CN118210342A

CN118210342A - Crop growth control method, device and medium for intelligent greenhouse

Info

Publication number: CN118210342A
Application number: CN202410328244.6A
Authority: CN
Inventors: 梁苍; 张厚森; 冯洋洋
Original assignee: Inspur Intelligent Technology Wuhan Co Ltd; Inspur Shandong Agricultural Internet Co Ltd
Current assignee: Inspur Intelligent Technology Wuhan Co Ltd; Inspur Shandong Agricultural Internet Co Ltd
Priority date: 2024-03-21
Filing date: 2024-03-21
Publication date: 2024-06-18

Abstract

The embodiment of the specification discloses a crop growth control method, equipment and medium for an intelligent greenhouse, and relates to the technical field of intelligent control, wherein the method comprises the following steps: acquiring a plurality of historical environmental data corresponding to each environmental factor of a specified intelligent greenhouse, determining a plurality of big data environmental factor prediction models according to the plurality of historical environmental data, and determining initial environmental prediction data corresponding to each environmental factor through the big data environmental factor prediction models; determining current environment prediction data corresponding to each environment factor based on weather early warning information acquired in advance; determining the crop growth prediction information in a prediction period through the current crop information and the current environment prediction data corresponding to the specified intelligent greenhouse, which are obtained in advance; and generating an equipment control scheme of at least one Internet of things control equipment according to the current environment prediction data and the crop growth prediction information, and regulating and controlling environmental factors of the designated intelligent greenhouse through the equipment control scheme to control the crop growth.

Description

Crop growth control method, device and medium for intelligent greenhouse

Technical Field

The specification relates to the technical field of intelligent control, in particular to a crop growth control method, device and medium for an intelligent greenhouse.

Background

With the continuous progress of agricultural technology and the development of intelligent technology, intelligent greenhouses as an important form of modern agriculture have gradually become a new trend of crop planting. The intelligent greenhouse realizes accurate monitoring and regulation of the crop growth environment by integrating advanced sensors, automatic control equipment and a data analysis system, so that the crop yield and quality are improved, and the agricultural production cost is reduced. In intelligent greenhouses, environmental control is critical to the growth of crops.

In the crop cultivation process of the intelligent greenhouse, the greenhouse environment is adjusted by combining the real-time environment data and the experience data in a mode of collecting the real-time environment data. However, the empirical data only represents a general situation, and the environment in the greenhouse is affected by various factors, such as day and night variation factors, weather factors, and the like, so that the accuracy of the environmental regulation mode obtained by the empirical data is low. In addition, the requirements of different regional conditions, different crop types and greenhouse environments corresponding to different crop stages are also different, the pertinence of regulating and controlling the greenhouse environments by using the empirical data is poor, and therefore, the crop yield still has an optimization space. And after the real-time environment data is collected, the real-time environment data is combined with the experience data to regulate and control the greenhouse environment, and a certain time hysteresis exists in the regulation and control process.

Therefore, the greenhouse environment is regulated and controlled by using the experience data at present, the requirements of accuracy and pertinence of environment regulation and control cannot be met under the influence of multiple factors, and the environment regulation is carried out by combining the real-time environment data and the experience data, so that certain time hysteresis exists, and the growth process of crops is further influenced.

Disclosure of Invention

One or more embodiments of the present disclosure provide a crop growth control method, apparatus, and medium for a smart greenhouse, for solving the following technical problems: at present, the greenhouse environment is regulated and controlled by using experience data, the requirements of accuracy and pertinence of environment regulation and control cannot be met under the influence of various factors, and the environment is regulated by combining real-time environment data and experience data, so that certain time lag exists, and the growth process of crops is further influenced.

One or more embodiments of the present disclosure adopt the following technical solutions:

One or more embodiments of the present specification provide a crop growth control method for a smart greenhouse, the method comprising: acquiring a plurality of historical environmental data corresponding to each environmental factor of a specified intelligent greenhouse, and determining a plurality of big data environmental factor prediction models corresponding to each environmental factor according to the plurality of historical environmental data corresponding to each environmental factor, wherein the environmental factors comprise temperature factors, humidity factors, illumination factors and gas factors; predicting a plurality of environmental factors of the specified intelligent greenhouse in a preset prediction period through the big data environmental factor prediction model, and determining initial environmental prediction data corresponding to each environmental factor in the prediction period; optimizing initial environmental prediction data corresponding to each environmental factor based on pre-acquired weather early warning information, and determining current environmental prediction data corresponding to each environmental factor; predicting the crop growth condition in the prediction period through the current crop information and the current environment prediction data corresponding to the appointed intelligent greenhouse, and determining the crop growth prediction information in the prediction period; generating an equipment control scheme of at least one Internet of things control equipment in the prediction period according to the current environment prediction data corresponding to each environment factor and the crop growth prediction information in the prediction period, and regulating and controlling at least one environment factor of the appointed intelligent greenhouse through the equipment control scheme so as to control the crop growth, wherein the Internet of things control equipment comprises temperature control equipment, humidity regulation equipment, illumination regulation equipment and gas regulation equipment.

Further, according to a plurality of historical environmental data corresponding to each environmental factor, determining a plurality of big data environmental factor prediction models corresponding to each environmental factor specifically includes: determining acquisition time information of each historical environmental data, and constructing an environmental data change sequence corresponding to each environmental factor according to each historical environmental data; determining a time segmentation interval of each environmental factor based on an environmental data change sequence corresponding to each environmental factor, splitting the plurality of historical environmental data corresponding to each environmental factor according to the time segmentation time and acquisition time information of each historical environmental data, and determining a plurality of historical environmental data subsets corresponding to each environmental factor; and constructing a big data model through each historical environment data subset so as to determine a big data environment factor prediction model of each time segmentation interval corresponding to each environment factor.

Further, predicting a plurality of environmental factors of the specified intelligent greenhouse in a preset prediction period through the big data environmental factor prediction model, and determining initial environmental prediction data corresponding to each environmental factor in the prediction period specifically includes: determining time information to be predicted, so as to determine a prediction period of each environmental factor based on the time information to be predicted and the time segmentation interval of each environmental factor; matching a plurality of big data environmental factor prediction models through each prediction period of the environmental factors to determine a current big data environmental factor prediction model corresponding to the prediction period; and predicting the environmental factors according to the current big data environmental factor prediction model corresponding to each environmental factor, and generating initial environmental prediction data corresponding to each environmental factor in the prediction period.

Further, based on the weather early warning information obtained in advance, optimizing initial environmental prediction data corresponding to each environmental factor, and determining current environmental prediction data corresponding to each environmental factor specifically includes: acquiring the weather early warning information, wherein the weather early warning information comprises an early warning type and an early warning level; determining at least one environmental influence factor influenced by weather early warning according to the early warning type of the weather early warning information, and determining the environmental influence quantity of each environmental influence factor according to the early warning level; and optimizing initial environmental prediction data corresponding to each environmental factor based on the environmental impact quantity affecting the environmental factor, and determining current environmental prediction data corresponding to each environmental factor.

Further, predicting the crop growth condition in the prediction period through the current crop information and the current environment prediction data corresponding to the specified intelligent greenhouse, and determining the crop growth prediction information in the prediction period specifically includes: acquiring current crop information corresponding to the specified intelligent greenhouse, wherein the current crop information comprises current crop variety information and current crop state information; predicting the crop growth condition in the prediction period according to the current crop information by a regression prediction technology, and determining first crop growth prediction information in the prediction period; predicting the crop growth condition in the prediction period according to the current environment prediction data and the current crop state information, and determining second crop growth prediction information in the prediction period; crop growth prediction information within the prediction period is determined based on the first crop growth prediction information and the second crop growth prediction information.

Further, according to the current environmental prediction data corresponding to each environmental factor and the crop growth prediction information in the prediction period, generating an equipment control scheme of at least one internet of things control equipment in the prediction period specifically comprises: determining expected crop growth information in the prediction period, so as to determine crop growth information to be adjusted according to the expected crop growth information and the predicted crop growth information in the prediction period; determining an environment adjustment strategy based on the crop growth information to be adjusted and the current environment prediction data, wherein the environment adjustment strategy comprises a plurality of environment factors to be adjusted and adjustment values of each environment factor to be adjusted; and generating a device control scheme of at least one Internet of things control device in the prediction period according to the environment adjustment strategy.

Further, according to the current environmental prediction data corresponding to each environmental factor and the crop growth prediction information in the prediction period, generating an equipment control scheme of at least one internet of things control equipment in the prediction period specifically comprises: determining expected crop growth information in the prediction period, and when the expected crop growth information is different from the expected crop growth information, matching in a preset expert database according to the expected crop growth information to determine expected environmental data; determining an environment adjustment strategy based on the expected environment data and the current environment prediction data, wherein the environment adjustment strategy comprises a plurality of environment factors to be adjusted and adjustment values of each environment factor to be adjusted; and generating a device control scheme of at least one Internet of things control device in the prediction period according to the environment adjustment strategy.

Further, by the device control scheme, at least one environmental factor of the designated intelligent greenhouse is regulated and controlled to control crop growth, specifically including: determining theoretical environmental data of each environmental factor after environmental adjustment according to a pre-acquired environmental adjustment strategy; and acquiring real-time environment data of each environment factor, determining an environment data adjustment item based on the real-time environment data and the theoretical environment data, adjusting the equipment control scheme based on the environment data adjustment item, generating a real-time equipment control scheme, and controlling crop growth.

One or more embodiments of the present specification provide a crop growth control apparatus for a smart greenhouse, including:

at least one processor; and

A memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor to enable the at least one processor to:

acquiring a plurality of historical environmental data corresponding to each environmental factor of a specified intelligent greenhouse, and determining a plurality of big data environmental factor prediction models corresponding to each environmental factor according to the plurality of historical environmental data corresponding to each environmental factor, wherein the environmental factors comprise temperature factors, humidity factors, illumination factors and gas factors; predicting a plurality of environmental factors of the specified intelligent greenhouse in a preset prediction period through the big data environmental factor prediction model, and determining initial environmental prediction data corresponding to each environmental factor in the prediction period; optimizing initial environmental prediction data corresponding to each environmental factor based on pre-acquired weather early warning information, and determining current environmental prediction data corresponding to each environmental factor; predicting the crop growth condition in the prediction period through the current crop information and the current environment prediction data corresponding to the appointed intelligent greenhouse, and determining the crop growth prediction information in the prediction period; generating an equipment control scheme of at least one Internet of things control equipment in the prediction period according to the current environment prediction data corresponding to each environment factor and the crop growth prediction information in the prediction period, and regulating and controlling at least one environment factor of the appointed intelligent greenhouse through the equipment control scheme so as to control the crop growth, wherein the Internet of things control equipment comprises temperature control equipment, humidity regulation equipment, illumination regulation equipment and gas regulation equipment.

One or more embodiments of the present specification provide a non-volatile computer storage medium storing computer-executable instructions configured to:

The above-mentioned at least one technical scheme that this description embodiment adopted can reach following beneficial effect: according to the technical scheme, the plurality of historical environment data of the appointed intelligent greenhouse are obtained, the plurality of big data environment factor prediction models are built for each environment factor, information in the historical data can be fully utilized, the accuracy of prediction is improved, the influence and the change trend of the environment factors can be considered by the models, and accordingly a prediction result which is closer to the actual situation is generated; the method has the advantages that the initial environment prediction data is optimized by combining the pre-acquired weather early warning information, the influence of sudden weather events on the crop growth environment can be considered, the prediction result is more close to the environmental condition which changes in real time, the healthy growth of crops is guaranteed, the crop growth condition in the prediction period is predicted by combining the current crop information and the optimized environment prediction data, and reasonable management strategies are formulated according to the crop growth requirements and the environmental condition, so that the crop yield and quality are improved; according to the current environment prediction data and the crop growth prediction information, generating an equipment control scheme of the Internet of things control equipment, intelligent regulation and control of environmental factors in the intelligent greenhouse can be realized, the environmental factors can be automatically regulated according to the crop growth requirements and the changes of environmental conditions, and the stability and the suitability of the crop growth environment are improved; the whole flow realizes the automation and the intellectualization of the crop growth prediction and the environment regulation, realizes the predictive regulation, reduces the regulation time lag of regulation after the data are collected in real time, reduces the subjectivity of human intervention and decision, improves the efficiency and the benefit of agricultural production, can reduce the agricultural production cost, improve the resource utilization efficiency and promote the sustainable development of agriculture through precise environment regulation and crop growth control.

Drawings

In order to more clearly illustrate the embodiments of the present description or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some of the embodiments described in the present description, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:

Fig. 1 is a schematic flow chart of a crop growth control method for intelligent greenhouse according to an embodiment of the present disclosure;

Fig. 2 is a schematic structural diagram of a crop growth control apparatus for intelligent greenhouses according to an embodiment of the present disclosure.

Detailed Description

In order to make the technical solutions in the present specification better understood by those skilled in the art, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only some embodiments of the present specification, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present disclosure.

The embodiment of the present disclosure provides a crop growth control method for an intelligent greenhouse, and it should be noted that the execution subject in the embodiment of the present disclosure may be a server, or any device having data processing capability. Fig. 1 is a schematic flow chart of a crop growth control method for intelligent greenhouse according to an embodiment of the present disclosure, as shown in fig. 1, mainly including the following steps:

Step S101, a plurality of historical environmental data corresponding to each environmental factor of the specified intelligent greenhouse are obtained, and a plurality of big data environmental factor prediction models corresponding to each environmental factor are determined according to the plurality of historical environmental data corresponding to each environmental factor.

In one embodiment of the present specification, real-time environmental data within a greenhouse is collected by an environmental collection device preset in the greenhouse, and the real-time environmental data is stored. When the growth control of crops in the greenhouse is required, historical environmental data of the greenhouse is acquired in a storage area. If the greenhouse needing to be controlled is the greenhouse using the intelligent equipment for the first time, controlling the geographic position of the greenhouse and the crop type according to the need, and selecting the environmental data of other greenhouses with the same area and the same crop as the historical environmental data. Each environmental factor corresponds to a plurality of historical environmental data, and as the temperature, the moderate degree, the illumination, the gas and the like in the greenhouse can influence the growth of crops, the environmental factors can comprise temperature factors, humidity factors, illumination factors and gas factors.

According to a plurality of historical environmental data corresponding to each environmental factor, determining a plurality of big data environmental factor prediction models corresponding to each environmental factor specifically comprises: determining acquisition time information of each historical environmental data, and constructing an environmental data change sequence corresponding to each environmental factor according to each historical environmental data; based on the environmental data change sequence corresponding to each environmental factor, determining a time segmentation interval of each environmental factor, splitting the plurality of historical environmental data corresponding to each environmental factor according to the time segmentation time and the acquisition time information of each historical environmental data, and determining a plurality of historical environmental data subsets corresponding to each environmental factor; and constructing a big data model through each historical environment data subset so as to determine a big data environment factor prediction model of each time segmentation interval corresponding to each environment factor.

In one embodiment of the present disclosure, the acquisition time information of each historical environmental data is determined, and an environmental data change sequence corresponding to each environmental factor is constructed according to each historical environmental data, that is, an environmental data change sequence of the historical environmental data corresponding to each environmental factor is constructed, where the environmental data change sequence may be a change curve of the historical environmental data every day, the abscissa is a time, the range is 24 hours, and the ordinate is a value of the historical environmental data. Since each environmental factor is affected by diurnal variation, there is a difference in the variation of environmental data in different time periods of each day. And calculating the environmental data change rate at each moment through the environmental data change sequence corresponding to each environmental factor, and determining the time segmentation interval of each environmental factor according to the environmental data change rate. It should be noted that, the environmental data change rates of the plurality of historical environmental data in the time division intervals are not greatly different, and the environmental data change rates of the adjacent time division intervals are greatly different. For example, a time point exceeding a threshold value at a plurality of times of 24 hours may be set as a time division point by presetting a threshold value of the change rate of the environmental data, and a time division section is formed between adjacent time division points. Splitting the plurality of historical environmental data corresponding to each environmental factor according to the time slicing time and the acquisition time information of each historical environmental data, and determining a plurality of historical environmental data subsets corresponding to each environmental factor. The obtained plurality of historical environment data subsets can represent the change rule in the time segmentation interval and have reference value. And constructing a big data model through each historical environment data subset to determine a big data environment factor prediction model of each time segmentation interval corresponding to each environment factor.

When the model is built, the collected original data is subjected to cleaning, denoising and standardization treatment so as to improve the data quality and comparability. And constructing a plurality of different big data models, such as a machine learning model, a deep learning model and the like, according to the preprocessed data. And training and verifying the constructed big data model by using the historical data, and evaluating the prediction precision and adaptability of each model. And comparing the prediction results of the models with actual environmental parameter data, and selecting the model which is most suitable for the current greenhouse environmental condition as the basis of a control strategy. The prediction model is refined into different time segmentation intervals, so that the obtained big data environmental factor prediction model is ensured to be more in line with the environmental change trend in the time segmentation intervals, the data fluctuation generated by day and night change is avoided, and the accuracy and the representativeness of the prediction model are further ensured.

Step S102, predicting a plurality of environmental factors of a specified intelligent greenhouse in a preset prediction period through a big data environmental factor prediction model, and determining initial environmental prediction data corresponding to each environmental factor in the prediction period.

Predicting a plurality of environmental factors of the specified intelligent greenhouse in a preset prediction period through the big data environmental factor prediction model, and determining initial environmental prediction data corresponding to each environmental factor in the prediction period, wherein the method specifically comprises the following steps of: determining time information to be predicted, so as to determine a prediction period of each environmental factor based on the time information to be predicted and the time segmentation interval of each environmental factor; matching a plurality of big data environmental factor prediction models through each prediction period of the environmental factors so as to determine a current big data environmental factor prediction model corresponding to the prediction period; and predicting the environmental factors according to the current big data environmental factor prediction model corresponding to each environmental factor, and generating initial environmental prediction data corresponding to each environmental factor in the prediction period.

In one embodiment of the present description, the time information to be predicted is determined, where the time information to be predicted may be determined by a trigger time of a crop growth control request initiated by a user. And determining a time segmentation interval in which the time information to be predicted falls according to the time segmentation interval corresponding to each environmental factor, and determining the prediction period of each environmental factor. It should be noted that, the prediction period herein is one of the time-slicing intervals, and the matching is performed on the multiple big data environmental factor prediction models through the time-slicing interval corresponding to the prediction period of each environmental factor, so as to determine the current big data environmental factor prediction model corresponding to the time-slicing interval. And predicting the environmental factors according to the current big data environmental factor prediction model corresponding to each environmental factor, and generating initial environmental prediction data corresponding to each environmental factor in the prediction period.

By means of the technical scheme, the specific environmental factors faced by crop growth in the current time period can be determined through accurate positioning of the time information to be predicted, crop growth conditions can be predicted more accurately, so that a more accurate crop management strategy is formulated, the time information to be predicted is determined according to the triggering time of a crop growth control request initiated by a user, the real-time property of prediction is guaranteed, and agricultural producers are very important because the agricultural producers can adjust agricultural production measures in time according to the real-time prediction results so as to cope with possible environmental changes; by matching the time segmentation interval corresponding to each environmental factor with the big data environmental factor prediction model, the most suitable prediction model can be selected for prediction, the prediction advantages of different models in different time periods are fully utilized, and the accuracy and reliability of prediction are improved.

Step S103, optimizing initial environment prediction data corresponding to each environmental factor based on weather early warning information acquired in advance, and determining current environment prediction data corresponding to each environmental factor.

Optimizing initial environmental prediction data corresponding to each environmental factor based on pre-acquired weather early warning information, and determining current environmental prediction data corresponding to each environmental factor specifically comprises the following steps: acquiring the weather early warning information, wherein the weather early warning information comprises an early warning type and an early warning level; determining at least one environmental influence factor influenced by the weather early warning information according to the early warning type of the weather early warning information, and determining the environmental influence quantity of each environmental influence factor according to the early warning level; and optimizing initial environmental prediction data corresponding to each environmental factor based on the environmental impact quantity of each environmental factor, and determining current environmental prediction data corresponding to each environmental factor.

In one embodiment of the present description, weather warning information is obtained, where the weather warning information includes a warning type and a warning level. The method comprises the steps of acquiring a plurality of historical environmental data under the early warning type through the early warning type of weather early warning information, comparing the historical environmental data with the historical environmental data under the conventional weather condition, determining the environmental data change condition generated by the weather factors at the same time, classifying the environmental data change according to the early warning level, namely determining at least one environmental influence factor affecting the weather, and determining the environmental influence quantity of each environmental influence factor according to the early warning level. The environmental impact herein includes both positive and negative effects. And optimizing initial environmental prediction data corresponding to each environmental factor based on the environmental influence quantity of each environmental factor, and determining current environmental prediction data corresponding to each environmental factor. When the environmental impact is positive, adding an absolute value of the environmental impact on the basis of the initial environmental prediction data to obtain current environmental prediction data corresponding to each environmental factor; and when the environmental impact quantity is negative, subtracting the absolute value of the environmental impact quantity on the basis of the initial environmental prediction data to obtain the current environmental prediction data corresponding to each environmental factor.

By the technical scheme, the weather early warning information corrects and optimizes the initial environment prediction data so that the initial environment prediction data is closer to the actual situation, and the accuracy of prediction is improved; different weather early warning information may correspond to different environmental factors and crop growth requirements; by combining the early warning information, the method can be used for more targeted prediction and optimization aiming at different environmental factors, so that the actual demands of crop growth are better met.

Step S104, predicting the crop growth condition in a prediction period through the current crop information and the current environment prediction data corresponding to the appointed intelligent greenhouse, which are obtained in advance, and determining the crop growth prediction information in the prediction period;

Predicting the crop growth condition in the prediction period through the current crop information and the current environment prediction data corresponding to the appointed intelligent greenhouse, and determining the crop growth prediction information in the prediction period, wherein the method specifically comprises the following steps: acquiring current crop information corresponding to the appointed intelligent greenhouse, wherein the current crop information comprises current crop variety information and current crop state information; predicting the crop growth condition in the prediction period according to the current crop information by a regression prediction technology, and determining first crop growth prediction information in the prediction period; predicting the crop growth condition in the prediction period according to the current environment prediction data and the current crop state information, and determining second crop growth prediction information in the prediction period; crop growth prediction information within the prediction period is determined based on the first crop growth prediction information and the second crop growth prediction information.

In one embodiment of the present specification, current crop information corresponding to a specified intelligent greenhouse is obtained, where the current crop information includes current crop variety information and the current crop status information. And predicting the crop growth condition in the prediction period according to the current crop information by a regression prediction algorithm, and determining the first crop growth prediction information in the prediction period. The first crop growth prediction information herein is the change over time of growth information obtained in combination with historical data.

And predicting the crop growth condition in the prediction period according to the current environment prediction data and the current crop state information, and determining second crop growth prediction information in the prediction period. Firstly, a state equation and an observation equation are established, wherein the state equation is used for describing the evolution process of the crop growth state along with time, the characteristics of crop varieties and the influence of various environmental factors on the growth state are required to be considered, and the state equation is required to be established according to a crop growth model and experimental data. The observation equation is used to describe how to obtain the growth state information of crops through observation means (such as remote sensing, sensors and the like). The initial state estimation value X (0|0) and the initial covariance matrix P (0|0) are set according to historical data, expert experience, or experimental determination, or the like.

At each time step, the state equation is used to predict the growth state of the crop, resulting in a predicted state X (k|k-1) and a predicted covariance matrix P (k|k-1). Where k represents the current time step and k-1 represents the last time step. When the observed value of the current time step is obtained, a kalman gain Kg (k) is calculated for reflecting the weight allocation between the predicted value and the observed value. The predicted state is corrected using the kalman gain to obtain a corrected state estimate X (k|k). The covariance matrix P (k|k) is updated for better prediction at the next time step. And taking the corrected state estimation X (k|k) and the updated covariance matrix P (k|k) as initial values of the next time step, and repeating the prediction and correction processes until a preset future time node is reached. And when the preset time node is reached, outputting a predicted value of the crop growth state at the time point, namely second crop growth prediction information.

According to the first crop growth prediction information and the second crop growth prediction information, determining crop growth prediction information in a prediction period, wherein the crop growth prediction information in the prediction period can be obtained by setting weight forms for the two prediction modes and carrying out weighted averaging on the first crop growth prediction information and the second crop growth prediction information.

By means of the technical scheme, the crop growth information is predicted by combining the two prediction modes, prediction deviation generated by a single prediction mode is avoided, prediction information corresponding to time variation is considered, prediction information obtained under prediction environment data is considered, a reference angle is comprehensive, and accuracy and comprehensiveness of the crop prediction information are guaranteed.

Step S105, generating an equipment control scheme of at least one Internet of things control equipment in the prediction period according to the current environment prediction data corresponding to each environmental factor and the crop growth prediction information in the prediction period, and regulating and controlling at least one environmental factor of the designated intelligent greenhouse through the equipment control scheme so as to control the crop growth.

The control equipment of the Internet of things comprises temperature control equipment, humidity adjusting equipment, illumination adjusting equipment and gas adjusting equipment.

According to the current environment prediction data corresponding to each environment factor and the crop growth prediction information in the prediction period, generating an equipment control scheme of at least one Internet of things control equipment in the prediction period specifically comprises the following steps: determining expected crop growth information in the prediction period, so as to determine crop growth information to be adjusted according to the expected crop growth information and the predicted crop growth information in the prediction period; determining an environmental adjustment strategy based on the crop growth information to be adjusted and the current environmental prediction data, wherein the environmental adjustment strategy comprises a plurality of environmental factors to be adjusted and adjustment values of each environmental factor to be adjusted; and generating a device control scheme of at least one Internet of things control device in the prediction period according to the environment adjustment strategy.

In one embodiment of the present description, crop growth desired information over a prediction period is determined. And determining the difference between the expected information of the crop growth and the predicted information of the crop growth in the prediction period according to the expected information of the crop growth and the predicted information of the crop growth in the prediction period so as to determine the information of the crop growth to be adjusted. And determining an environment adjustment strategy according to the crop growth information to be adjusted and the current environment prediction data, wherein the environment adjustment strategy comprises a plurality of environment factors to be adjusted and adjustment values of each environment factor to be adjusted. And generating a device control scheme of at least one Internet of things control device in the prediction period according to the environment adjustment strategy.

According to the current environment prediction data corresponding to each environment factor and the crop growth prediction information in the prediction period, generating an equipment control scheme of at least one Internet of things control equipment in the prediction period specifically comprises the following steps: determining expected crop growth information in the prediction period, and when the expected crop growth information is different from the expected crop growth information, matching in a preset expert database according to the expected crop growth information to determine expected environmental data; determining an environmental adjustment policy based on the expected environmental data and the current environmental prediction data, wherein the environmental adjustment policy includes a plurality of environmental factors to be adjusted and adjustment values for each of the environmental factors to be adjusted; and generating a device control scheme of at least one Internet of things control device in the prediction period according to the environment adjustment strategy.

In one embodiment of the present disclosure, when the plant control scheme is generated, the expected information of the crop growth in the prediction period may be determined, and when the predicted information of the crop growth is different from the expected information of the crop growth or different from the expected information of the crop growth by more than a preset requirement, the expected environmental data corresponding to the expected information of the crop growth may be determined by matching the expected information of the crop growth in a preset expert database. It should be noted that, the expert database includes a plurality of experience data for representing the requirement environment data corresponding to different crop growth states. Comparing the current environmental prediction data with expected environmental data, and determining an environmental adjustment strategy, wherein the environmental adjustment strategy comprises a plurality of environmental factors to be adjusted and adjustment values of the environmental factors to be adjusted. And generating a device control scheme of at least one Internet of things control device in the prediction period according to the environment adjustment strategy.

Through this equipment control scheme, regulate and control at least one environmental factor of this appointed wisdom big-arch shelter to control crop growth specifically includes: determining theoretical environmental data of each environmental factor after environmental adjustment according to a pre-acquired environmental adjustment strategy; and acquiring real-time environment data of each environment factor, determining an environment data adjustment item based on the real-time environment data and the theoretical environment data, adjusting the equipment control scheme based on the environment data adjustment item, generating a real-time equipment control scheme, and controlling crop growth.

In an embodiment of the present disclosure, since the device control scheme in real time is generated based on the prediction data, in order to avoid that the prediction data deviate from the actual data greatly, the device control scheme cannot effectively adjust the environment. Therefore, the real-time environmental data of each environmental factor is collected in real time, and the theoretical environmental data of each environmental factor after environmental adjustment is determined according to the environmental adjustment strategy acquired in advance. Comparing the theoretical environment data with the real-time environment data, and determining an environment data adjustment item according to the difference value of the theoretical environment data and the real-time environment data when the difference value of the theoretical environment data and the real-time environment data exceeds a preset threshold value, so as to adjust the equipment control scheme based on the environment data adjustment item, generate the real-time equipment control scheme and control the crop growth.

According to the technical scheme, the plurality of historical environment data of the appointed intelligent greenhouse are obtained, the plurality of big data environment factor prediction models are built for each environment factor, information in the historical data can be fully utilized, the accuracy of prediction is improved, the influence and the change trend of the environment factors can be considered by the models, and accordingly a prediction result which is closer to the actual situation is generated; the method has the advantages that the initial environment prediction data is optimized by combining the pre-acquired weather early warning information, the influence of sudden weather events on the crop growth environment can be considered, the prediction result is more close to the environmental condition which changes in real time, the healthy growth of crops is guaranteed, the crop growth condition in the prediction period is predicted by combining the current crop information and the optimized environment prediction data, and reasonable management strategies are formulated according to the crop growth requirements and the environmental condition, so that the crop yield and quality are improved; according to the current environment prediction data and the crop growth prediction information, generating an equipment control scheme of the Internet of things control equipment, intelligent regulation and control of environmental factors in the intelligent greenhouse can be realized, the environmental factors can be automatically regulated according to the crop growth requirements and the changes of environmental conditions, and the stability and the suitability of the crop growth environment are improved; the whole flow realizes the automation and the intellectualization of the crop growth prediction and the environment regulation, realizes the predictive regulation, reduces the regulation time lag of regulation after the data are collected in real time, reduces the subjectivity of human intervention and decision, improves the efficiency and the benefit of agricultural production, can reduce the agricultural production cost, improve the resource utilization efficiency and promote the sustainable development of agriculture through precise environment regulation and crop growth control.

The embodiment of the present specification also provides a crop growth control apparatus for intelligent greenhouse, as shown in fig. 2, the apparatus comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executable by the at least one processor to enable the at least one processor to:

Acquiring a plurality of historical environmental data corresponding to each environmental factor of a specified intelligent greenhouse, and determining a plurality of big-data environmental factor prediction models corresponding to each environmental factor according to the plurality of historical environmental data corresponding to each environmental factor, wherein the environmental factors comprise temperature factors, humidity factors, illumination factors and gas factors; predicting a plurality of environmental factors of the specified intelligent greenhouse in a preset prediction period through the big data environmental factor prediction model, and determining initial environmental prediction data corresponding to each environmental factor in the prediction period; optimizing initial environmental prediction data corresponding to each environmental factor based on pre-acquired weather early warning information, and determining current environmental prediction data corresponding to each environmental factor; predicting the crop growth condition in the prediction period through the current crop information and the current environment prediction data corresponding to the appointed intelligent greenhouse, and determining the crop growth prediction information in the prediction period; according to the current environment prediction data corresponding to each environmental factor and the crop growth prediction information in the prediction period, generating an equipment control scheme of at least one Internet of things control equipment in the prediction period, and regulating and controlling at least one environmental factor of the appointed intelligent greenhouse through the equipment control scheme to control the crop growth, wherein the Internet of things control equipment comprises temperature control equipment, humidity regulation equipment, illumination regulation equipment and gas regulation equipment.

The present specification embodiments also provide a non-volatile computer storage medium storing computer-executable instructions configured to:

In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for apparatus, devices, non-volatile computer storage medium embodiments, the description is relatively simple, as it is substantially similar to method embodiments, with reference to the section of the method embodiments being relevant.

The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

The devices and media provided in the embodiments of the present disclosure are in one-to-one correspondence with the methods, so that the devices and media also have similar beneficial technical effects as the corresponding methods, and since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media are not repeated here.

It will be appreciated by those skilled in the art that embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the present specification may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present description can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present description is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the specification. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.

The foregoing is merely one or more embodiments of the present description and is not intended to limit the present description. Various modifications and alterations to one or more embodiments of this description will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, or the like, which is within the spirit and principles of one or more embodiments of the present description, is intended to be included within the scope of the claims of the present description.

Claims

1. A crop growth control method for intelligent greenhouses, the method comprising:

Acquiring a plurality of historical environmental data corresponding to each environmental factor of a specified intelligent greenhouse, and determining a plurality of big data environmental factor prediction models corresponding to each environmental factor according to the plurality of historical environmental data corresponding to each environmental factor, wherein the environmental factors comprise temperature factors, humidity factors, illumination factors and gas factors;

Predicting a plurality of environmental factors of the specified intelligent greenhouse in a preset prediction period through the big data environmental factor prediction model, and determining initial environmental prediction data corresponding to each environmental factor in the prediction period;

Optimizing initial environmental prediction data corresponding to each environmental factor based on pre-acquired weather early warning information, and determining current environmental prediction data corresponding to each environmental factor;

Predicting the crop growth condition in the prediction period through the current crop information and the current environment prediction data corresponding to the appointed intelligent greenhouse, and determining the crop growth prediction information in the prediction period;

Generating an equipment control scheme of at least one Internet of things control equipment in the prediction period according to the current environment prediction data corresponding to each environment factor and the crop growth prediction information in the prediction period, and regulating and controlling at least one environment factor of the appointed intelligent greenhouse through the equipment control scheme so as to control the crop growth, wherein the Internet of things control equipment comprises temperature control equipment, humidity regulation equipment, illumination regulation equipment and gas regulation equipment.

2. The crop growth control method for intelligent greenhouses according to claim 1, wherein determining a plurality of big-data environmental factor prediction models corresponding to each environmental factor according to a plurality of historical environmental data corresponding to each environmental factor, specifically comprises:

determining acquisition time information of each historical environmental data, and constructing an environmental data change sequence corresponding to each environmental factor according to each historical environmental data;

Determining a time segmentation interval of each environmental factor based on an environmental data change sequence corresponding to each environmental factor, splitting the plurality of historical environmental data corresponding to each environmental factor according to the time segmentation time and acquisition time information of each historical environmental data, and determining a plurality of historical environmental data subsets corresponding to each environmental factor;

And constructing a big data model through each historical environment data subset so as to determine a big data environment factor prediction model of each time segmentation interval corresponding to each environment factor.

3. The crop growth control method for intelligent greenhouses according to claim 2, wherein the prediction of the environmental factors of the designated intelligent greenhouses in a preset prediction period is performed by the big-data environmental factor prediction model, and the determination of the initial environmental prediction data corresponding to each environmental factor in the prediction period specifically comprises:

determining time information to be predicted, so as to determine a prediction period of each environmental factor based on the time information to be predicted and the time segmentation interval of each environmental factor;

Matching a plurality of big data environmental factor prediction models through each prediction period of the environmental factors to determine a current big data environmental factor prediction model corresponding to the prediction period;

And predicting the environmental factors according to the current big data environmental factor prediction model corresponding to each environmental factor, and generating initial environmental prediction data corresponding to each environmental factor in the prediction period.

4. The crop growth control method for intelligent greenhouses according to claim 1, wherein the optimizing the initial environmental prediction data corresponding to each environmental factor based on the weather pre-warning information obtained in advance, determining the current environmental prediction data corresponding to each environmental factor specifically comprises:

Acquiring the weather early warning information, wherein the weather early warning information comprises an early warning type and an early warning level;

determining at least one environmental influence factor influenced by weather early warning according to the early warning type of the weather early warning information, and determining the environmental influence quantity of each environmental influence factor according to the early warning level;

And optimizing initial environmental prediction data corresponding to each environmental factor based on the environmental impact quantity affecting the environmental factor, and determining current environmental prediction data corresponding to each environmental factor.

5. The crop growth control method for intelligent greenhouses according to claim 1, wherein the predicting the crop growth condition in the prediction period by previously acquiring the current crop information and the current environment prediction data corresponding to the designated intelligent greenhouses, and determining the crop growth prediction information in the prediction period specifically comprises:

Acquiring current crop information corresponding to the specified intelligent greenhouse, wherein the current crop information comprises current crop variety information and current crop state information;

Predicting the crop growth condition in the prediction period according to the current crop information by a regression prediction technology, and determining first crop growth prediction information in the prediction period;

Predicting the crop growth condition in the prediction period according to the current environment prediction data and the current crop state information, and determining second crop growth prediction information in the prediction period;

Crop growth prediction information within the prediction period is determined based on the first crop growth prediction information and the second crop growth prediction information.

6. The crop growth control method for intelligent greenhouses according to claim 1, wherein the device control scheme of at least one internet of things control device in the prediction period is generated according to the current environmental prediction data corresponding to each environmental factor and the crop growth prediction information in the prediction period, and specifically comprises:

determining expected crop growth information in the prediction period, so as to determine crop growth information to be adjusted according to the expected crop growth information and the predicted crop growth information in the prediction period;

Determining an environment adjustment strategy based on the crop growth information to be adjusted and the current environment prediction data, wherein the environment adjustment strategy comprises a plurality of environment factors to be adjusted and adjustment values of each environment factor to be adjusted;

and generating a device control scheme of at least one Internet of things control device in the prediction period according to the environment adjustment strategy.

7. The crop growth control method for intelligent greenhouses according to claim 1, wherein the device control scheme of at least one internet of things control device in the prediction period is generated according to the current environmental prediction data corresponding to each environmental factor and the crop growth prediction information in the prediction period, and specifically comprises:

Determining expected crop growth information in the prediction period, and when the expected crop growth information is different from the expected crop growth information, matching in a preset expert database according to the expected crop growth information to determine expected environmental data;

determining an environment adjustment strategy based on the expected environment data and the current environment prediction data, wherein the environment adjustment strategy comprises a plurality of environment factors to be adjusted and adjustment values of each environment factor to be adjusted;

8. A crop growth control method for intelligent greenhouses according to claim 1, characterized by regulating at least one environmental factor of the designated intelligent greenhouse by the plant control scheme to control crop growth, comprising in particular:

Determining theoretical environmental data of each environmental factor after environmental adjustment according to a pre-acquired environmental adjustment strategy;

And acquiring real-time environment data of each environment factor, determining an environment data adjustment item based on the real-time environment data and the theoretical environment data, adjusting the equipment control scheme based on the environment data adjustment item, generating a real-time equipment control scheme, and controlling crop growth.

9. A crop growth control apparatus for intelligent greenhouses, the apparatus comprising:

at least one processor; and

A memory communicatively coupled to the at least one processor; wherein,

10. A non-transitory computer storage medium storing computer-executable instructions, the computer-executable instructions configured to: