CN115660291B - Plant disease occurrence and potential occurrence identification and evaluation method and system - Google Patents
Plant disease occurrence and potential occurrence identification and evaluation method and system Download PDFInfo
- Publication number
- CN115660291B CN115660291B CN202211587372.XA CN202211587372A CN115660291B CN 115660291 B CN115660291 B CN 115660291B CN 202211587372 A CN202211587372 A CN 202211587372A CN 115660291 B CN115660291 B CN 115660291B
- Authority
- CN
- China
- Prior art keywords
- disease
- plant
- microenvironment
- potential
- occurrence
- 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.)
- Active
Links
- 201000010099 disease Diseases 0.000 title claims abstract description 356
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 356
- 238000011156 evaluation Methods 0.000 title claims abstract description 46
- 230000007613 environmental effect Effects 0.000 claims abstract description 81
- 238000000034 method Methods 0.000 claims abstract description 42
- 230000003044 adaptive effect Effects 0.000 claims abstract description 12
- 230000004083 survival effect Effects 0.000 claims description 54
- 238000000605 extraction Methods 0.000 claims description 30
- 238000012549 training Methods 0.000 claims description 20
- 230000008859 change Effects 0.000 claims description 18
- 238000005295 random walk Methods 0.000 claims description 16
- 230000001717 pathogenic effect Effects 0.000 claims description 15
- 238000012216 screening Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000009467 reduction Effects 0.000 claims description 10
- 238000005070 sampling Methods 0.000 claims description 10
- 238000003860 storage Methods 0.000 claims description 10
- 239000011159 matrix material Substances 0.000 claims description 7
- 238000011161 development Methods 0.000 claims description 6
- 230000002776 aggregation Effects 0.000 claims description 5
- 238000004220 aggregation Methods 0.000 claims description 5
- 238000013135 deep learning Methods 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 5
- 230000007246 mechanism Effects 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 5
- 230000002265 prevention Effects 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 238000012163 sequencing technique Methods 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 5
- 230000003449 preventive effect Effects 0.000 claims description 4
- 230000001932 seasonal effect Effects 0.000 claims description 4
- 238000011282 treatment Methods 0.000 claims description 4
- 238000012800 visualization Methods 0.000 claims description 2
- 230000001105 regulatory effect Effects 0.000 abstract description 2
- 230000001276 controlling effect Effects 0.000 abstract 1
- 241000196324 Embryophyta Species 0.000 description 155
- 230000006978 adaptation Effects 0.000 description 7
- 238000011176 pooling Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000012271 agricultural production Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000003967 crop rotation Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000001863 plant nutrition Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 241001478887 unidentified soil bacteria Species 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011369 optimal treatment Methods 0.000 description 1
- 230000032696 parturition Effects 0.000 description 1
- 231100000915 pathological change Toxicity 0.000 description 1
- 230000036285 pathological change Effects 0.000 description 1
- 239000000575 pesticide Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/10—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture
- Y02A40/25—Greenhouse technology, e.g. cooling systems therefor
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method and a system for identifying and evaluating occurrence and potential occurrence of plant diseases, wherein the method comprises the following steps: obtaining environmental basic information and plant category information of a target area where a plant is located, evaluating a microenvironment of the target area to obtain an adaptive degree, comparing the currently obtained adaptive degree with historical adaptive degrees in a database, obtaining a disease susceptible set according to a growth stage of the plant and a microenvironment evaluation result based on a comparison result, and identifying plant diseases through the disease susceptible set; and when the plant disease identification result does not contain the disease information meeting the standard, acquiring the occurrence probability of the potential diseases according to the environmental characteristics of the current microenvironment for outputting, and regulating and controlling the microenvironment. The invention lays a foundation for improving the identification and early warning of plant diseases according to the evaluation result of the microenvironment, and can efficiently, accurately and objectively identify the occurrence and potential occurrence of the diseases, thereby taking corresponding measures to prevent and treat the diseases in time.
Description
Technical Field
The invention relates to the technical field of disease control, in particular to a method and a system for identifying and evaluating occurrence and potential occurrence of plant diseases.
Background
The plant diseases have the characteristics of diversity and periodicity, the change of the appearance of the plant is not obvious in the early stage of pathological changes, the disease characteristics are mostly shown in the level of macromolecular organic matters, and the disease characteristics can be shown through the change of the color, texture, shape and the like of plant leaves along with the aggravation of the disease conditions. Economic crops are affected by factors such as climate, soil and technical level in the growing process, are extremely easy to be damaged by various diseases, plant protection personnel and farmers with insufficient experience cannot correctly judge the diseases, even make wrong pesticide application schemes, so that the disease conditions cannot be stopped in time, the yield and income are greatly reduced, the quality is affected, accurate diagnosis and treatment of diseased plants need to be realized, the diseases need to be accurately identified, and the early stage and the latent stage of the diseases need to be accurately evaluated so as to be matched with the optimal treatment scheme.
Plant disease identification and assessment play an important role in the field of agricultural production, disease propagation can be effectively avoided, economic loss is reduced, and sustainable development of agricultural production is maintained. The agricultural disease identification and evaluation work becomes one of research hotspots, and how to utilize the modern scientific technology to carry out identification and evaluation before the plant diseases occur at the initial stage or do not occur and help agricultural producers to remedy the diseases in time is a problem to be solved urgently in the field.
Disclosure of Invention
In order to solve the technical problems, the invention provides a method and a system for identifying and evaluating occurrence and potential occurrence of plant diseases.
The invention provides a method for identifying and evaluating occurrence and potential occurrence of plant diseases in a first aspect, which comprises the following steps:
acquiring environment basic information and plant type information of a target area where a plant is located, evaluating a microenvironment of the target area according to the environment basic information, and acquiring the growth suitability degree of the microenvironment for the plant type;
storing the survival degree in a database in combination with a timestamp, comparing the currently acquired survival degree with the historical survival degree in the database, and judging whether the reduction amplitude of the survival degree is greater than a preset change threshold value;
if the plant disease is larger than the preset value, analyzing the growth stage of the current plant, acquiring a disease susceptible set according to the growth stage of the plant and a microenvironment evaluation result, and identifying the plant disease based on the disease susceptible set;
and when the plant disease identification result does not contain disease information meeting the standard, acquiring the occurrence probability of the potential diseases according to the environmental characteristics of the current microenvironment, outputting the potential diseases with the highest occurrence probability, and performing microenvironment regulation and control according to the plant diseases and the output results of the potential diseases.
In this scheme, acquire the environmental basis information and the plant classification information of plant place target area, evaluate the microenvironment of target area according to environmental basis information, acquire the microenvironment right the suitable degree of giving birth to of plant classification specifically does:
acquiring optimal adaptive growth conditions corresponding to plant categories through data retrieval, acquiring evaluation indexes for judging adaptive growth degree according to the correlation of each environmental index in the optimal adaptive growth conditions, and acquiring environmental technical information of a current target area to generate index values of each evaluation index;
calculating the index score of each evaluation index according to the index value and the score calculation mode of each evaluation index;
and matching the index scores of the evaluation indexes with preset weight information to obtain comprehensive scores of the microenvironment, constructing a comprehensive score threshold interval according to a preset threshold, and determining the growing suitability degree of the microenvironment of the target area to the plant categories according to the threshold interval in which the comprehensive scores fall.
In the scheme, the birth adaptation degree is stored in a database in combination with a timestamp, and the method specifically comprises the following steps:
constructing a database related to the microenvironment of the target area, storing the survival degree in the database in combination with the timestamp to generate a survival degree change sequence, and performing visualization processing on the survival degree;
analyzing the time variation characteristics of the survival degree according to the historical survival degree sequence, and early warning the survival degree of the current microenvironment according to the time variation characteristics and seasonal characteristics;
sending the early warning information according to a preset method, and reminding workers of carrying out preventive regulation and control on the microenvironment generation of the target area through the early warning information;
meanwhile, when the reduction amplitude of the survival degree is larger than a preset change threshold value, disease related early warning information is generated through the database to prompt.
In this scheme, the growth stage of current plant is analyzed, and the susceptible disease set is obtained according to the growth stage of plant and microenvironment evaluation result, carries out plant disease discernment based on susceptible disease set, specifically is:
according to the plant image information in the target area, preprocessing the image information to extract an interested area corresponding to the plant, and extracting plant image characteristics in the interested area;
determining the current growth stage of the plant based on the plant image characteristics through the plant category information, and performing data retrieval by using a big data means according to the plant category information to obtain the diseased condition of each disease in each growth stage of the plant;
selecting and marking the disease types of which the diseased conditions are larger than a preset threshold standard by taking the diseased conditions of the diseases corresponding to the current growth stage of the plant as a data base, and secondarily screening the marked disease types according to the environmental characteristics of the microenvironment to generate a disease susceptible set of the current growth stage of the plant;
building a disease recognition model based on deep learning, generating a training sample through a susceptible disease set, training the disease recognition model by using the training sample, and introducing plant image information into the trained disease recognition model;
extracting global features of plant image information by using a ResNet network, introducing an attention mechanism and combining with a channel feature extraction sub-network to perform feature selection on the global features, setting different weight factors for each channel feature extraction sub-network, and setting preset feature data in each channel feature extraction sub-network according to the weight factors;
calculating the global feature and preset feature data in each channel feature extraction sub-network by using similarity to extract features, and outputting the channel features larger than a preset similarity threshold to a full connection layer for aggregation and then outputting;
and performing softmax classification network to identify plant diseases according to the output characteristics.
In this scheme, when the plant disease recognition result does not contain the disease information that meets the standard, then obtain the emergence probability that potentially takes place the disease according to the environmental characteristic of current microenvironment, export the potential disease that the emergence probability is the highest, specifically do:
when no plant disease identification result exists in the output of the disease identification model, extracting the environmental characteristic factors corresponding to the occurrence of each disease according to the disease condition of the plant susceptible to the disease in the current growth stage, determining the correlation of the environmental characteristic factors, and carrying out standardization treatment on the environmental characteristic factors corresponding to each disease;
establishing a potential disease prediction model according to the standardized environment characteristic factors based on the Bayesian network structure, performing network structure training by using the standardized environment characteristic factors, calculating the numerical value of each leaf node, generating an optimal network structure of the model, and outputting the potential disease prediction model when the accuracy test of the model meets the preset standard;
and acquiring environmental characteristics of a microenvironment, constructing a characteristic matrix of the environmental characteristics, inputting the environmental characteristics into the potential disease prediction model to acquire the occurrence probability of each disease in the susceptible disease set, and outputting the potential disease with the highest occurrence probability.
In this scheme, carry out microenvironment regulation and control according to the output result of plant disease and potential disease, specifically do:
constructing a disease knowledge map based on plant types, environmental parameters, disease characteristics and a prevention and control method, extracting the disease knowledge map into a triple form of the knowledge map, determining the current disease severity according to a plant disease identification result, and acquiring corresponding pathogenic environmental parameters according to an output result of a potential disease;
mapping the severity of the current disease and the pathogenic environment parameters corresponding to the potential disease to a knowledge space, and determining a target node in the knowledge map according to the current disease development stage or the pathogenic environment parameters corresponding to the potential disease and the Euclidean distance of each knowledge node in the disease knowledge map;
taking the target node as a sampling starting point, performing expression learning on a knowledge graph by utilizing MetaPath random walk, setting weight information of related nodes according to historical disease frequency of each disease in a target area, and determining constraint conditions according to node contact between the sampling starting point and the control regulation and control nodes;
acquiring MetaPath random walk according to the constraint condition to generate a meta-path containing a target node, sequencing according to total weight information of each node in the meta-path, acquiring a preset number of meta-paths, and extracting an environment regulation scheme corresponding to each meta-path;
and screening the enforceability of each environment regulation scheme in the target area to obtain the final microenvironment regulation scheme.
The second aspect of the invention also provides a system for identifying and evaluating occurrence and potential occurrence of plant diseases, which comprises: the storage comprises a program of a plant disease occurrence and potential occurrence identification and evaluation method, and the program of the plant disease occurrence and potential occurrence identification and evaluation method realizes the following steps when executed by the processor:
acquiring environment basic information and plant type information of a target area where a plant is located, evaluating a microenvironment of the target area according to the environment basic information, and acquiring the growth suitability degree of the microenvironment for the plant type;
storing the survival degree in a database in combination with a timestamp, comparing the currently acquired survival degree with the historical survival degree in the database, and judging whether the reduction amplitude of the survival degree is greater than a preset change threshold value;
if the plant disease is larger than the preset value, analyzing the growth stage of the current plant, acquiring a disease susceptible set according to the growth stage of the plant and a microenvironment evaluation result, and identifying the plant disease based on the disease susceptible set;
and when the plant disease identification result does not contain disease information meeting the standard, acquiring the occurrence probability of the potential diseases according to the environmental characteristics of the current microenvironment, outputting the potential diseases with the highest occurrence probability, and performing microenvironment regulation and control according to the plant diseases and the output results of the potential diseases.
