near infrared light spectrum detecting method | |
| CN110118732A (en) | Soil moisture content detection method and device | |
| Lin et al. | Using the 3D model RAPID to invert the shoot dieback ratio of vertically heterogeneous Yunnan pine forests to detect beetle damage | |
| Qiao et al. | Estimating maize LAI by exploring deep features of vegetation index map from UAV multispectral images | |
| CN110398473A (en) | A kind of rapid test paper detection method and system | |
| CN107145831A (en) | Based on vector probabilistic diffusion and markov random file Hyperspectral Image Classification method | |
| Huang et al. | Hyperspectral imaging for identification of an invasive plant Mikania micrantha Kunth | |
| Marin et al. | Remotely piloted aircraft and random forest in the evaluation of the spatial variability of foliar nitrogen in coffee crop | |
| CN108764285A (en) | A kind of recognition methods of pine tree Deceased wood and system based on high resolution image | |
| Zhao et al. | Evaluating the potential of airborne hyperspectral LiDAR for assessing forest insects and diseases with 3D Radiative Transfer Modeling | |
| Forbes et al. | Comparing remote sensing and field-based approaches to estimate ladder fuels and predict wildfire burn severity | |
| Agjee et al. | Remote sensing bio-control damage on aquatic invasive alien plant species | |
| Puletti et al. | Enhancing wall-to-wall forest structure mapping through detailed co-registration of airborne and terrestrial laser scanning data in mediterranean forests | |
| Cunha et al. | Prediction of the vigor and health of peach tree orchard | |
| LU500715B1 (en) | Hyperspectral Image Classification Method Based on Discriminant Gabor Network |
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 |