CN107316105A - A kind of big regional agriculture forecasting system - Google Patents
A kind of big regional agriculture forecasting system Download PDFInfo
- Publication number
- CN107316105A CN107316105A CN201710431866.1A CN201710431866A CN107316105A CN 107316105 A CN107316105 A CN 107316105A CN 201710431866 A CN201710431866 A CN 201710431866A CN 107316105 A CN107316105 A CN 107316105A
- Authority
- CN
- China
- Prior art keywords
- neural network
- network model
- predicted
- modeling point
- network server
- 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.)
- Granted
Links
- 238000003062 neural network model Methods 0.000 claims abstract description 88
- 238000013528 artificial neural network Methods 0.000 claims abstract description 67
- 230000007613 environmental effect Effects 0.000 claims abstract description 18
- 238000012549 training Methods 0.000 claims description 20
- 238000013480 data collection Methods 0.000 claims description 4
- 238000012271 agricultural production Methods 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 abstract description 3
- 210000005036 nerve Anatomy 0.000 abstract description 3
- 230000015572 biosynthetic process Effects 0.000 abstract 1
- 230000005540 biological transmission Effects 0.000 description 13
- 241000209094 Oryza Species 0.000 description 7
- 235000007164 Oryza sativa Nutrition 0.000 description 7
- 235000009566 rice Nutrition 0.000 description 7
- 201000010099 disease Diseases 0.000 description 6
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000000034 method Methods 0.000 description 4
- 238000010219 correlation analysis Methods 0.000 description 3
- 238000010295 mobile communication Methods 0.000 description 3
- 239000002689 soil Substances 0.000 description 3
- 238000005286 illumination Methods 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 230000017260 vegetative to reproductive phase transition of meristem Effects 0.000 description 2
- 244000068988 Glycine max Species 0.000 description 1
- 235000010469 Glycine max Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 210000000225 synapse Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Biophysics (AREA)
- Tourism & Hospitality (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Agronomy & Crop Science (AREA)
- Animal Husbandry (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a kind of big regional agriculture forecasting system, it is related to field of agricultural production technologies.The system includes：The big regional nerve webserver, the modeling point neural network server corresponding to each modeling point and the environmental data collecting unit corresponding to each modeling point.By building neural network model formation Hierarchical Neural Networks model respectively on the big regional nerve webserver and modeling point neural network server, the environmental data that environmental data collecting unit is collected is used as input, it is predicted using the Hierarchical Neural Networks, exports the predicted value of the target to be predicted in big region.A kind of big regional agriculture forecasting system that the present invention is provided, realizes the prediction of big region target to be predicted, and system architecture is simple, and arrangement is convenient, it is easy to popularization and application.
Description
Technical Field
The embodiment of the invention relates to the technical field of agricultural production, in particular to a large-area agricultural prediction system.
Background
The artificial neural network is a mathematical model for information processing by applying a structure similar to brain nerve synapse connection, has the characteristics of self-learning, self-organization and self-adaption, and can master the internal rule of a learning object by learning a representative sample, thereby overcoming the problem of large information quantity to a certain extent and making up the defects of the traditional method.
In the field of agricultural production, artificial neural networks are applied to the fields of classification, evaluation, prediction, modeling and the like, and play an important role. The non-linear mapping digital model is suitable for solving a plurality of complex problems which are difficult to express by using a conventional mathematical method in the agricultural field, and particularly shows good application potential in the aspects of prediction and modeling.
At present, there are many application examples of prediction and modeling using an artificial neural network, for example, predicting soybean flowering phase and physiological maturity phase using an artificial neural network with daily maximum and minimum air temperature, light cycle, planting period or flowering phase as input variables; or predicting the soil moisture content value in the next period by using the soil moisture content value, rainfall or illumination equivalent value in the last ten days of a month as input variables.
However, when obtaining input variables such as soil moisture content values, rainfall or illumination, input variables of small areas (such as villages and towns) are often easy to obtain, and due to the limitation of regional areas, input variables of large areas (such as counties and cities) are difficult to obtain or obtained are inaccurate, so that the agricultural production target of the large areas cannot be predicted by using the artificial neural network.
Disclosure of Invention
In view of the problem in the prior art that the artificial neural network cannot be used for predicting the target of the large-area agricultural production, the embodiment of the present invention provides a large-area agricultural prediction system which overcomes or at least partially solves the above problem.