The invention discloses a method and a system for identifying and evaluating occurrence and potential occurrence of plant diseases, wherein the method comprises the following steps: obtaining environment basic information and plant category information of a target area where a plant is located, evaluating a microenvironment of the target area to obtain an adaptive degree, comparing the currently obtained adaptive degree with historical adaptive degrees in a database, obtaining a susceptible disease set according to a growth stage and a microenvironment evaluation result of the plant based on a comparison result, and identifying the plant disease through the susceptible disease set; and when the plant disease identification result does not contain disease information meeting the standard, acquiring the occurrence probability of the potential diseases according to the environmental characteristics of the current microenvironment for outputting, and performing microenvironment regulation and control according to the plant diseases and the output results of the potential diseases. The invention lays a foundation for improving the identification and early warning of plant diseases according to the evaluation result of the microenvironment, and can efficiently, accurately and objectively identify the occurrence and potential occurrence of the diseases, thereby taking corresponding measures to prevent and treat the diseases in time.
Drawings
FIG. 1 is a flow chart illustrating a method for identifying and evaluating the occurrence and potential occurrence of a plant disease according to the present invention;
FIG. 2 is a flow chart of a method for identifying plant diseases based on a disease susceptible set according to the present invention;
FIG. 3 is a flow chart of the method for microenvironment regulation according to the output results of plant diseases and potential diseases;
fig. 4 shows a block diagram of a plant disease occurrence and potential occurrence identification and evaluation system according to the invention.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention, taken in conjunction with the accompanying drawings and detailed description, is set forth below. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.
Fig. 1 shows a flow chart of a method for identifying and evaluating the occurrence and potential occurrence of plant diseases according to the invention.
As shown in fig. 1, the first aspect of the present invention provides a method for identifying and evaluating the occurrence and potential occurrence of plant diseases, comprising:
s102, acquiring environment basic information and plant type information of a target area where a plant is located, evaluating a microenvironment of the target area according to the environment basic information, and acquiring the growth suitability degree of the microenvironment for the plant type;
s104, storing the survival degree in a database in combination with a timestamp, comparing the currently acquired survival degree with the historical survival degree in the database, and judging whether the reduction amplitude of the survival degree is greater than a preset change threshold value;
s106, if the number of the plants is larger than the preset number, analyzing the current growth stage of the plants, acquiring a susceptible disease set according to the growth stage of the plants and a microenvironment evaluation result, and identifying plant diseases based on the susceptible disease set;
and S108, when the plant disease identification result does not contain the disease information meeting the standard, acquiring the occurrence probability of the potential diseases according to the environmental characteristics of the current microenvironment, outputting the potential diseases with the highest occurrence probability, and performing microenvironment regulation and control according to the plant diseases and the output results of the potential diseases.
It should be noted that the environmental basic information includes soil bacteria source, meteorological factors, temperature and humidity information, plant crop rotation information, plant nutrition conditions, management measures and the like, the optimal growth adaptation condition corresponding to the plant category is obtained through data retrieval, evaluation indexes for growth adaptation degree judgment are obtained according to the correlation of each environmental index in the optimal growth adaptation condition, and the environmental technical information of the current target area is obtained to generate index values of each evaluation index; calculating the index score of each evaluation index according to the index value and the score calculation mode of each evaluation index; and matching the index scores of all the evaluation indexes with preset weight information to obtain comprehensive scores of the microenvironment, constructing a comprehensive score threshold interval according to a preset threshold, and determining the growing suitability of the microenvironment of the target area to the plant categories according to the threshold interval in which the comprehensive scores fall.
It should be noted that a database related to the microenvironment of the target area is constructed, the survival degree is stored in the database in combination with the timestamp to generate a survival degree change sequence, and the survival degree is visualized; analyzing the time variation characteristics of the survival degree according to the historical survival degree sequence, and early warning the survival degree of the current microenvironment according to the time variation characteristics and seasonal characteristics; and sending the early warning information according to a preset method, and reminding workers of carrying out preventive regulation and control on the microenvironment generation of the target area through the early warning information. Meanwhile, when the reduction amplitude of the survival degree is larger than a preset change threshold value, disease related early warning information is generated through the database to prompt.
FIG. 2 shows a flow chart of a method for identifying plant diseases based on a disease susceptible set.
According to the embodiment of the invention, the growth stage of the current plant is analyzed, the disease susceptible set is obtained according to the growth stage of the plant and the microenvironment evaluation result, and the plant disease identification is carried out based on the disease susceptible set, which specifically comprises the following steps:
s202, according to plant image information in a target area, preprocessing the image information to extract an interested area corresponding to a plant, and extracting plant image characteristics in the interested area;
s204, determining the current growth stage of the plant based on the plant image characteristics through the plant category information, and performing data retrieval by using a big data means according to the plant category information to obtain the diseased condition of each disease in each growth stage of the plant;
s206, screening the disease types with the disease conditions larger than a preset threshold standard for marking by taking the disease conditions of the diseases corresponding to the current growth stage of the plant as a data base, and carrying out secondary screening on the marked disease types according to the environmental characteristics of the microenvironment to generate a susceptible disease set of the current growth stage of the plant;
s208, constructing a disease recognition model based on deep learning, generating a training sample through a susceptible disease set, training the disease recognition model by using the training sample, and introducing plant image information into the trained disease recognition model;
s210, extracting the global features of plant image information by using a ResNet network, introducing an attention mechanism and combining with a channel feature extraction sub-network to perform feature selection on the global features, setting different weight factors for each channel feature extraction sub-network, and setting preset feature data in each channel feature extraction sub-network according to the weight factors;
s212, performing feature extraction on the global features and preset feature data in each channel feature extraction sub-network by utilizing similarity calculation, and outputting the channel features larger than a preset similarity threshold to a full link layer for aggregation and then outputting;
and S214, performing softmax classification network to identify plant diseases according to the output characteristics.
