CN109767038A - Crop yield prediction technique, device and computer readable storage medium - Google Patents
Crop yield prediction technique, device and computer readable storage medium Download PDFInfo
- Publication number
- CN109767038A CN109767038A CN201910008175.XA CN201910008175A CN109767038A CN 109767038 A CN109767038 A CN 109767038A CN 201910008175 A CN201910008175 A CN 201910008175A CN 109767038 A CN109767038 A CN 109767038A
- Authority
- CN
- China
- Prior art keywords
- crop
- data
- production
- objective
- forecast
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to intelligent decisions, disclose a kind of crop yield prediction technique, this method comprises: obtaining crop sample data, the crop sample data include indicating the plantation characteristic and crops actual production value of crops;According to the crop sample data, training obtains Production Forecast Models;Obtain objective crop data;According to the Production Forecast Models, the objective crop data are predicted, determine the corresponding forecast production of the objective crop data.The present invention also proposes a kind of crop yield prediction meanss and a kind of computer readable storage medium.The present invention is based on historical data realizations precisely to be predicted the crop yield in areal difference soil, and is able to achieve quick compensation.
Description
Technical field
The present invention relates to field of computer technology more particularly to a kind of crop yield prediction techniques, device and computer
Readable storage medium storing program for executing.
Background technique
Crop yield insurance is to be lost using the crop yield of peasant as insurance subject, low with crops actual production
In a kind of insurance that contract engagement yield is insurance risk, traditional crop insurance price is generally based on history per unit area yield data
Data expansion method and Method of Stochastic based on known distribution function, both methods be all based on over whole number
It is predicted, the yield in the different soils in a geographic coverage can only all be provided so same according to the method with statistics
Prediction, above method can be practical in certain fields.But when the crop yield being applied under different geological conditions is pre-
In survey, effect all can be barely satisfactory.Due to areal, there is geological conditions, weather conditions, precipitation condition, illumination condition,
The differences such as nitrogenous fertilizer condition, therefore its crop yield is caused also to differ widely, the mode of traditional whole quantitative prediction is difficult to full
Accurate prediction of the foot to crop yield, and then cause crop yield insurance relatively large deviation occur, therefore rate is for high-quality
Soil can not obtain the yield in one piece of ground current year and specifically accurately predict as with soil inferior being.
Summary of the invention
The present invention provides a kind of crop yield prediction technique, device and computer readable storage medium, main purpose
It is to realize in the case where not recording additional corpus, improves training samples number.
To achieve the above object, the present invention also provides a kind of crop yield prediction techniques, which comprises
Crop sample data are obtained, the crop sample data include indicating the plantation characteristic and agriculture of crops
Crop actual production value;
According to the crop sample data, training obtains Production Forecast Models;
Obtain objective crop data;
According to the Production Forecast Models, the objective crop data are predicted, determine the objective crop
The corresponding forecast production of data.
Optionally, the plantation characteristic of the crops comprises at least one of the following or a variety of combinations: crops
Cultivated area, planting density in planting process, average irrigation volume, average evaporation capacity, are put down at the average precipitation in planting environment
Equal accumulated temperature, average daily light application time, average applying quantity of chemical fertilizer.
Optionally, according to the crop sample data, before training obtains Production Forecast Models, the method is also wrapped
It includes:
The crop sample data are normalized;
The crop sample data after normalization are handled using Principal Component Analysis, the farming after normalizing
Object sample data is reduced to low dimensional data from high dimensional data.
Optionally, the Production Forecast Models include BP neural network structure, and the BP neural network structure includes: input
Layer, hidden layer and output layer;
Input layer: different types of data input in the plantation characteristic for defining crops;
Hidden layer: for carrying out non-linearization using plantation characteristic of the excitation function to the crops that input layer inputs
Processing;
Output layer: for exporting forecast production value corresponding with data on crop yield after hidden layer.
Optionally, described according to the crop sample data, training obtains Production Forecast Models and includes:
Input crop sample data;
The loss function of Production Forecast Models is constructed, the loss function is for indicating that data on crop yield is corresponding pre-
Survey difference between yield values actual production value corresponding with data on crop yield;
The loss function is iterated to calculate, until the corresponding forecast production value of data on crop yield and crop yield number
It is less than preset value according to difference between corresponding actual production value.
Optionally, the method also includes:
Judge whether the corresponding forecast production of the objective crop data meets crop insurance and compensate condition;
If the corresponding forecast production of the objective crop data, which meets crop insurance, compensates condition;To the target agriculture
The terminal of the supplier of crop data, which is sent, compensates notice.
Optionally, described to judge whether the corresponding forecast production of the objective crop data meets crop insurance compensation
Condition includes:
Judge whether the corresponding forecast production of the objective crop data is less than preset value;
If the corresponding forecast production of the objective crop data is less than preset value;Determine the objective crop data pair
The forecast production answered meets crop insurance and compensates condition.
