CN109828623B - Production management method and device for greenhouse crop context awareness - Google Patents
Production management method and device for greenhouse crop context awareness Download PDFInfo
- Publication number
- CN109828623B CN109828623B CN201811621530.2A CN201811621530A CN109828623B CN 109828623 B CN109828623 B CN 109828623B CN 201811621530 A CN201811621530 A CN 201811621530A CN 109828623 B CN109828623 B CN 109828623B
- Authority
- CN
- China
- Prior art keywords
- parameters
- greenhouse
- monitoring
- monitoring parameters
- information
- 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
Images
Abstract
The embodiment of the invention provides a production management method and device for greenhouse crop context awareness, and belongs to the technical field of crop planting management. The method comprises the following steps: acquiring monitoring parameters of greenhouse crops, and preprocessing the monitoring parameters; and based on a deep learning model, performing context awareness on the preprocessed monitoring parameters to obtain decision information, and performing production management based on the decision information. The method provided by the embodiment of the invention is characterized in that the monitoring parameters of the greenhouse crops are taken and preprocessed. And based on a deep learning model, performing context awareness on the preprocessed monitoring parameters to obtain decision information, and performing production management based on the decision information. As multiple growth, physiological indexes and environmental parameters of crops can be sensed and corresponding decisions can be made, the traditional greenhouse crop management mode can be changed, the production, monitoring and regulation of greenhouse crops can be intelligentized, and the greenhouse monitoring data utilization rate can be improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of crop planting management, in particular to a production management method and device for greenhouse crop context awareness.
Background
At present, a control system is mostly constructed according to experience to realize greenhouse production management, automation and intellectualization of greenhouse production are realized, monitoring data are required to support on one hand, and a decision system is required to make technical support on the other hand. In the related technology, binocular image data and growth environment data of crops are collected, a binocular stereoscopic vision system is used for carrying out binocular image shooting on the crops, the image data of the crops are collected, meanwhile, a meteorological soil moisture monitoring system is used for monitoring the growth environment data of the crops, the growth environment data comprise indexes such as illumination, temperature, moisture and soil parameters, and the two data are combined to carry out field production auxiliary decision. In the process, when the context awareness data is used for decision making, the algorithm used for decision making is single, so that when the types of context information are increased, the algorithm is too complex and tedious, the maintenance and the upgrade of developers are not facilitated, and the fault rate of the whole context awareness system is increased.
Disclosure of Invention
In order to solve the above problems, embodiments of the present invention provide a method and apparatus for greenhouse crop context aware production management that overcomes or at least partially solves the above problems.
According to a first aspect of the embodiments of the present invention, there is provided a production management method for greenhouse crop context awareness, comprising:
acquiring monitoring parameters of greenhouse crops, and preprocessing the monitoring parameters, wherein the monitoring parameters at least comprise growth parameters, physiological parameters and environmental parameters;
and based on a deep learning model, performing context awareness on the preprocessed monitoring parameters to obtain decision information, and performing production management based on the decision information.
The method provided by the embodiment of the invention is characterized in that the monitoring parameters of the greenhouse crops are taken and preprocessed. And based on a deep learning model, performing context awareness on the preprocessed monitoring parameters to obtain decision information, and performing production management based on the decision information. As multiple growth, physiological indexes and environmental parameters of crops can be sensed and corresponding decisions can be made, the traditional greenhouse crop management mode can be changed, the production, monitoring and regulation of greenhouse crops can be intelligentized, and the greenhouse monitoring data utilization rate can be improved.
Secondly, the context awareness method and the concept are applied to greenhouse crop production, the context awareness decision is realized in the angle of greenhouse crops, and the production management of greenhouse crop feedback can be realized at lower cost. In addition, due to the fact that the scene perception framework is in a modularized design, combination can be conducted according to different greenhouse environments and conditions, maintenance and development can be conducted conveniently in the future, and then multi-level fusion is achieved to meet more complex production requirements. Finally, because the deep learning model is used as the inference machine of the context perception, more kinds of context information such as numerical values, texts, images and the like can be processed simultaneously according to the structure and the characteristics of the deep network, and the perception result is accurate and quick, so that the timeliness and the robustness required by the system can be met.
According to a second aspect of the embodiments of the present invention, there is provided a production management device for greenhouse crop context awareness, comprising:
the system comprises an acquisition module, a monitoring module and a control module, wherein the acquisition module is used for acquiring monitoring parameters of greenhouse crops, and the monitoring parameters at least comprise growth parameters, physiological parameters and environmental parameters;
the preprocessing module is used for preprocessing the monitoring parameters;
the context awareness module is used for performing context awareness on the preprocessed monitoring parameters based on the deep learning model to obtain decision information;
and the production management module is used for carrying out production management based on the decision information.
According to a third aspect of embodiments of the present invention, there is provided an electronic apparatus, including:
at least one processor; and
at least one memory communicatively coupled to the processor, wherein:
the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the greenhouse crop context aware production management method provided by any one of the various possible implementations of the first aspect.
According to a fourth aspect of the present invention, there is provided a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method for greenhouse crop context aware production management provided by any one of the various possible implementations of the first aspect.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory and are not restrictive of embodiments of the invention.
Drawings
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 description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a production management method for greenhouse crop context awareness according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a context awareness framework according to an embodiment of the present invention;
FIG. 3 is a data flow diagram according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a production management device for greenhouse crop context awareness according to an embodiment of the present invention;
fig. 5 is a block diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
At present, a control system is mostly constructed according to experience to realize greenhouse production management, automation and intellectualization of greenhouse production are realized, monitoring data are required to support on one hand, and a decision system is required to make technical support on the other hand. In the related technology, binocular image data and growth environment data of crops are collected, a binocular stereoscopic vision system is used for carrying out binocular image shooting on the crops, the image data of the crops are collected, meanwhile, a meteorological soil moisture monitoring system is used for monitoring the growth environment data of the crops, the growth environment data comprise indexes such as illumination, temperature, moisture and soil parameters, and the two data are combined to carry out field production auxiliary decision. In the process, when the context awareness data is used for decision making, the algorithm used for decision making is single, so that when the types of context information are increased, the algorithm is too complex and tedious, the maintenance and the upgrade of developers are not facilitated, and the fault rate of the whole context awareness system is increased.
In view of the above situation, the embodiment of the invention provides a production management method for greenhouse crop context awareness. Referring to fig. 1, the method includes:
101. acquiring monitoring parameters of greenhouse crops, and preprocessing the monitoring parameters, wherein the monitoring parameters at least comprise growth parameters, physiological parameters and environmental parameters.
The growth parameters may be obtained by a camera and/or a TOF (Time of Flight, or Time of Flight) device, the physiological parameters may be directly obtained by measurement by a photosynthetic measurement instrument, and the environmental parameters may be obtained by monitoring by a data acquisition device arranged in the greenhouse and integrated with various environmental sensors, which is not specifically limited in this embodiment of the present invention. It should be noted that after the monitoring parameters are obtained, the obtained data may also be summarized. In particular, the physiological parameters may be measured using a photosynthetic measurement instrument and the data derived for interpretation. The environmental parameter information can be transmitted to a database by using a GPRS module built in the data acquisition unit to be stored in real time and provide download service. The growth parameters are obtained by image processing. And finally, integrating the acquired various data information into a CSV format data set so as to facilitate the direct perception decision of the fusion system.
102. And based on a deep learning model, performing context awareness on the preprocessed monitoring parameters to obtain decision information, and performing production management based on the decision information.
The method provided by the embodiment of the invention is characterized in that the monitoring parameters of the greenhouse crops are taken and preprocessed. And based on a deep learning model, performing context awareness on the preprocessed monitoring parameters to obtain decision information, and performing production management based on the decision information. As multiple growth, physiological indexes and environmental parameters of crops can be sensed and corresponding decisions can be made, the traditional greenhouse crop management mode can be changed, the production, monitoring and regulation of greenhouse crops can be intelligentized, and the greenhouse monitoring data utilization rate can be improved.
Secondly, the context awareness method and the concept are applied to greenhouse crop production, the context awareness decision is realized in the angle of greenhouse crops, and the production management of greenhouse crop feedback can be realized at lower cost. In addition, due to the fact that the scene perception framework is in a modularized design, combination can be conducted according to different greenhouse environments and conditions, maintenance and development can be conducted conveniently in the future, and then multi-level fusion is achieved to meet more complex production requirements. Finally, because the deep learning model is used as the inference machine of the context perception, more kinds of context information such as numerical values, texts, images and the like can be processed simultaneously according to the structure and the characteristics of the deep network, and the perception result is accurate and quick, so that the timeliness and the robustness required by the system can be met.
Based on the content of the above embodiment, as an optional embodiment, the growth parameters at least comprise crop growth parameters, plant height and canopy leaf area parameters; the physiological parameters at least comprise crop net photosynthetic rate, canopy temperature, transpiration and crop fluorescence parameters; the environmental parameters include at least air temperature, air humidity, soil temperature, soil humidity, illumination intensity and CO2 concentration.
Based on the content of the foregoing embodiment, as an optional embodiment, before the preprocessing the monitoring parameter, the method further includes: the monitoring parameters were screened based on the type of greenhouse. The information screening is to select different context information as input of a fusion model according to different perceived targets, so that the expandability and generalization capability of the system are enhanced, and decision interference caused by information redundancy is avoided.
Based on the content of the foregoing embodiments, as an optional embodiment, regarding a manner of preprocessing the monitoring parameter, the embodiments of the present invention are not particularly limited to this, and include but are not limited to: and removing the missing value parameters in the monitoring parameters, matching the growth parameters, the physiological parameters and the environmental parameters in the monitoring parameters, and normalizing the matched monitoring parameters. It should be noted that the normalization process may be an optional step, that is, the fusion and decision of the normalized data are not necessarily beneficial, so that whether normalization is needed or not can be manually selected.
Based on the content of the foregoing embodiment, as an optional embodiment, the embodiment of the present invention does not specifically limit the manner of obtaining the decision information by performing context awareness on the preprocessed monitoring parameters based on the deep learning model, including but not limited to: based on a deep learning model, fusing monitoring parameters to obtain regional scene information; acquiring a greenhouse integral sensing result based on the regional context information; and matching the overall sensing result of the greenhouse with a preset regulation and control decision to obtain decision information.
Specifically, a deep learning model based on a Tensorflow toolkit can be trained by using a data set; and using the trained model as an inference machine of each middleware to fuse the data to obtain regional scene information. And then, giving the overall perception result of the greenhouse by using the information of each region in a minority subject to the majority principle. And matching the perception result with a customized regulation and control decision or service to obtain decision information. And finally, utilizing the decision information to regulate and control the environment of the greenhouse crops or provide corresponding services.
Based on the content of the above embodiment, as an optional embodiment, the decision information at least includes environment regulation and control information, water and fertilizer management information, and farm work operation information.
Based on the content of the above embodiments, as an alternative embodiment, the deep learning model is obtained based on wide and deep neural network training. The wide-deep neural network can utilize the characteristics of combined training and combined classification of the depth network and the width network, and is responsible for accurately classifying or predicting the input environmental information, growth information and physiological information, so that the effect of data fusion is achieved, environmental state decision information of all regions of the greenhouse is provided according to classification categories, and greenhouse environment regulation and control suggestions are given. The wide-deep neural network is formed by combining a width (wide) network and a depth (deep), the wide network is good at processing sparse features (such as text features), the deep network is good at processing high-dimensional features (meteorological and other numerical features), and the corresponding mathematical expression is as follows:
wherein Y is a classification category label, SoftMax (-) is a multi-category classification function,
For cross product transformation of original features x, b for bias of model, WwideIs the weight vector, W, of the wide modeldeepIs the weight vector of the deep network.
Based on the greenhouse crop context awareness production management method provided in the above embodiments, a specific application example of the method is provided by combining with an actual application scenario. The method can adjust the scale and perception category of the frame according to the requirement; the situation information can be manually input or crawled from a database, and a proper inference machine is selected to be built by combining the characteristics of the situation information.
Data acquisition aspect: the situation information required by situation perception needs to acquire monitoring data through data collectors uniformly distributed in the greenhouse, monitoring equipment adopts a greenhouse cloud environment data collector, and each data collector can be installed on a tripod. Each data collector can measure air temperature, air relative humidity, soil temperature, soil humidity and CO2The illumination intensity, the monitoring data type can be increased and decreased according to specific production requirements to set time intervals (30min) to be sent to a remote cloud server, the situation awareness system can be used for connecting a database interface to obtain real-time monitoring data, and an administrator can also manually input situation information to conduct awareness.
And (3) data processing: the data preprocessing needs to perform corresponding selection according to the characteristics of the inference engine algorithm, and the data set is uniformly adjusted into a CSV file format before data processing, so that the data processing and model perception are facilitated. When the wide-deep neural network is used for making greenhouse area environment state information decision, the input parameter non-preprocessing effect is better than the normalization and regularization preprocessing according to the comparison of the test effect. Therefore, no data preprocessing operations are taken when the context state information is sensed. Meanwhile, an administrator can manually select whether abnormal values in the model training set data are reserved or not according to production characteristics and perception requirements of the administrator, when the abnormal values are reserved, the trained wide and deep neural network can recognize the abnormal value data, and functions of warning, sensor fault prompting and the like are given according to recognition results.
Context-aware framework construction aspect: 6 data collection points were selected, 4858 data from 12/23/2017 to 1/2/2018 for model training and testing. Wherein, the training set 4009 pieces of data, and the testing set 849 pieces of data. Each data is continuously collected for 24h at 30min intervals. And performing class marking on the downloaded data, using the training set and the test set for constructing the wide and deep neural network, selecting the model structure as 7-100-50-7, and training and iterating for 2000 steps. The perception system building environment can be a MacOS operating system, the model implementation can be based on a Google open source Tensorflow toolkit, the programming language can be Python, and the Integrated Development Environment (IDE) can be jupyter notebook integrated in Anaconda.
Because the system adopts a modular design, development or maintenance personnel can increase or delete the levels of the framework according to specific requirements, each level consists of three modules of data integration, data processing and scene fusion, and the whole level is realized in a way of sensing the middleware of the system (the middleware is a class in a programming language). The middleware can package data uploaded by the sensor, namely converting text data into sparse data and converting numerical data into tensor type data. And then, a reasoning machine of the middleware is utilized to perform context awareness on the packaged data, the perception process is to classify the input features, and the classification accuracy (the ratio of the number of correct classification samples to the total classification samples) of the system can reach 98.00% by later verification, namely the expected prediction result can be reached by verification.
Corresponding decision information is provided according to the categories, the perceived decision information is transmitted to the application layer, the UI design of the application layer is realized by adopting the TKinter toolkit programming, and the context awareness system can be called conveniently. The system finally gives information of the current growth stage of the crops, current environment information, corresponding service strategies and necessary hardware regulation and control suggestions according to the classification result of the fusion model, and finally can realize real-time perception of the greenhouse crop state, so that greenhouse production related personnel can clearly master the growth state and the environment information of the greenhouse crops, and the effect of self-adaptive regulation is realized.
The context awareness framework related to the embodiment of the present invention may refer to fig. 2, and the data flow of the method provided by the embodiment of the present invention may refer to fig. 3. With reference to the above specific application example, the effects of the above specific application example are as follows:
first, utilize the scenario perception frame of modularization thought design to greenhouse crop, can realize the compatibility to different greenhouse environment and greenhouse condition, conveniently add or delete the subassembly of frame, can realize multistage perception to the complex environment of more contextual information and reach the effect that decision information is more accurate, have fine generalization ability.
And secondly, the core inference machine of the context awareness framework is composed of a deep learning model, and the deep learning model has stronger data processing capacity and more processing characteristic types, so that the complex and changeable context information can be better compatible when the framework components are increased or decreased, and the requirements of modular design are met.
Thirdly, due to the fact that the environment or the state of the greenhouse crops can be efficiently and accurately decided by the context awareness method, corresponding service and regulation and control mechanisms are provided, human resources can be reduced, management efficiency can be improved, and intellectualization and automation of greenhouse crop production are achieved.
And fourthly, the situation awareness and the deep learning are applied to greenhouse production, and the intelligent awareness of the greenhouse crop environment, growth, physiology and other information is realized. SPA (talking Plant approach) is applied to a facility agricultural production management platform, and efficient, energy-saving and optimal management of 'conversation with plants' is realized. The change of the plant is taken as the basis for changing the growth environment of the plant, and the traditional environment control and decision management mode is changed.