It should be noted that, the ResNet network is used to extract the global features of the plant image information, and the ResNet network has a feature extraction layerAnConvolution kernel sum ofAnThe pooling kernel component is used for outputting the global characteristics of plant image information after the data matrix is operated by the convolution layer and the pooling layer, performing characteristic extraction by utilizing similarity calculation on the global characteristics and preset characteristic data in each channel characteristic extraction sub-network, screening corresponding characteristics according to preset contents and selecting the optimal characteristic data in the global characteristics to perform plant disease identification on the channel characteristics larger than a preset similarity threshold.
It should be noted that when there is no plant disease identification result in the output of the disease identification model, extracting the environmental characteristic factors corresponding to the occurrence of each disease according to the disease condition of the plant susceptible to the disease at the current growth stage, determining the correlation of the environmental characteristic factors, and performing standardization processing on the environmental characteristic factors corresponding to each disease;
establishing a potential disease prediction model according to the standardized environment characteristic factors based on the Bayesian network structure, performing network structure training by using the standardized environment characteristic factors, calculating the numerical value of each leaf node, generating an optimal network structure of the model, and outputting the potential disease prediction model when the accuracy test of the model meets the preset standard;
and acquiring environmental characteristics of a microenvironment, constructing a characteristic matrix of the environmental characteristics, inputting the environmental characteristics into the potential disease prediction model to acquire the occurrence probability of each disease in the susceptible disease set, and outputting the potential disease with the highest occurrence probability.
It should be noted that the model is built step by step according to the added number of the environmental characteristic factors corresponding to each disease in the model, when a plurality of environmental characteristic factors are added, the number of each leaf node is continuously changed according to the pearson correlation coefficient and the actual logical relationship, the probability accuracy of the Bayesian network prediction is increased by adding new variables, the prior probability of each environmental characteristic factor is obtained through statistical analysis, and the probability information of the disease occurrence is calculated according to the local conditional probability.
FIG. 3 shows a flow chart of the method for micro-environment regulation according to the output results of plant diseases and potential diseases.
According to the embodiment of the invention, microenvironment regulation and control are carried out according to the output results of plant diseases and potential diseases, and the method specifically comprises the following steps:
s302, constructing a disease knowledge map based on plant types, environmental parameters, disease characteristics and a prevention and control method, extracting the disease knowledge map into a triple form of the knowledge map, determining the current disease severity according to a plant disease identification result, and acquiring corresponding pathogenic environmental parameters according to an output result of a potential disease;
s304, mapping the severity of the current disease and the pathogenic environment parameters corresponding to the potential disease to a knowledge space, and determining a target node in the knowledge map according to the pathogenic environment parameters corresponding to the current disease development stage or the potential disease and Euclidean distances of all knowledge nodes in the disease knowledge map;
s306, taking the target node as a sampling starting point, performing expression learning on the knowledge graph by utilizing MetaPath random walk, setting weight information of related nodes according to the historical disease frequency of each disease in the target area, and determining constraint conditions according to the node relation between the sampling starting point and the control regulation and control node;
s308, acquiring MetaPath random walk according to the constraint condition to generate a meta-path containing a target node, sequencing according to total weight information of each node in the meta-path, acquiring a preset number of meta-paths, and extracting an environment regulation scheme corresponding to each meta-path;
s310, screening the enforceability of each environment regulation scheme in the target area to obtain the final microenvironment regulation scheme.
It should be noted that the disease knowledge graph is learned and expressed through the MetaPath random walk, the connection correlation between different types of nodes is captured, the MetaPath random walk performs certain constraint on the walk path, and the formula is as follows:
wherein,the path of the wandering is shown,indicating the first in a random walk pathThe number of the nodes is one,which indicates the type of the node or nodes,representing nodesIs of the typeOf the network.
According to the embodiment of the invention, the change of the microenvironment of the target area is recorded through the database, and an exclusive data set is established, which specifically comprises the following steps:
selecting environmental characteristics of the microenvironment corresponding to the plant type fitness degree standard according to the fitness degree sequence of the microenvironment of the target area and the growth conditions of each stage of the plant;
combining the environmental characteristics of the microenvironment corresponding to the fitness degree standard with the time characteristics to generate a dynamic environmental characteristic set of each growth stage;
when the microenvironment of the target area is regulated, acquiring the characteristic deviation of the environmental characteristics of the current microenvironment and the characteristic data in the dynamic environmental characteristic set, and selecting a regulation scheme with the minimum cost according to the characteristic deviation and the implementation feasibility for implementation;
when the survival degree is greater than the reference and the rising amplitude is greater than the preset change threshold value, marking and storing the corresponding environmental features to generate an exclusive data set of the optimal survival degree of the target area, and optimizing the regulation and control target of the environmental regulation and control scheme of the microenvironment according to the exclusive data set.
Fig. 4 shows a block diagram of a plant disease occurrence and potential occurrence identification and evaluation system according to the invention.
The second aspect of the present invention also provides a plant disease occurrence and potential occurrence identification and evaluation system 4, which comprises: a memory 41 and a processor 42, wherein the memory includes a program for identifying and evaluating the occurrence and potential occurrence of plant diseases, and when the program is executed by the processor, the method realizes the following steps:
acquiring environment basic information and plant type information of a target area where a plant is located, evaluating a microenvironment of the target area according to the environment basic information, and acquiring the growth suitability degree of the microenvironment for the plant type;
storing the survival degree in a database in combination with a timestamp, comparing the currently acquired survival degree with the historical survival degree in the database, and judging whether the reduction amplitude of the survival degree is greater than a preset change threshold value;
if the plant disease is larger than the preset value, analyzing the growth stage of the current plant, acquiring a disease susceptible set according to the growth stage of the plant and a microenvironment evaluation result, and identifying the plant disease based on the disease susceptible set;
and when the plant disease identification result does not contain disease information meeting the standard, acquiring the occurrence probability of the potential diseases according to the environmental characteristics of the current microenvironment, outputting the potential diseases with the highest occurrence probability, and performing microenvironment regulation and control according to the plant diseases and the output results of the potential diseases.