To achieve the above object, a kind of crop yield prediction meanss, described device include memory and processor, described
The crop yield Prediction program that can be run on the processor, the crop yield Prediction program are stored on memory
Following steps are realized when being executed by the processor:
Crop sample data are obtained, the sample data includes indicating that the plantation characteristic of crops and crops are real
Border yield values;
According to the crop sample data, training obtains Production Forecast Models;
Obtain objective crop data;
According to the Production Forecast Models, the objective crop data are predicted, determine the objective crop
The corresponding forecast production of data.
Optionally, following steps are also realized when the crop yield Prediction program is executed by the processor:
Judge whether the corresponding forecast production of the objective crop data meets crop insurance and compensate condition;
If the corresponding forecast production of the objective crop data, which meets crop insurance, compensates condition;To the target agriculture
The terminal of the supplier of crop data, which is sent, compensates notice.
In addition, to achieve the above object, it is described computer-readable the present invention also provides a kind of computer readable storage medium
Crop yield Prediction program is stored on storage medium, the crop yield Prediction program can be handled by one or more
Device executes, the step of to realize crop yield prediction technique as described above.
The present invention obtains crop sample data, and the crop sample data include indicating the plantation characteristic of crops
According to and crops actual production value;According to the crop sample data, training obtains Production Forecast Models;Obtain target farming
Object data;According to the Production Forecast Models, the objective crop data are predicted, determine the objective crop number
According to corresponding forecast production.The present invention also proposes a kind of crop yield prediction meanss and a kind of computer-readable storage medium
Matter.The present invention is based on historical data realizations precisely to be predicted the crop yield in areal difference soil, and can be real
Now quickly compensate.
Detailed description of the invention
Fig. 1 is the flow diagram for the crop yield prediction technique that one embodiment of the invention provides;
Fig. 2 is the flow diagram for the crop yield prediction technique that one embodiment of the invention provides;
Fig. 3 is the schematic diagram of internal structure for the crop yield prediction meanss that one embodiment of the invention provides;
Fig. 4 is the module for crop yield prediction meanss middle peasant's crop production forecast program that one embodiment of the invention provides
Schematic diagram.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
The present invention provides a kind of crop yield prediction technique.It is the agriculture that one embodiment of the invention provides shown in referring to Fig.1
The flow diagram of crop production forecast method.This method can be executed by device, which can be by software and/or hard
Part is realized.
In the present embodiment, crop yield prediction technique includes:
S10, crop sample data are obtained, the crop sample data include indicating the plantation characteristic of crops
And crops actual production value.
In the present embodiment, crop sample data need the factor that can effectively indicate to influence crop yield.Institute
The plantation characteristic for stating crops comprises at least one of the following or a variety of combinations: the growing surface during crop planting
Product, planting density, the average precipitation in planting environment, average irrigation volume, average evaporation capacity, average accumulated temperature, average every daylight
According to time, average applying quantity of chemical fertilizer.The applying quantity of chemical fertilizer that is wherein averaged includes amount of application of nitrogen fertilizer, K Amounts etc..Due to ground
Area is different, and environmental factor is different, even if area is identical, soil also can be different, therefore measures farming using above-mentioned many factors
The plantation characteristic of object.
In one embodiment, the method also includes: the crop sample data are normalized;
The crop sample data after normalization are handled using Principal Component Analysis, the farming after normalizing
Object sample data is reduced to low dimensional data from high dimensional data.
Specifically, the crop sample data are normalized is to be allowed to fall by data bi-directional scaling
One small specific sections.Since each characteristic measure unit in plantation characteristic is different, in order to plant
Index in characteristic participates in evaluation and calculates, and needs to carry out standardization processing to index, is reflected its numerical value by functional transformation
It is mapped to some numerical intervals.The present invention does not do any restrictions to normalized method.
In characteristic vector pickup and processing, it is involved in the problems, such as that high dimensional feature vector tends to fall into dimension disaster and spy
Levy the strong problem of relevance.With the increase of data set dimension, the sample size that algorithm study needs exponentially increases.Some
In, it is very unfavorable for encountering such big data, and needs more memories and processing from big data focusing study
Ability.In addition, the sparsity of data can be higher and higher with the increase of dimension.Same number is explored in high-dimensional vector space
It is more difficult than being explored in same sparse data set according to collection.Using Principal Component Analysis to the crop sample after normalization
Data are handled, and the crop sample data after normalization are reduced to low dimensional data from high dimensional data, to subtract
Few calculation amount.
S11, according to the crop sample data, training obtains Production Forecast Models.
In an embodiment of the present invention, the Production Forecast Models include BP neural network structure, the BP neural network
Structure includes: input layer, hidden layer and output layer;Input layer: different type in the plantation characteristic for defining crops
Data input;Hidden layer: non-thread for being carried out using plantation characteristic of the excitation function to the crops that input layer inputs
Propertyization processing;Output layer: for exporting forecast production value corresponding with data on crop yield after hidden layer.