Based on the content of the above embodiment, the embodiment of the present invention further provides a production management device for greenhouse crop context awareness, where the device is configured to execute the production management method for greenhouse crop context awareness provided in the above method embodiment. Referring to fig. 4, the apparatus includes: an acquisition module 401, a preprocessing module 402, a context awareness module 403 and a production management module 404; wherein the content of the first and second substances,
the acquisition module 401 is used for acquiring monitoring parameters of greenhouse crops, wherein the monitoring parameters at least comprise growth parameters, physiological parameters and environmental parameters;
a preprocessing module 402, configured to preprocess the monitoring parameters;
the context awareness module 403 is configured to perform context awareness on the preprocessed monitoring parameters based on a deep learning model to obtain decision information;
and a production management module 404, configured to perform production management based on the decision information.
Based on the content of the above embodiment, as an optional embodiment, the growth parameters at least comprise crop growth parameters, plant height and canopy leaf area parameters; the physiological parameters at least comprise crop net photosynthetic rate, canopy temperature, transpiration and crop fluorescence parameters; the environmental parameters include at least air temperature, air humidity, soil temperature, soil humidity, illumination intensity and CO2 concentration.
Based on the content of the foregoing embodiment, as an alternative embodiment, the apparatus further includes:
and the screening module is used for screening the monitoring parameters based on the type of the greenhouse.
Based on the content of the foregoing embodiment, as an optional embodiment, the preprocessing module 402 is configured to remove missing value parameters in the monitoring parameters, match growth parameters, physiological parameters, and environmental parameters in the monitoring parameters, and normalize the matched monitoring parameters.
Based on the content of the foregoing embodiment, as an optional embodiment, the context awareness module 403 is configured to fuse the monitoring parameters based on a deep learning model to obtain regional context information; acquiring a greenhouse integral sensing result based on the regional context information; and matching the overall sensing result of the greenhouse with a preset regulation and control decision to obtain decision information.
Based on the content of the above embodiment, as an optional embodiment, the decision information at least includes environment regulation and control information, water and fertilizer management information, and farm work operation information.
Based on the content of the above embodiments, as an alternative embodiment, the deep learning model is obtained based on wide and deep neural network training.
The device provided by the embodiment of the invention is used for preprocessing the monitoring parameters of the greenhouse crops. And based on a deep learning model, performing context awareness on the preprocessed monitoring parameters to obtain decision information, and performing production management based on the decision information. As multiple growth, physiological indexes and environmental parameters of crops can be sensed and corresponding decisions can be made, the traditional greenhouse crop management mode can be changed, the production, monitoring and regulation of greenhouse crops can be intelligentized, and the greenhouse monitoring data utilization rate can be improved.
Secondly, the context awareness method and the concept are applied to greenhouse crop production, the context awareness decision is realized in the angle of greenhouse crops, and the production management of greenhouse crop feedback can be realized at lower cost. In addition, due to the fact that the scene perception framework is in a modularized design, combination can be conducted according to different greenhouse environments and conditions, maintenance and development can be conducted conveniently in the future, and then multi-level fusion is achieved to meet more complex production requirements. Finally, because the deep learning model is used as the inference machine of the context perception, more kinds of context information such as numerical values, texts, images and the like can be processed simultaneously according to the structure and the characteristics of the deep network, and the perception result is accurate and quick, so that the timeliness and the robustness required by the system can be met.
Fig. 5 illustrates a physical structure diagram of an electronic device, which may include, as shown in fig. 5: a processor (processor)510, a communication Interface (Communications Interface)520, a memory (memory)530 and a communication bus 540, wherein the processor 510, the communication Interface 520 and the memory 530 communicate with each other via the communication bus 540. Processor 510 may call logic instructions in memory 530 to perform the following method: acquiring monitoring parameters of greenhouse crops, and preprocessing the monitoring parameters, wherein the monitoring parameters at least comprise growth parameters, physiological parameters and environmental parameters; and based on a deep learning model, performing context awareness on the preprocessed monitoring parameters to obtain decision information, and performing production management based on the decision information. It should be noted that in actual implementation, the form of the electronic device may be a PC or a tablet computer, and the PC or the tablet computer may collect data and may have a decision control function, and the like.
Furthermore, the logic instructions in the memory 530 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, an electronic device, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Embodiments of the present invention further provide a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented to perform the method provided in the foregoing embodiments when executed by a processor, and the method includes: acquiring monitoring parameters of greenhouse crops, and preprocessing the monitoring parameters, wherein the monitoring parameters at least comprise growth parameters, physiological parameters and environmental parameters; and based on a deep learning model, performing context awareness on the preprocessed monitoring parameters to obtain decision information, and performing production management based on the decision information.
