WO2018058821A1 - Disease and insect pest forecasting method and apparatus based on planting equipment - Google Patents

Disease and insect pest forecasting method and apparatus based on planting equipment Download PDF

Info

Publication number
WO2018058821A1
WO2018058821A1 PCT/CN2016/112338 CN2016112338W WO2018058821A1 WO 2018058821 A1 WO2018058821 A1 WO 2018058821A1 CN 2016112338 W CN2016112338 W CN 2016112338W WO 2018058821 A1 WO2018058821 A1 WO 2018058821A1
Authority
WO
WIPO (PCT)
Prior art keywords
pest
diseases
prediction model
target plant
pests
Prior art date
Application number
PCT/CN2016/112338
Other languages
French (fr)
Chinese (zh)
Inventor
王刚
Original Assignee
深圳前海弘稼科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳前海弘稼科技有限公司 filed Critical 深圳前海弘稼科技有限公司
Publication of WO2018058821A1 publication Critical patent/WO2018058821A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
    • G01D21/00—Measuring or testing not otherwise provided for
    • G01D21/02—Measuring two or more variables by means not covered by a single other subclass
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/0098—Plants or trees

Definitions

  • the invention relates to the field of planting technology, in particular to a method and a device for predicting pests and diseases based on planting equipment.
  • planting equipment such as planting boxes and planting greenhouses are gradually increasing. Most of the planting boxes are used for the cultivation of small vegetable plants, which can be used not only for home decoration, but also for entertainment and parent-child education. Planting greenhouses are mostly used for the cultivation of large-scale vegetable plants, which can create economic benefits for users.
  • Plants grown in planting equipment are inevitably subject to pests and diseases if not properly maintained. Once the plants in the planting equipment are subject to pests and diseases, the user will be greatly damaged. Therefore, how to predict whether plants will develop pests and diseases in the next stage of growth is a technical problem that needs to be solved.
  • the object of the present invention is to provide a method and a device for predicting pests and diseases based on planting equipment, so as to accurately predict whether a target plant will develop pests and diseases in the next growth stage, and facilitate planting equipment or users to take relevant measures in time to reduce pests and diseases. The loss comes to enhance the user experience.
  • the present invention provides the following technical solutions:
  • a method for predicting pests and diseases based on planting equipment comprising:
  • the pest and disease prediction model is pre-established by the following steps:
  • each set of data in the training set includes the actual occurrence result of the pest and the pest and the influence dimension information in the plant growth process corresponding to the actual occurrence result of the pest and the pest;
  • the training set is used for machine learning to establish the pest prediction model.
  • the using the training set for machine learning to establish the pest and disease prediction model includes:
  • the predicting whether the target plant will cause pests and diseases in the next growth stage according to the influence dimension information of the target plant and the pre-established pest prediction model include:
  • the influence dimension information of the target plant is input into a pre-established pest prediction model, and a logistic regression algorithm is used to predict whether the target plant will have pests and diseases in the next growth stage.
  • the method further includes:
  • the pest and disease warning information is output.
  • the outputting pest and disease warning information includes:
  • the pest and disease warning information is sent to the planting equipment, so that the planting equipment adjusts corresponding environmental parameters according to the set plan.
  • a pest and disease prediction device based on planting equipment comprising:
  • a target plant determining module for determining a target plant to be predicted to grow in the planting device
  • a growth environment data obtaining module configured to obtain growth environment data of the target plant
  • An influence dimension information determining module configured to analyze the growth environment data, and determine influence dimension information that affects the pests and diseases of the target plant
  • a pest and disease prediction module configured to predict whether a pest or a pest occurs in the next growth stage according to the impact dimension information of the target plant and a pre-established pest prediction model
  • a pest prediction model establishing module configured to pre-establish the pest prediction model by: obtaining a plurality of sets of pest sample data of the same species as the target plant; and constructing a training set according to the obtained pest sample data, Each set of data in the training set includes the actual occurrence results of the pests and diseases and the influence dimension information in the plant growth process corresponding to the actual occurrence of the pests and diseases; using the training set for machine learning, the pest and disease prediction model is established.
  • the pest and disease prediction model establishing module is specifically configured to:
  • the pest prediction module is specifically configured to:
  • the method further includes an early warning information output module, configured to:
  • the pest warning information is output when the target plant is predicted to have pests and diseases in the next growth stage.
  • the early warning information output module is specifically configured to:
  • the pest and disease warning information is sent to the planting equipment, so that the planting equipment adjusts corresponding environmental parameters according to the set plan.
  • the pest and disease prediction model is pre-established by machine learning, and the target plant of the target plant to be predicted and grown in the planting equipment is determined, and the growth environment data of the target plant can be obtained, and the growth environment data is analyzed.
  • the impact dimension information affecting the target plant pests and diseases according to the impact dimension information of the target plant and the pre-established pest and disease prediction model, it can be predicted whether the target plant will have pests and diseases in the next growth stage.
  • FIG. 1 is a flow chart showing an implementation of a method for predicting pests and diseases based on planting equipment according to an embodiment of the present invention
  • FIG. 2 is a schematic structural view of a pest and disease prediction device based on planting equipment according to an embodiment of the present invention.
  • FIG. 1 is a flowchart of an implementation method for predicting pests and diseases based on planting equipment according to an embodiment of the present invention, the method may include the following steps:
  • S110 Determine a target plant to be predicted to grow pests and diseases in the planting equipment.
  • the target plant is a plant grown in planting equipment such as a planting box or a planting greenhouse, and may be in a certain growth stage.
  • the target plant may be subject to pests and diseases during the growth process due to the environmental conditions in which it is exposed. If the user or planting equipment can know in advance whether the target plant will cause pests and diseases in the next growth stage, it will help the user or planting equipment to take corresponding measures in advance, such as adjusting environmental parameters, etc., to reduce the losses caused by pests and diseases.
  • the technical solution provided by the embodiments of the present invention can be used to predict whether a target plant will develop pests and diseases in the next growth stage according to the predicted demand of the pests and diseases of the target plants.
  • the target plant to be predicted for the pest and the disease is determined, and the target plant to be predicted for the pest and disease is determined according to the set period, and the target plant is periodically grown next. Whether pests and diseases will occur in the stage for prediction.
  • the growth environment data is environmental information data during the growth process.
  • the growth environment data may be data such as humidity, temperature, carbon dioxide content in the air, amount of light, pH of the soil, and content of chemical components in the soil.
  • growth environment data of the target plant can be obtained.
  • the environmental information of the target plant can be obtained and recorded in real time through environmental monitoring means, for example, the temperature information is obtained by the temperature sensor built in the planting device, and the humidity information is obtained by the humidity sensor built in the planting device. .
  • the information can be stored in a database, and after determining the target plant to be predicted for pests and diseases, the growth environment data of the target plant is extracted in the database.
  • S130 Analyze the growth environment data to determine the influence dimension information that affects the pests and diseases of the target plant.
  • each type of growth environment data can be used as an influence dimension affecting plant diseases and insect pests.
  • the influence dimension may be temperature, humidity, carbon dioxide content in the air, amount of light, pH of the soil, and content of chemical components in the soil.
  • the growth environment data of the target plant is obtained in step S120, and the growth environment data may be further analyzed to determine the influence dimension information that affects the pest occurrence of the target plant.
  • the influence dimension a information is 124
  • the influence dimension b information is 159
  • the influence dimension c information is 255
  • the influence dimension d information is 31, and the influence dimension e information is 96.
  • Each of the influence dimension information may be a quantized value obtained by quantizing the actual value according to a preset quantization standard.
  • the influence dimension a is the content of the chemical composition in the soil. When the content is in the range of [0%, 20%], it can be quantified as 51, when the content is in the range of [40%, 60%]. It can be quantized to 124.
  • S140 predict whether the target plant will have pests and diseases in the next growth stage according to the influence dimension information of the target plant and the pre-established pest and disease prediction model.
  • the pest prediction model can be established in advance. Specifically, a pest and disease prediction model corresponding to the plant can be established for each plant, and a plurality of pest pest prediction models are classified into a model library for maintenance and management. When it is necessary to predict whether a target plant will develop pests and diseases in the next growth stage, a pest and disease prediction model corresponding to the target plant may be selected in the model library.
  • the pest prediction model can be established in advance by the following steps:
  • Step 1 obtaining a plurality of sets of pest and disease sample data of plants of the same species as the target plant;
  • Step 2 According to the obtained sample data of pests and diseases, construct a training set, and each set of data in the training set includes the actual occurrence result of the pests and diseases and the influence dimension information in the plant growth process corresponding to the actual occurrence result of the pests and diseases;
  • Step 3 Use the training set for machine learning and establish a pest and disease prediction model.
  • a plurality of sets of pest sample data of plants of the same species as the target plant can be obtained from an existing sample database or by means of collection.
  • the target plant is tomato
  • the pest and disease sample data of the tomato grown under different growth environments can be obtained.
  • a training set can be constructed.
  • Each set of data in the training set contains the actual occurrence results of the pests and diseases and the influence dimension information in the plant growth process corresponding to the actual occurrence of the pests and diseases.
  • the first set of data indicates that under the condition that the influence dimension a information is 51, the influence dimension b information is 159, the influence dimension c information is 253, the influence dimension d information is 159, and the influence dimension e information is 50, The actual occurrence of tomato pests and diseases is “not sick”.
  • the second set of data shows that the influence dimension a information is 124, the influence dimension b information is 253, the influence dimension c information is 255, the influence dimension d information is 63, and the influence dimension Under the condition that the e-information is 96, the actual occurrence of pests and diseases of tomato is "get sick", ....
  • Each of the influence dimension information in Table 2 is a result of quantification according to a preset quantization standard.
  • the training set for machine learning. Specifically, you can use the SparkMLlib tool for machine learning. After machine learning of the training set, a pest and disease prediction model can be established, and the pest prediction model The type corresponds to the type of the target plant.
  • the step of establishing a pest prediction model may include the following steps:
  • the first step using the training set for machine learning, establishing an initial pest prediction model
  • the second step determining the pest test results corresponding to each group of influence dimension information in the training set according to the influence dimension information and the initial pest and disease prediction model in the training set;
  • the third step comparing the pest test results corresponding to each group of influence dimension information in the training set with the corresponding actual occurrences of the pests and diseases, and calculating the error value;
  • the fourth step if the error value is not greater than the set threshold, the initial pest prediction model is determined as a pest prediction model;
  • the fifth step if the error value is greater than the set threshold, the training set is expanded, and the first step is repeatedly executed until the error value is not greater than the set threshold, and the pest prediction model is obtained.
  • the amount of data contained in the training set determines the accuracy of the prediction of the pest prediction model.
  • the pest and disease test results corresponding to each group of impact dimension information in the training set can be determined according to the influence dimension information in the training set and the initial pest and disease prediction model.
  • the data file of the training set is:
  • 0 no disease
  • 1 means sick.
  • the error value can be calculated.
  • Plant name Pest test results Actual occurrence of pests and diseases tomato 0.0 0.0 tomato 1.0 1.0 tomato 1.0 1.0 tomato 1.0 1.0 tomato 1.0 1.0
  • the error value is not greater than the set threshold, it indicates that the current initial pest pest prediction model can reach the set requirement, and the initial pest pest prediction model can be directly determined as the pest pest prediction model.
  • the threshold value can be set and adjusted according to the actual situation, which is not limited by the embodiment of the present invention.
  • the training set can be expanded. Specifically, more pest sample data can be collected. Build a training set.
  • the steps of using the training set for machine learning can be repeatedly performed until the error value is not greater than the set threshold, and the current pest prediction model is obtained for subsequent business use. In this way, the prediction accuracy of the pest prediction model can be improved.
  • the impact dimension information of the target plant and the pre-established pest and disease prediction model it can be predicted whether the target plant will have pests and diseases in the next growth stage.
  • the impact dimension information of the target plant is input into a pre-established pest prediction model, and a logistic regression algorithm is used to predict whether the target plant will develop pests and diseases in the next growth stage.
  • the pest and disease prediction model is pre-established by machine learning, and after determining the target plant to be predicted to grow pests and diseases in the planting equipment, the growth environment data of the target plant can be obtained, and the growth environment data is analyzed. Determine the influence dimension information that affects the target plant's pests and diseases. According to the impact dimension information of the target plant and the pre-established pest and disease prediction model, it can be predicted whether the target plant will have pests and diseases in the next growth stage.
  • the method can accurately predict whether the target plant will cause pests and diseases in the next growth stage, and facilitate planting equipment or users to take relevant measures in time to reduce the losses caused by pests and diseases and improve the user experience.
  • the method may further comprise the following steps:
  • the pest and disease warning information will be output.
  • the pest and disease warning information is output.
  • the warning information may be output to the planting equipment, and the built-in pest warning indicator flashes by the planting equipment, or the warning may be The information is output to the user, so that the user takes corresponding measures for the warning information.
  • the pest and disease warning information may be specifically sent to the planting equipment, so that the planting equipment adjusts the corresponding environmental parameters according to the set plan.
  • a plan can be set for pests and diseases and stored in the planting equipment.
  • the planting equipment receives the pest and disease warning information
  • the corresponding environmental parameters can be adjusted according to the set plan. For example, the temperature inside the planting device is adjusted by its built-in thermostat, or the nutrient solution is replaced by its built-in nutrient replacement device.
  • the embodiment of the present invention further provides a pest and disease prediction device based on planting equipment, a pest control device based on planting equipment described below and a pest and disease prediction based on planting equipment described above
  • the methods can be referred to each other.
  • the device includes the following modules:
  • a target plant determining module 210 configured to determine a target plant to be predicted to grow pests and diseases within the planting device
  • a growth environment data obtaining module 220 configured to obtain growth environment data of the target plant
  • the impact dimension information determining module 230 is configured to analyze the growth environment data to determine the impact dimension information that affects the pests and diseases of the target plant;
  • the pest and disease prediction module 240 is configured to predict whether the target plant will have pests and diseases in the next growth stage according to the influence dimension information of the target plant and the pre-established pest and disease prediction model;
  • the pest prediction model establishing module 250 is configured to pre-establish the pest prediction model by the following steps: Type: Obtaining a plurality of sets of pest and disease sample data of plants of the same species as the target plant; constructing a training set according to the obtained pest and disease sample data, each set of data in the training set includes the actual occurrence of the pests and diseases and the plant growth corresponding to the actual occurrence of the pests and diseases Influencing dimensional information in the process; using training sets for machine learning, establishing pest and disease prediction models.
  • the apparatus provided by the embodiment of the present invention pre-establishes a pest and disease prediction model through machine learning, determines a target plant to be predicted to grow pests and diseases in the planting equipment, obtains growth environment data of the target plant, and analyzes the growth environment data. Determine the influence dimension information that affects the target plant's pests and diseases. According to the impact dimension information of the target plant and the pre-established pest and disease prediction model, it can be predicted whether the target plant will have pests and diseases in the next growth stage.
  • the device provided by the embodiment of the invention it is possible to accurately predict whether the target plant will have pests and diseases in the next growth stage, and it is convenient for the planting equipment or the user to take relevant measures in time to reduce the loss caused by the pests and diseases and improve the user experience.
  • the pest prediction model establishing module 250 is specifically configured to:
  • the pest test results corresponding to each group of influence dimension information in the training set are determined;
  • the initial pest prediction model is determined as a pest prediction model
  • the training set is expanded, and the step of performing machine learning using the training set is repeatedly performed until the error value is not greater than the set threshold, and the pest prediction model is obtained.
  • the pest prediction module 240 is specifically configured to:
  • the impact dimension information of the target plant is input into a pre-established pest prediction model, and a logistic regression algorithm is used to predict whether the target plant will develop pests and diseases in the next growth stage.
  • the method further includes an early warning information output module, configured to:
  • the pest and disease warning information is output.
  • the early warning information output module is specifically configured to:
  • the pest and disease warning information is sent to the planting equipment, so that the planting equipment adjusts the corresponding environmental parameters according to the set plan.
  • the steps of a method or algorithm described in connection with the embodiments disclosed herein can be implemented directly in hardware, a software module executed by a processor, or a combination of both.
  • the software module can be placed in random access memory (RAM), memory, read only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or technical field. Any other form of storage medium known.

Landscapes

  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Medicinal Chemistry (AREA)
  • Botany (AREA)
  • Food Science & Technology (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Wood Science & Technology (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Catching Or Destruction (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

A disease and insect pest forecasting method and apparatus based on planting equipment. The method comprises the following steps: pre-building a disease and insect pest forecasting model by means of machine learning, to determine target plants which grow in planting equipment and on which disease and insect pest forecasting is to be performed (S110); obtaining growing environment data of the target plants (S120); analyzing the growing environment data to determine influence dimension information influencing the occurrence of diseases and insect pests in the target plants (S130); and forecasting whether the diseases and insect pests will occur in the target plants in the next growth stage according to the influence dimension information of the target plants and the pre-built disease and insect pest forecasting model (S140). The method and apparatus can accurately forecast whether diseases and insect pests will occur in the target plants in the next growth stage, so that the planting equipment or a user can take relevant measures in time to reduce loss caused by the diseases and insect pests, and user experience is improved.

Description

一种基于种植设备的病虫害预测方法及装置Method and device for predicting pests and diseases based on planting equipment
本申请要求于2016年9月30日提交中国专利局、申请号为201610875105.0、发明名称为“一种基于种植设备的病虫害预测方法及装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。This application claims priority to Chinese Patent Application No. 201610875105.0, entitled "A Method and Apparatus for Pest Control Based on Planting Equipment", filed on September 30, 2016, the entire contents of which are incorporated by reference. In this application.
技术领域Technical field
本发明涉及种植技术领域，特别是涉及一种基于种植设备的病虫害预测方法及装置。The invention relates to the field of planting technology, in particular to a method and a device for predicting pests and diseases based on planting equipment.
背景技术Background technique
随着科学技术的发展进步，种植箱、种植大棚等种植设备逐渐增多。种植箱多数应用于小型蔬菜植物的种植，不仅可以用于家庭装饰，还可以达到娱乐及亲子教育的目的。种植大棚多数应用于大规模蔬菜植物的种植，可以为用户创造经济效益。With the development of science and technology, planting equipment such as planting boxes and planting greenhouses are gradually increasing. Most of the planting boxes are used for the cultivation of small vegetable plants, which can be used not only for home decoration, but also for entertainment and parent-child education. Planting greenhouses are mostly used for the cultivation of large-scale vegetable plants, which can create economic benefits for users.
在种植设备中生长的植物，如果维护不当，难免会遭受病虫害。一旦种植设备中植物遭受病虫害，将给用户带来较大损失。所以，如何预测植物下一生长阶段是否会发生病虫害，是目前亟需解决的技术问题。Plants grown in planting equipment are inevitably subject to pests and diseases if not properly maintained. Once the plants in the planting equipment are subject to pests and diseases, the user will be greatly damaged. Therefore, how to predict whether plants will develop pests and diseases in the next stage of growth is a technical problem that needs to be solved.
发明内容Summary of the invention
本发明的目的是提供一种基于种植设备的病虫害预测方法及装置，以对目标植物在下一生长阶段是否会发生病虫害进行较为准确的预测，便于种植设备或者用户及时采取相关措施，减小病虫害带来的损失，提升用户体验。The object of the present invention is to provide a method and a device for predicting pests and diseases based on planting equipment, so as to accurately predict whether a target plant will develop pests and diseases in the next growth stage, and facilitate planting equipment or users to take relevant measures in time to reduce pests and diseases. The loss comes to enhance the user experience.
为解决上述技术问题，本发明提供如下技术方案：In order to solve the above technical problem, the present invention provides the following technical solutions:
一种基于种植设备的病虫害预测方法，包括：A method for predicting pests and diseases based on planting equipment, comprising:
确定在种植设备内生长的待预测病虫害的目标植物；Determining the target plant to be predicted for pests and diseases grown in the planting equipment;
获得所述目标植物的生长环境数据；Obtaining growth environment data of the target plant;
对所述生长环境数据进行分析，确定影响所述目标植物发生病虫害的影响维度信息； Performing analysis on the growth environment data to determine influence dimension information affecting the target plant to cause pests and diseases;
根据所述目标植物的影响维度信息和预先建立的病虫害预测模型，预测所述目标植物在下一生长阶段是否会发生病虫害；Determining whether the target plant will develop pests and diseases in the next growth stage according to the influence dimension information of the target plant and the pre-established pest prediction model;
其中，通过以下步骤预先建立所述病虫害预测模型：Wherein, the pest and disease prediction model is pre-established by the following steps:
获得与所述目标植物的种类相同的植物的多组病虫害样本数据；Obtaining a plurality of sets of pest sample data of plants of the same species as the target plant;
根据获得的病虫害样本数据，构建训练集，所述训练集中的每组数据包含病虫害实际发生结果及该病虫害实际发生结果对应的植物生长过程中的影响维度信息；Constructing a training set according to the obtained pest and disease sample data, wherein each set of data in the training set includes the actual occurrence result of the pest and the pest and the influence dimension information in the plant growth process corresponding to the actual occurrence result of the pest and the pest;
使用所述训练集进行机器学习，建立所述病虫害预测模型。The training set is used for machine learning to establish the pest prediction model.
在本发明的一种具体实施方式中，所述使用所述训练集进行机器学习，建立所述病虫害预测模型，包括：In a specific implementation manner of the present invention, the using the training set for machine learning to establish the pest and disease prediction model includes:
使用所述训练集进行机器学习，建立初始病虫害预测模型；Performing machine learning using the training set to establish an initial pest prediction model;
根据所述训练集中的影响维度信息和所述初始病虫害预测模型，确定所述训练集中每组影响维度信息对应的病虫害测试结果；Determining a pest test result corresponding to each group of influence dimension information in the training set according to the influence dimension information in the training set and the initial pest and disease prediction model;
将所述训练集中每组影响维度信息对应的病虫害测试结果与相应的病虫害实际发生结果进行比较，计算误差值；Comparing the pest test results corresponding to each group of influence dimension information in the training set with corresponding actual pest occurrence results, and calculating an error value;
如果所述误差值不大于设定阈值，则将所述初始病虫害预测模型确定为所述病虫害预测模型；If the error value is not greater than a set threshold, determining the initial pest prediction model as the pest prediction model;
如果所述误差值大于所述设定阈值，则扩大所述训练集，重复执行所述使用所述训练集进行机器学习的步骤，直至所述误差值不大于所述设定阈值，获得所述病虫害预测模型。If the error value is greater than the set threshold, expanding the training set, and repeatedly performing the step of performing machine learning using the training set until the error value is not greater than the set threshold, obtaining the Pest and disease prediction model.
在本发明的一种具体实施方式中，所述根据所述目标植物的影响维度信息和预先建立的病虫害预测模型，预测所述目标植物在下一生长阶段是否会发生病虫害，包括：In a specific embodiment of the present invention, the predicting whether the target plant will cause pests and diseases in the next growth stage according to the influence dimension information of the target plant and the pre-established pest prediction model include:
将所述目标植物的影响维度信息输入到预先建立的病虫害预测模型中，采用逻辑回归算法预测所述目标植物在下一生长阶段是否会发生病虫害。The influence dimension information of the target plant is input into a pre-established pest prediction model, and a logistic regression algorithm is used to predict whether the target plant will have pests and diseases in the next growth stage.
在本发明的一种具体实施方式中，还包括：In a specific implementation manner of the present invention, the method further includes:
如果预测所述目标植物在下一生长阶段会发生病虫害，则输出病虫害预警信息。If the target plant is predicted to have pests and diseases in the next growth stage, the pest and disease warning information is output.
在本发明的一种具体实施方式中，所述输出病虫害预警信息，包括： In a specific implementation manner of the present invention, the outputting pest and disease warning information includes:
将病虫害预警信息发送给所述种植设备，以使所述种植设备根据设定的预案调整相应的环境参数。The pest and disease warning information is sent to the planting equipment, so that the planting equipment adjusts corresponding environmental parameters according to the set plan.
一种基于种植设备的病虫害预测装置，包括：A pest and disease prediction device based on planting equipment, comprising:
目标植物确定模块，用于确定在种植设备内生长的待预测病虫害的目标植物；a target plant determining module for determining a target plant to be predicted to grow in the planting device;
生长环境数据获得模块，用于获得所述目标植物的生长环境数据；a growth environment data obtaining module, configured to obtain growth environment data of the target plant;
影响维度信息确定模块，用于对所述生长环境数据进行分析，确定影响所述目标植物发生病虫害的影响维度信息；An influence dimension information determining module, configured to analyze the growth environment data, and determine influence dimension information that affects the pests and diseases of the target plant;
病虫害预测模块，用于根据所述目标植物的影响维度信息和预先建立的病虫害预测模型，预测所述目标植物在下一生长阶段是否会发生病虫害；a pest and disease prediction module, configured to predict whether a pest or a pest occurs in the next growth stage according to the impact dimension information of the target plant and a pre-established pest prediction model;
病虫害预测模型建立模块，用于通过以下步骤预先建立所述病虫害预测模型：获得与所述目标植物的种类相同的植物的多组病虫害样本数据；根据获得的病虫害样本数据，构建训练集，所述训练集中的每组数据包含病虫害实际发生结果及该病虫害实际发生结果对应的植物生长过程中的影响维度信息；使用所述训练集进行机器学习，建立所述病虫害预测模型。a pest prediction model establishing module, configured to pre-establish the pest prediction model by: obtaining a plurality of sets of pest sample data of the same species as the target plant; and constructing a training set according to the obtained pest sample data, Each set of data in the training set includes the actual occurrence results of the pests and diseases and the influence dimension information in the plant growth process corresponding to the actual occurrence of the pests and diseases; using the training set for machine learning, the pest and disease prediction model is established.
在本发明的一种具体实施方式中，所述病虫害预测模型建立模块，具体用于：In a specific embodiment of the present invention, the pest and disease prediction model establishing module is specifically configured to:
使用所述训练集进行机器学习，建立初始病虫害预测模型；Performing machine learning using the training set to establish an initial pest prediction model;
根据所述训练集中的影响维度信息和所述初始病虫害预测模型，确定所述训练集中每组影响维度信息对应的病虫害测试结果；Determining a pest test result corresponding to each group of influence dimension information in the training set according to the influence dimension information in the training set and the initial pest and disease prediction model;
将所述训练集中每组影响维度信息对应的病虫害测试结果与相应的病虫害实际发生结果进行比较，计算误差值；Comparing the pest test results corresponding to each group of influence dimension information in the training set with corresponding actual pest occurrence results, and calculating an error value;
如果所述误差值不大于设定阈值，则将所述初始病虫害预测模型确定为所述病虫害预测模型；If the error value is not greater than a set threshold, determining the initial pest prediction model as the pest prediction model;
如果所述误差值大于所述设定阈值，则扩大所述训练集，重复执行所述使用所述训练集进行机器学习的步骤，直至所述误差值不大于所述设定阈值，获得所述病虫害预测模型。If the error value is greater than the set threshold, expanding the training set, and repeatedly performing the step of performing machine learning using the training set until the error value is not greater than the set threshold, obtaining the Pest and disease prediction model.
在本发明的一种具体实施方式中，所述病虫害预测模块，具体用于：In a specific embodiment of the present invention, the pest prediction module is specifically configured to:
将所述目标植物的影响维度信息输入到预先建立的病虫害预测模型中，采 用逻辑回归算法预测所述目标植物在下一生长阶段是否会发生病虫害。Inputting the impact dimension information of the target plant into a pre-established pest and disease prediction model A logistic regression algorithm is used to predict whether the target plant will develop pests and diseases in the next growth stage.
在本发明的一种具体实施方式中，还包括预警信息输出模块，用于：In a specific implementation manner of the present invention, the method further includes an early warning information output module, configured to:
在预测所述目标植物在下一生长阶段会发生病虫害时，输出病虫害预警信息。The pest warning information is output when the target plant is predicted to have pests and diseases in the next growth stage.
在本发明的一种具体实施方式中，所述预警信息输出模块，具体用于：In an embodiment of the present invention, the early warning information output module is specifically configured to:
将病虫害预警信息发送给所述种植设备，以使所述种植设备根据设定的预案调整相应的环境参数。The pest and disease warning information is sent to the planting equipment, so that the planting equipment adjusts corresponding environmental parameters according to the set plan.
本发明实施例所提供的技术方案，通过机器学习预先建立病虫害预测模型，确定在种植设备内生长的待预测病虫害的目标植物后，可以获得目标植物的生长环境数据，并对生长环境数据进行分析，确定影响目标植物发生病虫害的影响维度信息，根据目标植物的影响维度信息与预先建立的病虫害预测模型，可以预测目标植物在下一生长阶段是否会发生病虫害。应用本发明实施例所提供的技术方案，可以对目标植物在下一生长阶段是否会发生病虫害进行较为准确的预测，便于种植设备或者用户及时采取相关措施，减小病虫害带来的损失，提升用户体验。According to the technical solution provided by the embodiment of the present invention, the pest and disease prediction model is pre-established by machine learning, and the target plant of the target plant to be predicted and grown in the planting equipment is determined, and the growth environment data of the target plant can be obtained, and the growth environment data is analyzed. To determine the impact dimension information affecting the target plant pests and diseases, according to the impact dimension information of the target plant and the pre-established pest and disease prediction model, it can be predicted whether the target plant will have pests and diseases in the next growth stage. By applying the technical solution provided by the embodiments of the present invention, it is possible to accurately predict whether a target plant will have pests and diseases in the next growth stage, and it is convenient for the planting equipment or the user to take relevant measures in time to reduce the loss caused by the pests and diseases and improve the user experience. .
附图说明DRAWINGS
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below. Obviously, the drawings in the following description are only It is a certain embodiment of the present invention, and other drawings can be obtained from those skilled in the art without any creative work.
图1为本发明实施例中一种基于种植设备的病虫害预测方法的实施流程图；1 is a flow chart showing an implementation of a method for predicting pests and diseases based on planting equipment according to an embodiment of the present invention;
图2为本发明实施例中一种基于种植设备的病虫害预测装置的结构示意图。2 is a schematic structural view of a pest and disease prediction device based on planting equipment according to an embodiment of the present invention.
具体实施方式detailed description
为了使本技术领域的人员更好地理解本发明方案，下面结合附图和具体实施方式对本发明作进一步的详细说明。显然，所描述的实施例仅仅是本发明一 部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。The present invention will be further described in detail below in conjunction with the drawings and embodiments. Obviously, the described embodiment is only one of the present invention. Some embodiments, but not all of the embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts are within the scope of the present invention.
参见图1所示，为本发明实施例所提供的一种基于种植设备的病虫害预测方法的实施流程图，该方法可以包括以下步骤：Referring to FIG. 1 , which is a flowchart of an implementation method for predicting pests and diseases based on planting equipment according to an embodiment of the present invention, the method may include the following steps:
S110：确定在种植设备内生长的待预测病虫害的目标植物。S110: Determine a target plant to be predicted to grow pests and diseases in the planting equipment.
在本发明实施例中，目标植物为在种植箱、种植大棚等种植设备中生长的植物，可能正处于某个生长阶段。In the embodiment of the present invention, the target plant is a plant grown in planting equipment such as a planting box or a planting greenhouse, and may be in a certain growth stage.
在实际应用中，目标植物在生长过程中，受其所处的环境条件的影响，可能会遭受病虫害。如果用户或者种植设备能够提前获知目标植物在下一生长阶段是否会发生病虫害，则有助于用户或者种植设备提前采取相应措施，如调整环境参数等，减小病虫害带来的损失。针对目标植物的病虫害的预测需求，应用本发明实施例所提供的技术方案，可以预测目标植物在下一生长阶段是否会发生病虫害。In practical applications, the target plant may be subject to pests and diseases during the growth process due to the environmental conditions in which it is exposed. If the user or planting equipment can know in advance whether the target plant will cause pests and diseases in the next growth stage, it will help the user or planting equipment to take corresponding measures in advance, such as adjusting environmental parameters, etc., to reduce the losses caused by pests and diseases. The technical solution provided by the embodiments of the present invention can be used to predict whether a target plant will develop pests and diseases in the next growth stage according to the predicted demand of the pests and diseases of the target plants.
在本发明实施例中，可以在接收到用户针对目标植物的病虫害预测请求时，确定待预测病虫害的目标植物，还可以按照设定周期确定待预测病虫害的目标植物，定期对目标植物在下一生长阶段是否会发生病虫害进行预测。In the embodiment of the present invention, when the user receives the pest and disease prediction request for the target plant, the target plant to be predicted for the pest and the disease is determined, and the target plant to be predicted for the pest and disease is determined according to the set period, and the target plant is periodically grown next. Whether pests and diseases will occur in the stage for prediction.
S120：获得目标植物的生长环境数据。S120: Obtain growth environment data of the target plant.
在本发明实施例中，生长环境数据为生长过程中的环境信息数据。In the embodiment of the present invention, the growth environment data is environmental information data during the growth process.
具体的，生长环境数据可以是湿度、温度、空气中二氧化碳含量、光照量、土壤PH值、土壤中设定化学成分的含量等数据。Specifically, the growth environment data may be data such as humidity, temperature, carbon dioxide content in the air, amount of light, pH of the soil, and content of chemical components in the soil.
在步骤S110确定在种植设备内生长的待预测病虫害的目标植物后，可以获得目标植物的生长环境数据。在目标植物生长过程中，可以通过环境监测手段实时获取并记录目标植物所处的环境信息，比如，通过种植设备中内置的温度传感器获取温度信息，通过种植设备中内置的湿度传感器获取湿度信息等。这些信息可以存储于数据库中，在确定待预测病虫害的目标植物后，在数据库中提取该目标植物的生长环境数据。After the target plant to be predicted to be predicted to grow in the planting apparatus is determined in step S110, growth environment data of the target plant can be obtained. In the process of growing the target plant, the environmental information of the target plant can be obtained and recorded in real time through environmental monitoring means, for example, the temperature information is obtained by the temperature sensor built in the planting device, and the humidity information is obtained by the humidity sensor built in the planting device. . The information can be stored in a database, and after determining the target plant to be predicted for pests and diseases, the growth environment data of the target plant is extracted in the database.
S130：对生长环境数据进行分析，确定影响目标植物发生病虫害的影响维度信息。 S130: Analyze the growth environment data to determine the influence dimension information that affects the pests and diseases of the target plant.
可以理解的是，植物是否会发生病虫害与其所处的生长环境有较大关系。Understandably, whether a plant will cause pests and diseases has a great relationship with the growing environment in which it is located.
在本发明实施例中，每一类生长环境数据即可作为一种影响植物发生病虫害的影响维度。具体的，影响维度可以是温度、湿度、空气中二氧化碳含量、光照量、土壤PH值、土壤中设定化学成分的含量等。In the embodiment of the present invention, each type of growth environment data can be used as an influence dimension affecting plant diseases and insect pests. Specifically, the influence dimension may be temperature, humidity, carbon dioxide content in the air, amount of light, pH of the soil, and content of chemical components in the soil.
在步骤S120获得了目标植物的生长环境数据，进一步可以对该生长环境数据进行分析，确定影响目标植物发生病虫害的影响维度信息。The growth environment data of the target plant is obtained in step S120, and the growth environment data may be further analyzed to determine the influence dimension information that affects the pest occurrence of the target plant.
比如，对目标植物的生长环境数据进行分析后，可以确定出影响目标植物发生病虫害的5个影响维度，每个影响维度对应的影响维度信息如表1所示：For example, after analyzing the growth environment data of the target plant, five impact dimensions affecting the pests and diseases of the target plant can be determined, and the impact dimension information corresponding to each impact dimension is as shown in Table 1:
影响维度aInfluence dimension a 影响维度bInfluence dimension b 影响维度cInfluence dimension c 影响维度dInfluence dimension d 影响维度eInfluence dimension e
124124 159159 255255 3131 9696
表1Table 1
在表1中，影响维度a信息为124、影响维度b信息为159，影响维度c信息为255，影响维度d信息为31，影响维度e信息为96。In Table 1, the influence dimension a information is 124, the influence dimension b information is 159, the influence dimension c information is 255, the influence dimension d information is 31, and the influence dimension e information is 96.
每个影响维度信息可以是根据预设的量化标准对实际值进行量化后的量化值。举例而言，影响维度a为土壤中设定化学成分的含量，当该含量处于[0％,20％]范围时，可以将其量化为51，当该含量处于[40％,60％]范围时，可以将其量化为124。Each of the influence dimension information may be a quantized value obtained by quantizing the actual value according to a preset quantization standard. For example, the influence dimension a is the content of the chemical composition in the soil. When the content is in the range of [0%, 20%], it can be quantified as 51, when the content is in the range of [40%, 60%]. It can be quantized to 124.
需要说明的是，上述仅为示例，可以根据实际情况对影响维度信息进行量化。在执行本发明实施例所提供的技术方案过程中，使用相同的量化标准即可。It should be noted that the foregoing is only an example, and the influence dimension information may be quantized according to actual conditions. In the process of implementing the technical solution provided by the embodiment of the present invention, the same quantization standard may be used.