It should be noted that the environmental basic information includes soil bacteria source, meteorological factors, temperature and humidity information, plant crop rotation information, plant nutrition conditions, management measures and the like, the optimal growth adaptation condition corresponding to the plant category is obtained through data retrieval, evaluation indexes for growth adaptation degree judgment are obtained according to the correlation of each environmental index in the optimal growth adaptation condition, and the environmental technical information of the current target area is obtained to generate index values of each evaluation index; calculating the index score of each evaluation index according to the index value and the score calculation mode of each evaluation index; and matching the index scores of all the evaluation indexes with preset weight information to obtain comprehensive scores of the microenvironment, constructing a comprehensive score threshold interval according to a preset threshold, and determining the growing suitability of the microenvironment of the target area to the plant categories according to the threshold interval in which the comprehensive scores fall.
It should be noted that a database related to the microenvironment of the target area is constructed, the survival degree is stored in the database in combination with the timestamp to generate a survival degree change sequence, and the survival degree is visualized; analyzing the time variation characteristics of the survival degree according to the historical survival degree sequence, and early warning the survival degree of the current microenvironment according to the time variation characteristics and seasonal characteristics; and sending the early warning information according to a preset method, and reminding workers of carrying out preventive regulation and control on the microenvironment generation of the target area through the early warning information. Meanwhile, when the reduction amplitude of the survival degree is larger than a preset change threshold value, disease related early warning information is generated through the database to prompt.
According to the embodiment of the invention, the growth stage of the current plant is analyzed, the disease susceptible set is obtained according to the growth stage and the microenvironment evaluation result of the plant, and the plant disease identification is carried out based on the disease susceptible set, which specifically comprises the following steps:
according to the plant image information in the target area, preprocessing the image information to extract an interested area corresponding to the plant, and extracting plant image characteristics in the interested area;
determining the current growth stage of the plant based on the plant image characteristics through the plant category information, and performing data retrieval by using a big data means according to the plant category information to obtain the diseased condition of each disease in each growth stage of the plant;
selecting and marking the disease types of which the diseased conditions are larger than a preset threshold standard by taking the diseased conditions of the diseases corresponding to the current growth stage of the plant as a data base, and secondarily screening the marked disease types according to the environmental characteristics of the microenvironment to generate a disease susceptible set of the current growth stage of the plant;
building a disease recognition model based on deep learning, generating a training sample through a susceptible disease set, training the disease recognition model by using the training sample, and introducing plant image information into the trained disease recognition model;
extracting global features of plant image information by using a ResNet network, introducing an attention mechanism and combining with a channel feature extraction sub-network to perform feature selection on the global features, setting different weight factors for each channel feature extraction sub-network, and setting preset feature data in each channel feature extraction sub-network according to the weight factors;
performing feature extraction on the global features and preset feature data in each channel feature extraction sub-network by utilizing similarity calculation, and outputting channel features larger than a preset similarity threshold to a full link layer for aggregation and then outputting;
and performing softmax classification network to identify plant diseases according to the output characteristics.
It should be noted that, the ResNet network is used to extract the global features of the plant image information, and the ResNet network has a feature extraction layerAnAndanThe pooling kernel component outputs the global characteristics of plant image information after the data matrix is operated by a convolution layer and a pooling layer, performs characteristic extraction by utilizing similarity calculation on the global characteristics and preset characteristic data in each channel characteristic extraction sub-network, realizes screening corresponding characteristics according to preset contents on the channel characteristics larger than a preset similarity threshold value, selects the optimal characteristic data in the global characteristics to perform plant diseaseAnd (5) identifying.
When there is no plant disease identification result in the output of the disease identification model, extracting the environmental characteristic factors corresponding to the occurrence of each disease according to the disease condition of the plant susceptible to the disease in the current growth stage, determining the correlation of the environmental characteristic factors, and performing standardization processing on the environmental characteristic factors corresponding to each disease;
establishing a potential disease prediction model according to the standardized environment characteristic factors based on the Bayesian network structure, performing network structure training by using the standardized environment characteristic factors, calculating the numerical value of each leaf node, generating an optimal network structure of the model, and outputting the potential disease prediction model when the accuracy test of the model meets the preset standard;
and acquiring environmental characteristics of a microenvironment, constructing a characteristic matrix of the environmental characteristics, inputting the environmental characteristics into the potential disease prediction model to acquire the occurrence probability of each disease in the susceptible disease set, and outputting the potential disease with the highest occurrence probability.
It should be noted that the model is established step by step according to the number of the added environment characteristic factors corresponding to each disease in the model, when a plurality of environment characteristic factors are added, the number of each leaf node is continuously changed according to the pearson correlation coefficient and the actual logical relationship, the probability accuracy of the Bayesian network prediction is increased by adding new variables, the prior probability of each environment characteristic factor is obtained through statistical analysis, and the probability information of the disease occurrence is calculated according to the local conditional probability.
According to the embodiment of the invention, microenvironment regulation and control are carried out according to the output results of plant diseases and potential diseases, and the method specifically comprises the following steps:
constructing a disease knowledge map based on plant types, environmental parameters, disease characteristics and a prevention and control method, extracting the disease knowledge map into a triple form of the knowledge map, determining the current disease severity according to a plant disease identification result, and acquiring corresponding pathogenic environmental parameters according to an output result of a potential disease;
mapping the severity of the current disease and the pathogenic environment parameters corresponding to the potential disease to a knowledge space, and determining a target node in the knowledge map according to the current disease development stage or the pathogenic environment parameters corresponding to the potential disease and the Euclidean distance of each knowledge node in the disease knowledge map;
taking the target node as a sampling starting point, performing expression learning on a knowledge graph by utilizing MetaPath random walk, setting weight information of related nodes according to historical disease frequency of each disease in a target area, and determining constraint conditions according to node contact between the sampling starting point and the control regulation and control nodes;
acquiring MetaPath random walk according to the constraint condition to generate a meta-path containing a target node, sequencing according to total weight information of each node in the meta-path, acquiring a preset number of meta-paths, and extracting an environment regulation scheme corresponding to each meta-path;
and screening the enforceability of each environment regulation scheme in the target area to obtain the final microenvironment regulation scheme.