The above-described embodiments of the apparatus are merely illustrative, and 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, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (7)
1. A greenhouse crop context-aware production management method is characterized by comprising the following steps:
acquiring monitoring parameters of greenhouse crops, and preprocessing the monitoring parameters, wherein the monitoring parameters at least comprise growth parameters, physiological parameters and environmental parameters;
based on a deep learning model, performing context awareness on the preprocessed monitoring parameters to obtain decision information, and performing production management based on the decision information;
the method for obtaining the decision information by performing context awareness on the preprocessed monitoring parameters based on the deep learning model comprises the following steps:
based on a deep learning model, fusing monitoring parameters to obtain regional scene information;
providing the overall perception result of the greenhouse by using the scene information of each region according to a majority principle in a minority;
matching the greenhouse integral sensing result with a preset regulation and control decision to obtain decision information;
before the preprocessing of the monitoring parameters, the method further comprises the following steps:
screening the monitoring parameters based on the type of the greenhouse crop;
the decision information at least comprises environment regulation and control information, water and fertilizer management information and farming operation information.
2. The method according to claim 1, wherein the growth parameters comprise at least crop growth parameters, plant height and canopy leaf area parameters; the physiological parameters at least comprise crop net photosynthetic rate, canopy temperature, transpiration and crop fluorescence parameters; the environmental parameters at least comprise air temperature, air humidity, soil temperature, soil humidity, illumination intensity and CO2And (4) concentration.
3. The method of claim 1, wherein the pre-processing the monitored parameter comprises:
and removing the missing value parameters in the monitoring parameters, matching the growth parameters, the physiological parameters and the environmental parameters in the monitoring parameters, and normalizing the matched monitoring parameters.
4. The method of any one of claims 1 to 3, wherein the deep learning model is based on wide-deep neural network training.
5. A greenhouse crop context aware production management device, comprising:
the system comprises an acquisition module, a monitoring module and a control module, wherein the acquisition module is used for acquiring monitoring parameters of greenhouse crops, and the monitoring parameters at least comprise growth parameters, physiological parameters and environmental parameters;
the preprocessing module is used for preprocessing the monitoring parameters;
the context awareness module is used for performing context awareness on the preprocessed monitoring parameters based on a deep learning model to obtain decision information;
the production management module is used for carrying out production management based on the decision information;
a screening module for screening the monitoring parameters based on the type of the greenhouse crop;
the context awareness module is further used for fusing the monitoring parameters based on the deep learning model to obtain regional context information; providing the overall perception result of the greenhouse by using the scene information of each region according to a majority principle in a minority; and matching the greenhouse integral sensing result with a preset regulation and control decision to obtain the decision information.
6. An electronic device, comprising:
at least one processor; and
at least one memory communicatively coupled to the processor, wherein:
the memory stores program instructions executable by the processor, the processor invoking the program instructions to perform the method of any of claims 1 to 4.
7. A non-transitory computer-readable storage medium storing computer instructions that cause a computer to perform the method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811621530.2A CN109828623B (en) | 2018-12-28 | 2018-12-28 | Production management method and device for greenhouse crop context awareness |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811621530.2A CN109828623B (en) | 2018-12-28 | 2018-12-28 | Production management method and device for greenhouse crop context awareness |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109828623A CN109828623A (en) | 2019-05-31 |
| CN109828623B true CN109828623B (en) | 2021-03-12 |
Family
ID=66861167
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811621530.2A Active CN109828623B (en) | 2018-12-28 | 2018-12-28 | Production management method and device for greenhouse crop context awareness |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109828623B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111108879A (en) * | 2020-01-03 | 2020-05-08 | 华维节水科技集团股份有限公司 | Solanaceous fruit water and fertilizer and environment management method based on expert decision system |