BP neural network will not make global training result after its part or partial neuron is destroyed
At very big influence, that is to say, that though what system still can work normally when by local damage.That is BP neural network
With certain fault-tolerant ability.BP neural network can be automatically extracted between output, output data in training by study
" rule of reason ", and it is adaptive learning Content is remembered in the weight of network, i.e., BP neural network has height self study
With adaptive ability.BP neural network has stronger generalization ability, i.e., to consider that network is guaranteeing to required prediction object
Correct production forecast is carried out, also wants concerned about network after training, to unseen mode or there can be the mould of noise pollution
Formula is correctly predicted.
For example, the structure of BP neural network includes that input layer nerve is single as shown in Fig. 2, predicting to corn yield
First number is 8, i.e., the precipitation, irrigation volume, evaporation capacity, accumulated temperature, average daily light application time, planting density, nitrogenous fertilizer are applied
Eight dosage, K Amounts variables, output layer neuron number of nodes are 1, i.e. corn yield, and implying network layer is 1, hidden layer
Number of nodes is 7.
In an embodiment of the present invention, described according to the crop sample data, training obtains Production Forecast Models packet
It includes:
Input crop sample data;
The loss function of Production Forecast Models is constructed, the loss function is for indicating that data on crop yield is corresponding pre-
Survey difference between yield values actual production value corresponding with data on crop yield;
The loss function is iterated to calculate, until the corresponding forecast production value of data on crop yield and crop yield number
It is less than preset value according to difference between corresponding actual production value.
Any restrictions are not wherein done to loss function, such as loss function can damage for logarithm loss function, least square
Lose function.
Specifically, the loss function is iterated to calculate using gradient descent algorithm.Gradient descent algorithm is neural network mould
The most common optimization algorithm of type training.Be substantially using gradient descent algorithm in existing artificial intelligence model carry out it is excellent
Change training.It can make the loss function fast convergence using gradient descent algorithm.
S12, objective crop data are obtained.
In the present embodiment, the objective crop data can be peasant household's upload, such as peasant household utilizes the end of oneself
Related data is filled on a user interface in end (such as mobile phone).Crop yield device from grabbing the objective crop number from the background
According to.
S13, according to the Production Forecast Models, the objective crop data are predicted, determine the target agriculture
The corresponding forecast production of crop data.
In the present embodiment, feature extraction is carried out to objective crop data, and the objective crop data is carried out
Normalized, and dimension-reduction treatment is carried out to objective crop data using Principal Component Analysis.
The objective crop data include the combination of following one or more: the growing surface during crop planting
Product, planting density, the average precipitation in planting environment, average irrigation volume, average evaporation capacity, average accumulated temperature, average every daylight
According to time, average applying quantity of chemical fertilizer.The applying quantity of chemical fertilizer that is wherein averaged includes amount of application of nitrogen fertilizer, K Amounts etc..
In one embodiment, the method also includes:
Judge whether the corresponding forecast production of the objective crop data meets crop insurance and compensate condition;
If the corresponding forecast production of the objective crop data, which meets crop insurance, compensates condition;To the target agriculture
The terminal of the supplier of crop data, which is sent, compensates notice.
One in the specific implementation, described judge whether the corresponding forecast production of the objective crop data meets crops
Insurance benefits condition includes:
Judge whether the corresponding forecast production of the objective crop data is less than preset value;
If the corresponding forecast production of the objective crop data is less than preset value;Determine the objective crop data pair
The forecast production answered meets crop insurance and compensates condition.
One in the specific implementation, the corresponding forecast production of the objective crop data, which meets crop insurance, compensates item
Part then calculates insurance indemnity in the way of practical insured amount/full insurance amount of money * (forecast production-actual production) * unit price
The amount of money.
In the inventive solutions, the present invention obtains crop sample data, and the crop sample data include
Indicate the plantation characteristic and crops actual production value of crops;According to the crop sample data, training is produced
Measure prediction model;Obtain objective crop data;According to the Production Forecast Models, the objective crop data are carried out pre-
It surveys, determines the corresponding forecast production of the objective crop data.The present invention is based on historical datas to realize to areal difference
The crop yield in soil is precisely predicted, and is able to achieve quick compensation.
The present invention also provides a kind of crop yield prediction meanss.Referring to shown in Fig. 3, provided for one embodiment of the invention
The schematic diagram of internal structure of crop yield prediction meanss.
In the present embodiment, crop yield prediction meanss 1 can be PC (Personal Computer, PC),
It is also possible to the terminal devices such as smart phone, tablet computer, portable computer.The crop yield prediction meanss 1 include at least
Memory 11, processor 12, communication bus 13 and network interface 14.
Wherein, memory 11 include at least a type of readable storage medium storing program for executing, the readable storage medium storing program for executing include flash memory,
Hard disk, multimedia card, card-type memory (for example, SD or DX memory etc.), magnetic storage, disk, CD etc..Memory 11
It can be the internal storage unit of crop yield prediction meanss 1, such as crop yield prediction dress in some embodiments
Set 1 hard disk.Memory 11 is also possible to the External memory equipment of crop yield prediction meanss 1 in further embodiments,
Such as the plug-in type hard disk being equipped in crop yield prediction meanss 1, intelligent memory card (Smart Media Card, SMC), peace
Digital (Secure Digital, SD) card, flash card (Flash Card) etc..Further, memory 11 can also be wrapped both
The internal storage unit for including crop yield prediction meanss 1 also includes External memory equipment.Memory 11 can be not only used for depositing
Storage is installed on the application software and Various types of data of crop yield prediction meanss 1, such as the generation of crop yield Prediction program 01
Code etc., can be also used for temporarily storing the data that has exported or will export.