It should be noted that the disease knowledge graph is learned and expressed through the MetaPath random walk, the connection correlation between different types of nodes is captured, the MetaPath random walk performs certain constraint on the walk path, and the formula is as follows:
wherein,the path of the wandering is shown,indicating the first in a random walk pathThe number of the nodes is equal to the number of the nodes,which indicates the type of the node or nodes,representing nodesIs of the typeOf the network.
The third aspect of the present invention also provides a computer readable storage medium, which includes a program of a method for identifying and evaluating occurrence and potential occurrence of plant diseases, when the program of the method for identifying and evaluating occurrence and potential occurrence of plant diseases is executed by a processor, the steps of the method for identifying and evaluating occurrence and potential occurrence of plant diseases as described in any one of the above are implemented.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units; can be located in one place or distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, all the functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and various media capable of storing program codes.
Alternatively, the integrated unit of the present invention may be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or a part contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, a ROM, a RAM, a magnetic or optical disk, or various other media that can store program code.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily think of the changes or substitutions within the technical scope of the present invention, and shall cover the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (6)
1. A method for identifying and evaluating occurrence and potential occurrence of plant diseases is characterized by comprising the following steps:
acquiring environment basic information and plant type information of a target area where a plant is located, evaluating a microenvironment of the target area according to the environment basic information, and acquiring the growth suitability degree of the microenvironment for the plant type;
storing the survival degree in a database in combination with a timestamp, comparing the currently acquired survival degree with the historical survival degree in the database, and judging whether the reduction amplitude of the survival degree is greater than a preset change threshold value;
if the plant disease is larger than the preset value, analyzing the growth stage of the current plant, acquiring a disease susceptible set according to the growth stage of the plant and a microenvironment evaluation result, and identifying the plant disease based on the disease susceptible set;
when the plant disease identification result does not contain disease information meeting the standard, acquiring the occurrence probability of potential diseases according to the environmental characteristics of the current microenvironment, outputting the potential diseases with the highest occurrence probability, and performing microenvironment regulation and control according to the plant diseases and the output results of the potential diseases;
analyzing the growth stage of the current plant, acquiring a susceptible disease set according to the growth stage of the plant and a microenvironment evaluation result, and identifying plant diseases based on the susceptible disease set, wherein the susceptible disease set specifically comprises the following steps:
according to the plant image information in the target area, preprocessing the image information to extract an interested area corresponding to the plant, and extracting plant image characteristics in the interested area;
determining the current growth stage of the plant based on the plant image characteristics through the plant category information, and performing data retrieval by using a big data means according to the plant category information to obtain the diseased condition of each disease in each growth stage of the plant;
selecting and marking the disease types of which the diseased conditions are larger than a preset threshold standard by taking the diseased conditions of the diseases corresponding to the current growth stage of the plant as a data base, and secondarily screening the marked disease types according to the environmental characteristics of the microenvironment to generate a disease susceptible set of the current growth stage of the plant;
building a disease recognition model based on deep learning, generating a training sample through a susceptible disease set, training the disease recognition model by using the training sample, and introducing plant image information into the trained disease recognition model;
extracting global features of plant image information by using a ResNet network, introducing an attention mechanism and combining with a channel feature extraction sub-network to perform feature selection on the global features, setting different weight factors for each channel feature extraction sub-network, and setting preset feature data in each channel feature extraction sub-network according to the weight factors;
performing feature extraction on the global features and preset feature data in each channel feature extraction sub-network by utilizing similarity calculation, and outputting channel features larger than a preset similarity threshold to a full link layer for aggregation and then outputting;
performing softmax classification network to identify plant diseases according to the output characteristics;
the microenvironment regulation and control are carried out according to the output results of the plant diseases and the potential diseases, and the method specifically comprises the following steps:
constructing a disease knowledge map based on plant types, environmental parameters, disease characteristics and a prevention and control method, extracting the disease knowledge map into a triple form of the knowledge map, determining the current disease severity according to a plant disease identification result, and acquiring corresponding pathogenic environmental parameters according to an output result of a potential disease;
mapping the severity of the current disease and the pathogenic environment parameters corresponding to the potential disease to a knowledge space, and determining a target node in the knowledge map according to the current disease development stage or the pathogenic environment parameters corresponding to the potential disease and the Euclidean distance of each knowledge node in the disease knowledge map;
the target node is used as a sampling starting point, a knowledge graph is expressed and learned by utilizing MetaPath random walk, weight information of related nodes is set according to the historical disease frequency of each disease in the target area, and constraint conditions are determined according to the node connection between the sampling starting point and the control regulation and control node;
acquiring MetaPath random walk according to the constraint condition to generate a meta-path containing a target node, sequencing according to total weight information of each node in the meta-path, acquiring a preset number of meta-paths, and extracting an environment regulation scheme corresponding to each meta-path;
and screening the enforceability of each environment regulation scheme in the target area to obtain the final microenvironment regulation scheme.
2. The method for identifying and evaluating the occurrence and potential occurrence of plant diseases according to claim 1, wherein the environmental basic information and the plant type information of the target area where the plant is located are obtained, the microenvironment of the target area is evaluated according to the environmental basic information, and the growth suitability degree of the microenvironment for the plant type is obtained, specifically:
acquiring optimal adaptive growth conditions corresponding to plant categories through data retrieval, acquiring evaluation indexes for judging adaptive growth degree according to the correlation of each environmental index in the optimal adaptive growth conditions, and acquiring environmental technical information of a current target area to generate index values of each evaluation index;
calculating the index score of each evaluation index according to the index value and the score calculation mode of each evaluation index;
and matching the index scores of all the evaluation indexes with preset weight information to obtain comprehensive scores of the microenvironment, constructing a comprehensive score threshold interval according to a preset threshold, and determining the growing suitability of the microenvironment of the target area to the plant categories according to the threshold interval in which the comprehensive scores fall.
3. The method for identifying and evaluating the occurrence and potential occurrence of plant diseases according to claim 1, wherein the degree of fitness is stored in a database in combination with a time stamp, specifically:
constructing a database related to the microenvironment of the target area, storing the survival degree in the database in combination with the timestamp to generate a survival degree change sequence, and performing visualization processing on the survival degree;
analyzing the time variation characteristics of the survival degree according to the historical survival degree sequence, and early warning the survival degree of the current microenvironment according to the time variation characteristics and the seasonal characteristics;
sending the early warning information according to a preset method, and reminding workers of carrying out preventive regulation and control on the microenvironment generation of the target area through the early warning information;
meanwhile, when the reduction amplitude of the survival degree is larger than a preset change threshold value, disease related early warning information is generated through the database to prompt.