Family Cites Families (14)
| 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 |
| US8114353B2 (en) * | 2007-12-20 | 2012-02-14 | Chevron Phillips Chemical Company Lp | Continuous catalyst activator |
| CN101953287B (en) * | 2010-08-25 | 2012-11-21 | 中国农业大学 | Multi-data based crop water demand detection system and method |
| KR101173823B1 (en) * | 2011-07-01 | 2012-08-20 | 연세대학교 산학협력단 | System and method for predicting an energy consumption of multi-family housing |
| CN102736596B (en) * | 2012-06-11 | 2014-10-29 | 南京农业大学 | Multi-scale greenhouse environment control system based on crop information fusion |
| CN103914786B (en) * | 2014-03-10 | 2017-06-30 | 北京农业信息技术研究中心 | A kind of broadacre agriculture produces context aware computational methods and device |
| CN104408258B (en) * | 2014-12-01 | 2017-12-15 | 四川农业大学 | The large scale soil organic matter spatial distribution analogy method of integrated environment factor |
| CN105005234B (en) * | 2015-06-02 | 2017-10-13 | 哈尔滨工业大学（威海） | The remote measurement of intelligent greenhouse environment and control system based on zigbee |
| US11287411B2 (en) * | 2015-07-30 | 2022-03-29 | Ecoation Innovative Solutions Inc. | Systems and methods for crop health monitoring, assessment and prediction |
| CN106326472B (en) * | 2016-08-31 | 2017-06-16 | 广东京奥信息科技有限公司 | One kind investigation information integrity verification method |
| CN106971160A (en) * | 2017-03-23 | 2017-07-21 | 西京学院 | Winter jujube disease recognition method based on depth convolutional neural networks and disease geo-radar image |
| CN108334139A (en) * | 2018-03-01 | 2018-07-27 | 深圳春沐源控股有限公司 | A kind of method and system of the greenhouse automation control based on big data |
| CN108983849A (en) * | 2018-07-12 | 2018-12-11 | 沈阳大学 | It is a kind of to utilize compound extreme learning machine ANN Control greenhouse method |
| CN109086826B (en) * | 2018-08-06 | 2021-05-07 | 中国农业科学院农业资源与农业区划研究所 | Wheat drought identification method based on image deep learning |
-
2018
- 2018-12-28 CN CN201811621530.2A patent/CN109828623B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109828623A (en) | 2019-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | An AIoT based smart agricultural system for pests detection | |
| Channe et al. | Multidisciplinary model for smart agriculture using internet-of-things (IoT), sensors, cloud-computing, mobile-computing & big-data analysis | |
| US20180342020A1 (en) | System, method and apparatus for management of agricultural resource | |
| CN113557890B (en) | Intelligent water precise irrigation control system and method for fruit and vegetable cultivation in sunlight greenhouse | |
| EP3482630B1 (en) | Method, system and computer program for performing a pest forecast | |
| CN109344738A (en) | The recognition methods of crop diseases and pest crop smothering and device | |
| WO2020160548A1 (en) | Systems and methods for measuring beehive strength | |
| CN117036088A (en) | Data acquisition and analysis method for identifying growth situation of greening plants by AI | |
| CN112286263A (en) | Crop regulation and control method, device and system and communication equipment | |
| Murugamani et al. | Machine learning technique for precision agriculture applications in 5G-based internet of things | |
| Suneja et al. | Cloud-based tomato plant growth and health monitoring system using IOT | |
| CN114359745A (en) | Information processing method, storage medium, and electronic device | |
| Musa et al. | An intelligent plant dissease detection system for smart hydroponic using convolutional neural network | |
| CN115861686A (en) | Litchi key growth period identification and detection method and system based on edge deep learning | |
| CN109828623B (en) | Production management method and device for greenhouse crop context awareness | |
| CN113545280B (en) | System and method for carrying out accurate irrigation based on plant wilting degree | |
| Anitha Mary et al. | Scope and recent trends of artificial intelligence in Indian agriculture | |
| Araneta et al. | Controlled Environment for Spinach Cultured Plant with Health Analysis using Machine Learning | |
| Helfer et al. | Ubiquitous computing in precision agriculture: A systematic review | |
| Tidake et al. | Design efficient model to increase crop yield using deep learning | |
| CN114663652A (en) | Image processing method, image processing apparatus, management system, electronic device, and storage medium | |
| FAISAL | A pest monitoring system for agriculture using deep learning | |
| Chen et al. | Agricultural pests damage detection using deep learning | |
| Berger et al. | A YOLO-Based Insect Detection: Potential Use of Small Multirotor Unmanned Aerial Vehicles (UAVs) Monitoring | |
| Singh et al. | A tool for climate smart crop insurance: Combining farmers’ pictures with dynamic crop modelling for accurate yield estimation prior to harvest |
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 |