Processor 12 can be in some embodiments a central processing unit (Central Processing Unit,
CPU), controller, microcontroller, microprocessor or other data processing chips, the program for being stored in run memory 11
Code or processing data, such as execute crop yield Prediction program 01 etc..
Communication bus 13 is for realizing the connection communication between these components.
Network interface 14 optionally may include standard wireline interface and wireless interface (such as WI-FI interface), be commonly used in
Communication connection is established between the device 1 and other electronic equipments.
Optionally, which can also include user interface, and user interface may include display (Display), input
Unit such as keyboard (Keyboard), optional user interface can also include standard wireline interface and wireless interface.It is optional
Ground, in some embodiments, display can be light-emitting diode display, liquid crystal display, touch-control liquid crystal display and organic hair
Optical diode (Organic Light-Emitting Diode, OLED) touches device etc..Wherein, display appropriate can also claim
It is visual for being shown in the information handled in crop yield prediction meanss 1 and for showing for display screen or display unit
The user interface of change.
Fig. 3 illustrates only the crop yield prediction meanss with component 11-14 and crop yield Prediction program 01
1, it will be appreciated by persons skilled in the art that structure shown in fig. 1 does not constitute the limit to crop yield prediction meanss 1
It is fixed, it may include perhaps combining certain components or different component layouts than illustrating less perhaps more components.
In 1 embodiment of device shown in Fig. 3, crop yield Prediction program 01 is stored in memory 11;Processor
Following steps are realized when the crop yield Prediction program 01 stored in 12 execution memories 11:
Crop sample data are obtained, the crop sample data include indicating the plantation characteristic and agriculture of crops
Crop actual production value.
In the present embodiment, crop sample data need the factor that can effectively indicate to influence crop yield.Institute
The plantation characteristic for stating crops comprises at least one of the following or a variety of combinations: the growing surface during crop planting
Product, planting density, the average precipitation in planting environment, average irrigation volume, average evaporation capacity, average accumulated temperature, average every daylight
According to time, average applying quantity of chemical fertilizer.The applying quantity of chemical fertilizer that is wherein averaged includes amount of application of nitrogen fertilizer, K Amounts etc..Due to ground
Area is different, and environmental factor is different, even if area is identical, soil also can be different, therefore measures farming using above-mentioned many factors
The plantation characteristic of object.
In one embodiment, the method also includes: the crop sample data are normalized;
The crop sample data after normalization are handled using Principal Component Analysis, the farming after normalizing
Object sample data is reduced to low dimensional data from high dimensional data.
Specifically, the crop sample data are normalized is to be allowed to fall by data bi-directional scaling
One small specific sections.Since each characteristic measure unit in plantation characteristic is different, in order to plant
Index in characteristic participates in evaluation and calculates, and needs to carry out standardization processing to index, is reflected its numerical value by functional transformation
It is mapped to some numerical intervals.The present invention does not do any restrictions to normalized method.
In characteristic vector pickup and processing, it is involved in the problems, such as that high dimensional feature vector tends to fall into dimension disaster and spy
Levy the strong problem of relevance.With the increase of data set dimension, the sample size that algorithm study needs exponentially increases.Some
In, it is very unfavorable for encountering such big data, and needs more memories and processing from big data focusing study
Ability.In addition, the sparsity of data can be higher and higher with the increase of dimension.Same number is explored in high-dimensional vector space
It is more difficult than being explored in same sparse data set according to collection.Using Principal Component Analysis to the crop sample after normalization
Data are handled, and the crop sample data after normalization are reduced to low dimensional data from high dimensional data, to subtract
Few calculation amount.
According to the crop sample data, training obtains Production Forecast Models.
In an embodiment of the present invention, the Production Forecast Models include BP neural network structure, the BP neural network
Structure includes: input layer, hidden layer and output layer;Input layer: different type in the plantation characteristic for defining crops
Data input;Hidden layer: non-thread for being carried out using plantation characteristic of the excitation function to the crops that input layer inputs
Propertyization processing;Output layer: for exporting forecast production value corresponding with data on crop yield after hidden layer.
BP neural network will not make global training result after its part or partial neuron is destroyed
At very big influence, that is to say, that though what system still can work normally when by local damage.That is BP neural network
With certain fault-tolerant ability.BP neural network can be automatically extracted between output, output data in training by study
" rule of reason ", and it is adaptive learning Content is remembered in the weight of network, i.e., BP neural network has height self study
With adaptive ability.BP neural network has stronger generalization ability, i.e., to consider that network is guaranteeing to required prediction object
Correct production forecast is carried out, also wants concerned about network after training, to unseen mode or there can be the mould of noise pollution
Formula is correctly predicted.
For example, the structure of BP neural network includes that input layer nerve is single as shown in Fig. 2, predicting to corn yield
First number is 8, i.e., the precipitation, irrigation volume, evaporation capacity, accumulated temperature, average daily light application time, planting density, nitrogenous fertilizer are applied
Eight dosage, K Amounts variables, output layer neuron number of nodes are 1, i.e. corn yield, and implying network layer is 1, hidden layer
Number of nodes is 7.
In an embodiment of the present invention, described according to the crop sample data, training obtains Production Forecast Models packet
It includes:
Input crop sample data;
The loss function of Production Forecast Models is constructed, the loss function is for indicating that data on crop yield is corresponding pre-
Survey difference between yield values actual production value corresponding with data on crop yield;
The loss function is iterated to calculate, until the corresponding forecast production value of data on crop yield and crop yield number
It is less than preset value according to difference between corresponding actual production value.
Any restrictions are not wherein done to loss function, such as loss function can damage for logarithm loss function, least square
Lose function.
Specifically, the loss function is iterated to calculate using gradient descent algorithm.Gradient descent algorithm is neural network mould
The most common optimization algorithm of type training.Be substantially using gradient descent algorithm in existing artificial intelligence model carry out it is excellent
Change training.It can make the loss function fast convergence using gradient descent algorithm.
Obtain objective crop data.
In the present embodiment, the objective crop data can be peasant household's upload, such as peasant household utilizes the end of oneself
Related data is filled on a user interface in end (such as mobile phone).Crop yield device from grabbing the objective crop number from the background
According to.
According to the Production Forecast Models, the objective crop data are predicted, determine the objective crop
The corresponding forecast production of data.
In the present embodiment, feature extraction is carried out to objective crop data, and the objective crop data is carried out
Normalized, and dimension-reduction treatment is carried out to objective crop data using Principal Component Analysis.
The objective crop data include the combination of following one or more: the growing surface during crop planting
Product, planting density, the average precipitation in planting environment, average irrigation volume, average evaporation capacity, average accumulated temperature, average every daylight
According to time, average applying quantity of chemical fertilizer.The applying quantity of chemical fertilizer that is wherein averaged includes amount of application of nitrogen fertilizer, K Amounts etc..
In one embodiment, the step of processor executes further include:
Judge whether the corresponding forecast production of the objective crop data meets crop insurance and compensate condition;
If the corresponding forecast production of the objective crop data, which meets crop insurance, compensates condition;To the target agriculture
The terminal of the supplier of crop data, which is sent, compensates notice.
One in the specific implementation, described judge whether the corresponding forecast production of the objective crop data meets crops
Insurance benefits condition includes:
Judge whether the corresponding forecast production of the objective crop data is less than preset value;
If the corresponding forecast production of the objective crop data is less than preset value;Determine the objective crop data pair
The forecast production answered meets crop insurance and compensates condition.
One in the specific implementation, the corresponding forecast production of the objective crop data, which meets crop insurance, compensates item
Part then calculates insurance indemnity in the way of practical insured amount/full insurance amount of money * (forecast production-actual production) * unit price
The amount of money.
In the inventive solutions, the present invention obtains crop sample data, and the crop sample data include
Indicate the plantation characteristic and crops actual production value of crops;According to the crop sample data, training is produced
Measure prediction model;Obtain objective crop data;According to the Production Forecast Models, the objective crop data are carried out pre-
It surveys, determines the corresponding forecast production of the objective crop data.The present invention is based on historical datas to realize to areal difference
The crop yield in soil is precisely predicted, and is able to achieve quick compensation.
Optionally, in other embodiments, crop yield Prediction program can also be divided into one or more mould
Block, one or more module are stored in memory 11, and (the present embodiment is processor by one or more processors
12) performed to complete the present invention, the so-called module of the present invention is the series of computation machine program for referring to complete specific function
Instruction segment, for describing implementation procedure of the crop yield Prediction program in crop yield prediction meanss.
For example, referring to shown in Fig. 4, predicted for the crop yield in one embodiment of crop yield prediction meanss of the present invention
The program module schematic diagram of program, in the embodiment, crop yield Prediction program can be divided into plate obtain module 10,
Training module 30 and determining module 30, illustratively:
Module 10 is obtained, for obtaining crop sample data, the crop sample data include indicating crops
Plant characteristic and crops actual production value.
Training module 20, for according to the crop sample data, training to obtain Production Forecast Models.
The acquisition module 10 is also used to obtain objective crop data.
Determining module 30 is used to predict the objective crop data according to the Production Forecast Models, determine
The corresponding forecast production of the objective crop data.
The program modules such as above-mentioned acquisition module 10, training module 20 and determining module 30 be performed realized function or
Operating procedure is substantially the same with above-described embodiment, and details are not described herein.
In addition, the embodiment of the present invention also proposes a kind of computer readable storage medium, the computer readable storage medium
On be stored with crop yield Prediction program, the crop yield Prediction program can be executed by one or more processors, with
Realize following operation:
Crop sample data are obtained, the crop sample data include indicating the plantation characteristic and agriculture of crops
Crop actual production value;
According to the crop sample data, training obtains Production Forecast Models;
Obtain objective crop data;
According to the Production Forecast Models, the objective crop data are predicted, determine the objective crop
The corresponding forecast production of data.
Computer readable storage medium specific embodiment of the present invention and above-mentioned crop yield prediction meanss and method are each
Embodiment is essentially identical, does not make tired state herein.
It should be noted that the serial number of the above embodiments of the invention is only for description, do not represent the advantages or disadvantages of the embodiments.And
The terms "include", "comprise" herein or any other variant thereof is intended to cover non-exclusive inclusion, so that packet
Process, device, article or the method for including a series of elements not only include those elements, but also including being not explicitly listed
Other element, or further include for this process, device, article or the intrinsic element of method.Do not limiting more
In the case where, the element that is limited by sentence "including a ...", it is not excluded that including process, device, the article of the element
Or there is also other identical elements in method.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in one as described above
In storage medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that terminal device (it can be mobile phone,
Computer, server or network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of crop yield prediction technique, which is characterized in that the described method includes:
Crop sample data are obtained, the crop sample data include indicating plantation characteristic and the crops of crops
Actual production value;
According to the crop sample data, training obtains Production Forecast Models;
Obtain objective crop data;
According to the Production Forecast Models, the objective crop data are predicted, determine the objective crop data
Corresponding forecast production.
2. crop yield prediction technique as described in claim 1, which is characterized in that the plantation characteristic of the crops
It comprises at least one of the following or a variety of combinations: in the cultivated area, planting density, planting environment during crop planting
Average precipitation, average irrigation volume, average evaporation capacity, average accumulated temperature, average daily light application time, average applying quantity of chemical fertilizer.
3. crop yield prediction technique as described in claim 1, which is characterized in that according to the crop sample number
According to, before training obtains Production Forecast Models, the method also includes:
The crop sample data are normalized;
The crop sample data after normalization are handled using Principal Component Analysis, the crops sample after normalizing
Notebook data is reduced to low dimensional data from high dimensional data.
4. crop yield prediction technique as described in claim 1, which is characterized in that the Production Forecast Models include BP mind
Through network structure, the BP neural network structure includes: input layer, hidden layer and output layer;
Input layer: different types of data input in the plantation characteristic for defining crops;
Hidden layer: for being carried out at non-linearization using plantation characteristic of the excitation function to the crops that input layer inputs
Reason;
Output layer: for exporting forecast production value corresponding with data on crop yield after hidden layer.
5. crop yield prediction technique as described in claim 1, which is characterized in that described according to the crop sample number
According to training obtains Production Forecast Models and includes:
Input crop sample data;
The loss function of Production Forecast Models is constructed, the loss function is for indicating that the corresponding prediction of data on crop yield produces
Difference between magnitude actual production value corresponding with data on crop yield;
The loss function is iterated to calculate, until the corresponding forecast production value of data on crop yield and data on crop yield pair
Difference is less than preset value between the actual production value answered.
6. such as crop yield prediction technique described in any one of claim 1 to 5, which is characterized in that the method also includes:
Judge whether the corresponding forecast production of the objective crop data meets crop insurance and compensate condition;
If the corresponding forecast production of the objective crop data, which meets crop insurance, compensates condition;To the objective crop
The terminal of the supplier of data, which is sent, compensates notice.
7. crop yield prediction technique as claimed in claim 6, which is characterized in that the judgement objective crop number
Include: according to whether corresponding forecast production meets crop insurance compensation condition
Judge whether the corresponding forecast production of the objective crop data is less than preset value;
If the corresponding forecast production of the objective crop data is less than preset value;Determine that the objective crop data are corresponding
Forecast production meets crop insurance and compensates condition.
8. a kind of crop yield prediction meanss, which is characterized in that described device includes memory and processor, the memory
On be stored with the crop yield Prediction program that can be run on the processor, the crop yield Prediction program is described
Processor realizes following steps when executing:
Crop sample data are obtained, the sample data includes indicating the plantation characteristic of crops and the practical production of crops
Magnitude;
According to the crop sample data, training obtains Production Forecast Models;
Obtain objective crop data;
According to the Production Forecast Models, the objective crop data are predicted, determine the objective crop data
Corresponding forecast production.
9. crop yield prediction meanss as claimed in claim 8, which is characterized in that the pre- ranging of crop yield
Sequence also realizes following steps when being executed by the processor:
Judge whether the corresponding forecast production of the objective crop data meets crop insurance and compensate condition;
If the corresponding forecast production of the objective crop data, which meets crop insurance, compensates condition;To the objective crop
The terminal of the supplier of data, which is sent, compensates notice.
10. a kind of computer readable storage medium, which is characterized in that be stored with crops on the computer readable storage medium
Production forecast program, the crop yield Prediction program can be executed by one or more processor, to realize as right is wanted
Crop yield prediction technique described in asking any one of 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910008175.XA CN109767038A (en) | 2019-01-04 | 2019-01-04 | Crop yield prediction technique, device and computer readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910008175.XA CN109767038A (en) | 2019-01-04 | 2019-01-04 | Crop yield prediction technique, device and computer readable storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109767038A true CN109767038A (en) | 2019-05-17 |
Family
ID=66452589
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910008175.XA Pending CN109767038A (en) | 2019-01-04 | 2019-01-04 | Crop yield prediction technique, device and computer readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109767038A (en) |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108229739A (en) * | 2017-12-29 | 2018-06-29 | 深圳春沐源控股有限公司 | Crop yield prediction method, terminal and computer readable storage medium |
CN110332957A (en) * | 2019-07-12 | 2019-10-15 | 仲恺农业工程学院 | A kind of arviculture information processing system and method |
CN110428114A (en) * | 2019-08-12 | 2019-11-08 | 深圳前海微众银行股份有限公司 | Output of the fruit tree prediction technique, device, equipment and computer readable storage medium |
CN110443420A (en) * | 2019-08-05 | 2019-11-12 | 山东农业大学 | A kind of crop production forecast method based on machine learning |
CN110516858A (en) * | 2019-08-13 | 2019-11-29 | 兰州大学 | A method of prediction clover yield and quality |
CN110689191A (en) * | 2019-09-24 | 2020-01-14 | 深圳前海微众银行股份有限公司 | Agricultural insurance compensation amount prediction method, device, equipment and readable storage medium |
CN111260241A (en) * | 2020-01-23 | 2020-06-09 | 北京师范大学 | Design method of index type agricultural insurance product and product thereof |
CN111461435A (en) * | 2020-04-01 | 2020-07-28 | 中国农业科学院农业信息研究所 | Crop yield prediction method and system |
CN111985724A (en) * | 2020-08-28 | 2020-11-24 | 深圳前海微众银行股份有限公司 | Crop yield estimation method, device, equipment and storage medium |
CN112308284A (en) * | 2019-08-02 | 2021-02-02 | 丰田自动车株式会社 | Crop characteristic prediction system and method, and computer readable storage medium |
CN112734585A (en) * | 2021-01-25 | 2021-04-30 | 联仁健康医疗大数据科技股份有限公司 | Method, device, equipment and storage medium for predicting medical insurance fund expenditure |
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 |
CN113378793A (en) * | 2021-07-09 | 2021-09-10 | 北京京东乾石科技有限公司 | Crop yield prediction method and device |
CN113743762A (en) * | 2021-08-26 | 2021-12-03 | 中国科学院地理科学与资源研究所 | Grassland grass yield inversion method and system based on neural network model |
CN114331090A (en) * | 2021-12-24 | 2022-04-12 | 江苏业派生物科技有限公司 | Agricultural product market supply and demand data monitoring system and method based on big data |
CN116757338A (en) * | 2023-08-21 | 2023-09-15 | 浙江天演维真网络科技股份有限公司 | Crop yield prediction method, device, electronic equipment and storage medium |
CN117314125A (en) * | 2023-11-28 | 2023-12-29 | 中农国稷科技发展有限公司 | Risk monitoring method, system, equipment and storage medium in agricultural planting |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2010166851A (en) * | 2009-01-22 | 2010-08-05 | Chiharu Hongo | Method and device for predicting crop yield |
CN107909491A (en) * | 2017-11-30 | 2018-04-13 | 河南云保遥感科技有限公司 | A kind of Quantity Insurance Claims Resolution method using space big data |
CN108022023A (en) * | 2017-12-20 | 2018-05-11 | 深圳春沐源控股有限公司 | Plantation production prediction method, device and the storage medium of a kind of crops |
CN108665107A (en) * | 2018-05-15 | 2018-10-16 | 中国农业大学 | Crop yield prediction technique and system |
-
2019
- 2019-01-04 CN CN201910008175.XA patent/CN109767038A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2010166851A (en) * | 2009-01-22 | 2010-08-05 | Chiharu Hongo | Method and device for predicting crop yield |
CN107909491A (en) * | 2017-11-30 | 2018-04-13 | 河南云保遥感科技有限公司 | A kind of Quantity Insurance Claims Resolution method using space big data |
CN108022023A (en) * | 2017-12-20 | 2018-05-11 | 深圳春沐源控股有限公司 | Plantation production prediction method, device and the storage medium of a kind of crops |
CN108665107A (en) * | 2018-05-15 | 2018-10-16 | 中国农业大学 | Crop yield prediction technique and system |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108229739A (en) * | 2017-12-29 | 2018-06-29 | 深圳春沐源控股有限公司 | Crop yield prediction method, terminal and computer readable storage medium |
CN110332957A (en) * | 2019-07-12 | 2019-10-15 | 仲恺农业工程学院 | A kind of arviculture information processing system and method |
CN112308284A (en) * | 2019-08-02 | 2021-02-02 | 丰田自动车株式会社 | Crop characteristic prediction system and method, and computer readable storage medium |
CN110443420A (en) * | 2019-08-05 | 2019-11-12 | 山东农业大学 | A kind of crop production forecast method based on machine learning |
CN110428114A (en) * | 2019-08-12 | 2019-11-08 | 深圳前海微众银行股份有限公司 | Output of the fruit tree prediction technique, device, equipment and computer readable storage medium |
CN110516858A (en) * | 2019-08-13 | 2019-11-29 | 兰州大学 | A method of prediction clover yield and quality |
CN110689191A (en) * | 2019-09-24 | 2020-01-14 | 深圳前海微众银行股份有限公司 | Agricultural insurance compensation amount prediction method, device, equipment and readable storage medium |
CN111260241A (en) * | 2020-01-23 | 2020-06-09 | 北京师范大学 | Design method of index type agricultural insurance product and product thereof |
CN111461435A (en) * | 2020-04-01 | 2020-07-28 | 中国农业科学院农业信息研究所 | Crop yield prediction method and system |
CN111985724A (en) * | 2020-08-28 | 2020-11-24 | 深圳前海微众银行股份有限公司 | Crop yield estimation method, device, equipment and storage medium |
CN111985724B (en) * | 2020-08-28 | 2023-07-25 | 深圳前海微众银行股份有限公司 | Crop yield estimation method, device, equipment and storage medium |
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 |
CN112734585A (en) * | 2021-01-25 | 2021-04-30 | 联仁健康医疗大数据科技股份有限公司 | Method, device, equipment and storage medium for predicting medical insurance fund expenditure |
CN113378793A (en) * | 2021-07-09 | 2021-09-10 | 北京京东乾石科技有限公司 | Crop yield prediction method and device |
CN113743762A (en) * | 2021-08-26 | 2021-12-03 | 中国科学院地理科学与资源研究所 | Grassland grass yield inversion method and system based on neural network model |
CN114331090A (en) * | 2021-12-24 | 2022-04-12 | 江苏业派生物科技有限公司 | Agricultural product market supply and demand data monitoring system and method based on big data |
CN116757338A (en) * | 2023-08-21 | 2023-09-15 | 浙江天演维真网络科技股份有限公司 | Crop yield prediction method, device, electronic equipment and storage medium |
CN116757338B (en) * | 2023-08-21 | 2024-01-19 | 浙江天演维真网络科技股份有限公司 | Crop yield prediction method, device, electronic equipment and storage medium |
CN117314125A (en) * | 2023-11-28 | 2023-12-29 | 中农国稷科技发展有限公司 | Risk monitoring method, system, equipment and storage medium in agricultural planting |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109767038A (en) | Crop yield prediction technique, device and computer readable storage medium | |
Jiang et al. | A deep learning approach to conflating heterogeneous geospatial data for corn yield estimation: A case study of the US Corn Belt at the county level | |
Kamilaris et al. | A review on the practice of big data analysis in agriculture | |
Ge et al. | Prediction of corn price fluctuation based on multiple linear regression analysis model under big data | |
Polglase et al. | Potential for forest carbon plantings to offset greenhouse emissions in Australia: economics and constraints to implementation | |
TWI769763B (en) | Data processing method and device | |
Fisher et al. | Understanding technology adoption through system dynamics modeling: implications for agribusiness management | |
CN109377265A (en) | Site selecting method, device, equipment and storage medium | |
McNunn et al. | Using a crop modeling framework for precision cost-benefit analysis of variable seeding and nitrogen application rates | |
KR102547491B1 (en) | System for providing artificial intelligence based price decision service for business-to-business market | |
Zhou et al. | Comprehensive evaluation of land reclamation and utilisation schemes based on a modified VIKOR method for surface mines | |
Bhatnagar et al. | Crop yield estimation using decision trees and random forest machine learning algorithms on data from terra (EOS AM-1) & Aqua (EOS PM-1) satellite data | |
Kumar et al. | Multiparameter optimization system with DCNN in precision agriculture for advanced irrigation planning and scheduling based on soil moisture estimation | |
Mehra et al. | Spatial analysis of soil resources in the Mewat district in the semiarid regions of Haryana, India | |
CN108376301A (en) | Shares changing tendency prediction meanss, method and readable storage medium storing program for executing | |
Abera et al. | A data-mining approach for developing site-specific fertilizer response functions across the wheat-growing environments in Ethiopia | |
Kaninde et al. | Stock price prediction using facebook prophet | |
Jie | RETRACTED ARTICLE: Precision and intelligent agricultural decision support system based on big data analysis | |
Ang et al. | A novel ensemble machine learning and time series approach for oil palm yield prediction using Landsat time series imagery based on NDVI | |
Togneri et al. | Data-driven water need estimation for IoT-based smart irrigation: A survey | |
Keane et al. | Comparing deep neural network and econometric approaches to predicting the impact of climate change on agricultural yield | |
Anwar et al. | Quality and potential utility of ENSO-based forecasts of spring rainfall and wheat yield in south-eastern Australia | |
Sundaram et al. | Disaster relief compensation computational framework | |
Montesino-San Martín et al. | Can crop-climate models be accurate and precise? A case study for wheat production in Denmark | |
Chouhan et al. | An improved feature selection and classification using decision tree for crop datasets |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190517 |
|
RJ01 | Rejection of invention patent application after publication |