The embodiment of the invention provides a large-area agricultural prediction system, which comprises: a large-area neural network server and a modeling point neural network server corresponding to each modeling point; wherein,
the modeling point neural network server is used for acquiring a first predicted value of a target to be predicted of a modeling point by using a first preset neural network model based on environmental data of the modeling point and sending the first predicted value to the large-area neural network server;
the large-area neural network server is used for obtaining the predicted value of the target to be predicted in the large area by utilizing a second preset neural network model based on the first predicted value.
The device also comprises a modeling point selecting unit used for selecting a small area as the modeling point according to the correlation between the large area and the small area contained in the large area.
The system comprises a data acquisition terminal, a routing node and a coordination node, wherein the data acquisition terminal is used for acquiring environmental data of each modeling point; wherein,
the data acquisition terminal is connected with the routing node through a public channel and used for acquiring environment data of a modeling point and transmitting the environment data to the routing node;
the routing node is connected with the coordination node through a common channel and used for transmitting the environment data to the coordination node;
the co-regulation point is connected with the modeling point neural network server and used for transmitting the environment data to the modeling point neural network server.
The modeling point neural network server is further used for constructing a first initial neural network model and training the first initial neural network model through a first training sample to obtain the first preset neural network model.
The large-area neural network server is further used for constructing a second initial neural network model, and training the second initial neural network model through a second training sample to obtain the second preset neural network model.
The first initial neural network model is a BP neural network model which takes the environment data as an input layer and the first predicted value as an output layer.
The first training sample comprises historical data of the environment data and real values of the target to be measured of the corresponding modeling points.
And the second initial neural network model is a BP neural network model which takes the first predicted value as an input layer and takes the predicted value of the target to be detected as an output layer.
And the second training sample comprises historical data of the first predicted value and a real value of the target to be detected in a corresponding large area.
The system further comprises a client side, and the client side is used for obtaining the predicted value of the target to be predicted, which is output by the large-area neural network server.
According to the large-area agricultural prediction system provided by the embodiment of the invention, the neural network models are respectively constructed on the large-area neural network server and the modeling point neural network server to form the hierarchical neural network model, the environmental data of the modeling point is used as input, the hierarchical neural network model is used for prediction, the prediction value of the target to be predicted in the large area is obtained, the prediction of the target to be predicted in the large area is realized, and the system is simple in structure, convenient to arrange and easy to popularize and apply.
Drawings
FIG. 1 is a schematic diagram of a large-area agricultural prediction system according to an embodiment of the present invention;
FIG. 2 is a block diagram of a large-area agricultural prediction system according to an embodiment of the present invention;
fig. 3 is a block diagram of an environment data acquisition module according to the embodiment of fig. 2 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 described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some embodiments, 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.
Fig. 1 is a schematic view of a large-area agricultural prediction system provided in an embodiment of the present invention, and fig. 2 is a block diagram of a structure of the large-area agricultural prediction system provided in the embodiment of the present invention, and as shown in fig. 1 and fig. 2, the system includes: a large area neural network server 11 and modeling point neural network servers 12 corresponding to the respective modeling points. Wherein:
the modeling point neural network server 12 is configured to output a first predicted value of a target to be predicted of the modeling point by using a first preset neural network model based on the environment data of the modeling point, and send the first predicted value to the large area neural network server 11. The large-area neural network server 11 is configured to output the predicted value of the target to be predicted in the large area by using a second preset neural network model based on the first predicted value.
The large area is provided with a plurality of modeling points, and the number and the positions of the modeling points are determined according to actual requirements. The environmental data includes temperature, humidity, sunlight, wind power, and the like. The first preset neural network model is stored in the modeling point neural network server 12, the second preset neural network model is stored in the large area neural network server 11, and the plurality of first preset neural network models in the plurality of modeling point neural network servers 12 and the second preset neural network model in the large area neural network server 11 form a hierarchical neural network model together. In specific implementation, a plurality of first preset neural network models suitable for different prediction targets may be pre-stored in the modeling point neural network server 12, and a plurality of corresponding second preset neural network models suitable for different prediction targets may be pre-stored in the large area neural network server 11, so that a plurality of hierarchical neural network models may be formed by combination according to different prediction targets.
The input of the first preset neural network model is the environment data of the modeling points, the output is the first predicted value of the target to be predicted of the modeling points, the input of the second preset neural network model is the first predicted value of the target to be predicted of a plurality of modeling points in a large area, and the output is the predicted value of the target to be predicted of the large area, namely the input of the hierarchical neural network model is the environment data of the modeling points, and the output is the predicted value of the target to be predicted of the large area.
