CN116703638A - Greenhouse vegetable planting management system and method thereof - Google Patents
Greenhouse vegetable planting management system and method thereof Download PDFInfo
- Publication number
- CN116703638A CN116703638A CN202310757692.3A CN202310757692A CN116703638A CN 116703638 A CN116703638 A CN 116703638A CN 202310757692 A CN202310757692 A CN 202310757692A CN 116703638 A CN116703638 A CN 116703638A
- Authority
- CN
- China
- Prior art keywords
- fertilizer
- water
- feature
- classification
- matrix
- 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
- 235000013311 vegetables Nutrition 0.000 title claims abstract description 75
- 238000000034 method Methods 0.000 title claims description 14
- 239000003337 fertilizer Substances 0.000 claims abstract description 176
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 125
- 239000002689 soil Substances 0.000 claims abstract description 78
- 238000007726 management method Methods 0.000 claims abstract description 52
- 239000013598 vector Substances 0.000 claims description 191
- 239000011159 matrix material Substances 0.000 claims description 96
- 238000012545 processing Methods 0.000 claims description 43
- 238000013527 convolutional neural network Methods 0.000 claims description 40
- 238000000605 extraction Methods 0.000 claims description 33
- 230000004913 activation Effects 0.000 claims description 31
- 230000007246 mechanism Effects 0.000 claims description 29
- 238000011176 pooling Methods 0.000 claims description 16
- 238000005457 optimization Methods 0.000 claims description 14
- 230000009467 reduction Effects 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 5
- 230000004927 fusion Effects 0.000 claims description 5
- 238000012546 transfer Methods 0.000 claims description 5
- 238000012549 training Methods 0.000 description 14
- 238000010586 diagram Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 12
- 230000008901 benefit Effects 0.000 description 11
- 238000003860 storage Methods 0.000 description 11
- 230000012010 growth Effects 0.000 description 9
- 230000008635 plant growth Effects 0.000 description 9
- 238000004590 computer program Methods 0.000 description 7
- 238000011161 development Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 150000003839 salts Chemical class 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 2
- 238000007792 addition Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000033228 biological regulation Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000013145 classification model Methods 0.000 description 2
- 238000000354 decomposition reaction Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000011010 flushing procedure Methods 0.000 description 2
- 238000003973 irrigation Methods 0.000 description 2
- 230000002262 irrigation Effects 0.000 description 2
- 230000014759 maintenance of location Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008121 plant development Effects 0.000 description 2
- 230000006798 recombination Effects 0.000 description 2
- 238000005215 recombination Methods 0.000 description 2
- 238000012731 temporal analysis Methods 0.000 description 2
- 238000000700 time series analysis Methods 0.000 description 2
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 description 1
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 description 1
- KWYUFKZDYYNOTN-UHFFFAOYSA-M Potassium hydroxide Chemical compound [OH-].[K+] KWYUFKZDYYNOTN-UHFFFAOYSA-M 0.000 description 1
- 230000003213 activating effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 235000005523 excessive nutrition Nutrition 0.000 description 1
- 230000004720 fertilization Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 235000001705 insufficient nutrition Nutrition 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- 239000000618 nitrogen fertilizer Substances 0.000 description 1
- 235000015097 nutrients Nutrition 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000002686 phosphate fertilizer Substances 0.000 description 1
- 229910052698 phosphorus Inorganic materials 0.000 description 1
- 239000011574 phosphorus Substances 0.000 description 1
- 229940072033 potash Drugs 0.000 description 1
- 239000011591 potassium Substances 0.000 description 1
- 229910052700 potassium Inorganic materials 0.000 description 1
- 235000015320 potassium carbonate Nutrition 0.000 description 1
- BWHMMNNQKKPAPP-UHFFFAOYSA-L potassium carbonate Substances [K+].[K+].[O-]C([O-])=O BWHMMNNQKKPAPP-UHFFFAOYSA-L 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 230000017260 vegetative to reproductive phase transition of meristem Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- 238000004383 yellowing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/047—Probabilistic or stochastic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/10—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture
- Y02A40/25—Greenhouse technology, e.g. cooling systems therefor
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Business, Economics & Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Resources & Organizations (AREA)
- Animal Husbandry (AREA)
- Agronomy & Crop Science (AREA)
- Mining & Mineral Resources (AREA)
- Marine Sciences & Fisheries (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to the field of intelligent management, and particularly discloses a greenhouse vegetable planting management system and a greenhouse vegetable planting management method. Through the mode, the moisture and fertilizer content of greenhouse vegetables can be monitored in real time, the water and fertilizer condition of soil can be adjusted in time, and the planting condition of the greenhouse vegetables is ensured.
Description
Technical Field
The application relates to the field of intelligent management, in particular to a greenhouse vegetable planting management system and a greenhouse vegetable planting management method.
Background
In the greenhouse vegetable planting process, water and fertilizer are key. Fertilizer is the means and water is the soul of the whole management. However, fertilization is not as good as possible, too much will increase production cost and damage to the surrounding environment, too little vegetables will not be nourished, resulting in reduced yield. The watering amount is also suitable, too much can cause the root of the vegetable to rot, and too little can cause the vegetable to grow slowly and even die. Therefore, if the water and fertilizer ratio is not proper, the growth and development of the vegetables can be affected, and the problems of slow growth, low yield, poor quality and the like of the vegetables are caused. The prior art can not accurately control the water and fertilizer proportion of greenhouse vegetable planting.
Therefore, an optimized greenhouse vegetable planting management scheme is desired.
Disclosure of Invention
The present application has been made to solve the above-mentioned technical problems. The embodiment of the application provides a greenhouse vegetable planting management system and a greenhouse vegetable planting management method, wherein an artificial intelligence technology based on a deep neural network model is adopted to acquire humidity values and EC values of soil at a plurality of preset time points in a preset time period, the humidity values and the EC values are arranged into vectors and then are subjected to associated coding, then a characteristic matrix is obtained through a convolutional neural network, and further characteristic enhancement is performed through a spatial attention mechanism module to obtain a classification result for indicating whether the water-fertilizer ratio of a current time point needs to be adjusted. Through the mode, the moisture and fertilizer content of greenhouse vegetables can be monitored in real time, the water and fertilizer condition of soil can be adjusted in time, and the planting condition of the greenhouse vegetables is ensured.
According to one aspect of the present application, there is provided a greenhouse vegetable planting management system comprising: the data acquisition module is used for acquiring the humidity value and the EC value of the soil at a plurality of preset time points in a preset time period; the time sequence arrangement module is used for arranging the humidity value and the EC value of the soil at a plurality of preset time points into a humidity time sequence input vector and an EC time sequence input vector according to the time dimension respectively; the association coding module is used for carrying out association coding on the humidity time sequence input vector and the EC time sequence input vector to obtain a water and fertilizer association matrix; the water and fertilizer characteristic extraction module is used for enabling the water and fertilizer incidence matrix to pass through a convolutional neural network with a block structure to obtain a water and fertilizer characteristic matrix; the attention extraction module is used for enabling the water and fertilizer characteristic matrix to pass through the empty space The inter-attention mechanism module is used for obtaining a classification feature vector; the optimizing module is used for carrying out dimension reduction optimization on the classification characteristic vector so as to obtain an optimized classification characteristic vector; and the classification result module is used for enabling the optimized classification feature vector to pass through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the water-fertilizer ratio of the current time point needs to be adjusted or not. In the greenhouse vegetable planting management system, the association coding module is used for: performing association coding on the humidity time sequence input vector and the EC time sequence input vector by using the following association formula to obtain a water and fertilizer association matrix; wherein, the association formula is:wherein->Representing the humidity timing input vector,/a>Representing said->Time sequence input vector,/->Representing the water and fertilizer incidence matrix, < >>Representing matrix multiplication.
In the greenhouse vegetable planting management system, the water and fertilizer characteristic extraction module is used for: each layer of the convolutional neural network model comprising the block structural feature extraction module respectively carries out input data in forward transfer of the layer: performing convolution processing, pooling processing and nonlinear processing on the input data based on a first two-dimensional convolution kernel to obtain a first activation feature map; performing convolution processing, pooling processing and nonlinear activation processing based on a second two-dimensional convolution kernel on the first activation feature map to obtain a second activation feature map, wherein the first two-dimensional convolution kernel and the second two-dimensional convolution kernel are transposed with each other; the input of the first layer of the convolutional neural network model comprising the block structure feature extraction module is the water and fertilizer correlation matrix, and the output of the last layer of the convolutional neural network model comprising the block structure feature extraction module is the water and fertilizer feature matrix.
In the above greenhouse vegetable planting management system, the attention extraction module includes: the depth convolution coding unit is used for performing depth convolution coding on the water fertilizer feature matrix by using a convolution coding part of the spatial attention mechanism module so as to obtain a detection convolution feature map; a spatial attention unit for inputting the detected convolution feature map into a spatial attention portion of the spatial attention mechanism module to obtain a spatial attention map; an activation unit, configured to activate the spatial attention map through a Softmax activation function to obtain a spatial attention profile; the computing unit is used for computing the position-wise point multiplication of the spatial attention feature map and the detection convolution feature map to obtain a fusion feature map; and the pooling unit is used for pooling the feature matrixes along the channel dimension of the fusion feature graph to obtain the classification feature vector.
In the above greenhouse vegetable planting management system, the optimizing module includes: the probability unit is used for inputting the classification feature vector into a Sigmoid activation function to be activated so as to obtain a probability classification feature vector; the zeroing processing unit is used for zeroing the characteristic values of all the positions in the probabilistic classified characteristic vectors to obtain a plurality of probabilistic mask classified characteristic vectors; a divergence calculating unit, configured to calculate KL divergences between the probabilistic classification feature vector and the respective probabilistic mask classification feature vectors, respectively, to obtain a plurality of KL divergences; and an optimizing unit, configured to determine whether to reject feature values of each position in the probabilistic classified feature vector based on a comparison between the KL divergence and a predetermined threshold value, so as to obtain an optimized classified feature vector.
In the above greenhouse vegetable planting management system, the classification result module includes: the full-connection coding unit is used for carrying out full-connection coding on the optimized classification feature vector by using a full-connection layer of the classifier so as to obtain a coding classification feature vector; and a classification result unit, configured to pass the encoded classification feature vector through a Softmax classification function of the classifier to obtain the classification result.
According to another aspect of the present application, there is provided a greenhouse vegetable planting management method, comprising: acquiring humidity values and EC values of soil at a plurality of preset time points in a preset time period; arranging the humidity values and the EC values of the soil at a plurality of preset time points into humidity time sequence input vectors and EC time sequence input vectors according to the time dimension respectively; performing association coding on the humidity time sequence input vector and the EC time sequence input vector to obtain a water and fertilizer association matrix; the water and fertilizer incidence matrix is passed through a convolutional neural network with a block structure to obtain a water and fertilizer feature matrix; the water and fertilizer feature matrix passes through a spatial attention mechanism module to obtain a classification feature vector; performing dimension reduction optimization on the classification feature vector to obtain an optimized classification feature vector; and the optimized classification feature vector passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the water-fertilizer ratio at the current time point needs to be adjusted.
Compared with the prior art, the greenhouse vegetable planting management system and the greenhouse vegetable planting management method provided by the application adopt an artificial intelligence technology based on a deep neural network model, acquire the humidity value and the EC value of soil at a plurality of preset time points in a preset time period, arrange the humidity value and the EC value into vectors, then perform associated coding, obtain a feature matrix through a convolutional neural network, and further perform feature enhancement through a spatial attention mechanism module so as to obtain a classification result for indicating whether the water and fertilizer proportion at the current time point needs to be adjusted. Through the mode, the moisture and fertilizer content of greenhouse vegetables can be monitored in real time, the water and fertilizer condition of soil can be adjusted in time, and the planting condition of the greenhouse vegetables is ensured.
Drawings
The above and other objects, features and advantages of the present application will become more apparent by describing embodiments of the present application in more detail with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate the application and together with the embodiments of the application, and not constitute a limitation to the application. In the drawings, like reference numerals generally refer to like parts or steps.
Fig. 1 is a block diagram of a greenhouse vegetable planting management system according to an embodiment of the present application.
Fig. 2 is a schematic architecture diagram of a greenhouse vegetable planting management system according to an embodiment of the present application.
Fig. 3 is a block diagram of an attention extraction module in a greenhouse vegetable planting management system according to an embodiment of the present application.
Fig. 4 is a flowchart of a greenhouse vegetable planting management method according to an embodiment of the present application.
Fig. 5 is a block diagram of an electronic device according to an embodiment of the application.
Detailed Description
Hereinafter, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
Summary of the application: as mentioned above, the control of the water-fertilizer ratio is an important link in greenhouse vegetable planting. The improper proportion of water and fertilizer can affect the growth of greenhouse vegetables, which can cause the greenhouse vegetables to absorb excessive nutrition to overgrow or grow slowly due to insufficient nutrition. In the early growth stage, vegetables need a great deal of nitrogen, phosphorus, potassium and other nutrients to promote the growth of root systems and leaves, and more nitrogenous fertilizer and phosphate fertilizer are needed to be provided. And after the vegetables enter the flowering and fruiting period, more potash fertilizer needs to be provided to promote the growth and development of the fruits. Too much watering can cause poor growth of plants, such as yellowing of leaves, dry tips of the leaves, and the like, and too little watering can cause slow growth and even dead vegetables, thereby influencing the yield and quality of the plants. Therefore, an optimized greenhouse vegetable planting management scheme is desired.
Aiming at the technical problems, the applicant of the application obtains the humidity value and the EC value of soil at a plurality of preset time points in a preset time period, arranges the humidity value and the EC value into vectors, then carries out associated coding, obtains a feature matrix through a convolutional neural network after heating, and carries out feature enhancement through a spatial attention mechanism module to obtain a classification result for indicating whether the water and fertilizer ratio at the current time point needs to be adjusted.
Accordingly, in the technical scheme of the application, the humidity and the EC value of the soil are considered to be important indexes for measuring the moisture and the fertilizer content of the soil. Soil moisture values reflect the moisture content of the soil, which is one of the important factors determining plant growth and development. Through monitoring soil humidity value, can in time know the moisture situation in the soil, judge whether need irrigate or adjust irrigation volume to keep suitable soil humidity, promote the normal growth of plant. EC value (conductivity) is an indicator of the amount of dissolved salt in soil, which reflects the amount of fertilizer and the concentration of salt in soil. Too high or too low an EC value of the soil can negatively affect plant growth. By monitoring the EC value of the soil, the supply condition of the fertilizer in the soil can be known, and whether the fertilizer application amount is required to be adjusted or the flushing treatment is required to be carried out is judged, so that proper fertilizer supply and soil salinity concentration are maintained, and the healthy growth of plants is ensured. Therefore, the acquisition of the soil humidity value and the EC value can provide important information about soil moisture and fertilizer content, provide scientific basis for greenhouse vegetable management, help a manager to realize reasonable water and fertilizer regulation and control, and improve the yield and quality of vegetables.
In recent years, deep learning and neural networks have been widely used in the fields of computer vision, natural language processing, text signal processing, and the like. In addition, deep learning and neural networks have also shown levels approaching and even exceeding humans in the fields of image classification, object detection, semantic segmentation, text translation, and the like.
Specifically, in the technical scheme of the application, firstly, the humidity value and the EC value of the soil at a plurality of preset time points in a preset time period are obtained. The purpose of arranging humidity and EC input vectors in the time dimension is to capture the trend of soil humidity and EC values over time. By chronologically arranging the data, the water and fertilizer status of the soil can be analyzed and predicted using the characteristics of the time series. The changes in humidity and EC values over time can provide important information about soil moisture content and fertilizer content. By arranging these data into input vectors in a time dimension, we can learn and capture patterns and trends at different time points using time series analysis methods such as convolutional neural networks and spatial attention mechanisms.
By arranging the input vectors according to the time dimension, a model can be established, the change rule of soil humidity and EC value can be learned from historical data, and the future water and fertilizer conditions can be predicted. Therefore, the soil condition can be monitored in real time, and whether the water and fertilizer proportion needs to be adjusted or not is automatically judged, so that the water and fertilizer utilization efficiency is improved, and the resource waste and the environmental pollution are reduced.
Next, in consideration of correlating the humidity timing input vector and the EC timing input vector, correlation and mutual influence therebetween can be captured. By correlating the codes, we can integrate the information of humidity and EC values to better understand the relationship between them. In particular, in the agricultural field, the moisture and fertilizer content of soil are often interrelated. The variation in moisture can affect the spread and effectiveness of the fertilizer in the soil, and the content of fertilizer can also affect the moisture retention capacity of the soil. Therefore, by performing associated coding on the humidity and the EC value, we can explore the dynamic relationship between the humidity and the EC value, and further know the water and fertilizer conditions of the soil. Through the association coding, the time sequence information of humidity and EC value can be converted into a water and fertilizer association matrix, so that a more comprehensive basis is provided for subsequent analysis and decision.
Further, it is considered that features and patterns in the water-fertilizer correlation matrix can be better captured by the convolutional neural network with a block structure. Block structured convolutional neural networks can extract features on different local regions through convolution operations when processing two-dimensional data, and then integrate these features to form a more global representation. In particular, for a water-fertilizer correlation matrix, it typically has a two-dimensional structure, where the rows represent the time dimension of humidity and the time dimension of EC values. By using the convolutional neural network with the block structure, the characteristics can be extracted on different areas of the water and fertilizer association matrix, and the water and fertilizer association modes of different time points and different time periods can be captured. The advantage of a convolutional neural network of block structure is that it can take into account both local and global information. By performing convolution operations on different blocks, the network can learn features of different scales and integrate them into the final feature matrix. Therefore, the characteristics in the water and fertilizer association matrix can be effectively extracted, so that the water and fertilizer conditions of the soil can be better understood, and corresponding adjustment and decision can be made.
And then, the water and fertilizer feature matrix passes through a spatial attention mechanism module to obtain a classification feature vector. The spatial attention mechanism is considered, so that the model can pay more attention to important spatial positions and characteristic channels when processing the water and fertilizer characteristic matrix, and the classification accuracy is improved. In particular, in a water and fertilizer feature matrix, different spatial locations and feature channels may have different importance. Through the spatial attention mechanism module, the spatial attention of the water and fertilizer feature matrix can be adjusted, so that important features are highlighted and unimportant features are restrained. Thus, the interference of redundant information can be reduced, and more discriminative characteristics can be extracted. The feature vector obtained through the spatial attention mechanism can better represent key information in the water and fertilizer feature matrix, so that the performance of classification tasks is improved. Such feature vectors can better capture the correlation between different spatial locations and feature channels, enabling the classification model to better distinguish between different classes of samples. Thus, the feature vectors are obtained by the spatial attention module in order to extract key information and improve the performance of classification tasks.
In particular, in the solution of the present application, considering that the classification feature vector may contain some relatively unimportant feature dimensions, these dimensions may introduce noise or redundant information, which negatively affects the final decoding, and may also cause the classification feature vector to be over-fitted or under-fitted when the classification judgment is performed by the classifier. Here, overfitting refers to the model performing well on training data, but poorly on unseen test data. In this case, the model overfits specific noise and variations in the training data without learning the general features of the data well. The performance of the overfitting is that the model is too complex, overfitting training data, resulting in its generalization ability in real situations being reduced. Under fitting (Underfitting) refers to the fact that the model does not fit the training data well, resulting in poor performance on both training data and test data. The reason for the under-fitting is typically that the model is too simple and the features and patterns of the data are not well captured. The performance of the under-fitting is that the model cannot effectively fit the true potential relationship of the training data, resulting in its inability to achieve good performance in practical applications.
Based on the above, in the technical scheme of the application, the classification feature vector is subjected to dimension reduction optimization to obtain an optimized classification feature vector. Specifically, inputting the classification feature vector into a Sigmoid activation function to activate so as to obtain a probabilistic classification feature vector; for the characteristic values of all positions in the probabilistic classified characteristic vector, carrying out zero-resetting treatment on the characteristic values of all positions to obtain a plurality of probabilistic mask classified characteristic vectors; respectively calculating the KL divergence between the probabilistic classification feature vector and each probabilistic mask classification feature vector to obtain a plurality of KL divergences; and determining whether to reject feature values of each position in the probabilistic classified feature vector to obtain an optimized classified feature vector based on a comparison between the KL divergence and a predetermined threshold.
In this way, the importance and stability of the feature values of each position in the classification feature vector are quantitatively measured based on KL divergence to delete the relatively unimportant feature dimension from the classification feature vector, and in this way, not only the relatively more important feature dimension is indirectly enhanced, but also the classification feature vector is subjected to dimension sparsification to avoid over-fitting or under-fitting when the classification feature vector is subjected to classification judgment through a classifier.
Further, the optimized classification feature vector is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the water-fertilizer ratio at the current time point needs to be adjusted. Considering that different water and fertilizer characteristic vectors can be associated with corresponding water and fertilizer proportion adjustment through training the classifier. The classifier can learn and recognize modes and features of different feature vectors, so that the water and fertilizer feature vectors at the current time point are classified, and whether the water and fertilizer proportion needs to be adjusted is predicted. The output result of the classifier can indicate whether the water-fertilizer ratio at the current time point needs to be adjusted. If the classification result is that adjustment is needed, corresponding measures can be taken to adjust the water-fertilizer ratio so as to meet the requirements of vegetables. If the classification result is that adjustment is not needed, the current water-fertilizer ratio can be maintained. Therefore, the classifier is used for classifying the optimized classification feature vector, so that the water-fertilizer ratio at the current time point can be judged whether to need to be adjusted, and the growth environment of plants is optimized.
Based on this, the present application provides a greenhouse vegetable planting management system, comprising: the data acquisition module is used for acquiring the humidity value and the EC value of the soil at a plurality of preset time points in a preset time period; the time sequence arrangement module is used for arranging the humidity value and the EC value of the soil at a plurality of preset time points into a humidity time sequence input vector and an EC time sequence input vector according to the time dimension respectively; the association coding module is used for carrying out association coding on the humidity time sequence input vector and the EC time sequence input vector to obtain a water and fertilizer association matrix; the water and fertilizer characteristic extraction module is used for enabling the water and fertilizer incidence matrix to pass through a convolutional neural network with a block structure to obtain a water and fertilizer characteristic matrix; the attention extraction module is used for enabling the water and fertilizer feature matrix to pass through the spatial attention mechanism module so as to obtain a classification feature vector; the optimizing module is used for carrying out dimension reduction optimization on the classification characteristic vector so as to obtain an optimized classification characteristic vector; and the classification result module is used for enabling the optimized classification feature vector to pass through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the water-fertilizer ratio of the current time point needs to be adjusted or not.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
Exemplary System: fig. 1 is a block diagram of a greenhouse vegetable planting management system according to an embodiment of the present application. As shown in fig. 1, a greenhouse vegetable planting management system 100 according to an embodiment of the present application includes: a data acquisition module 110 for acquiring humidity values and EC values of soil at a plurality of predetermined time points within a predetermined period of time; a time sequence arrangement module 120, configured to arrange the humidity values and EC values of the soil at the plurality of predetermined time points into a humidity time sequence input vector and an EC time sequence input vector according to a time dimension, respectively; the association coding module 130 is configured to perform association coding on the humidity time sequence input vector and the EC time sequence input vector to obtain a water and fertilizer association matrix; the water and fertilizer feature extraction module 140 is configured to pass the water and fertilizer correlation matrix through a convolutional neural network with a block structure to obtain a water and fertilizer feature matrix; the attention extraction module 150 is configured to pass the water and fertilizer feature matrix through a spatial attention mechanism module to obtain a classification feature vector; the optimizing module 160 is configured to perform dimension reduction optimization on the classification feature vector to obtain an optimized classification feature vector; and a classification result module 170, configured to pass the optimized classification feature vector through a classifier to obtain a classification result, where the classification result is used to indicate whether the water-fertilizer ratio at the current time point needs to be adjusted.
Fig. 2 is a schematic architecture diagram of a greenhouse vegetable planting management system according to an embodiment of the present application. As shown in fig. 2, first, the humidity value and EC value of the soil at a plurality of predetermined time points within a predetermined period of time are acquired. Next, arranging the humidity value and the EC value of the soil at the plurality of predetermined time points into a humidity time sequence input vector and an EC time sequence input vector according to a time dimension, respectively. And then, carrying out association coding on the humidity time sequence input vector and the EC time sequence input vector to obtain a water and fertilizer association matrix. And then, the water and fertilizer incidence matrix is passed through a convolutional neural network with a block structure to obtain a water and fertilizer feature matrix. And then, the water and fertilizer feature matrix passes through a spatial attention mechanism module to obtain a classification feature vector. And then, performing dimension reduction optimization on the classification feature vector to obtain an optimized classification feature vector. And finally, the optimized classification feature vector passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the water-fertilizer ratio at the current time point needs to be adjusted.
In an embodiment of the present application, the data obtaining module 110 is configured to obtain the humidity value and the EC value of the soil at a plurality of predetermined time points within a predetermined period of time. Considering that the humidity and EC value of soil are important indicators for measuring the moisture content and fertilizer content of soil. Soil moisture values reflect the moisture content of the soil, which is one of the important factors determining plant growth and development. Through monitoring soil humidity value, can in time know the moisture situation in the soil, judge whether need irrigate or adjust irrigation volume to keep suitable soil humidity, promote the normal growth of plant. EC value (conductivity) is an indicator of the amount of dissolved salt in soil, which reflects the amount of fertilizer and the concentration of salt in soil. Too high or too low an EC value of the soil can negatively affect plant growth. By monitoring the EC value of the soil, the supply condition of the fertilizer in the soil can be known, and whether the fertilizer application amount is required to be adjusted or the flushing treatment is required to be carried out is judged, so that proper fertilizer supply and soil salinity concentration are maintained, and the healthy growth of plants is ensured. Therefore, the acquisition of the soil humidity value and the EC value can provide important information about soil moisture and fertilizer content, provide scientific basis for greenhouse vegetable management, help a manager to realize reasonable water and fertilizer regulation and control, and improve the yield and quality of vegetables.
In the embodiment of the present application, the time sequence arrangement module 120 is configured to arrange the humidity values and the EC values of the soil at the plurality of predetermined time points into a humidity time sequence input vector and an EC time sequence input vector according to a time dimension, respectively. The purpose of arranging humidity and EC input vectors in the time dimension is to capture the trend of soil humidity and EC values over time. By chronologically arranging the data, the water and fertilizer status of the soil can be analyzed and predicted using the characteristics of the time series. The changes in humidity and EC values over time can provide important information about soil moisture content and fertilizer content. By arranging these data into input vectors in a time dimension, we can learn and capture patterns and trends at different time points using time series analysis methods such as convolutional neural networks and spatial attention mechanisms. By arranging the input vectors according to the time dimension, a model can be established, the change rule of soil humidity and EC value can be learned from historical data, and the future water and fertilizer conditions can be predicted. Therefore, the soil condition can be monitored in real time, and whether the water and fertilizer proportion needs to be adjusted or not is automatically judged, so that the water and fertilizer utilization efficiency is improved.
In the embodiment of the present application, the association encoding module 130 is configured to perform association encoding on the humidity time sequence input vector and the EC time sequence input vector to obtain a water and fertilizer association matrix. The correlation and interaction between humidity and EC timing input vectors can be captured in view of their correlation. By correlating the codes, we can integrate the information of humidity and EC values to better understand the relationship between them. In particular, in the agricultural field, the moisture and fertilizer content of soil are often interrelated. The variation in moisture can affect the spread and effectiveness of the fertilizer in the soil, and the content of fertilizer can also affect the moisture retention capacity of the soil. Therefore, by performing associated coding on the humidity and the EC value, we can explore the dynamic relationship between the humidity and the EC value, and further know the water and fertilizer conditions of the soil. Through the association coding, the time sequence information of humidity and EC value can be converted into a water and fertilizer association matrix, so that a more comprehensive basis is provided for subsequent analysis and decision.
Specifically, in the embodiment of the present application, the association encoding module is configured to: performing association coding on the humidity time sequence input vector and the EC time sequence input vector by using the following association formula to obtain a water and fertilizer association matrix; wherein, the association formula is: Wherein->Representing the humidity timing input vector,/a>Representing said->Time sequence input vector,/->Representing the water and fertilizer incidence matrix, < >>Representing matrix multiplication.
In the embodiment of the present application, the water and fertilizer feature extraction module 140 is configured to pass the water and fertilizer correlation matrix through a convolutional neural network with a block structure to obtain a water and fertilizer feature matrix. It is considered that the characteristics and modes in the water and fertilizer incidence matrix can be better captured through the convolutional neural network with the block structure. Block structured convolutional neural networks can extract features on different local regions through convolution operations when processing two-dimensional data, and then integrate these features to form a more global representation. In particular, for a water-fertilizer correlation matrix, it typically has a two-dimensional structure, where the rows represent the time dimension of humidity and the time dimension of EC values. By using the convolutional neural network with the block structure, the characteristics can be extracted on different areas of the water and fertilizer association matrix, and the water and fertilizer association modes of different time points and different time periods can be captured. The advantage of a convolutional neural network of block structure is that it can take into account both local and global information. By performing convolution operations on different blocks, the network can learn features of different scales and integrate them into the final feature matrix. Therefore, the characteristics in the water and fertilizer association matrix can be effectively extracted, so that the water and fertilizer conditions of the soil can be better understood, and corresponding adjustment and decision can be made.
Specifically, in the embodiment of the application, the water and fertilizer characteristic extraction module is used for: each layer of the convolutional neural network model comprising the block structural feature extraction module respectively carries out input data in forward transfer of the layer: performing convolution processing, pooling processing and nonlinear processing on the input data based on a first two-dimensional convolution kernel to obtain a first activation feature map; performing convolution processing, pooling processing and nonlinear activation processing based on a second two-dimensional convolution kernel on the first activation feature map to obtain a second activation feature map, wherein the first two-dimensional convolution kernel and the second two-dimensional convolution kernel are transposed with each other; the input of the first layer of the convolutional neural network model comprising the block structure feature extraction module is the water and fertilizer correlation matrix, and the output of the last layer of the convolutional neural network model comprising the block structure feature extraction module is the water and fertilizer feature matrix.
In the embodiment of the present application, the attention extraction module 150 is configured to pass the water and fertilizer feature matrix through a spatial attention mechanism module to obtain a classification feature vector. The spatial attention mechanism is considered, so that the model can pay more attention to important spatial positions and characteristic channels when processing the water and fertilizer characteristic matrix, and the classification accuracy is improved. In particular, in a water and fertilizer feature matrix, different spatial locations and feature channels may have different importance. Through the spatial attention mechanism module, the spatial attention of the water and fertilizer feature matrix can be adjusted, so that important features are highlighted and unimportant features are restrained. Thus, the interference of redundant information can be reduced, and more discriminative characteristics can be extracted. The feature vector obtained through the spatial attention mechanism can better represent key information in the water and fertilizer feature matrix, so that the performance of classification tasks is improved. Such feature vectors can better capture the correlation between different spatial locations and feature channels, enabling the classification model to better distinguish between different classes of samples. Thus, the feature vectors are obtained by the spatial attention module in order to extract key information and improve the performance of classification tasks.
Fig. 3 is a block diagram of an attention extraction module in greenhouse vegetable planting management according to an embodiment of the present application. Specifically, in an embodiment of the present application, as shown in fig. 3, the attention extraction module 150 includes: a depth convolution encoding unit 151, configured to perform depth convolution encoding on the water-fertilizer feature matrix by using a convolution encoding portion of the spatial attention mechanism module to obtain a detected convolution feature map; a spatial attention unit 152 for inputting the detected convolution feature map into a spatial attention portion of the spatial attention mechanism module to obtain a spatial attention map; an activation unit 153 for activating the spatial attention map by Softmax activation function to obtain a spatial attention profile; a calculating unit 154, configured to calculate a point-by-point multiplication of the spatial attention feature map and the detected convolution feature map to obtain a fusion feature map; and a pooling unit 155, configured to perform pooling processing on each feature matrix along the channel dimension on the fused feature map to obtain a classification feature vector.
In the embodiment of the present application, the optimization module 160 is configured to perform dimension reduction optimization on the classification feature vector to obtain an optimized classification feature vector.
In particular, in the solution of the present application, considering that the classification feature vector may contain some relatively unimportant feature dimensions, these dimensions may introduce noise or redundant information, which negatively affects the final decoding, and may also cause the classification feature vector to be over-fitted or under-fitted when the classification judgment is performed by the classifier. Here, overfitting refers to the model performing well on training data, but poorly on unseen test data. In this case, the model overfits specific noise and variations in the training data without learning the general features of the data well. The performance of the overfitting is that the model is too complex, overfitting training data, resulting in its generalization ability in real situations being reduced. Under fitting (Underfitting) refers to the fact that the model does not fit the training data well, resulting in poor performance on both training data and test data. The reason for the under-fitting is typically that the model is too simple and the features and patterns of the data are not well captured. The performance of the under-fitting is that the model cannot effectively fit the true potential relationship of the training data, resulting in its inability to achieve good performance in practical applications.
Specifically, in an embodiment of the present application, the optimization module includes: the probability unit is used for inputting the classification feature vector into a Sigmoid activation function to be activated so as to obtain a probability classification feature vector; the zeroing processing unit is used for zeroing the characteristic values of all the positions in the probabilistic classified characteristic vectors to obtain a plurality of probabilistic mask classified characteristic vectors; a divergence calculating unit, configured to calculate KL divergences between the probabilistic classification feature vector and the respective probabilistic mask classification feature vectors, respectively, to obtain a plurality of KL divergences; and an optimizing unit, configured to determine whether to reject feature values of each position in the probabilistic classified feature vector based on a comparison between the KL divergence and a predetermined threshold value, so as to obtain an optimized classified feature vector.
In this way, the importance and stability of the feature values of each position in the classification feature vector are quantitatively measured based on KL divergence to delete the relatively unimportant feature dimension from the classification feature vector, and in this way, not only the relatively more important feature dimension is indirectly enhanced, but also the classification feature vector is subjected to dimension sparsification to avoid over-fitting or under-fitting when the classification feature vector is subjected to classification judgment through a classifier.
In the embodiment of the present application, the classification result module 170 is configured to pass the optimized classification feature vector through a classifier to obtain a classification result, where the classification result is used to indicate whether the water-fertilizer ratio at the current time point needs to be adjusted. Considering that different water and fertilizer characteristic vectors can be associated with corresponding water and fertilizer proportion adjustment through training the classifier. The classifier can learn and recognize modes and features of different feature vectors, so that the water and fertilizer feature vectors at the current time point are classified, and whether the water and fertilizer proportion needs to be adjusted is predicted. The output result of the classifier can indicate whether the water-fertilizer ratio at the current time point needs to be adjusted. If the classification result is that adjustment is needed, corresponding measures can be taken to adjust the water-fertilizer ratio so as to meet the requirements of vegetables. If the classification result is that adjustment is not needed, the current water-fertilizer ratio can be maintained. Therefore, the classifier is used for classifying the optimized classification feature vector, so that the water-fertilizer ratio at the current time point can be judged whether to need to be adjusted, and the growth environment of plants is optimized.
Specifically, in an embodiment of the present application, the classification result module includes: the full-connection coding unit is used for carrying out full-connection coding on the optimized classification feature vector by using a full-connection layer of the classifier so as to obtain a coding classification feature vector; and a classification result unit, configured to pass the encoded classification feature vector through a Softmax classification function of the classifier to obtain the classification result.
In summary, the greenhouse vegetable planting management system 100 according to the embodiment of the present application is illustrated, and an artificial intelligence technology based on a deep neural network model is adopted to obtain humidity values and EC values of soil at a plurality of predetermined time points in a predetermined period of time, and the humidity values and EC values are arranged into vectors to perform association coding, then a feature matrix is obtained through a convolutional neural network, and further feature enhancement is performed through a spatial attention mechanism module to obtain a classification result for indicating whether the water-fertilizer ratio at the current time point needs to be adjusted. Through the mode, the moisture and fertilizer content of greenhouse vegetables can be monitored in real time, the water and fertilizer condition of soil can be adjusted in time, and the planting condition of the greenhouse vegetables is ensured.
An exemplary method is: fig. 4 is a flowchart of a greenhouse vegetable planting management method according to an embodiment of the present application. As shown in fig. 4, the greenhouse vegetable planting management method according to the embodiment of the application includes: s110, acquiring humidity values and EC values of soil at a plurality of preset time points in a preset time period; s120, arranging the humidity values and the EC values of the soil at a plurality of preset time points into humidity time sequence input vectors and EC time sequence input vectors according to a time dimension respectively; s130, performing association coding on the humidity time sequence input vector and the EC time sequence input vector to obtain a water and fertilizer association matrix; s140, the water and fertilizer incidence matrix is passed through a convolutional neural network with a block structure to obtain a water and fertilizer feature matrix; s150, the water and fertilizer feature matrix passes through a spatial attention mechanism module to obtain a classification feature vector; s160, performing dimension reduction optimization on the classification feature vector to obtain an optimized classification feature vector; and S170, the optimized classification feature vector is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the water-fertilizer ratio of the current time point needs to be adjusted.
In one example, in the greenhouse vegetable planting management method described above, the humidity timing input is performedAnd carrying out association coding on the vector and the EC time sequence input vector to obtain a water and fertilizer association matrix, wherein the water and fertilizer association matrix is used for: performing association coding on the humidity time sequence input vector and the EC time sequence input vector by using the following association formula to obtain a water and fertilizer association matrix; wherein, the association formula is:wherein->Representing the humidity timing input vector,/a>Representing said->Time sequence input vector,/->Representing the water and fertilizer incidence matrix, < >>Representing matrix multiplication.
In one example, in the greenhouse vegetable planting management method, the water and fertilizer correlation matrix is passed through a convolutional neural network with a block structure to obtain a water and fertilizer characteristic moment, and the method comprises the following steps: each layer of the convolutional neural network model comprising the block structural feature extraction module respectively carries out input data in forward transfer of the layer: performing convolution processing, pooling processing and nonlinear processing on the input data based on a first two-dimensional convolution kernel to obtain a first activation feature map; performing convolution processing, pooling processing and nonlinear activation processing based on a second two-dimensional convolution kernel on the first activation feature map to obtain a second activation feature map, wherein the first two-dimensional convolution kernel and the second two-dimensional convolution kernel are transposed with each other; the input of the first layer of the convolutional neural network model comprising the block structure feature extraction module is the water and fertilizer correlation matrix, and the output of the last layer of the convolutional neural network model comprising the block structure feature extraction module is the water and fertilizer feature matrix.
Here, it will be understood by those skilled in the art that the specific operations of the respective steps in the above-described greenhouse vegetable planting management method have been described in detail in the above description of the greenhouse vegetable planting management system with reference to fig. 1 to 3, and thus, repetitive descriptions thereof will be omitted.
Exemplary electronic device: next, an electronic device according to an embodiment of the present application is described with reference to fig. 5. Fig. 5 is a block diagram of an electronic device according to an embodiment of the application. As shown in fig. 5, the electronic device 10 includes one or more processors 11 and a memory 12.
The processor 11 may be a central processing module (CPU) or other form of processing module having data processing and/or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.
Memory 12 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, random Access Memory (RAM) and/or cache memory (cache), and the like. The non-volatile memory may include, for example, read Only Memory (ROM), hard disk, flash memory, and the like. One or more computer program instructions may be stored on the computer readable storage medium that the processor 11 may execute to implement the functions in the greenhouse vegetable planting management system and methods thereof, and/or other desired functions of the various embodiments of the present application described above. Various contents such as a humidity value and an EC value of soil at a plurality of predetermined time points may also be stored in the computer-readable storage medium.
In one example, the electronic device 10 may further include: an input device 13 and an output device 14, which are interconnected by a bus system and/or other forms of connection mechanisms (not shown).
The input means 13 may comprise, for example, a keyboard, a mouse, etc.
The output device 14 may output various information including the classification result and the like to the outside. The output means 14 may include, for example, a display, speakers, a printer, and a communication network and remote output devices connected thereto, etc.
Of course, only some of the components of the electronic device 10 that are relevant to the present application are shown in fig. 5 for simplicity, components such as buses, input/output interfaces, etc. are omitted. In addition, the electronic device 10 may include any other suitable components depending on the particular application.
Exemplary computer program product and computer readable storage Medium: in addition to the methods and apparatus described above, embodiments of the application may also be a computer program product comprising computer program instructions which, when executed by a processor, cause the processor to perform steps in the functions of the greenhouse vegetable planting management method according to the various embodiments of the application described in the "exemplary methods" section of this specification.
The computer program product may write program code for performing operations of embodiments of the present application in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server.
Furthermore, embodiments of the present application may also be a computer-readable storage medium, on which computer program instructions are stored, which, when being executed by a processor, cause the processor to perform steps in the functions of the greenhouse vegetable planting management method according to the various embodiments of the present application described in the "exemplary method" section above of the present specification.
The computer readable storage medium may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The basic principles of the present application have been described above in connection with specific embodiments, however, it should be noted that the advantages, benefits, effects, etc. mentioned in the present application are merely examples and not intended to be limiting, and these advantages, benefits, effects, etc. are not to be considered as essential to the various embodiments of the present application. Furthermore, the specific details disclosed herein are for purposes of illustration and understanding only, and are not intended to be limiting, as the application is not necessarily limited to practice with the above described specific details.
The block diagrams of the devices, apparatuses, devices, systems referred to in the present application are only illustrative examples and are not intended to require or imply that the connections, arrangements, configurations must be made in the manner shown in the block diagrams. As will be appreciated by one of skill in the art, the devices, apparatuses, devices, systems may be connected, arranged, configured in any manner. Words such as "including," "comprising," "having," and the like are words of openness and mean "including but not limited to," and are used interchangeably therewith. The terms "or" and "as used herein refer to and are used interchangeably with the term" and/or "unless the context clearly indicates otherwise. The term "such as" as used herein refers to, and is used interchangeably with, the phrase "such as, but not limited to.
It is also noted that in the apparatus, devices and methods of the present application, the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent aspects of the present application.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, the present application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit embodiments of the application to the form disclosed herein. Although a number of example aspects and embodiments have been discussed above, a person of ordinary skill in the art will recognize certain variations, modifications, alterations, additions, and subcombinations thereof.
The basic principles of the present application have been described above in connection with specific embodiments, however, it should be noted that the advantages, benefits, effects, etc. mentioned in the present application are merely examples and not intended to be limiting, and these advantages, benefits, effects, etc. are not to be considered as essential to the various embodiments of the present application. Furthermore, the specific details disclosed herein are for purposes of illustration and understanding only, and are not intended to be limiting, as the application is not necessarily limited to practice with the above described specific details.
The block diagrams of the devices, apparatuses, devices, systems referred to in the present application are only illustrative examples and are not intended to require or imply that the connections, arrangements, configurations must be made in the manner shown in the block diagrams. As will be appreciated by one of skill in the art, the devices, apparatuses, devices, systems may be connected, arranged, configured in any manner. Words such as "including," "comprising," "having," and the like are words of openness and mean "including but not limited to," and are used interchangeably therewith. The terms "or" and "as used herein refer to and are used interchangeably with the term" and/or "unless the context clearly indicates otherwise. The term "such as" as used herein refers to, and is used interchangeably with, the phrase "such as, but not limited to.
It is also noted that in the apparatus, devices and methods of the present application, the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent aspects of the present application.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, the present application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit embodiments of the application to the form disclosed herein. Although a number of example aspects and embodiments have been discussed above, a person of ordinary skill in the art will recognize certain variations, modifications, alterations, additions, and subcombinations thereof.
Claims (10)
1. A greenhouse vegetable planting management system, comprising: the data acquisition module is used for acquiring the humidity value and the EC value of the soil at a plurality of preset time points in a preset time period; the time sequence arrangement module is used for arranging the humidity value and the EC value of the soil at a plurality of preset time points into a humidity time sequence input vector and an EC time sequence input vector according to the time dimension respectively; the association coding module is used for carrying out association coding on the humidity time sequence input vector and the EC time sequence input vector to obtain a water and fertilizer association matrix; the water and fertilizer characteristic extraction module is used for enabling the water and fertilizer incidence matrix to pass through a convolutional neural network with a block structure to obtain a water and fertilizer characteristic matrix; the attention extraction module is used for enabling the water and fertilizer feature matrix to pass through the spatial attention mechanism module so as to obtain a classification feature vector; the optimizing module is used for carrying out dimension reduction optimization on the classification characteristic vector so as to obtain an optimized classification characteristic vector; and the classification result module is used for enabling the optimized classification feature vector to pass through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the water-fertilizer ratio of the current time point needs to be adjusted or not.
2. The greenhouse vegetable planting management system of claim 1, wherein the association encoding module is configured to: performing association coding on the humidity time sequence input vector and the EC time sequence input vector by using the following association formula to obtain a water and fertilizer association matrix; wherein, the association formula is:wherein->Representing the humidity timing input vector,/a>Representing said->Time sequence input vector,/->Representing the water and fertilizer incidence matrix, < >>Representing matrix multiplication.
3. The greenhouse vegetable planting management system of claim 2, wherein the water and fertilizer feature extraction module is configured to: each layer of the convolutional neural network model comprising the block structural feature extraction module respectively carries out input data in forward transfer of the layer: performing convolution processing, pooling processing and nonlinear processing on the input data based on a first two-dimensional convolution kernel to obtain a first activation feature map; performing convolution processing, pooling processing and nonlinear activation processing based on a second two-dimensional convolution kernel on the first activation feature map to obtain a second activation feature map, wherein the first two-dimensional convolution kernel and the second two-dimensional convolution kernel are transposed with each other; the input of the first layer of the convolutional neural network model comprising the block structure feature extraction module is the water and fertilizer correlation matrix, and the output of the last layer of the convolutional neural network model comprising the block structure feature extraction module is the water and fertilizer feature matrix.
4. A greenhouse vegetable planting management system as claimed in claim 3, wherein the attention extraction module comprises: the depth convolution coding unit is used for performing depth convolution coding on the water fertilizer feature matrix by using a convolution coding part of the spatial attention mechanism module so as to obtain a detection convolution feature map; a spatial attention unit for inputting the detected convolution feature map into a spatial attention portion of the spatial attention mechanism module to obtain a spatial attention map; an activation unit, configured to activate the spatial attention map through a Softmax activation function to obtain a spatial attention profile; the computing unit is used for computing the position-wise point multiplication of the spatial attention feature map and the detection convolution feature map to obtain a fusion feature map; and the pooling unit is used for pooling the feature matrixes along the channel dimension of the fusion feature graph to obtain the classification feature vector.
5. The greenhouse vegetable planting management system of claim 4, wherein the optimization module comprises: the probability unit is used for inputting the classification feature vector into a Sigmoid activation function to be activated so as to obtain a probability classification feature vector; the zeroing processing unit is used for zeroing the characteristic values of all the positions in the probabilistic classified characteristic vectors to obtain a plurality of probabilistic mask classified characteristic vectors; a divergence calculating unit, configured to calculate KL divergences between the probabilistic classification feature vector and the respective probabilistic mask classification feature vectors, respectively, to obtain a plurality of KL divergences; and an optimizing unit, configured to determine whether to reject feature values of each position in the probabilistic classified feature vector based on a comparison between the KL divergence and a predetermined threshold value, so as to obtain an optimized classified feature vector.
6. The greenhouse vegetable planting management system of claim 4, wherein the optimization module comprises: the probability unit is used for inputting the classification feature vector into a Sigmoid activation function to be activated so as to obtain a probability classification feature vector; the zeroing processing unit is used for zeroing the characteristic values of all the positions in the probabilistic classified characteristic vectors to obtain a plurality of probabilistic mask classified characteristic vectors; a divergence calculating unit, configured to calculate KL divergences between the probabilistic classification feature vector and the respective probabilistic mask classification feature vectors, respectively, to obtain a plurality of KL divergences; and an optimizing unit, configured to determine whether to reject feature values of each position in the probabilistic classified feature vector based on a comparison between the KL divergence and a predetermined threshold value, so as to obtain an optimized classified feature vector.
7. The greenhouse vegetable planting management method is characterized by comprising the following steps of: acquiring humidity values and EC values of soil at a plurality of preset time points in a preset time period; arranging the humidity values and the EC values of the soil at a plurality of preset time points into humidity time sequence input vectors and EC time sequence input vectors according to the time dimension respectively; performing association coding on the humidity time sequence input vector and the EC time sequence input vector to obtain a water and fertilizer association matrix; the water and fertilizer incidence matrix is passed through a convolutional neural network with a block structure to obtain a water and fertilizer feature matrix; the water and fertilizer feature matrix passes through a spatial attention mechanism module to obtain a classification feature vector; performing dimension reduction optimization on the classification feature vector to obtain an optimized classification feature vector; and the optimized classification feature vector passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the water-fertilizer ratio at the current time point needs to be adjusted.
8. The greenhouse vegetable planting management method according to claim 7, wherein the humidity time sequence input directionPerforming association coding on the quantity and the EC time sequence input vector to obtain a water and fertilizer association matrix, wherein the water and fertilizer association matrix is used for: performing association coding on the humidity time sequence input vector and the EC time sequence input vector by using the following association formula to obtain a water and fertilizer association matrix; wherein, the association formula is:wherein->Representing the humidity timing input vector,/a>Representing said->Time sequence input vector,/->Representing the water and fertilizer incidence matrix, < >>Representing matrix multiplication.
9. The greenhouse vegetable planting management method according to claim 8, wherein the water and fertilizer correlation matrix is passed through a convolutional neural network having a block structure to obtain a water and fertilizer characteristic moment, comprising:
each layer of the convolutional neural network model comprising the block structural feature extraction module respectively carries out input data in forward transfer of the layer: performing convolution processing, pooling processing and nonlinear processing on the input data based on a first two-dimensional convolution kernel to obtain a first activation feature map; performing convolution processing, pooling processing and nonlinear activation processing based on a second two-dimensional convolution kernel on the first activation feature map to obtain a second activation feature map, wherein the first two-dimensional convolution kernel and the second two-dimensional convolution kernel are transposed with each other; the input of the first layer of the convolutional neural network model comprising the block structure feature extraction module is the water and fertilizer correlation matrix, and the output of the last layer of the convolutional neural network model comprising the block structure feature extraction module is the water and fertilizer feature matrix.
10. The greenhouse vegetable planting management method according to claim 9, wherein the optimizing the classification feature vector through a classifier to obtain a classification result, the classification result is used for indicating whether the water-fertilizer ratio of the current time point needs to be adjusted, and the method comprises: performing full-connection coding on the optimized classification feature vector by using a full-connection layer of the classifier to obtain a coding classification feature vector; and passing the coding classification feature vector through a Softmax classification function of the classifier to obtain the classification result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310757692.3A CN116703638A (en) | 2023-06-26 | 2023-06-26 | Greenhouse vegetable planting management system and method thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310757692.3A CN116703638A (en) | 2023-06-26 | 2023-06-26 | Greenhouse vegetable planting management system and method thereof |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116703638A true CN116703638A (en) | 2023-09-05 |
Family
ID=87844921
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310757692.3A Pending CN116703638A (en) | 2023-06-26 | 2023-06-26 | Greenhouse vegetable planting management system and method thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116703638A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117743975A (en) * | 2024-02-21 | 2024-03-22 | 君研生物科技(山西)有限公司 | Hillside cultivated land soil environment improvement method |
-
2023
- 2023-06-26 CN CN202310757692.3A patent/CN116703638A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117743975A (en) * | 2024-02-21 | 2024-03-22 | 君研生物科技(山西)有限公司 | Hillside cultivated land soil environment improvement method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN117540908B (en) | Agricultural resource integration method and system based on big data | |
Priya et al. | An IoT based gradient descent approach for precision crop suggestion using MLP | |
CN116703638A (en) | Greenhouse vegetable planting management system and method thereof | |
Chen et al. | Research on agricultural environment prediction based on deep learning | |
CN114821296A (en) | Underground disease ground penetrating radar image identification method and system, storage medium and terminal | |
CN110852149B (en) | Vegetation index prediction method, system and equipment based on classification and regression tree algorithm | |
Balti et al. | Big data based architecture for drought forecasting using LSTM, ARIMA, and Prophet: Case study of the Jiangsu Province, China | |
Liu et al. | A state of art review on time series forecasting with machine learning for environmental parameters in agricultural greenhouses | |
CN110826764B (en) | Random forest algorithm-based vegetation index prediction method, system and equipment | |
CN117114913A (en) | Intelligent agricultural data acquisition system based on big data | |
Nyakuri et al. | IoT and AI based smart soil quality assessment for data-driven irrigation and fertilization | |
Mahendran et al. | Application of Machine Learning and Internet of Things for Identification of Nutrient Deficiencies in Oil Palm | |
Ashok et al. | Crop prediction based on environmental factors using machine learning ensemble algorithms | |
Zhang et al. | Collaborative Forecasting and Analysis of Fish Catch in Hokkaido From Multiple Scales by Using Neural Network and ARIMA Model | |
CN115828758A (en) | Seawater three-dimensional prediction method and system based on improved firework algorithm optimization network | |
Sikandar et al. | Automatic Crop Expert System Using Improved LSTM with Attention Block. | |
Munaganuri et al. | Cap-DiBiL: an automated model for crop water requirement prediction and suitable crop recommendation in agriculture | |
Liu et al. | A method for missing data recovery of waste gas monitoring in animal building based on GA-SVM | |
Devi et al. | AI‐Based Weather Forecasting System for Smart Agriculture System Using a Recurrent Neural Networks (RNN) Algorithm | |
Priya et al. | A survey on deep learning based IoT approach for precision crop suggestion | |
Chen et al. | Waterfowl breeding environment humidity prediction based on the SRU-based sequence to sequence model | |
Gurmessa | A Big Data Analytics Framework in Climate Smart Agriculture | |
CN117520823A (en) | Dynamic monitoring data processing system and method based on feature mining | |
Jiang et al. | Advancing storm surge forecasting from scarce observation data: A causal-inference based Spatio-Temporal Graph Neural Network approach | |
CN110991685A (en) | Meteorological temperature prediction method |
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 |