S140：根据目标植物的影响维度信息及预先建立的病虫害预测模型，预测目标植物在下一生长阶段是否会发生病虫害。S140: predict whether the target plant will have pests and diseases in the next growth stage according to the influence dimension information of the target plant and the pre-established pest and disease prediction model.
在本发明实施例中，可以预先建立病虫害预测模型。具体的，可以针对每种植物，建立与该种植物对应的病虫害预测模型，并将多个病虫害预测模型归入到一个模型库中进行维护和管理。当需要对目标植物在下一生长阶段是否会发生病虫害进行预测时，可以在模型库中选择出该目标植物对应的病虫害预测模型。In the embodiment of the present invention, the pest prediction model can be established in advance. Specifically, a pest and disease prediction model corresponding to the plant can be established for each plant, and a plurality of pest pest prediction models are classified into a model library for maintenance and management. When it is necessary to predict whether a target plant will develop pests and diseases in the next growth stage, a pest and disease prediction model corresponding to the target plant may be selected in the model library.
在本发明一种具体实施方式中，可以通过以下步骤预先建立病虫害预测模型：In a specific embodiment of the present invention, the pest prediction model can be established in advance by the following steps:
步骤一：获得与目标植物的种类相同的植物的多组病虫害样本数据； Step 1: obtaining a plurality of sets of pest and disease sample data of plants of the same species as the target plant;
步骤二：根据获得的病虫害样本数据，构建训练集，训练集中的每组数据包含病虫害实际发生结果及该病虫害实际发生结果对应的植物生长过程中的影响维度信息；Step 2: According to the obtained sample data of pests and diseases, construct a training set, and each set of data in the training set includes the actual occurrence result of the pests and diseases and the influence dimension information in the plant growth process corresponding to the actual occurrence result of the pests and diseases;
步骤三：使用训练集进行机器学习，建立病虫害预测模型。Step 3: Use the training set for machine learning and establish a pest and disease prediction model.
为便于描述，将上述三个步骤结合起来进行说明。For the convenience of description, the above three steps are combined for explanation.
在本发明实施例中，可以从已有的样本数据库或者通过收集方式，获得与目标植物的种类相同的植物的多组病虫害样本数据。比如，目标植物为番茄，可以获得在不同生长环境下生长的番茄的病虫害样本数据。In the embodiment of the present invention, a plurality of sets of pest sample data of plants of the same species as the target plant can be obtained from an existing sample database or by means of collection. For example, if the target plant is tomato, the pest and disease sample data of the tomato grown under different growth environments can be obtained.
根据获得的病虫害样本数据，可以构建训练集。训练集中每组数据包含病虫害实际发生结果及该病虫害实际发生结果对应的植物生长过程中的影响维度信息。Based on the obtained pest and disease sample data, a training set can be constructed. Each set of data in the training set contains the actual occurrence results of the pests and diseases and the influence dimension information in the plant growth process corresponding to the actual occurrence of the pests and diseases.
比如，训练集中的数据如表2所示：For example, the data in the training set is shown in Table 2:
Figure PCTCN2016112338-appb-000001
Figure PCTCN2016112338-appb-000001
表2Table 2
在表2中，第一组数据表明，在影响维度a信息为51、影响维度b信息为159、影响维度c信息为253、影响维度d信息为159、影响维度e信息为50的条件下，番茄的病虫害实际发生结果为“不得病”，同样，第二组数据表明，影响维度a信息为124、影响维度b信息为253、影响维度c信息为255、影响维度d信息为63、影响维度e信息为96的条件下，番茄的病虫害实际发生结果为“得病”，……。In Table 2, the first set of data indicates that under the condition that the influence dimension a information is 51, the influence dimension b information is 159, the influence dimension c information is 253, the influence dimension d information is 159, and the influence dimension e information is 50, The actual occurrence of tomato pests and diseases is “not sick”. Similarly, the second set of data shows that the influence dimension a information is 124, the influence dimension b information is 253, the influence dimension c information is 255, the influence dimension d information is 63, and the influence dimension Under the condition that the e-information is 96, the actual occurrence of pests and diseases of tomato is "get sick", ....
表2中每个影响维度信息为根据预设的量化标准进行量化的结果。Each of the influence dimension information in Table 2 is a result of quantification according to a preset quantization standard.
使用训练集进行机器学习，具体的，可以采用SparkMLlib工具进行机器学习。对训练集进行机器学习后，可以建立病虫害预测模型，该病虫害预测模 型与目标植物的种类相对应。Use the training set for machine learning. Specifically, you can use the SparkMLlib tool for machine learning. After machine learning of the training set, a pest and disease prediction model can be established, and the pest prediction model The type corresponds to the type of the target plant.
在本发明的一种具体实施方式中，使用训练集进行机器学习，建立病虫害预测模型的步骤可以包括以下步骤：In a specific embodiment of the present invention, using the training set for machine learning, the step of establishing a pest prediction model may include the following steps:
第一个步骤：使用训练集进行机器学习，建立初始病虫害预测模型；The first step: using the training set for machine learning, establishing an initial pest prediction model;
第二个步骤：根据训练集中的影响维度信息和初始病虫害预测模型，确定训练集中每组影响维度信息对应的病虫害测试结果；The second step: determining the pest test results corresponding to each group of influence dimension information in the training set according to the influence dimension information and the initial pest and disease prediction model in the training set;
第三个步骤：将训练集中每组影响维度信息对应的病虫害测试结果与相应的病虫害实际发生结果进行比较，计算误差值；The third step: comparing the pest test results corresponding to each group of influence dimension information in the training set with the corresponding actual occurrences of the pests and diseases, and calculating the error value;
第四个步骤：如果误差值不大于设定阈值，则将初始病虫害预测模型确定为病虫害预测模型；The fourth step: if the error value is not greater than the set threshold, the initial pest prediction model is determined as a pest prediction model;
第五个步骤：如果误差值大于设定阈值，则扩大训练集，重复执行第一个步骤，直至误差值不大于设定阈值，获得病虫害预测模型。The fifth step: if the error value is greater than the set threshold, the training set is expanded, and the first step is repeatedly executed until the error value is not greater than the set threshold, and the pest prediction model is obtained.
为便于描述，将上述五个步骤结合起来进行说明。For convenience of description, the above five steps are combined for explanation.
可以理解的是，训练集中包含的数据量的多少，决定了病虫害预测模型预测的准确程度。It can be understood that the amount of data contained in the training set determines the accuracy of the prediction of the pest prediction model.
在使用训练集进行机器学习，建立初始病虫害预测模型之后，可以根据训练集中的影响维度信息和该初始病虫害预测模型，确定训练集中每组影响维度信息对应的病虫害测试结果。After using the training set for machine learning and establishing the initial pest and disease prediction model, the pest and disease test results corresponding to each group of impact dimension information in the training set can be determined according to the influence dimension information in the training set and the initial pest and disease prediction model.
比如，训练集的数据文件为：For example, the data file of the training set is:
0 128:51 129:159 130:253……0 128:51 129:159 130:253...
1 159:124 160:253 161:253……1 159:124 160:253 161:253...
1 125:145 126:255 127:211……1 125:145 126:255 127:211...
1 153:5 154:63 155:197……1 153:5 154:63 155:197...
1 152:1 153:168 154:242……1 152:1 153:168 154:242...
……......
其中，0代表不得病，1代表得病。Among them, 0 means no disease, 1 means sick.
将训练集中每组影响维度信息对应的病虫害测试结果与相应的病虫害实际发生结果进行比较，可以计算得到误差值。Comparing the pest test results corresponding to each group of influence dimension information in the training set with the corresponding actual pest occurrence results, the error value can be calculated.
比如，上例训练集中的影响维度信息对应的病虫害测试结果与相应的病虫 害实际发生结果的关系表如表3所示：For example, the pest test results corresponding to the impact dimension information in the above training set and the corresponding pests and diseases The relationship table of the actual occurrence results is shown in Table 3:
植物名称Plant name 病虫害测试结果Pest test results 病虫害实际发生结果Actual occurrence of pests and diseases
番茄tomato 0.00.0 0.00.0
番茄tomato 1.01.0 1.01.0
番茄tomato 1.01.0 1.01.0
番茄tomato 1.01.0 1.01.0
番茄tomato 1.01.0 1.01.0
表3table 3
根据表3，可以计算病虫害测试结果与病虫害实际发生结果的误差值为：According to Table 3, the error values of the pest test results and the actual occurrence of pests and diseases can be calculated as:
TrainErr＝0.0。TrainErr=0.0.
如果该误差值不大于设定阈值，则表明当前的初始病虫害预测模型的准确程度能够达到设定要求，可以直接将该初始病虫害预测模型确定为病虫害预测模型。设定阈值可以根据实际情况进行设定和调整，本发明实施例对此不做限制。If the error value is not greater than the set threshold, it indicates that the current initial pest pest prediction model can reach the set requirement, and the initial pest pest prediction model can be directly determined as the pest pest prediction model. The threshold value can be set and adjusted according to the actual situation, which is not limited by the embodiment of the present invention.
如果该误差值大于设定阈值，则表明当前的初始病虫害预测模型的准确程度不能够达到设定要求，在这种情况下，可以扩大训练集，具体的，可以通过收集更多的病虫害样本数据构建训练集。If the error value is greater than the set threshold, it indicates that the accuracy of the current initial pest prediction model cannot meet the set requirements. In this case, the training set can be expanded. Specifically, more pest sample data can be collected. Build a training set.
扩大训练集后，可以重复执行使用训练集进行机器学习的步骤，直至误差值不大于设定阈值，获得当前的病虫害预测模型，以供后续业务使用。这样，可以提高病虫害预测模型的预测准确程度。After the training set is expanded, the steps of using the training set for machine learning can be repeatedly performed until the error value is not greater than the set threshold, and the current pest prediction model is obtained for subsequent business use. In this way, the prediction accuracy of the pest prediction model can be improved.
根据目标植物的影响维度信息及预先建立的病虫害预测模型，可以预测目标植物在下一生长阶段是否会发生病虫害。According to the impact dimension information of the target plant and the pre-established pest and disease prediction model, it can be predicted whether the target plant will have pests and diseases in the next growth stage.
具体的，将目标植物的影响维度信息输入到预先建立的病虫害预测模型中，采用逻辑回归算法预测目标植物在下一生长阶段是否会发生病虫害。Specifically, the impact dimension information of the target plant is input into a pre-established pest prediction model, and a logistic regression algorithm is used to predict whether the target plant will develop pests and diseases in the next growth stage.
本发明实施例所提供的方法，通过机器学习预先建立病虫害预测模型，确定在种植设备内生长的待预测病虫害的目标植物后，可以获得目标植物的生长环境数据，并对生长环境数据进行分析，确定影响目标植物发生病虫害的影响维度信息，根据目标植物的影响维度信息与预先建立的病虫害预测模型，可以预测目标植物在下一生长阶段是否会发生病虫害。应用本发明实施例所提供的 方法，可以对目标植物在下一生长阶段是否会发生病虫害进行较为准确的预测，便于种植设备或者用户及时采取相关措施，减小病虫害带来的损失，提升用户体验。According to the method provided by the embodiments of the present invention, the pest and disease prediction model is pre-established by machine learning, and after determining the target plant to be predicted to grow pests and diseases in the planting equipment, the growth environment data of the target plant can be obtained, and the growth environment data is analyzed. Determine the influence dimension information that affects the target plant's pests and diseases. According to the impact dimension information of the target plant and the pre-established pest and disease prediction model, it can be predicted whether the target plant will have pests and diseases in the next growth stage. Application of the embodiments of the present invention The method can accurately predict whether the target plant will cause pests and diseases in the next growth stage, and facilitate planting equipment or users to take relevant measures in time to reduce the losses caused by pests and diseases and improve the user experience.