Specifically, according to the target to be predicted, which needs to be predicted, a corresponding hierarchical neural network model is selected, the type of the required environment data is determined, and then the environment data of the modeling point is screened. And taking the screened environmental data as input, predicting by using the first preset neural network model, and outputting a predicted value of the prediction target of the corresponding small area, namely outputting the first predicted value. The plurality of modeling point neural network servers 12 send the first predicted values to the large area neural network server 11, use the plurality of first predicted values as input, perform prediction by using the second preset neural network model, and output predicted values of the prediction targets of the large area, that is, use the environment data of the screened modeling points as input of the hierarchical neural network model, and output predicted values of the prediction targets of the large area.
According to the large-area agricultural prediction system provided by the embodiment of the invention, the neural network models are respectively constructed on the large-area neural network server and the modeling point neural network server to form the hierarchical neural network model, the environmental data of the modeling point is used as input, the hierarchical neural network model is used for prediction, the prediction value of the target to be predicted in the large area is obtained, the prediction of the target to be predicted in the large area is realized, and the system is simple in structure, convenient to arrange and easy to popularize and apply.
In the above embodiment, the system further includes a modeling point selecting unit, configured to select a small region serving as the modeling point according to a correlation between the large region and a small region included in the large region.
The large area comprises a plurality of small areas, the environment data of each small area cannot be collected in actual production practice, only a part of the small areas can be selected as modeling points for arranging environment data collection units, and certain correlation exists between the small areas of the selected modeling points and the large area to be used as the modeling points.
Specifically, the real value of the target to be predicted in the large area and the real values of the targets to be predicted in the small areas within a period of time are obtained, correlation analysis is performed according to the real values, correlation values between the large area and the small areas are obtained, and the small areas with high correlation are selected as modeling points.
Furthermore, the correlation between the large area and the small area is analyzed at regular intervals, and when the correlation changes, the modeling point is reselected, so that the inaccuracy of the system for predicting the target to be predicted after the correlation changes can be avoided.
According to the embodiment of the invention, the modeling point is selected by carrying out correlation analysis on the large area and the small area, so that the accuracy of the hierarchical neural network model in the system for predicting the target to be predicted can be ensured.
In the above embodiment, as shown in fig. 2 and fig. 3, the system further includes an environment data acquisition unit for acquiring environment data of each modeling point, where the environment data acquisition unit includes a data acquisition terminal 31, a routing node 32, and a coordination node 33. Wherein:
the data acquisition terminal 31 is connected to the routing node 32 through a common channel, and is configured to acquire environment data of a modeling point and transmit the environment data to the routing node 32. The routing node 32 is connected to the coordinating node 33 via a common channel for transmitting the context data to the coordinating node 33. The coordinating node 33 is connected to the modeling point neural network server, and is configured to transmit the environment data to the modeling point neural network server.
The environment data acquisition unit comprises a plurality of data acquisition terminals 31, the data acquisition terminals are connected through a 2.4G public channel, and are relayed and connected through a 2.4G public channel via the routing node 32 to form a wireless sensor network. The data acquisition terminal specifically comprises various sensors, for example, the data acquisition terminal for acquiring temperature comprises a temperature sensor for acquiring the temperature of a small area where the modeling point is located.
Specifically, a C language can be adopted, a driver is written and a Z-Stack protocol Stack is modified to drive data to the wireless sensor network, so that automatic acquisition of the environment data and transmission of the environment data in the wireless sensor network are realized, and finally the environment data is transmitted to the modeling point neural network server through the coordination node 33 via a serial port.
The embodiment of the invention realizes the automatic acquisition and transmission of environmental data by constructing the wireless sensor network, improves the automation degree of the system, makes the use of the system more convenient and is beneficial to popularization and application.
In the above embodiment, the modeling point neural network server is further configured to construct a first initial neural network model, and train the first initial neural network model through a first training sample to obtain the first preset neural network model. And the first initial neural network model is a BP neural network model which takes the environment data as an input layer and the first predicted value as an output layer. The first training sample comprises historical data of the environment data and real values of the target to be measured of the corresponding modeling points.
The BP neural network model consists of two parts: the forward propagation of sample data and the back propagation of errors. In the forward pass, the input information is computed layer by layer from output layer to output layer. If the output layer does not obtain the expected output, the error of the output layer is transmitted back along the original connection path through the network, and the weight and the threshold of each neuron are modified until the expected error target is reached. And when the first initial neural network model is constructed, constructing a BP neural network model by taking the environment data as an input layer and the first predicted value as an output layer. Historical data of the environment data and real values of the targets to be detected corresponding to the modeling points in a period of time are stored in the neural network server of the modeling points in a form to form a first historical database, and when the method is specifically implemented, the JDBC technology can be adopted to realize the operations of warehousing, increasing, deleting, modifying, checking and the like of the first historical database.