4. The method for identifying and evaluating the occurrence and potential occurrence of plant diseases according to claim 1, wherein when the plant disease identification result does not contain disease information meeting a standard, the occurrence probability of the potential occurrence of the disease is obtained according to the environmental characteristics of the current microenvironment, and the potential disease with the highest occurrence probability is output, specifically:
when no plant disease identification result exists in the output of the disease identification model, extracting the environmental characteristic factors corresponding to the occurrence of the diseases according to the disease conditions of the plants susceptible to the diseases in the current growth stage, determining the correlation of the environmental characteristic factors, and carrying out standardization treatment on the environmental characteristic factors corresponding to the diseases;
establishing a potential disease prediction model according to the standardized environment characteristic factors based on the Bayesian network structure, performing network structure training by using the standardized environment characteristic factors, calculating the numerical value of each leaf node, generating an optimal network structure of the model, and outputting the potential disease prediction model when the accuracy test of the model meets the preset standard;
and acquiring environmental characteristics of a microenvironment, constructing a characteristic matrix of the environmental characteristics, inputting the environmental characteristics into the potential disease prediction model to acquire the occurrence probability of each disease in the susceptible disease set, and outputting the potential disease with the highest occurrence probability.
5. A system for identifying and evaluating the occurrence and potential occurrence of plant diseases, the system comprising: the storage comprises a program of a plant disease occurrence and potential occurrence identification and evaluation method, and the program of the plant disease occurrence and potential occurrence identification and evaluation method realizes the following steps when being executed by the processor:
acquiring environment basic information and plant type information of a target area where a plant is located, evaluating a microenvironment of the target area according to the environment basic information, and acquiring the growth suitability degree of the microenvironment for the plant type;
storing the survival degree in a database in combination with a timestamp, comparing the currently acquired survival degree with the historical survival degree in the database, and judging whether the reduction amplitude of the survival degree is greater than a preset change threshold value;
if the plant disease is larger than the preset value, analyzing the growth stage of the current plant, acquiring a disease susceptible set according to the growth stage of the plant and a microenvironment evaluation result, and identifying the plant disease based on the disease susceptible set;
when the plant disease identification result does not contain disease information meeting the standard, acquiring the occurrence probability of potential diseases according to the environmental characteristics of the current microenvironment, outputting the potential diseases with the highest occurrence probability, and performing microenvironment regulation and control according to the plant diseases and the output results of the potential diseases;
analyzing the growth stage of the current plant, acquiring a susceptible disease set according to the growth stage of the plant and a microenvironment evaluation result, and identifying plant diseases based on the susceptible disease set, wherein the method specifically comprises the following steps:
according to the plant image information in the target area, preprocessing the image information to extract an interested area corresponding to the plant, and extracting plant image characteristics in the interested area;
determining the current growth stage of the plant based on the plant image characteristics through the plant category information, and performing data retrieval by using a big data means according to the plant category information to obtain the diseased condition of each disease in each growth stage of the plant;
selecting and marking the disease types of which the diseased conditions are larger than a preset threshold standard by taking the diseased conditions of the diseases corresponding to the current growth stage of the plant as a data base, and secondarily screening the marked disease types according to the environmental characteristics of the microenvironment to generate a disease susceptible set of the current growth stage of the plant;
building a disease recognition model based on deep learning, generating a training sample through a susceptible disease set, training the disease recognition model by using the training sample, and introducing plant image information into the trained disease recognition model;
extracting global features of plant image information by using a ResNet network, introducing an attention mechanism and combining with a channel feature extraction sub-network to perform feature selection on the global features, setting different weight factors for each channel feature extraction sub-network, and setting preset feature data in each channel feature extraction sub-network according to the weight factors;
performing feature extraction on the global features and preset feature data in each channel feature extraction sub-network by utilizing similarity calculation, and outputting channel features larger than a preset similarity threshold to a full link layer for aggregation and then outputting;
performing softmax classification network to identify plant diseases according to the output characteristics;
the microenvironment regulation and control are carried out according to the output results of the plant diseases and the potential diseases, and the method specifically comprises the following steps:
constructing a disease knowledge map based on plant types, environmental parameters, disease characteristics and a prevention and control method, extracting the disease knowledge map into a triple form of the knowledge map, determining the current disease severity according to a plant disease identification result, and acquiring corresponding pathogenic environmental parameters according to an output result of a potential disease;
mapping the severity of the current disease and the pathogenic environment parameters corresponding to the potential disease to a knowledge space, and determining a target node in the knowledge map according to the current disease development stage or the pathogenic environment parameters corresponding to the potential disease and the Euclidean distance of each knowledge node in the disease knowledge map;
taking the target node as a sampling starting point, performing expression learning on a knowledge graph by utilizing MetaPath random walk, setting weight information of related nodes according to historical disease frequency of each disease in a target area, and determining constraint conditions according to node contact between the sampling starting point and the control regulation and control nodes;
acquiring MetaPath random walk according to the constraint condition to generate a meta-path containing a target node, sequencing according to total weight information of each node in the meta-path, acquiring a preset number of meta-paths, and extracting an environment regulation scheme corresponding to each meta-path;
and screening the enforceability of each environment regulation scheme in the target area to obtain the final microenvironment regulation scheme.