在本发明的一个实施例中，该方法还可以包括以下步骤：In an embodiment of the invention, the method may further comprise the following steps:
如果预测目标植物在下一生长阶段会发生病虫害，则输出病虫害预警信息。If the target plant is predicted to have pests and diseases in the next growth stage, the pest and disease warning information will be output.
如果预测目标植物在下一生长阶段会发生病虫害，则输出病虫害预警信息，具体的，可以将该预警信息输出给种植设备，由种植设备控制其内置的病虫害预警指示灯闪烁，或者，可以将该预警信息输出给用户，以使用户针对该预警信息采取相应措施。If the target plant is predicted to have pests and diseases in the next growth stage, the pest and disease warning information is output. Specifically, the warning information may be output to the planting equipment, and the built-in pest warning indicator flashes by the planting equipment, or the warning may be The information is output to the user, so that the user takes corresponding measures for the warning information.
在本发明的一种具体实施方式中，具体可以将病虫害预警信息发送给种植设备，以使种植设备根据设定的预案调整相应的环境参数。In a specific embodiment of the present invention, the pest and disease warning information may be specifically sent to the planting equipment, so that the planting equipment adjusts the corresponding environmental parameters according to the set plan.
在本发明实施例中，可以针对病虫害设定预案，并在种植设备中保存。当种植设备接收到病虫害预警信息时，可以根据设定的预案调整相应的环境参数。比如，通过其内置的温度调节装置调节种植设备内温度，或者通过其内置的营养液更换装置更换营养液等。In the embodiment of the present invention, a plan can be set for pests and diseases and stored in the planting equipment. When the planting equipment receives the pest and disease warning information, the corresponding environmental parameters can be adjusted according to the set plan. For example, the temperature inside the planting device is adjusted by its built-in thermostat, or the nutrient solution is replaced by its built-in nutrient replacement device.
这样，可以有效避免病虫害的发生，减小病虫害带来的损失。In this way, the occurrence of pests and diseases can be effectively avoided, and the losses caused by pests and diseases can be reduced.
相应于上面的方法实施例，本发明实施例还提供了一种基于种植设备的病虫害预测装置，下文描述的一种基于种植设备的病虫害预测装置与上文描述的一种基于种植设备的病虫害预测方法可相互对应参照。Corresponding to the above method embodiment, the embodiment of the present invention further provides a pest and disease prediction device based on planting equipment, a pest control device based on planting equipment described below and a pest and disease prediction based on planting equipment described above The methods can be referred to each other.
参见图2所示，该装置包括以下模块：Referring to Figure 2, the device includes the following modules:
目标植物确定模块210，用于确定在种植设备内生长的待预测病虫害的目标植物；a target plant determining module 210, configured to determine a target plant to be predicted to grow pests and diseases within the planting device;
生长环境数据获得模块220，用于获得目标植物的生长环境数据；a growth environment data obtaining module 220, configured to obtain growth environment data of the target plant;
影响维度信息确定模块230，用于对生长环境数据进行分析，确定影响目标植物发生病虫害的影响维度信息；The impact dimension information determining module 230 is configured to analyze the growth environment data to determine the impact dimension information that affects the pests and diseases of the target plant;
病虫害预测模块240，用于根据目标植物的影响维度信息和预先建立的病虫害预测模型，预测目标植物在下一生长阶段是否会发生病虫害；The pest and disease prediction module 240 is configured to predict whether the target plant will have pests and diseases in the next growth stage according to the influence dimension information of the target plant and the pre-established pest and disease prediction model;
病虫害预测模型建立模块250，用于通过以下步骤预先建立病虫害预测模 型：获得与目标植物的种类相同的植物的多组病虫害样本数据；根据获得的病虫害样本数据，构建训练集，训练集中的每组数据包含病虫害实际发生结果及该病虫害实际发生结果对应的植物生长过程中的影响维度信息；使用训练集进行机器学习，建立病虫害预测模型。The pest prediction model establishing module 250 is configured to pre-establish the pest prediction model by the following steps: Type: Obtaining a plurality of sets of pest and disease sample data of plants of the same species as the target plant; constructing a training set according to the obtained pest and disease sample data, each set of data in the training set includes the actual occurrence of the pests and diseases and the plant growth corresponding to the actual occurrence of the pests and diseases Influencing dimensional information in the process; using training sets for machine learning, establishing pest and disease prediction models.
本发明实施例所提供的装置，通过机器学习预先建立病虫害预测模型，确定在种植设备内生长的待预测病虫害的目标植物后，可以获得目标植物的生长环境数据，并对生长环境数据进行分析，确定影响目标植物发生病虫害的影响维度信息，根据目标植物的影响维度信息与预先建立的病虫害预测模型，可以预测目标植物在下一生长阶段是否会发生病虫害。应用本发明实施例所提供的装置，可以对目标植物在下一生长阶段是否会发生病虫害进行较为准确的预测，便于种植设备或者用户及时采取相关措施，减小病虫害带来的损失，提升用户体验。The apparatus provided by the embodiment of the present invention pre-establishes a pest and disease prediction model through machine learning, determines a target plant to be predicted to grow pests and diseases in the planting equipment, obtains growth environment data of the target plant, and analyzes the growth environment data. Determine the influence dimension information that affects the target plant's pests and diseases. According to the impact dimension information of the target plant and the pre-established pest and disease prediction model, it can be predicted whether the target plant will have pests and diseases in the next growth stage. By using the device provided by the embodiment of the invention, it is possible to accurately predict whether the target plant will have pests and diseases in the next growth stage, and it is convenient for the planting equipment or the user to take relevant measures in time to reduce the loss caused by the pests and diseases and improve the user experience.
在本发明的一种具体实施方式中，病虫害预测模型建立模块250，具体用于：In a specific embodiment of the present invention, the pest prediction model establishing module 250 is specifically configured to:
使用训练集进行机器学习，建立初始病虫害预测模型；Use the training set for machine learning to establish an initial pest and disease prediction model;
根据训练集中的影响维度信息和初始病虫害预测模型，确定训练集中每组影响维度信息对应的病虫害测试结果；According to the influence dimension information and the initial pest and disease prediction model in the training set, the pest test results corresponding to each group of influence dimension information in the training set are determined;
将训练集中每组影响维度信息对应的病虫害测试结果与相应的病虫害实际发生结果进行比较，计算误差值；Comparing the pest test results corresponding to each group of influence dimension information in the training set with the corresponding actual pest occurrence results, and calculating the error value;
如果误差值不大于设定阈值，则将初始病虫害预测模型确定为病虫害预测模型；If the error value is not greater than the set threshold, the initial pest prediction model is determined as a pest prediction model;
如果误差值大于设定阈值，则扩大训练集，重复执行使用训练集进行机器学习的步骤，直至误差值不大于设定阈值，获得病虫害预测模型。If the error value is greater than the set threshold, the training set is expanded, and the step of performing machine learning using the training set is repeatedly performed until the error value is not greater than the set threshold, and the pest prediction model is obtained.
在本发明的一种具体实施方式中，病虫害预测模块240，具体用于：In a specific embodiment of the present invention, the pest prediction module 240 is specifically configured to:
将目标植物的影响维度信息输入到预先建立的病虫害预测模型中，采用逻辑回归算法预测目标植物在下一生长阶段是否会发生病虫害。The impact dimension information of the target plant is input into a pre-established pest prediction model, and a logistic regression algorithm is used to predict whether the target plant will develop pests and diseases in the next growth stage.
在本发明的一种具体实施方式中，还包括预警信息输出模块，用于：In a specific implementation manner of the present invention, the method further includes an early warning information output module, configured to:
在预测目标植物在下一生长阶段会发生病虫害时，输出病虫害预警信息。When the target plants are predicted to have pests and diseases in the next growth stage, the pest and disease warning information is output.
在本发明的一种具体实施方式中，预警信息输出模块，具体用于： In a specific implementation manner of the present invention, the early warning information output module is specifically configured to:
将病虫害预警信息发送给种植设备，以使种植设备根据设定的预案调整相应的环境参数。The pest and disease warning information is sent to the planting equipment, so that the planting equipment adjusts the corresponding environmental parameters according to the set plan.
本说明书中各个实施例采用递进的方式描述，每个实施例重点说明的都是与其它实施例的不同之处，各个实施例之间相同或相似部分互相参见即可。对于实施例公开的装置而言，由于其与实施例公开的方法相对应，所以描述的比较简单，相关之处参见方法部分说明即可。The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on differences from other embodiments, and the same or similar parts of the respective embodiments may be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.
专业人员还可以进一步意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、计算机软件或者二者的结合来实现，为了清楚地说明硬件和软件的可互换性，在上述说明中已经按照功能一般性地描述了各示例的组成及步骤。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本发明的范围。A person skilled in the art will further appreciate that the elements and algorithm steps of the various examples described in connection with the embodiments disclosed herein can be implemented in electronic hardware, computer software or a combination of both, in order to clearly illustrate the hardware and software. Interchangeability, the composition and steps of the various examples have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the solution. A person skilled in the art can use different methods for implementing the described functions for each particular application, but such implementation should not be considered to be beyond the scope of the present invention.
结合本文中所公开的实施例描述的方法或算法的步骤可以直接用硬件、处理器执行的软件模块，或者二者的结合来实施。软件模块可以置于随机存储器(RAM)、内存、只读存储器(ROM)、电可编程ROM、电可擦除可编程ROM、寄存器、硬盘、可移动磁盘、CD-ROM、或技术领域内所公知的任意其它形式的存储介质中。The steps of a method or algorithm described in connection with the embodiments disclosed herein can be implemented directly in hardware, a software module executed by a processor, or a combination of both. The software module can be placed in random access memory (RAM), memory, read only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or technical field. Any other form of storage medium known.
本文中应用了具体个例对本发明的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本发明的技术方案及其核心思想。应当指出，对于本技术领域的普通技术人员来说，在不脱离本发明原理的前提下，还可以对本发明进行若干改进和修饰，这些改进和修饰也落入本发明权利要求的保护范围内。 The principles and embodiments of the present invention have been described with reference to specific examples. The description of the above embodiments is only for helping to understand the technical solutions of the present invention and the core ideas thereof. It should be noted that those skilled in the art can make various modifications and changes to the present invention without departing from the spirit and scope of the invention.

Claims (10)

  1. 一种基于种植设备的病虫害预测方法，其特征在于，包括：A method for predicting pests and diseases based on planting equipment, characterized in that it comprises:
    确定在种植设备内生长的待预测病虫害的目标植物；Determining the target plant to be predicted for pests and diseases grown in the planting equipment;
    获得所述目标植物的生长环境数据；Obtaining growth environment data of the target plant;
    对所述生长环境数据进行分析，确定影响所述目标植物发生病虫害的影响维度信息；Performing analysis on the growth environment data to determine influence dimension information affecting the target plant to cause pests and diseases;
    根据所述目标植物的影响维度信息和预先建立的病虫害预测模型，预测所述目标植物在下一生长阶段是否会发生病虫害；Determining whether the target plant will develop pests and diseases in the next growth stage according to the influence dimension information of the target plant and the pre-established pest prediction model;
    其中，通过以下步骤预先建立所述病虫害预测模型：Wherein, the pest and disease prediction model is pre-established by the following steps:
    获得与所述目标植物的种类相同的植物的多组病虫害样本数据；Obtaining a plurality of sets of pest sample data of plants of the same species as the target plant;
    根据获得的病虫害样本数据，构建训练集，所述训练集中的每组数据包含病虫害实际发生结果及该病虫害实际发生结果对应的植物生长过程中的影响维度信息；Constructing a training set according to the obtained pest and disease sample data, wherein each set of data in the training set includes the actual occurrence result of the pest and the pest and the influence dimension information in the plant growth process corresponding to the actual occurrence result of the pest and the pest;
    使用所述训练集进行机器学习，建立所述病虫害预测模型。The training set is used for machine learning to establish the pest prediction model.
  2. 根据权利要求1所述的基于种植设备的病虫害预测方法，其特征在于，所述使用所述训练集进行机器学习，建立所述病虫害预测模型，包括：The planting device-based pest and disease prediction method according to claim 1, wherein the using the training set for machine learning to establish the pest and disease prediction model comprises:
    使用所述训练集进行机器学习，建立初始病虫害预测模型；Performing machine learning using the training set to establish an initial pest prediction model;
    根据所述训练集中的影响维度信息和所述初始病虫害预测模型，确定所述训练集中每组影响维度信息对应的病虫害测试结果；Determining a pest test result corresponding to each group of influence dimension information in the training set according to the influence dimension information in the training set and the initial pest and disease prediction model;
    将所述训练集中每组影响维度信息对应的病虫害测试结果与相应的病虫害实际发生结果进行比较，计算误差值；Comparing the pest test results corresponding to each group of influence dimension information in the training set with corresponding actual pest occurrence results, and calculating an error value;
    如果所述误差值不大于设定阈值，则将所述初始病虫害预测模型确定为所述病虫害预测模型；If the error value is not greater than a set threshold, determining the initial pest prediction model as the pest prediction model;
    如果所述误差值大于所述设定阈值，则扩大所述训练集，重复执行所述使用所述训练集进行机器学习的步骤，直至所述误差值不大于所述设定阈值，获得所述病虫害预测模型。If the error value is greater than the set threshold, expanding the training set, and repeatedly performing the step of performing machine learning using the training set until the error value is not greater than the set threshold, obtaining the Pest and disease prediction model.
  3. 根据权利要求1所述的基于种植设备的病虫害预测方法，其特征在于，所述根据所述目标植物的影响维度信息和预先建立的病虫害预测模型，预测所述目标植物在下一生长阶段是否会发生病虫害，包括： The planting device-based pest and disease prediction method according to claim 1, wherein the predicting whether the target plant will occur in a next growth stage according to the influence dimension information of the target plant and a pre-established pest prediction model Pests and diseases, including:
    将所述目标植物的影响维度信息输入到预先建立的病虫害预测模型中，采用逻辑回归算法预测所述目标植物在下一生长阶段是否会发生病虫害。The influence dimension information of the target plant is input into a pre-established pest prediction model, and a logistic regression algorithm is used to predict whether the target plant will have pests and diseases in the next growth stage.
  4. 根据权利要求1至3任一项所述的基于种植设备的病虫害预测方法，其特征在于，还包括：The planting device-based pest and disease prediction method according to any one of claims 1 to 3, further comprising:
    如果预测所述目标植物在下一生长阶段会发生病虫害，则输出病虫害预警信息。If the target plant is predicted to have pests and diseases in the next growth stage, the pest and disease warning information is output.
  5. 根据权利要求4所述的基于种植设备的病虫害预测方法，其特征在于，所述输出病虫害预警信息，包括：The planting device-based pest and disease prediction method according to claim 4, wherein the outputting pest and disease warning information comprises:
    将病虫害预警信息发送给所述种植设备，以使所述种植设备根据设定的预案调整相应的环境参数。The pest and disease warning information is sent to the planting equipment, so that the planting equipment adjusts corresponding environmental parameters according to the set plan.
  6. 一种基于种植设备的病虫害预测装置，其特征在于，包括：A pest and disease prediction device based on planting equipment, comprising:
    目标植物确定模块，用于确定在种植设备内生长的待预测病虫害的目标植物；a target plant determining module for determining a target plant to be predicted to grow in the planting device;
    生长环境数据获得模块，用于获得所述目标植物的生长环境数据；a growth environment data obtaining module, configured to obtain growth environment data of the target plant;
    影响维度信息确定模块，用于对所述生长环境数据进行分析，确定影响所述目标植物发生病虫害的影响维度信息；An influence dimension information determining module, configured to analyze the growth environment data, and determine influence dimension information that affects the pests and diseases of the target plant;
    病虫害预测模块，用于根据所述目标植物的影响维度信息和预先建立的病虫害预测模型，预测所述目标植物在下一生长阶段是否会发生病虫害；a pest and disease prediction module, configured to predict whether a pest or a pest occurs in the next growth stage according to the impact dimension information of the target plant and a pre-established pest prediction model;
    病虫害预测模型建立模块，用于通过以下步骤预先建立所述病虫害预测模型：获得与所述目标植物的种类相同的植物的多组病虫害样本数据；根据获得的病虫害样本数据，构建训练集，所述训练集中的每组数据包含病虫害实际发生结果及该病虫害实际发生结果对应的植物生长过程中的影响维度信息；使用所述训练集进行机器学习，建立所述病虫害预测模型。a pest prediction model establishing module, configured to pre-establish the pest prediction model by: obtaining a plurality of sets of pest sample data of the same species as the target plant; and constructing a training set according to the obtained pest sample data, Each set of data in the training set includes the actual occurrence results of the pests and diseases and the influence dimension information in the plant growth process corresponding to the actual occurrence of the pests and diseases; using the training set for machine learning, the pest and disease prediction model is established.
  7. 根据权利要求6所述的基于种植设备的病虫害预测装置，其特征在于，所述病虫害预测模型建立模块，具体用于：The apparatus for predicting pests and diseases based on planting equipment according to claim 6, wherein the pest and disease prediction model establishing module is specifically configured to:
    使用所述训练集进行机器学习，建立初始病虫害预测模型；Performing machine learning using the training set to establish an initial pest prediction model;
    根据所述训练集中的影响维度信息和所述初始病虫害预测模型，确定所述训练集中每组影响维度信息对应的病虫害测试结果；Determining a pest test result corresponding to each group of influence dimension information in the training set according to the influence dimension information in the training set and the initial pest and disease prediction model;
    将所述训练集中每组影响维度信息对应的病虫害测试结果与相应的病虫 害实际发生结果进行比较，计算误差值；Pest test results corresponding to each group of influence dimension information in the training set and corresponding pests and diseases Compare the actual occurrence results and calculate the error value;
    如果所述误差值不大于设定阈值，则将所述初始病虫害预测模型确定为所述病虫害预测模型；If the error value is not greater than a set threshold, determining the initial pest prediction model as the pest prediction model;
    如果所述误差值大于所述设定阈值，则扩大所述训练集，重复执行所述使用所述训练集进行机器学习的步骤，直至所述误差值不大于所述设定阈值，获得所述病虫害预测模型。If the error value is greater than the set threshold, expanding the training set, and repeatedly performing the step of performing machine learning using the training set until the error value is not greater than the set threshold, obtaining the Pest and disease prediction model.
  8. 根据权利要求6所述的基于种植设备的病虫害预测装置，其特征在于，所述病虫害预测模块，具体用于：The apparatus for predicting pests and diseases based on planting equipment according to claim 6, wherein the pest and disease prediction module is specifically configured to:
    将所述目标植物的影响维度信息输入到预先建立的病虫害预测模型中，采用逻辑回归算法预测所述目标植物在下一生长阶段是否会发生病虫害。The influence dimension information of the target plant is input into a pre-established pest prediction model, and a logistic regression algorithm is used to predict whether the target plant will have pests and diseases in the next growth stage.
  9. 根据权利要求6至8任一项所述的基于种植设备的病虫害预测装置，其特征在于，还包括预警信息输出模块，用于：The planting device-based pest and disease prediction device according to any one of claims 6 to 8, further comprising an early warning information output module, configured to:
    在预测所述目标植物在下一生长阶段会发生病虫害时，输出病虫害预警信息。The pest warning information is output when the target plant is predicted to have pests and diseases in the next growth stage.
  10. 根据权利要求9所述的基于种植设备的病虫害预测装置，其特征在于，所述预警信息输出模块，具体用于：The planting device-based pest and disease prediction device according to claim 9, wherein the warning information output module is specifically configured to:
    将病虫害预警信息发送给所述种植设备，以使所述种植设备根据设定的预案调整相应的环境参数。 The pest and disease warning information is sent to the planting equipment, so that the planting equipment adjusts corresponding environmental parameters according to the set plan.
PCT/CN2016/112338 2016-09-30 2016-12-27 Disease and insect pest forecasting method and apparatus based on planting equipment WO2018058821A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610875105.0A CN106645563A (en) 2016-09-30 2016-09-30 Disease and pest predicting method and device based on planting equipment
CN201610875105.0 2016-09-30

Publications (1)

Publication Number Publication Date
WO2018058821A1 true WO2018058821A1 (en) 2018-04-05

Family

ID=58855041

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/112338 WO2018058821A1 (en) 2016-09-30 2016-12-27 Disease and insect pest forecasting method and apparatus based on planting equipment

Country Status (2)

Country Link
CN (1) CN106645563A (en)
WO (1) WO2018058821A1 (en)

Cited By (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109902268A (en) * 2019-03-19 2019-06-18 石家庄市农林科学研究院 A kind of monitoring and pre-alarming method and device of tomato base rot disease
CN111046204A (en) * 2019-12-16 2020-04-21 北京植得智能互联科技有限公司 Plant disease and insect pest recognition and control system
CN111914914A (en) * 2020-07-21 2020-11-10 上海理想信息产业（集团）有限公司 Method, device, equipment and storage medium for identifying plant diseases and insect pests
CN111986149A (en) * 2020-07-16 2020-11-24 江西斯源科技有限公司 Plant disease and insect pest detection method based on convolutional neural network
CN112215293A (en) * 2020-10-20 2021-01-12 平安国际智慧城市科技股份有限公司 Plant disease and insect pest identification method and device and computer equipment
CN112785047A (en) * 2021-01-06 2021-05-11 上海信联信息发展股份有限公司 Method and device for predicting crop yield
CN113435825A (en) * 2021-05-06 2021-09-24 中国农业科学院烟草研究所(中国烟草总公司青州烟草研究所) Intelligent management method, system and storage medium based on soil-borne disease control
CN114550108A (en) * 2022-04-26 2022-05-27 广东省农业科学院植物保护研究所 Spodoptera frugiperda identification and early warning method and system
CN114708506A (en) * 2022-04-07 2022-07-05 河北科技师范学院 Chinese chestnut disease monitoring system
WO2022167240A1 (en) 2021-02-03 2022-08-11 Bayer Aktiengesellschaft Prediction of residues of plant protection agents in harvested products
CN116307458A (en) * 2022-12-22 2023-06-23 四川长虹云数信息技术有限公司 Disease and pest identification, prevention and early warning system and method
CN117391265A (en) * 2023-12-13 2024-01-12 金乡县林业保护和发展服务中心(金乡县湿地保护中心、金乡县野生动植物保护中心、金乡县国有白洼林场) Forestry pest hazard risk prediction method based on big data analysis
CN117523617A (en) * 2024-01-08 2024-02-06 陕西安康玮创达信息技术有限公司 Insect pest detection method and system based on machine learning
CN117789067A (en) * 2024-02-27 2024-03-29 山东字节信息科技有限公司 Unmanned aerial vehicle crop monitoring method and system based on machine learning
CN117854012A (en) * 2024-03-07 2024-04-09 成都智慧城市信息技术有限公司 Crop environment monitoring method and system based on big data

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106779188A (en) * 2016-11-30 2017-05-31 深圳前海弘稼科技有限公司 Plant pest Forecasting Methodology and device in a kind of plantation equipment
CN107357271B (en) * 2017-06-30 2018-07-17 深圳春沐源控股有限公司 The control method of chamber crop pest and disease damage, prevention system
CN108596657A (en) * 2018-04-11 2018-09-28 北京木业邦科技有限公司 Trees Value Prediction Methods, device, electronic equipment and storage medium
JP2021112136A (en) * 2020-01-16 2021-08-05 横河電機株式会社 Support system and support method
CN111639750A (en) * 2020-05-26 2020-09-08 珠海格力电器股份有限公司 Control method and device of intelligent flowerpot, intelligent flowerpot and storage medium
CN112836903B (en) * 2021-03-25 2022-01-28 中化现代农业有限公司 Disease and pest risk prediction method
CN113303151A (en) * 2021-05-19 2021-08-27 苏州三润景观工程有限公司 Green plant disease and insect pest repairing method based on big data
CN113705875A (en) * 2021-08-19 2021-11-26 大气候物联网科技(广州)有限公司 Crop disease and pest early warning method, system, device and storage medium
CN115147837B (en) * 2022-08-16 2023-10-27 河北省农林科学院植物保护研究所 Athetis lepigone feeding method and system based on optical image recognition
CN115965875B (en) * 2023-03-16 2023-06-20 德阳稷农农业科技有限公司 Intelligent monitoring method and system for crop diseases and insect pests

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101052147A (en) * 2007-05-24 2007-10-10 中国科学院合肥物质科学研究院 Intelligent early warning system for field crop pest and disease disasters
CN101162384A (en) * 2006-10-12 2008-04-16 魏珉 Artificial intelligence plant growth surroundings regulate and control expert decision-making system
CN103093389A (en) * 2013-01-15 2013-05-08 苏州迪芬德物联网科技有限公司 Agricultural product production management system based on network
CN103869780A (en) * 2014-03-13 2014-06-18 河南洛士达科技有限公司 Smart agriculture greenhouse terminal information processing system
CN104008633A (en) * 2014-05-26 2014-08-27 中国农业大学 Early-warning method and system of facility spinach diseases
US20160148104A1 (en) * 2014-11-24 2016-05-26 Prospera Technologies, Ltd. System and method for plant monitoring

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1273874C (en) * 2003-05-15 2006-09-06 沈佐锐 Intelligent system for monitoring healthy of ecology in greenhouse
CN102084794B (en) * 2010-10-22 2013-03-06 华南农业大学 Method and device for early detecting crop pests based on multisensor information fusion
CN103034910B (en) * 2012-12-03 2016-03-09 北京农业信息技术研究中心 Based on the regional scale disease and pest Forecasting Methodology of multi-source information
WO2015132208A1 (en) * 2014-03-03 2015-09-11 Avia-Gis Method for the profiling of pests and for the determination and prediction of associated risks and means for adapted pest control
CN104035412A (en) * 2014-06-12 2014-09-10 江苏恒创软件有限公司 Crop diseases and pest monitoring system and method based on unmanned plane
KR101661846B1 (en) * 2015-03-05 2016-09-30 (주) 더아이엠씨 Disease and Insect Pest Signs Predicting Method
CN104794537A (en) * 2015-04-17 2015-07-22 中国农业科学院柑桔研究所 Method for building prediction models for unaspis yanonensis kuwana emergence periods of mandarins
CN105843862A (en) * 2016-03-17 2016-08-10 中国科学院遥感与数字地球研究所 Method for establishing crop disease and pest remote sensing and forecasting system and remote sensing and forecasting system

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101162384A (en) * 2006-10-12 2008-04-16 魏珉 Artificial intelligence plant growth surroundings regulate and control expert decision-making system
CN101052147A (en) * 2007-05-24 2007-10-10 中国科学院合肥物质科学研究院 Intelligent early warning system for field crop pest and disease disasters
CN103093389A (en) * 2013-01-15 2013-05-08 苏州迪芬德物联网科技有限公司 Agricultural product production management system based on network
CN103869780A (en) * 2014-03-13 2014-06-18 河南洛士达科技有限公司 Smart agriculture greenhouse terminal information processing system
CN104008633A (en) * 2014-05-26 2014-08-27 中国农业大学 Early-warning method and system of facility spinach diseases
US20160148104A1 (en) * 2014-11-24 2016-05-26 Prospera Technologies, Ltd. System and method for plant monitoring

Cited By (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109902268A (en) * 2019-03-19 2019-06-18 石家庄市农林科学研究院 A kind of monitoring and pre-alarming method and device of tomato base rot disease
CN111046204A (en) * 2019-12-16 2020-04-21 北京植得智能互联科技有限公司 Plant disease and insect pest recognition and control system
CN111986149A (en) * 2020-07-16 2020-11-24 江西斯源科技有限公司 Plant disease and insect pest detection method based on convolutional neural network
CN111914914A (en) * 2020-07-21 2020-11-10 上海理想信息产业（集团）有限公司 Method, device, equipment and storage medium for identifying plant diseases and insect pests
CN112215293A (en) * 2020-10-20 2021-01-12 平安国际智慧城市科技股份有限公司 Plant disease and insect pest identification method and device and computer equipment
CN112785047A (en) * 2021-01-06 2021-05-11 上海信联信息发展股份有限公司 Method and device for predicting crop yield
WO2022167240A1 (en) 2021-02-03 2022-08-11 Bayer Aktiengesellschaft Prediction of residues of plant protection agents in harvested products
CN113435825A (en) * 2021-05-06 2021-09-24 中国农业科学院烟草研究所(中国烟草总公司青州烟草研究所) Intelligent management method, system and storage medium based on soil-borne disease control
CN114708506B (en) * 2022-04-07 2024-05-14 河北科技师范学院 Chinese chestnut disease monitoring system
CN114708506A (en) * 2022-04-07 2022-07-05 河北科技师范学院 Chinese chestnut disease monitoring system
CN114550108A (en) * 2022-04-26 2022-05-27 广东省农业科学院植物保护研究所 Spodoptera frugiperda identification and early warning method and system
CN116307458A (en) * 2022-12-22 2023-06-23 四川长虹云数信息技术有限公司 Disease and pest identification, prevention and early warning system and method
CN117391265B (en) * 2023-12-13 2024-03-05 金乡县林业保护和发展服务中心(金乡县湿地保护中心、金乡县野生动植物保护中心、金乡县国有白洼林场) Forestry pest hazard risk prediction method based on big data analysis
CN117391265A (en) * 2023-12-13 2024-01-12 金乡县林业保护和发展服务中心(金乡县湿地保护中心、金乡县野生动植物保护中心、金乡县国有白洼林场) Forestry pest hazard risk prediction method based on big data analysis
CN117523617A (en) * 2024-01-08 2024-02-06 陕西安康玮创达信息技术有限公司 Insect pest detection method and system based on machine learning
CN117523617B (en) * 2024-01-08 2024-04-05 陕西安康玮创达信息技术有限公司 Insect pest detection method and system based on machine learning
CN117789067A (en) * 2024-02-27 2024-03-29 山东字节信息科技有限公司 Unmanned aerial vehicle crop monitoring method and system based on machine learning
CN117789067B (en) * 2024-02-27 2024-05-10 山东字节信息科技有限公司 Unmanned aerial vehicle crop monitoring method and system based on machine learning
CN117854012A (en) * 2024-03-07 2024-04-09 成都智慧城市信息技术有限公司 Crop environment monitoring method and system based on big data
CN117854012B (en) * 2024-03-07 2024-05-14 成都智慧城市信息技术有限公司 Crop environment monitoring method and system based on big data

Also Published As

Publication number Publication date
CN106645563A (en) 2017-05-10

Similar Documents

Publication Publication Date Title
WO2018058821A1 (en) Disease and insect pest forecasting method and apparatus based on planting equipment
WO2018099220A1 (en) Method and device for predicting plant diseases and pests in planter
Pecchi et al. Species distribution modelling to support forest management. A literature review
Row et al. Developing approaches for linear mixed modeling in landscape genetics through landscape‐directed dispersal simulations
Sinclair et al. The options by context approach: a paradigm shift in agronomy
CN106408132A (en) Method and device of crop yield prediction based on plantation device
Wayte et al. An effective harvest strategy using improved catch-curves
Zhou et al. Dynamic allometric scaling of tree biomass and size
CN111126662A (en) Irrigation decision making method, device, server and medium based on big data
Matilainen et al. Employing a Monte Carlo algorithm in Newton-type methods for restricted maximum likelihood estimation of genetic parameters
Ma et al. Exploring the relative importance of biotic and abiotic factors that alter the self-thinning rule: insights from individual-based modelling and machine-learning
Rupšys New insights into tree height distribution based on mixed effects univariate diffusion processes
CN110826764B (en) Random forest algorithm-based vegetation index prediction method, system and equipment
He et al. Potential geographical distribution and its multi-factor analysis of Pinus massoniana in China based on the maxent model
Cronie et al. Some edge correction methods for marked spatio-temporal point process models
Manjunath et al. An Efficient Crop Yield Prediction Framework Using Hybrid Machine Learning Model.
Rohde et al. Lettuce modelling for growth control in precision agriculture
Sai et al. SAI: fast and automated quantification of stomatal parameters on microscope images
Xu et al. Growth dynamics and heritability for plant high‐throughput phenotyping studies using hierarchical functional data analysis
Sellman et al. Realistic assumptions about spatial locations and clustering of premises matter for models of foot-and-mouth disease spread in the United States
Jiao et al. [Retracted] Prediction Model of Rice Seedling Growth and Rhizosphere Fertility Based on the Improved Elman Neural Network
Uniyal et al. Wine Quality Evaluation Using Machine Learning Algorithms
CN116230087B (en) Method and device for optimizing culture medium components
Gimenez et al. The efficient semiparametric regression modeling of capture-recapture data: assessing the impact of climate on survival of two Antarctic seabird species
CN115907178B (en) Clean ecosystem CO 2 Exchange amount prediction method

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16917565

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC - FORM 1205A (20.08.2019)

122 Ep: pct application non-entry in european phase

Ref document number: 16917565

Country of ref document: EP

Kind code of ref document: A1