Specifically, the building of the first preset neural network model by the modeling point neural network server generally includes two steps: the method comprises the steps of firstly, constructing a first initial neural network model, and secondly, training the first initial neural network model to obtain a first preset neural network model. In the first step, the environmental data of the modeling point is screened according to the type of the target to be predicted, the screened environmental data is used as an input layer, for example, when the target to be predicted is the disease state of rice blast of middle rice, the temperature, the humidity, the sunshine and the wind power are selected as the input layer; and then using the first predicted value as an output layer. In the second step, selecting the historical data of the environmental data and the real value of the target to be tested of the corresponding modeling point from the first historical database as the first training sample according to the input layer of the first initial neural network model, and inputting the first training sample into the first initial neural network model to train the first initial neural network model to obtain the first preset neural network model. In implementation, the first predetermined neural network model may be constructed in JAVA.
Furthermore, the first preset neural network model corresponding to a plurality of common targets to be predicted can be pre-stored in the modeling point neural network server, and the corresponding first preset neural network model can be directly selected for prediction after the targets to be predicted are determined, so that the system can work more efficiently.
In the above embodiment, the large-area neural network server is further configured to construct a second initial neural network model, and train the second initial neural network model through a second training sample to obtain the second preset neural network model. The second initial neural network model is a BP neural network model which takes the first predicted value as an input layer and takes the predicted value of the target to be predicted as an output layer. The second training sample comprises historical data of the first predicted value and a real value of the target to be detected in a corresponding large area.
The BP neural network model consists of two parts: the forward propagation of sample data and the back propagation of errors. In the forward pass, the input information is computed layer by layer from output layer to output layer. If the output layer does not obtain the expected output, the error of the output layer is transmitted back along the original connection path through the network, and the weight and the threshold of each neuron are modified until the expected error target is reached. And when the second initial neural network model is constructed, constructing a BP neural network model by taking the first predicted value as an input layer and taking the predicted value of the target to be predicted in the large area as an output layer. And storing the historical data of the first predicted value in a period of time and the real value of the target to be detected corresponding to the large area in the form of a form in the large area neural network server to form a second historical database, wherein in specific implementation, the JDBC technology can be adopted to realize the operations of warehousing, increasing, deleting, modifying, checking and the like of the second historical database.
Specifically, the building of the second preset neural network model by the large-area neural network server generally includes two steps: the method comprises the steps of firstly, constructing a second initial neural network model, and secondly, training the second initial neural network model to obtain the second preset neural network model. In the first step, the first predicted value of each modeling point is used as an input layer, and then the first predicted value is used as an output layer. In the second step, selecting the historical data of the first predicted value and the real value of the target to be tested in the corresponding large area from the second historical database as the second training sample, and inputting the second training sample into the second initial neural network model to train the second initial neural network model to obtain the second preset neural network model. In a specific implementation, the second predetermined neural network model may be constructed in JAVA.
Furthermore, the second preset neural network models corresponding to a plurality of common targets to be predicted can be pre-stored in the large-area neural network server, and the corresponding second preset neural network models can be directly selected for prediction after the targets to be predicted are determined, so that the system can work more efficiently.
In the above embodiment, the system further includes a first mobile data transmission module and a second mobile data transmission module, the first mobile data transmission module is connected to the modeling point neural network server through a serial port, the second mobile data transmission module is connected to the large area neural network server through a serial port, and the first mobile data transmission module is connected to the second mobile data transmission module through a mobile network.
Specifically, the modeling point neural network server transmits the environment data to the first mobile data transmission module through a serial port, the first data transmission module transmits the environment data to the second mobile data transmission module through wireless communication, and the second data transmission module transmits the environment data to the large area neural network server through a serial port.
In the above embodiment, the system further includes a client configured to obtain a predicted value of the target to be predicted, which is output by the large-area neural network server.
The client comprises a PC and a mobile communication tool, and the mobile communication tool comprises a mobile phone, a tablet computer and the like.
Specifically, the user may access the large area neural network server through the internet by using the PC to obtain the predicted value of the target to be predicted, and meanwhile, the large area neural network server may also be used as a WEB server to store historical data of the predicted value of the target to be predicted, and the user may query the historical data through the PC. And the user uses a mobile communication tool to receive the predicted value of the target to be predicted, which is sent by the second mobile data transmission module, through a mobile network.
The following examples further illustrate the embodiments of the present invention, and assuming that the system is used to predict the disease state of middle rice blast in Taojiang county, Hunan province, the target to be predicted is the disease state of middle rice blast. Firstly, a modeling point selecting unit of the system selects 5 towns in the jurisdiction of the Yangtze county as modeling points through correlation analysis, and environment acquisition units are respectively arranged at the 5 modeling points. And constructing or selecting a hierarchical neural network model corresponding to the rice blast disease condition in the system. And 5 environment acquisition units send the acquired environment data of each modeling point to the neural network server of each modeling point, and the large-area neural network server outputs rice blast disease condition prediction values in Taojiang county through prediction of the hierarchical neural network model. Meanwhile, the user can receive the predicted value of the disease condition of the rice blast in Taojiang county in the form of a short message, and can also inquire the predicted value through a PC.
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 (10)
1. A large-area agricultural prediction system, comprising: a large-area neural network server and a modeling point neural network server corresponding to each modeling point; wherein,
the modeling point neural network server is used for acquiring a first predicted value of a target to be predicted of the modeling point by using a first preset neural network model based on the environment data of the modeling point and sending the first predicted value to the large-area neural network server;
the large-area neural network server is used for obtaining the predicted value of the target to be predicted in the large area by utilizing a second preset neural network model based on the first predicted value.
2. The system according to claim 1, further comprising a modeling point selecting unit configured to select a small region as the modeling point according to a correlation between the large region and a small region included in the large region.
3. The system of claim 1, further comprising an environmental data collection unit for collecting environmental data of each modeling point, wherein the environmental data collection unit comprises a data collection terminal, a routing node and a coordination node; wherein,
the data acquisition terminal is connected with the routing node through a public channel and used for acquiring environment data of a modeling point and transmitting the environment data to the routing node;
the routing node is connected with the coordination node through a common channel and used for transmitting the environment data to the coordination node;
the co-regulation point is connected with the modeling point neural network server and used for transmitting the environment data to the modeling point neural network server.
4. The system of claim 1, wherein the modeling point neural network server is further configured to construct a first initial neural network model, and to train the first initial neural network model through a first training sample to obtain the first preset neural network model.
5. The system of claim 1, wherein the large area neural network server is further configured to construct a second initial neural network model, and train the second initial neural network model through a second training sample to obtain the second preset neural network model.
6. The system of claim 4, wherein the first initial neural network model is a BP neural network model with the environmental data as an input layer and the first predicted value as an output layer.
7. The system of claim 4, wherein the first training sample comprises historical data of the environmental data and actual values of the target to be measured of corresponding modeling points.
8. The system of claim 5, wherein the second initial neural network model is a BP neural network model with the first predicted value as an input layer and the predicted value of the target to be predicted as an output layer.
9. The system of claim 5, wherein the second training sample comprises historical data of the first predicted value and a true value of the target to be measured of a corresponding large area.
10. The system of claim 1, further comprising a client configured to obtain a predicted value of the target to be predicted output by the large-area neural network server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710431866.1A CN107316105B (en) | 2017-06-09 | 2017-06-09 | Large-area agricultural prediction system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710431866.1A CN107316105B (en) | 2017-06-09 | 2017-06-09 | Large-area agricultural prediction system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107316105A true CN107316105A (en) | 2017-11-03 |
| CN107316105B CN107316105B (en) | 2020-12-04 |