6. The system for identifying and evaluating the occurrence and potential occurrence of plant diseases according to claim 5, wherein when the plant disease identification result does not contain disease information meeting the standard, the occurrence probability of the potential occurrence of the disease is obtained according to the environmental characteristics of the current microenvironment, and the potential disease with the highest occurrence probability is output, specifically:
when no plant disease identification result exists in the output of the disease identification model, extracting the environmental characteristic factors corresponding to the occurrence of each disease according to the disease condition of the plant susceptible to the disease in the current growth stage, determining the correlation of the environmental characteristic factors, and carrying out standardization treatment on the environmental characteristic factors corresponding to each disease;
establishing a potential disease prediction model according to the standardized environment characteristic factors based on the Bayesian network structure, performing network structure training by using the standardized environment characteristic factors, calculating the numerical value of each leaf node, generating an optimal network structure of the model, and outputting the potential disease prediction model when the accuracy test of the model meets the preset standard;
and acquiring environmental characteristics of a microenvironment, constructing a characteristic matrix of the environmental characteristics, inputting the environmental characteristics into the potential disease prediction model to acquire the occurrence probability of each disease in the susceptible disease set, and outputting the potential disease with the highest occurrence probability.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211587372.XA CN115660291B (en) | 2022-12-12 | 2022-12-12 | Plant disease occurrence and potential occurrence identification and evaluation method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211587372.XA CN115660291B (en) | 2022-12-12 | 2022-12-12 | Plant disease occurrence and potential occurrence identification and evaluation method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115660291A CN115660291A (en) | 2023-01-31 |
CN115660291B true CN115660291B (en) | 2023-03-14 |
Family
ID=85020103
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211587372.XA Active CN115660291B (en) | 2022-12-12 | 2022-12-12 | Plant disease occurrence and potential occurrence identification and evaluation method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115660291B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116386869B (en) * | 2023-04-11 | 2024-01-19 | 中国科学技术大学 | Disease critical degree assessment method based on multiple variables |
CN116246176B (en) * | 2023-05-12 | 2023-09-19 | 山东建筑大学 | Crop disease detection method and device, electronic equipment and storage medium |
CN116976671B (en) * | 2023-08-01 | 2024-04-16 | 哈尔滨市大地勘察测绘有限公司 | Comprehensive informatization management method and system for unmanned farm |
CN117496196B (en) * | 2023-11-03 | 2024-07-16 | 廊坊市园林绿化事务中心 | Garden plant maintenance monitoring method, system, equipment and medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112598031A (en) * | 2020-12-08 | 2021-04-02 | 北京农业信息技术研究中心 | Vegetable disease detection method and system |
CN113095555A (en) * | 2021-03-31 | 2021-07-09 | 佛山一本农业科技有限公司 | Crop disease and insect pest monitoring method and system based on Internet of things and storage medium |
CN114511157A (en) * | 2022-04-18 | 2022-05-17 | 广东省农业科学院植物保护研究所 | Microecological regulation and control method and system based on vegetable bacterial wilt prevention and control |
CN114707773A (en) * | 2022-06-06 | 2022-07-05 | 广东省农业科学院植物保护研究所 | Insect pest control scheme generation method and system based on deep learning and storage medium |
CN115311588A (en) * | 2022-09-16 | 2022-11-08 | 航天宏图信息技术股份有限公司 | Pine wood nematode disease stumpage detection method and device based on unmanned aerial vehicle remote sensing image |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2009142758A1 (en) * | 2008-05-23 | 2009-11-26 | Spectral Image, Inc. | Systems and methods for hyperspectral medical imaging |
CN111695593A (en) * | 2020-04-29 | 2020-09-22 | 平安科技(深圳)有限公司 | XGboost-based data classification method and device, computer equipment and storage medium |
-
2022
- 2022-12-12 CN CN202211587372.XA patent/CN115660291B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112598031A (en) * | 2020-12-08 | 2021-04-02 | 北京农业信息技术研究中心 | Vegetable disease detection method and system |
CN113095555A (en) * | 2021-03-31 | 2021-07-09 | 佛山一本农业科技有限公司 | Crop disease and insect pest monitoring method and system based on Internet of things and storage medium |
CN114511157A (en) * | 2022-04-18 | 2022-05-17 | 广东省农业科学院植物保护研究所 | Microecological regulation and control method and system based on vegetable bacterial wilt prevention and control |
CN114707773A (en) * | 2022-06-06 | 2022-07-05 | 广东省农业科学院植物保护研究所 | Insect pest control scheme generation method and system based on deep learning and storage medium |
CN115311588A (en) * | 2022-09-16 | 2022-11-08 | 航天宏图信息技术股份有限公司 | Pine wood nematode disease stumpage detection method and device based on unmanned aerial vehicle remote sensing image |
Also Published As
Publication number | Publication date |
---|---|
CN115660291A (en) | 2023-01-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN115660291B (en) | Plant disease occurrence and potential occurrence identification and evaluation method and system | |
RU2607999C2 (en) | Use of machine learning techniques for extraction of association rules in datasets of plants and animals containing molecular genetic markers accompanied by classification or prediction using features created by these association rules | |
CN112270129B (en) | Plant growth prediction method based on big data analysis | |
Modi et al. | Crop recommendation using machine learning algorithm | |
Parameswari et al. | Machine learning approaches for crop recommendation | |
Setiadi et al. | Implementation of naïve bayes method in food crops planting recommendation | |
CN115618021A (en) | Method and device for recommending suitable planting area of crop variety | |
CN112163020A (en) | Multi-dimensional time series anomaly detection method and system | |
CN117670066A (en) | Judicial management method, system, equipment and storage medium based on intelligent decision | |
CN117592870B (en) | Comprehensive analysis system based on water environment monitoring information | |
CN117173400B (en) | Low-carbon treatment scheme recommendation method and system for litchi insect pest | |
CN117481654A (en) | Depression symptom state detection method based on bias mark learning | |
Sundari et al. | Crop recommendation and yield prediction using machine learning algorithms | |
CN116150604B (en) | Transformer fault diagnosis method and device and electronic equipment | |
CN111816311A (en) | State identification method, system and device | |
Thangarasu et al. | Detection of Cyberbullying Tweets in Twitter Media Using Random Forest Classification | |
CN114742599A (en) | User value layering method and device based on self-training, storage medium and equipment | |
Suchithra et al. | Label ranking‐based recommendation system to rank crops for agroecological units | |
Işık et al. | Predicting soil quality index with a deep regression approach | |
CN117476183B (en) | Construction system of autism children rehabilitation effect AI evaluation model | |
Sabeeh et al. | Enhancing Agricultural Decision-Making through Data Analysis: Predicting Crop Health Outcomes | |
CN117745148B (en) | Multi-source data-based rice stubble flue-cured tobacco planting quality evaluation method and system | |
Streefland et al. | A Gradient Boosting model to predict the milk production | |
CN117976081B (en) | Composting formula method, system, equipment and medium based on model predictive optimization | |
Khoza | Predicting process performance in the manufacturing and agricultural sectors using machine learning techniques |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |