CN107609078A - Growing state survey model update method, sensor, server and system - Google Patents
Growing state survey model update method, sensor, server and system Download PDFInfo
- Publication number
- CN107609078A CN107609078A CN201710786197.XA CN201710786197A CN107609078A CN 107609078 A CN107609078 A CN 107609078A CN 201710786197 A CN201710786197 A CN 201710786197A CN 107609078 A CN107609078 A CN 107609078A
- Authority
- CN
- China
- Prior art keywords
- data
- crop
- growing way
- spectroscopic data
- growing
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The embodiment of the present invention provides a kind of Growing state survey model update method, sensor, server and system, and methods described includes：Gather the spectroscopic data of crop；Obtain the growing way parametric data of crop；Spectroscopic data and growing way parametric data are sent to server, so that server is according to spectroscopic data, crop growing state parametric data and crop-planting distribution map, extract effective spectroscopic data in Different Crop type distributed area and effective growing way parametric data, and effective spectroscopic data and effective growing way parametric data are input to neuroid and carry out machine learning, obtain the mapping relations between crop spectroscopic data and growing way parametric data；The mapping relations that the reception server is sent.Growing state survey model update method, sensor, server and system provided in an embodiment of the present invention can realize the dynamic renewal of model in the shared and sensors of multiple sensors observation data, improve the universality and precision of model.
Description
Technical field
The present embodiments relate to field of computer technology, more particularly to a kind of Growing state survey model update method, sensing
Device, server and system.
Background technology
Because China home farm is fast-developing, by the end of the year 2012, national 30 province, district and city's (being free of Tibet)
The shared home farm 87.7 ten thousand for meeting this survey condition, manages cultivated area and reaches 1.76 hundred million mu, account for the whole nation and hold
The 13.4% of bag cultivated area.The large-scale planting management mode that home farm is brought, wherein there is an urgent need to plant growth
Monitoring and management fine Cheng Jinhang, fertilizer and pesticide input is reduced, improves yield and quality.
Crop growing state refers to the upgrowth situation and trend of crop, and the growing way of crop can utilize individual related to population characteristic
Parameter describe.The existing parameter for characterizing crop growing state mainly includes：Leaf area index, chlorophyll content, Nitrogen Accumulation amount,
Biomass and potential production etc..The thinking that existing field crops Growing state survey is mainly taken is surveyed using crop key developmental stages
The spectroscopic data of amount, carry out statistical regression with reference to the crop growing state parameter actually measured and establish empirical model.And existing fixation
Formula or portable crop measurement sensor are all that have cured the related empirical model of these the yield by estimation.Due to crop, kind to be present poor
Different, different Cultivate administration methods and different planting areas, the model for causing this single solidification is difficult with universality.User is again
Model parameter can not be adjusted using local measurement data, cause to utilize production during these sensors progress crop condition monitoring
Raw relatively large deviation, it is difficult to play a role.
As technology of Internet of things is fast-developing, emerged in an endless stream for the various kinds of sensors of crop monitoring, including field is fixed
Formula, vehicle-mounted removable and monitoring sensor based on smart mobile phone etc., these sensors can realize direct measurement crop spectrum
And then crop growing state parameter is estimated, these carry out crop condition monitoring method by unit measurement has easy, direct feature, gram
The deficiency qualitatively judged can only be done by having taken conventional visual observation, tentatively realize the quantification in site measurement of crop growing state parameter,
Rich water optimized planting management is carried out according to the yield by estimation provide support for home farm.
The spectral class sensor of existing estimation crop growing state, the Growing state survey model that sensor embeds in itself is static
, it is impossible to corresponding adjustment is made according to crop varieties change, caused when applied to Different Crop kind or different planting areas
Estimation error is larger, and universality is low, limits the quick-speed large-scale popularization and application of sensors with auxiliary electrode.
The content of the invention
For problems of the prior art, the embodiment of the present invention provides a kind of Growing state survey model update method, passed
Sensor, server and system.
In a first aspect, the embodiment of the present invention provides a kind of Growing state survey model update method, methods described includes：
Gather the spectroscopic data of crop；
Obtain the growing way parametric data of the crop；
The spectroscopic data and the growing way parametric data are sent to server, so that the server is according to the light
Modal data, the crop growing state parametric data and crop-planting distribution map, extract effective in Different Crop type distributed area
Spectroscopic data and effective growing way parametric data, and the effectively spectroscopic data and the effectively growing way parametric data are input to god
Machine learning is carried out through metanetwork, obtains the mapping relations between crop spectroscopic data and growing way parametric data；
Receive the mapping relations that the server is sent.
Second aspect, the embodiment of the present invention provide a kind of Growing state survey model update method, and methods described includes：
Receive the spectroscopic data and growing way parametric data for the crop that Growing state survey sensor is sent；
Obtain crop-planting distribution map；
According to the crop-planting distribution map, the spectroscopic data and the growing way parametric data, Different Crop is extracted
Effective spectroscopic data and effective growing way parametric data in type distributed area；
By the effectively spectroscopic data and the effectively growing way parametric data, it is input to neuroid and carries out engineering
Practise, obtain the mapping relations between crop spectroscopic data and growing way parametric data.
The third aspect, the embodiment of the present invention provide a kind of Growing state survey sensor, and the sensor includes：
Acquisition module, for gathering the spectroscopic data of crop；
First acquisition module, for obtaining the growing way parametric data of the crop；
Sending module, for the spectroscopic data and the growing way parametric data to be sent to server, for the clothes
Device be engaged according to the spectroscopic data, the crop growing state parametric data and crop-planting distribution map, extracts Different Crop type
Effective spectroscopic data and effective growing way parametric data in distributed area, and the effectively spectroscopic data and the effectively growing way are joined
Data are measured, neuroid is input to and carries out machine learning, obtain the mapping between crop spectroscopic data and growing way parametric data
Relation；
First receiving module, the mapping relations sent for receiving the server.
Fourth aspect, the embodiment of the present invention provide a kind of server, and the server includes：
Second receiving module, for receiving the crop spectroscopic data and growing way parametric data of the transmission of Growing state survey sensor；
Second acquisition module, for obtaining crop-planting distribution map；
Valid data extraction module, for being joined according to the crop-planting distribution map, the spectroscopic data and the growing way
Data are measured, extract effective spectroscopic data in Different Crop type distributed area and effective growing way parametric data；
Model modification module, for by the effectively spectroscopic data and the effectively growing way parametric data, being input to nerve
Metanetwork carries out machine learning, obtains the mapping relations between crop spectroscopic data and growing way parametric data.
5th aspect, the embodiment of the present invention provide a kind of Growing state survey model modification system, and the system includes at least one
Individual above-mentioned Growing state survey sensor and above-mentioned server.
6th aspect, the embodiment of the present invention provide a kind of Growing state survey model modification equipment, and the equipment includes memory
And processor, the processor and the memory complete mutual communication by bus；The memory storage has can quilt
The programmed instruction of the computing device, the processor call described program instruction to be able to carry out above-mentioned Growing state survey model more
New method.
7th aspect, the embodiment of the present invention provide a kind of computer-readable recording medium, are stored thereon with computer program,
The computer program realizes above-mentioned Growing state survey model update method when being executed by processor.
Growing state survey model update method, sensor, server and system provided in an embodiment of the present invention, make full use of and work as
The technologies such as preceding mobile interchange, Intelligent internet of things, multiple crop condition monitoring sensors are connected on space-time, fully excavated
Using history observation and measurement data, current newest moment crop condition monitoring mould is obtained based on neuroid learning training
Type, this model Dynamic Updating Mechanism can both realize by using the history gathered data of single Growing state survey sensor,
It can also realize by using the data that multiple Growing state survey sensors in the fixed period gather jointly, increase by this method
The representativeness of modeling sample is added, the model after renewal is had more universality and higher precision.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the required accompanying drawing used in technology description to be briefly described, it should be apparent that, drawings in the following description are this hairs
Some bright embodiments, for those of ordinary skill in the art, on the premise of not paying creative work, can be with root
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is Growing state survey model update method flow chart provided in an embodiment of the present invention；
Fig. 2 is the Growing state survey model update method flow chart that another embodiment of the present invention provides；
Fig. 3 is the structural representation of Growing state survey sensor provided in an embodiment of the present invention；
Fig. 4 is the structural representation of server provided in an embodiment of the present invention；
Fig. 5 is the structural representation of Growing state survey model modification system provided in an embodiment of the present invention；
Fig. 6 is the structural representation of Growing state survey model modification equipment provided in an embodiment of the present invention.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is explicitly described, it is clear that described embodiment be the present invention
Part of the embodiment, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not having
The every other embodiment obtained under the premise of creative work is made, belongs to the scope of protection of the invention.
Fig. 1 is Growing state survey model update method flow chart provided in an embodiment of the present invention, as shown in figure 1, methods described
Including：
Step 10, the spectroscopic data for gathering crop；
Step 11, the growing way parametric data for obtaining the crop；
Step 12, the spectroscopic data and the growing way parametric data sent to server, for the server root
According to the spectroscopic data, the crop growing state parametric data and crop-planting distribution map, extraction Different Crop type distributed area
Interior effective spectroscopic data and effective growing way parametric data, and by the effectively spectroscopic data and the effectively growing way parametric data
It is input to neuroid and carries out machine learning, obtains the mapping relations between crop spectroscopic data and growing way parametric data；
Step 13, receive the mapping relations that the server is sent.
Specifically, Growing state survey sensor can gather the spectroscopic data of crop in real time, wherein, wrapped in the spectroscopic data
Include temporal information and positional information, such as timestamp and latitude and longitude information.Growing state survey sensor can also obtain crop ground
The growing way parametric data of actual measurement, such as the leaf area index of crop, chlorophyll content, Nitrogen Accumulation amount, biomass and potential production
The data such as amount, the growing way parametric data include the temporal information and positional information of measurement.
Then, Growing state survey sensor will be adopted by network communication mode, such as the mode such as WIFI and GPRS signals transmission
The spectroscopic data collected and the growing way parametric data got are sent to server, so that the server is according to institute
State crop spectroscopic data, the growing way parametric data and the crop-planting distribution map got, extraction Different Crop type point
Effective spectroscopic data and effective growing way parametric data in cloth area, then, effectively growing way described in the effectively spectroscopic data is joined
Data input is measured into neuroid, carries out machine learning, the mapping obtained between crop spectroscopic data and growing way parameter is closed
System, the mapping relations are the crop condition monitoring model after updating, and then, the mapping relations are sent to crop growing state
Monitor sensor.
The mapping relations that Growing state survey sensor the reception server sends over, and using the mapping relations and
The crop spectroscopic data collected, obtains the predicted value of crop growing state parametric data.
Crop condition monitoring model update method provided in an embodiment of the present invention, object light will be made by Growing state survey sensor
Modal data growing way parametric data is sent to server, so that the server extremely carries out above-mentioned data input to neuroid
Machine learning, crop condition monitoring model is updated, and the model after renewal is sent to Growing state survey sensor, model
Dynamic Updating Mechanism can both be realized by using the history gathered data of single Growing state survey sensor, can also pass through profit
The data that are gathered jointly with multiple Growing state survey sensors in the fixed period are realized, add modeling sample by this method
Representativeness, the model after renewal is had more universality and higher precision.
Fig. 2 is the Growing state survey model update method flow chart that another embodiment of the present invention provides, as shown in Fig. 2 described
Method includes：
Step 20, the spectroscopic data and growing way parametric data for receiving the crop that Growing state survey sensor is sent；
Step 21, obtain crop-planting distribution map；
Step 22, according to the crop-planting distribution map, the spectroscopic data and the growing way parametric data, extract not
With effective spectroscopic data in agrotype distributed area and effective growing way parametric data；
Step 23, by the effectively spectroscopic data and the effectively growing way parametric data, be input to neuroid progress
Machine learning, obtain the mapping relations between crop spectroscopic data and growing way parametric data.
Specifically, server receives Growing state survey sensor and passed by network communication mode, such as WIFI and GPRS signals
The crop growing state parametric data of the mode such as defeated, the crop spectroscopic data sended over and ground actual measurement, is wrapped in the spectroscopic data
Include temporal information and positional information, such as timestamp and latitude and longitude information, the growing way parametric data, such as the leaf area of crop
In the data such as index, chlorophyll content, Nitrogen Accumulation amount, biomass and potential production, also include temporal information and the position of measurement
Confidence ceases.Server can also obtain crop-planting distribution map from database, and the crop-planting distribution map includes position
Information and corresponding agrotype information.
Because the measurement process of crop growing state parametric data relatively takes time and effort, and crop spectroscopic data is Growing state survey biography
What sensor was got by gathering in real time, so, in same position and same time period, the spectroscopic data amount of crop is generally than reality
The growing way parametric data amount of survey is bigger.By the spectroscopic data and the growing way parametric data be input to neuroid it
It is preceding, it is necessary to first extract effective spectroscopic data and effective growing way parametric data, specifically include：Server obtains work from database
Species plant distribution map, according to plantation distribution map, the spectroscopic data and the growing way parametric data, extract different works
Effective spectroscopic data and effective growing way parametric data in species type distributed area.Then, server is by above-mentioned effective spectroscopic data
It is input to effective growing way parametric data in neuroid, will be described effective using the effectively spectroscopic data as input quantity
Growing way parametric data carries out machine learning as output quantity, after default end condition is met, output crop spectroscopic data and
Mapping relations between growing way parametric data, the crop growing state parameter monitoring model after as updating.
Crop condition monitoring model update method provided in an embodiment of the present invention, by by the spectroscopic data of crop and actual measurement
Growing way parametric data, be input to neuroid carry out machine learning, crop condition monitoring model is updated, model moves
State update mechanism can both realize by using the history gathered data of single Growing state survey sensor, can also be by using
Multiple Growing state survey sensors gather jointly in the fixed period data are realized, add modeling sample by this method
Representativeness, the model after renewal is set to have more universality and higher precision.
Optionally, on the basis of above-described embodiment, it is described according to the crop-planting distribution map, the spectroscopic data and
The growing way parametric data, effective spectroscopic data in Different Crop type distributed area and effective growing way parametric data are extracted,
Including：
According to positional information to the progress of the crop-planting distribution map, the spectroscopic data and the growing way parametric data
Match somebody with somebody, obtain the first spectroscopic data and the first growing way parametric data in Different Crop type distributed area；
According to temporal information and positional information, first spectroscopic data and the first growing way parametric data are matched,
Obtain effective spectroscopic data in Different Crop type distributed area and effective growing way parametric data.
Specifically, the effective spectroscopic data and effective growing way parametric data referred in above-described embodiment is by the following method
Obtain：The crop-planting distribution map that server obtains from database includes positional information and agrotype information, service
The crop spectroscopic data and actual measurement growing way parametric data that device receives include positional information and temporal information, first, according to position
Confidence breath matches to above-mentioned crop-planting distribution map, spectroscopic data and growing way parametric data, can obtain Different Crop class
The first spectroscopic data and the first growing way parametric data in type distributed area.For example the positional information in crop-planting distribution map is
Region A, corresponding agrotype are corn, then the spectroscopic data by positional information in the A of region, as in corn distributed area
First spectroscopic data, by growing way parametric data of the positional information in the A of region, as the first growing way parameter in corn distributed area
Data；Then, according to temporal information and positional information, to first spectroscopic data and the progress of the first growing way parametric data
Match somebody with somebody, obtain effective spectroscopic data in Different Crop type distributed area and effective growing way parametric data, such as, can be by the area
Positional information in the A of domain first spectroscopic data consistent with temporal information and the first growing way parametric data, are distributed as corn
Effective spectroscopic data and effective growing way parametric data in area.
Crop condition monitoring model update method provided in an embodiment of the present invention, by being believed according to positional information and time
Breath, is matched to crop spectroscopic data, growing way parametric data and crop-planting distribution map, extracts the distribution of Different Crop type
Effective spectroscopic data and effective growing way parametric data in area, improve the model accuracy after renewal so that the crop growing state
Monitoring model update method more science, rationally.
Optionally, on the basis of above-described embodiment, methods described also includes：
According to effectively spectroscopic data and the mapping relations, the growing way parametric data predicted；
If the coefficient of determination between the growing way parametric data of the prediction and effective growing way parametric data is more than default threshold
Value, then send the mapping relations to the Growing state survey sensor.
Specifically, the mapping relations that server obtains the above method are sent to before Growing state survey sensor, to described
Mapping relations are verified.Specifically include：Server chooses effective spectroscopic data of predetermined number, is entered into the mapping
In relation, the growing way parametric data predicted.Then, effective growing way parametric data corresponding to the effectively spectroscopic data is calculated
The coefficient of determination between the growing way parametric data of the prediction, if server is known by judgement, the coefficient of determination is more than
Default threshold value, such as 0.8, then it is sent to Growing state survey using the mapping relations as the growing way parameter monitoring model after renewal
Sensor, otherwise, the mapping relations are not sent to the Growing state survey sensor.
Crop condition monitoring model update method provided in an embodiment of the present invention, by testing the mapping relations
Card, if the coefficient of determination between actual measurement growing way parametric data and the prediction growing way parametric data obtained according to the mapping relations is big
In default threshold value, then Growing state survey service is sent to using the mapping relations as the growing way parameter monitoring model after renewal
Device so that the crop condition monitoring model update method, more science, rationally.
Fig. 3 is the structural representation of Growing state survey sensor provided in an embodiment of the present invention, as shown in figure 3, the sensing
Device includes：Acquisition module 30, the first acquisition module 31, the receiving module 33 of sending module 32 and first, wherein：
Acquisition module 30 is used for the spectroscopic data for gathering crop；First acquisition module 31 is used for the growing way for obtaining the crop
Parametric data；First sending module 32 is used to send the spectroscopic data and the growing way parametric data to server, for
The server extracts different works according to the spectroscopic data, the crop growing state parametric data and crop-planting distribution map
Effective spectroscopic data and effective growing way parametric data in species type distributed area, and by it is described effectively spectroscopic data and it is described effectively
Growing way parametric data, it is input to neuroid and carries out machine learning, obtain between crop spectroscopic data and growing way parametric data
Mapping relations；First receiving module 33 is used to receive the mapping relations that the server is sent.
Specifically, acquisition module 30 can gather the spectroscopic data of crop in real time, wherein, when the spectroscopic data includes
Between information and positional information, such as timestamp and latitude and longitude information.First acquisition module 31 can obtain the actual measurement of crop ground
Growing way parametric data, such as the number such as the leaf area index of crop, chlorophyll content, Nitrogen Accumulation amount, biomass and potential production
According to the growing way parametric data includes the temporal information and positional information of measurement.
Then, sending module 32 will gather mould by network communication mode, such as the mode such as WIFI and GPRS signals transmission
The growing way parametric data that the spectroscopic data and the first acquisition module 31 that block 30 collects are got is sent to clothes in time
Business device, so that the server is according to the crop spectroscopic data, the growing way parametric data and the crop-planting got
Distribution map, effective spectroscopic data in Different Crop type distributed area and effective growing way parametric data are extracted, then, is had described
Effectively growing way parametric data described in effect spectroscopic data is input in neuroid, is carried out machine learning, is obtained crop spectrum number
According to the mapping relations between growing way parameter, the mapping relations are the crop condition monitoring model after updating, and first receives
After the mapping relations that the reception server of module 33 sends over.
Growing state survey sensor provided in an embodiment of the present invention, its function is referring in particular to above method embodiment, herein not
Repeat again.
Growing state survey sensor provided in an embodiment of the present invention, crop spectroscopic data is grown by Growing state survey sensor
Gesture parametric data is sent to server, for the server by above-mentioned data input to neuroid to carrying out engineering
Practise, crop condition monitoring model is updated, and the model after renewal is sent to Growing state survey sensor, model dynamic is more
New mechanism can both realize by using the history gathered data of single Growing state survey sensor, can also be by using fixation
Multiple Growing state survey sensors gather jointly in period data are realized, add the representative of modeling sample by this method
Property, the model after renewal is had more universality and higher precision.
Fig. 4 is the structural representation of server provided in an embodiment of the present invention, as shown in figure 4, the server includes：The
Two receiving modules 40, the second acquisition module 41, valid data extraction module 42 and model modification module 43, wherein：
Second receiving module 40 is used for the crop spectroscopic data and growing way parametric data for receiving the transmission of Growing state survey sensor；
Second acquisition module 41 is used to obtain crop-planting distribution map；Valid data extraction module 42 is used for according to the crop-planting point
Butut, the spectroscopic data and the growing way parametric data, extract effective spectroscopic data in Different Crop type distributed area
With effective growing way parametric data；Model modification module 43 is used for the effectively spectroscopic data and the effectively growing way parameter number
According to, be input to neuroid carry out machine learning, obtain the mapping relations between crop spectroscopic data and growing way parametric data.
Specifically, the second receiving module 40 receives Growing state survey sensor by network communication mode, for example, WIFI and
The crop growing state parametric data of the modes such as GPRS signals transmission, the crop spectroscopic data sended over and ground actual measurement, the light
Modal data includes temporal information and positional information, such as timestamp and latitude and longitude information, the growing way parametric data, for example makees
Also corresponding measure is included in the data such as leaf area index, chlorophyll content, Nitrogen Accumulation amount, biomass and the potential production of thing
Temporal information and positional information.Then, the second acquisition module 41 obtains crop-planting distribution map, the Crop Species from database
Planting distribution map includes positional information and corresponding agrotype information.
Because the measurement process of crop growing state parametric data relatively takes time and effort, and crop spectroscopic data is Growing state survey biography
What sensor was got by gathering in real time, so, in same position and same time period, the spectroscopic data amount of crop is generally than reality
The growing way parametric data amount of survey is bigger.Will be defeated by the spectroscopic data and the growing way parametric data in model modification module 43
, it is necessary to first extract effective spectroscopic data and effective growing way parametric data before entering to neuroid, specifically include：Second obtains
Modulus block 41 obtains crop-planting distribution map from database, and valid data extraction module 42 is according to the plantation distribution map, institute
Spectroscopic data and the growing way parametric data are stated, extracts effective spectroscopic data in Different Crop type distributed area and effectively
Growing way parametric data.Then, above-mentioned effectively spectroscopic data and effective growing way parametric data are input to god by model modification module 43
Through in metanetwork, using the effectively spectroscopic data as input quantity, using the effectively growing way parametric data as output quantity, carrying out
Machine learning, after default end condition is met, the mapping relations between crop spectroscopic data and growing way parametric data are exported,
Crop growing state parameter monitoring model after as updating.
Server provided in an embodiment of the present invention, its function is referring in particular to above method embodiment, and here is omitted.
Server provided in an embodiment of the present invention, by by the spectroscopic data of crop and actual measurement growing way parametric data, it is defeated
Enter to neuroid and carry out machine learning, crop condition monitoring model is updated, model Dynamic Updating Mechanism both can be with
Realized by using the history gathered data of single Growing state survey sensor, can also be by using multiple length in the fixed period
The gesture data that gather jointly of monitoring sensor are realized, the representativeness of modeling sample are added by this method, after making renewal
Model have more universality and higher precision.
Optionally, on the basis of above-described embodiment, the valid data extraction module, including：First matching unit and
Second matching unit, wherein：
First matching unit is used for according to positional information to the crop-planting distribution map, the spectroscopic data and the length
Gesture parametric data is matched, and obtains the first spectroscopic data and the first growing way parametric data in Different Crop type distributed area；
Second matching unit is used for according to temporal information and positional information, and first spectroscopic data and the first growing way parametric data are entered
Row matching, obtains effective spectroscopic data in Different Crop type distributed area and effective growing way parametric data.
Specifically, the effective spectroscopic data and effective growing way parametric data referred in above-described embodiment is by the following method
Obtain：The crop-planting distribution map that second acquisition module obtains from database includes positional information and agrotype letter
Breath, the crop spectroscopic data and actual measurement growing way parametric data that the second receiving module receives include positional information and time letter
Breath, first, the first matching unit enters according to positional information to above-mentioned crop-planting distribution map, spectroscopic data and growing way parametric data
Row matching, can obtain the first spectroscopic data and the first growing way parametric data in Different Crop type distributed area.Such as crop
The positional information planted in distribution map is region A, and corresponding agrotype is corn, then the light by positional information in the A of region
Modal data, as the first spectroscopic data in corn distributed area, by growing way parametric data of the positional information in the A of region, as
The first growing way parametric data in corn distributed area；Then, the second matching unit is according to temporal information and positional information, to described
First spectroscopic data and the first growing way parametric data are matched, and obtain effective spectroscopic data in Different Crop type distributed area
With effective growing way parametric data, such as, can be by first spectrum consistent with temporal information of the positional information in the region A
Data and the first growing way parametric data, as effective spectroscopic data in corn distributed area and effective growing way parametric data.
Server provided in an embodiment of the present invention, by according to positional information and temporal information, to crop spectroscopic data, length
Gesture parametric data and crop-planting distribution map are matched, extract effective spectroscopic data in Different Crop type distributed area and
Effective growing way parametric data, improves the model accuracy after renewal so that the server more science, rationally.
Fig. 5 is the structural representation of Growing state survey model modification system provided in an embodiment of the present invention, as shown in figure 5, institute
The system of stating includes：At least one Growing state survey sensor 51 and server 52.
Specifically, each Growing state survey sensor can gather the spectroscopic data of crop in real time, wherein, the spectrum number
According to including temporal information and positional information, such as timestamp and latitude and longitude information.Growing state survey sensor can also obtain ground
Face actual measurement crop growing state parametric data, such as the leaf area index of crop, chlorophyll content, Nitrogen Accumulation amount, biomass and
The data such as potential production, the growing way parametric data include corresponding time of measuring information and positional information.Then, one or
Multiple above-mentioned Growing state survey sensors by network communication mode, such as the mode such as WIFI and GPRS signals transmission, will be adopted respectively
The spectroscopic data collected and the growing way parametric data got are sent to server in time.
The crop spectroscopic data and the crop length of ground actual measurement that the server reception Growing state survey sensor sends over
Gesture parametric data, then, crop-planting distribution map is obtained from database, the crop-planting distribution map includes positional information
With corresponding agrotype information.
Due to the measurement process of crop growing state parametric data, compare and take time and effort, so, in general, the actual measurement of crop
Growing way parametric data amount is less, and crop spectroscopic data is Growing state survey sensor is got by gathering in real time, so, phase
With in position and same time period, the spectroscopic data amount of crop is generally bigger than the growing way parametric data amount of actual measurement.Server exists
The growing way parametric data of the spectroscopic data and the actual measurement is input to before neuroid, it is necessary to first extract effective light
Modal data and effective growing way parametric data.Specifically, server obtains crop-planting distribution map from database, according to the kind
Distribution map, the spectroscopic data and the growing way parametric data are planted, extracts effective light in Different Crop type distributed area
Modal data and effective growing way parametric data.Then, server is by above-mentioned effectively spectroscopic data and effective growing way parametric data, input
It is trained into neuroid.Specifically, using the effectively spectroscopic data as input quantity, by the effectively growing way parameter
Data are trained in neuroid as output quantity, after meeting default end condition, output crop spectroscopic data and
Mapping relations between crop growing state parametric data, the crop growing state parameter monitoring model after as updating, then, server will
The mapping relations are sent to Growing state survey sensor each described.
After the mapping relations that Growing state survey sensor the reception server sends over, using the mapping relations and
The spectroscopic data collected, export the predicted value of crop growing state parameter.
Crop condition monitoring model modification system provided in an embodiment of the present invention, by the way that Growing state survey sensor will be gathered
To spectroscopic data and the ground that gets survey growing way parametric data, be input to neuroid and carry out machine learning, to making
Thing Growing state survey model is updated, and model Dynamic Updating Mechanism both can be by using the history of single Growing state survey sensor
Gathered data is realized, can also be come by using the data that multiple Growing state survey sensors in the fixed period gather jointly real
It is existing, the representativeness of modeling sample is added by this method, the model after renewal is had more universality and higher precision.
Fig. 6 is the structural representation of Growing state survey model modification equipment provided in an embodiment of the present invention, as shown in fig. 6, institute
Stating Growing state survey model modification equipment includes：Processor (processor) 61, memory (memory) 62 and bus 63, wherein：
The processor 61 and the memory 62 complete mutual communication by the bus 63；The processor 61
For calling the programmed instruction in the memory 62, to perform the method that above-mentioned each method embodiment is provided, such as including：
Receive the spectroscopic data and growing way parametric data for the crop that Growing state survey sensor is sent；Obtain crop-planting distribution map；According to
The crop-planting distribution map, the spectroscopic data and the growing way parametric data, are extracted in Different Crop type distributed area
Effective spectroscopic data and effective growing way parametric data；It is defeated by the effectively spectroscopic data and the effectively growing way parametric data
Enter to neuroid and carry out machine learning, obtain the mapping relations between crop spectroscopic data and growing way parametric data.
The embodiment of the present invention discloses a kind of computer program product, and the computer program product is non-transient including being stored in
Computer program on computer-readable recording medium, the computer program include programmed instruction, when described program instructs quilt
When computer performs, computer is able to carry out the method that above-mentioned each method embodiment is provided, such as including：Receive Growing state survey
The spectroscopic data and growing way parametric data for the crop that sensor is sent；Obtain crop-planting distribution map；According to the crop-planting
Distribution map, the spectroscopic data and the growing way parametric data, extract effective spectrum number in Different Crop type distributed area
According to effective growing way parametric data；By the effectively spectroscopic data and the effectively growing way parametric data, neuron net is input to
Network carries out machine learning, obtains the mapping relations between crop spectroscopic data and growing way parametric data.
The embodiment of the present invention provides a kind of non-transient computer readable storage medium storing program for executing, the non-transient computer readable storage
Medium storing computer instructs, and the computer instruction makes the computer perform the side that above-mentioned each method embodiment is provided
Method, such as including：Receive the spectroscopic data and growing way parametric data for the crop that Growing state survey sensor is sent；Obtain crop-planting
Distribution map；According to the crop-planting distribution map, the spectroscopic data and the growing way parametric data, Different Crop class is extracted
Effective spectroscopic data and effective growing way parametric data in type distributed area；By the effectively spectroscopic data and the effectively growing way ginseng
Data are measured, neuroid is input to and carries out machine learning, obtain the mapping between crop spectroscopic data and growing way parametric data
Relation.
One of ordinary skill in the art will appreciate that：Realizing all or part of step of above method embodiment can pass through
Programmed instruction related hardware is completed, and foregoing program can be stored in a computer read/write memory medium, the program
Upon execution, the step of execution includes above method embodiment；And foregoing storage medium includes：ROM, RAM, magnetic disc or light
Disk etc. is various can be with the medium of store program codes.
The embodiments such as Growing state survey model modification equipment described above are only schematical, wherein described be used as is divided
Unit from part description can be or may not be it is physically separate, can be as the part that unit is shown or
It may not be physical location, you can with positioned at a place, or can also be distributed on multiple NEs.Can basis
It is actual to need to select some or all of module therein to realize the purpose of this embodiment scheme.Ordinary skill people
Member is not in the case where paying performing creative labour, you can to understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
Realized by the mode of software plus required general hardware platform, naturally it is also possible to pass through hardware.Based on such understanding, on
The part that technical scheme substantially in other words contributes to prior art is stated to embody in the form of software product, should
Computer software product can store in a computer-readable storage medium, such as ROM/RAM, magnetic disc, CD, including some fingers
Make to cause a computer equipment (can be personal computer, server, or network equipment etc.) to perform each implementation
Method described in some parts of example or embodiment.
Finally it should be noted that：Various embodiments above is rather than right only illustrating the technical scheme of embodiments of the invention
It is limited；Although embodiments of the invention are described in detail with reference to foregoing embodiments, the ordinary skill of this area
Personnel should be understood：It can still modify to the technical scheme described in foregoing embodiments, or to which part
Or all technical characteristic carries out equivalent substitution；And these modifications or replacement, do not make the essence disengaging of appropriate technical solution
The scope of each embodiment technical scheme of embodiments of the invention.
Claims (10)
- A kind of 1. Growing state survey model update method, it is characterised in that including：Gather the spectroscopic data of crop；Obtain the growing way parametric data of the crop；The spectroscopic data and the growing way parametric data are sent to server, so that the server is according to the spectrum number According to, the crop growing state parametric data and crop-planting distribution map, effective spectrum in extraction Different Crop type distributed area Data and effective growing way parametric data, and the effectively spectroscopic data and the effectively growing way parametric data are input to neuron Network carries out machine learning, obtains the mapping relations between crop spectroscopic data and growing way parametric data；Receive the mapping relations that the server is sent.
- A kind of 2. Growing state survey model update method, it is characterised in that including：Receive the spectroscopic data and growing way parametric data for the crop that Growing state survey sensor is sent；Obtain crop-planting distribution map；According to the crop-planting distribution map, the spectroscopic data and the growing way parametric data, Different Crop type is extracted Effective spectroscopic data and effective growing way parametric data in distributed area；By the effectively spectroscopic data and the effectively growing way parametric data, it is input to neuroid and carries out machine learning, obtain Mapping relations between crop spectroscopic data and growing way parametric data.
- 3. according to the method for claim 2, it is characterised in that described according to the crop-planting distribution map, the spectrum Data and the growing way parametric data, extract effective spectroscopic data in Different Crop type distributed area and effective growing way parameter Data, including：The crop-planting distribution map, the spectroscopic data and the growing way parametric data are matched according to positional information, Obtain the first spectroscopic data and the first growing way parametric data in Different Crop type distributed area；According to temporal information and positional information, first spectroscopic data and the first growing way parametric data are matched, obtained Effective spectroscopic data and effective growing way parametric data in Different Crop type distributed area.
- 4. according to the method for claim 3, it is characterised in that methods described also includes：According to effectively spectroscopic data and the mapping relations, the growing way parametric data predicted；If the coefficient of determination between the growing way parametric data of the prediction and effective growing way parametric data is more than default threshold value, The mapping relations are sent to the Growing state survey sensor.
- A kind of 5. Growing state survey sensor, it is characterised in that including：Acquisition module, for gathering the spectroscopic data of crop；First acquisition module, for obtaining the growing way parametric data of the crop；Sending module, for the spectroscopic data and the growing way parametric data to be sent to server, for the server According to the spectroscopic data, the crop growing state parametric data and crop-planting distribution map, the type distribution of extraction Different Crop Effective spectroscopic data and effective growing way parametric data in area, and by the effectively spectroscopic data and the effectively growing way parameter number According to, be input to neuroid carry out machine learning, obtain the mapping relations between crop spectroscopic data and growing way parametric data；First receiving module, the mapping relations sent for receiving the server.
- A kind of 6. server, it is characterised in that including：Second receiving module, for receiving the crop spectroscopic data and growing way parametric data of the transmission of Growing state survey sensor；Second acquisition module, for obtaining crop-planting distribution map；Valid data extraction module, for according to the crop-planting distribution map, the spectroscopic data and the growing way parameter number According to extracting effective spectroscopic data in Different Crop type distributed area and effective growing way parametric data；Model modification module, for by the effectively spectroscopic data and the effectively growing way parametric data, being input to neuron net Network carries out machine learning, obtains the mapping relations between crop spectroscopic data and growing way parametric data.
- 7. server according to claim 6, it is characterised in that the valid data extraction module, including：First matching unit, for according to positional information to the crop-planting distribution map, the spectroscopic data and the growing way Parametric data is matched, and obtains the first spectroscopic data and the first growing way parametric data in Different Crop type distributed area；Second matching unit, for according to temporal information and positional information, to first spectroscopic data and the first growing way parameter Data are matched, and obtain effective spectroscopic data in Different Crop type distributed area and effective growing way parametric data.
- 8. a kind of Growing state survey model modification system, it is characterised in that supervised including at least one growing way as claimed in claim 5 Survey sensor, and server as claimed in claims 6 or 7.
- A kind of 9. Growing state survey model modification equipment, it is characterised in that including memory and processor, the processor and described Memory completes mutual communication by bus；The memory storage have can by the programmed instruction of the computing device, The processor calls described program instruction to be able to carry out the method as described in Claims 1-4 is any.
- 10. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that the computer program quilt The method as described in Claims 1-4 is any is realized during computing device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710786197.XA CN107609078B (en) | 2017-09-04 | 2017-09-04 | Growth monitoring model updating method, sensor, server and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710786197.XA CN107609078B (en) | 2017-09-04 | 2017-09-04 | Growth monitoring model updating method, sensor, server and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107609078A true CN107609078A (en) | 2018-01-19 |
| CN107609078B CN107609078B (en) | 2020-04-10 |
Family
ID=61057313
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710786197.XA Active CN107609078B (en) | 2017-09-04 | 2017-09-04 | Growth monitoring model updating method, sensor, server and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107609078B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109272416A (en) * | 2018-10-13 | 2019-01-25 | 莫彪 | A kind of greenhouse corps implant system |
| CN109508696A (en) * | 2018-12-14 | 2019-03-22 | 红云红河烟草(集团)有限责任公司 | A kind of yield of tobacco prediction analysis method based on multispectral technology |
| CN110024648A (en) * | 2019-04-11 | 2019-07-19 | 哈尔滨工业大学 | The accurate implantation methods of bulbus fritillariae cirrhosae based on deep neural network |
| WO2020159913A1 (en) * | 2019-01-29 | 2020-08-06 | Rensselaer Polytechnic Institute | System for early detection of plant disease |
| CN111585950A (en) * | 2020-03-20 | 2020-08-25 | 中山大学 | Asymmetric encryption based on-site spectrum detection and analysis method, system and medium |
| CN112149836A (en) * | 2019-06-28 | 2020-12-29 | 杭州海康威视数字技术股份有限公司 | Machine learning program updating method, device and equipment |
| CN112149836B (en) * | 2019-06-28 | 2024-05-24 | 杭州海康威视数字技术股份有限公司 | Machine learning program updating method, device and equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102564593A (en) * | 2011-12-30 | 2012-07-11 | 河海大学常州校区 | Plant growth condition monitoring system based on compute vision and internet of things |
| WO2013126023A1 (en) * | 2012-02-21 | 2013-08-29 | Vendeka Bilgi Teknolojileri Ticaret Limited Şirketi | A plant growth system and monitoring method |
| CN103278197A (en) * | 2013-05-31 | 2013-09-04 | 南京农业大学 | Crop growth monitoring device and method based on vehicle-mounted system |
| CN104614321A (en) * | 2015-01-20 | 2015-05-13 | 山东农业大学 | Real-time crop growth condition monitoring method based on spectrum images |
| CN104730005A (en) * | 2015-03-27 | 2015-06-24 | 中国农业科学院农业信息研究所 | Ground-air integrated agricultural monitoring system and method |
| US20160217562A1 (en) * | 2014-06-30 | 2016-07-28 | Trimble Navigation Limited | Active Imaging Systems for Plant Growth Monitoring |
| CN107122855A (en) * | 2017-04-25 | 2017-09-01 | 无锡中科智能农业发展有限责任公司 | A kind of field-crop evapotranspiration forecasting system based on machine learning |
-
2017
- 2017-09-04 CN CN201710786197.XA patent/CN107609078B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102564593A (en) * | 2011-12-30 | 2012-07-11 | 河海大学常州校区 | Plant growth condition monitoring system based on compute vision and internet of things |
| WO2013126023A1 (en) * | 2012-02-21 | 2013-08-29 | Vendeka Bilgi Teknolojileri Ticaret Limited Şirketi | A plant growth system and monitoring method |
| CN103278197A (en) * | 2013-05-31 | 2013-09-04 | 南京农业大学 | Crop growth monitoring device and method based on vehicle-mounted system |
| US20160217562A1 (en) * | 2014-06-30 | 2016-07-28 | Trimble Navigation Limited | Active Imaging Systems for Plant Growth Monitoring |
| CN104614321A (en) * | 2015-01-20 | 2015-05-13 | 山东农业大学 | Real-time crop growth condition monitoring method based on spectrum images |
| CN104730005A (en) * | 2015-03-27 | 2015-06-24 | 中国农业科学院农业信息研究所 | Ground-air integrated agricultural monitoring system and method |
| CN107122855A (en) * | 2017-04-25 | 2017-09-01 | 无锡中科智能农业发展有限责任公司 | A kind of field-crop evapotranspiration forecasting system based on machine learning |
Non-Patent Citations (1)
| Title |
|---|
| 于海达 等: "《草原植被长势遥感监测研究进展》", 《地理科学进展》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109272416A (en) * | 2018-10-13 | 2019-01-25 | 莫彪 | A kind of greenhouse corps implant system |
| CN109272416B (en) * | 2018-10-13 | 2022-06-03 | 临沂确信软件技术有限公司 | Greenhouse crop planting system |
| CN109508696A (en) * | 2018-12-14 | 2019-03-22 | 红云红河烟草(集团)有限责任公司 | A kind of yield of tobacco prediction analysis method based on multispectral technology |
| WO2020159913A1 (en) * | 2019-01-29 | 2020-08-06 | Rensselaer Polytechnic Institute | System for early detection of plant disease |
| CN110024648A (en) * | 2019-04-11 | 2019-07-19 | 哈尔滨工业大学 | The accurate implantation methods of bulbus fritillariae cirrhosae based on deep neural network |
| CN112149836A (en) * | 2019-06-28 | 2020-12-29 | 杭州海康威视数字技术股份有限公司 | Machine learning program updating method, device and equipment |
| CN112149836B (en) * | 2019-06-28 | 2024-05-24 | 杭州海康威视数字技术股份有限公司 | Machine learning program updating method, device and equipment |
| CN111585950A (en) * | 2020-03-20 | 2020-08-25 | 中山大学 | Asymmetric encryption based on-site spectrum detection and analysis method, system and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107609078B (en) | 2020-04-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107609078A (en) | Growing state survey model update method, sensor, server and system | |
| Channe et al. | Multidisciplinary model for smart agriculture using internet-of-things (IoT), sensors, cloud-computing, mobile-computing & big-data analysis | |
| CN107944596A (en) | A kind of muskmelon growth management expert system based on Internet of Things | |
| CN110545531A (en) | Crop growth monitoring method and system based on big data and cloud computing | |
| CN106254476A (en) | Agroecological environment information management based on Internet of Things, big data and cloud computing and monitoring method and system | |
| CN110458032A (en) | Lichee upgrowth situation complete monitoring method, system, Cloud Server and storage medium | |
| EP3358518A1 (en) | Farmwork plan support system | |
| CN103164777A (en) | Investigation method for crop breeding field characters | |
| JP6704148B1 (en) | Crop yield forecast program and crop quality forecast program | |
| KR20210109575A (en) | Information processing devices and information processing systems | |
| JP2021128756A (en) | Futures Trading Information Display Program | |
| CN112215522A (en) | Crop growth monitoring system, method, computer equipment and storage medium | |
| CN106686054A (en) | Service system of using strategy model to solve plantation problem | |
| CN110321774B (en) | Crop disaster situation evaluation method, device, equipment and computer readable storage medium | |
| CN113962476A (en) | Insect pest prediction method, device, equipment and storage medium | |
| CN110414859B (en) | 5T evaluation method for rice storage operation based on Internet of things technology | |
| CN113010529A (en) | Crop management method and device based on knowledge graph | |
| Tan et al. | An integrated cloud-based platform for labor monitoring and data analysis in precision agriculture | |
| CN116186392A (en) | Citrus variety planting recommendation method and device, terminal equipment and storage medium | |
| CN114359725A (en) | Crop growth remote sensing monitoring system and method based on crop model and assimilation technology | |
| Bhatia et al. | IoT Enabled Smart Irrigation Techniques With Leaf Disease Detection | |
| Ionescu et al. | Intelligent monitoring and analysis system of soil moisture parameters and trunk diameter used in fruit tree culture | |
| CN117911957B (en) | Prevention and control monitoring system and method for ornamental sunflower diseases and insect pests | |
| US11574466B2 (en) | Machine learning methods and systems for variety profile index crop characterization | |
| Abdulghani et al. | Cyber-Physical System Based Data Mining and Processing Toward Autonomous Agricultural Systems |
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 |