Family
ID=60184047
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710431866.1A Expired - Fee Related CN107316105B (en) | 2017-06-09 | 2017-06-09 | Large-area agricultural prediction system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107316105B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114063459A (en) * | 2020-08-10 | 2022-02-18 | 青岛海信电子产业控股股份有限公司 | Terminal and intelligent household control method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103489053A (en) * | 2013-05-13 | 2014-01-01 | 湖南云控科技有限公司 | Intelligent water resource control platform based on cloud computing and expert system |
| CN104219682A (en) * | 2014-08-20 | 2014-12-17 | 北京农业信息技术研究中心 | Method and system for constructing network layers of hybrid power supply wireless sensor networks of farmlands |
| CN104732295A (en) * | 2015-03-31 | 2015-06-24 | 国家电网公司 | Power load predicating model based on big data technology |
| JP2016136001A (en) * | 2015-01-23 | 2016-07-28 | 中国電力株式会社 | Prediction device |
| CN105872030A (en) * | 2016-03-25 | 2016-08-17 | 湖南省农业信息与工程研究所 | System and method for detecting and reporting diseases and insect pests |
| CN106408343A (en) * | 2016-09-23 | 2017-02-15 | 广州李子网络科技有限公司 | Modeling method and device for user behavior analysis and prediction based on BP neural network |
-
2017
- 2017-06-09 CN CN201710431866.1A patent/CN107316105B/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103489053A (en) * | 2013-05-13 | 2014-01-01 | 湖南云控科技有限公司 | Intelligent water resource control platform based on cloud computing and expert system |
| CN104219682A (en) * | 2014-08-20 | 2014-12-17 | 北京农业信息技术研究中心 | Method and system for constructing network layers of hybrid power supply wireless sensor networks of farmlands |
| JP2016136001A (en) * | 2015-01-23 | 2016-07-28 | 中国電力株式会社 | Prediction device |
| CN104732295A (en) * | 2015-03-31 | 2015-06-24 | 国家电网公司 | Power load predicating model based on big data technology |
| CN105872030A (en) * | 2016-03-25 | 2016-08-17 | 湖南省农业信息与工程研究所 | System and method for detecting and reporting diseases and insect pests |
| CN106408343A (en) * | 2016-09-23 | 2017-02-15 | 广州李子网络科技有限公司 | Modeling method and device for user behavior analysis and prediction based on BP neural network |
Non-Patent Citations (1)
| Title |
|---|
| 张海艳 等: "基于概率神经网络的农作物虫情预测", 《电子质量》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114063459A (en) * | 2020-08-10 | 2022-02-18 | 青岛海信电子产业控股股份有限公司 | Terminal and intelligent household control method |
| CN114063459B (en) * | 2020-08-10 | 2024-03-15 | 海信集团控股股份有限公司 | Terminal and intelligent home control method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107316105B (en) | 2020-12-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN205301934U (en) | Industrialized agriculture thing networking environment measurement and control device | |
| Biradar et al. | Review on IOT based multidisciplinary models for smart farming | |
| Visconti et al. | IoT-oriented software platform applied to sensors-based farming facility with smartphone farmer app | |
| Coelho et al. | Monitoring of soil moisture and atmospheric sensors with internet of things (IoT) applied in precision agriculture | |
| CN111079977A (en) | Heterogeneous federated learning mine electromagnetic radiation trend tracking method based on SVD algorithm | |
| CN105954493B (en) | A kind of soil collection detecting system | |
| CN105651336A (en) | Pollution source dynamic data monitoring system and method | |
| Pujahari et al. | Intelligent farming system through weather forecast support and crop production | |
| CN111339092A (en) | Deep learning-based multi-scale air quality forecasting method | |
| Arunachalam et al. | RaspberryPi‐Arduino (RPA) powered smart mirrored and reconfigurable IoT facility for plant science research | |
| Sumathi et al. | Retracted: Soil monitoring and evaluation system using EDL‐ASQE: Enhanced deep learning model for IoT smart agriculture network | |
| Patil et al. | IoT based real time soil nutrients detection | |
| WO2023035067A1 (en) | Systems and methods for load forecasting for improved forecast results based on tuned weather data | |
| CN117770106A (en) | Digital twinning-based farmland irrigation method | |
| CN107316105B (en) | Large-area agricultural prediction system | |
| CN118258769A (en) | Crop pest detection method and system based on multi-mode deep learning | |
| Raju et al. | Architecture development with measurement index for agriculture decision-making system using internet of things and machine learning | |
| Kumar et al. | Weather Monitoring and Prediction System based on Machine Learning and IoT | |
| CN117764238A (en) | Crop pest prediction method based on complex graph characterization, electronic equipment and storage medium | |
| CN111062633A (en) | Power transmission and transformation line and equipment state evaluation system based on multi-source heterogeneous data | |
| Afiatna et al. | The Monitoring System of Soil PH Factor Using IoT-Webserver-Android and Machine Learning: A Case Study. | |
| Hu et al. | [Retracted] Optimization and Simulation of Farmland Protection Dynamic Monitoring System Based on Internet of Things Technology | |
| CN113673846B (en) | Demand situation awareness method under electric power Internet of things architecture | |
| Murthy et al. | Cloud technology on agriculture using sensors | |
| CN202385134U (en) | Agricultural and forest diseases and insect pests intelligent monitoring service system based on PDA |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20201204 |