CN114331753A

CN114331753A - Intelligent farm work method and device and control equipment

Info

Publication number: CN114331753A
Application number: CN202210205255.6A
Authority: CN
Inventors: 张梦婷; 郝汉杰; 高婷; 郭婷婷; 陈强
Original assignee: Alibaba Damo Institute Hangzhou Technology Co Ltd
Current assignee: Alibaba Damo Institute Hangzhou Technology Co Ltd
Priority date: 2022-03-04
Filing date: 2022-03-04
Publication date: 2022-04-12
Anticipated expiration: 2042-03-04
Also published as: CN114331753B

Abstract

The method comprises the steps of acquiring real-time monitoring data of a target land block in the current growing season of planted crops based on a yield estimation request in the growing season of the crops, acquiring corresponding historical monitoring data in a time interval uncovered by the real-time monitoring data, estimating the yield of the target land block in the current growing season according to the real-time monitoring data, the historical monitoring data and a yield estimation model of the target land block, and dynamically estimating the yield of the target land block in real time in the whole growing season; and issuing a first farming task for the target plot according to the estimated yield of the target plot in the current growing season, the historical yield information of the crops, the real-time monitoring data and the agricultural knowledge map information, so that when the estimated yield is low, farming operation can be performed on the target plot with the estimated yield in time, and the crop yield of the target plot can be greatly improved.

Description

Intelligent farm work method and device and control equipment

Technical Field

The application relates to the technical field of farm work intellectualization, in particular to a method, a device and control equipment for farm work intellectualization.

Background

Crop yield assessment has been an important scientific problem in agricultural science research. In the crop yield estimation method, a crop model based on the mechanism processes of crop photosynthesis, respiration, transpiration, nutrition and the like can accurately simulate the continuous evolution of a crop object in time and space by means of the inherent physical process and the dynamic mechanism, can accurately simulate the growth and development conditions and the yield of a single-point crop, and is one of the methods commonly used by agricultural research experts.

With the development of agricultural technologies, the farming operation is more and more intelligent. In the current agricultural intelligent platform, a crop yield estimation method based on a crop model adopts a mode of manual single-point sampling to obtain sampling point data, and performs crop yield estimation of a single sampling point based on the sampling point data. However, when the crop yield estimation method based on the crop model is applied to the crop yield estimation of large spatial regional scales (such as county, city, and even larger regional ranges), due to the heterogeneity of the surface and near-surface environments, the acquisition of some macroscopic data and the regionalization of parameters in the crop model are very difficult, the sampling time is long, the sampling and yield estimation are usually performed once when the crop is close to the mature period, the crop yield estimation cannot be performed dynamically in the whole growth period of the crop, and the crop yield estimation is not favorable for improving the crop yield; in addition, when the estimated yield is low, the reason of the estimated yield is low through manual analysis and the farming task is manually adjusted, so that the intelligent degree is low.

Disclosure of Invention

The application provides a method and a device for intellectualization of farming and control equipment.

In one aspect, the present application provides a method for farm intelligence, comprising:

responding to a yield estimation request of a target plot, and acquiring real-time monitoring data of the target plot in the current growing season of the planted crops and historical monitoring data corresponding to a time interval of the current growing season, which is not covered by the real-time monitoring data;

determining the estimated yield of the target plot in the current growing season according to the real-time monitoring data, the historical monitoring data and the estimated yield model of the target plot;

and issuing a first farming task for the target plot according to the estimated yield of the target plot in the current growing season, the historical yield information of the crops, the real-time monitoring data and the agricultural knowledge map information.

In another aspect, the present application provides a farm-oriented intelligent device, including:

the data acquisition module is used for responding to a yield estimation request of a target plot, acquiring real-time monitoring data of the target plot in the current growing season of the planted crops and historical monitoring data corresponding to a time interval of the current growing season, which is not covered by the real-time monitoring data;

the crop yield estimation module is used for determining the estimated yield of the target plot in the current growing season according to the real-time monitoring data, the historical monitoring data and the yield estimation model of the target plot;

and the farming processing module is used for issuing a first farming task for the target plot according to the estimated yield of the target plot in the current growing season, the historical yield information of the crops, the real-time monitoring data and the agricultural knowledge map information.

On the other hand, this application provides a farming intellectuality's controlgear, includes: a processor, and a memory communicatively coupled to the processor;

the memory stores computer-executable instructions;

the processor executes the computer execution instructions stored in the memory to realize the farming intelligence method.

According to the method, the device and the control equipment for the intellectualization of the farming, real-time monitoring data of a target land block to be estimated in the current growing season of the planted crop is obtained based on an estimation request at any time in one growing season of the crop, corresponding historical monitoring data is obtained for a time interval uncovered by the real-time monitoring data, the real-time monitoring data and the historical monitoring data cover the whole growing season of the crop, the estimation yield of the target land block in the current growing season is determined by estimating the crop according to the real-time monitoring data, the historical monitoring data and an estimation model of the target land block, and the crop estimation can be dynamically carried out in real time in the whole growing season; and issuing a first farming task for the target plot according to the estimated yield of the target plot in the current growing season, the historical yield information of the crops, the real-time monitoring data and the agricultural knowledge map information, and carrying out farming operation on the target plot with the estimated yield being low in time when the estimated yield is low, so that the crop yield of the target plot can be greatly improved.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.

FIG. 1 is an exemplary architecture of a farming intelligence system provided herein;

FIG. 2 is an exemplary framework diagram of a farming intelligence system provided herein;

FIG. 3 is a flowchart of a method for providing farm intelligence in accordance with an embodiment of the present application;

FIG. 4 is a flow chart of a method for crop yield assessment according to another embodiment of the present application;

FIG. 5 is a flowchart of a method for providing intelligent farming activities according to another embodiment of the present application;

FIG. 6 is a flow chart of another method for farm intelligence provided in accordance with another embodiment of the present application;

FIG. 7 is a flowchart of a method for providing intelligent farming activities according to another embodiment of the present application;

fig. 8 is a schematic structural diagram of a farm-oriented intelligent device according to an embodiment of the present application.

With the above figures, there are shown specific embodiments of the present application, which will be described in more detail below. These drawings and written description are not intended to limit the scope of the inventive concepts in any manner, but rather to illustrate the inventive concepts to those skilled in the art by reference to specific embodiments.

Detailed Description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

The terms referred to in this application are explained first:

circle drawing of the land blocks: through the function provided by the platform, the vector layer circling process can be carried out on the map so as to finish the circling of the analysis area.

The Internet of things: the intelligent sensing, identifying and managing system is characterized in that any object or process needing monitoring, connection and interaction is collected in real time through various devices and technologies such as various information sensors, radio frequency identification technologies, global positioning systems, infrared sensors, laser scanners and the like, various needed information such as sound, light, heat, electricity, mechanics, chemistry, biology, positions and the like is collected, and the ubiquitous connection of objects, objects and people is realized through various possible network accesses, so that the intelligent sensing, identifying and managing of the objects and the processes are realized.

Knowledge graph: the knowledge graph is a modern theory which achieves the aim of multi-discipline fusion by combining theories and methods of applying subjects such as mathematics, graphics, information visualization technology, information science and the like with methods such as metrology introduction analysis, co-occurrence analysis and the like and utilizing a visualized graph to vividly display the core structure, development history, frontier field and overall knowledge framework of the subjects.

Remote sensing vegetation index: according to the spectral characteristics of the vegetation, the visible light and the near infrared wave bands of the satellite are combined to form various vegetation indexes. Common vegetation indices such as normalized vegetation index (NDVI), Enhanced Vegetation Index (EVI), greenness index (GDVI), environmentally optimized vegetation index (HJVI), and the like.

Wherein the normalized vegetation index (NDVI) is:

。

the Enhanced Vegetation Index (EVI) is:

。

greenness index (GDVI) is:

the environmentally optimized vegetation index (HJVI) is:

。

in the above formula, the first and second carbon atoms are,

、

、

、

and the earth surface reflectivity information of blue light, green light, red light and near infrared of the remote sensing data sensor respectively.

Furthermore, the terms "first," "second," "third," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicit to a number of indicated technical features. In the description of the following examples, "plurality" means two or more unless specifically limited otherwise.

With the development of agricultural technologies, the farming operation is more and more intelligent. In the current agricultural intelligent platform, a crop yield estimation method based on a crop model adopts a mode of manual single-point sampling to obtain sampling point data, and performs crop yield estimation of a single sampling point based on the sampling point data. However, when the crop yield estimation method based on the crop model is applied to the crop yield estimation of large spatial regional scales (such as county, city, and even larger regional ranges), due to the non-uniformity of the surface and near-surface environments, the acquisition of some macroscopic data and the parameter localization in the crop model are very difficult, the sampling time is long, the crop yield estimation can not be performed dynamically in the whole growth period of the crop because one-time sampling and yield estimation are usually performed when the crop is close to the maturity period, and the improvement of the crop yield is not facilitated. In addition, when the estimated yield is low, the reason of the estimated yield is low through manual analysis and the farming task is manually adjusted, so that the intelligent degree is low.

The application provides a farm-oriented intelligent method, which can be applied to a farm-oriented intelligent system, and fig. 1 shows an example architecture of the farm-oriented intelligent system, and as shown in fig. 1, the farm-oriented intelligent system comprises a data monitoring device 11, a farm-oriented intelligent control device 12 and a farm task execution device 13. The data monitoring device 11 is used for collecting monitoring data in real time. The intelligent farm control device 12 is in communication connection with the data monitoring device 11, and can acquire real-time monitoring data from the data monitoring device 11. The farm-oriented intelligent control device 12 is in communication connection with the farm-oriented task execution device 13, and can issue a farm-oriented task to the farm-oriented task execution device 13, and the farm-oriented task execution device 13 is used for executing the farm-oriented task. The farm-oriented intelligent control device 12 is used for executing the farm-oriented intelligent method provided by the application, and based on real-time monitoring data of the target plot in the current growing season of the planted crops and historical monitoring data corresponding to a time interval of the current growing season which is not covered by the real-time monitoring data, the estimated yield of the target plot in the current growing season is determined by using an estimated yield model; and according to the estimated yield of the target plot in the current growing season and the historical yield information of the crops, if the estimated yield is determined to meet the low-yield condition, generating a first farming task for the target plot according to the real-time monitoring data and the agricultural knowledge map information, and issuing the first farming task for the target plot to the farming task execution equipment 13.

Illustratively, the data monitoring device 11 may include an internet of things environment sensing device, and may be configured to visually monitor real-time weather data such as temperature, humidity, wind speed, wind direction, illuminance, rainfall, carbon dioxide, atmospheric pressure, and real-time soil data such as soil moisture, nutrients, fertility, and soil temperature and humidity. In addition, the farm intelligent control device 12 can also obtain weather forecast data publicly released by the weather bureau, such as temperature, precipitation, relative humidity, weather phenomenon, wind speed and direction), disaster forecast, and the like. The farm-oriented intelligent control device 12 can also obtain a short-term weather forecast extrapolated from a short-term radar, and the like.

Illustratively, the data monitoring device 11 may include a multisource satellite capable of acquiring telemetry data from the multisource satellite, including: high-resolution satellite data, high-view satellite data, sentinel satellite data, Landsat (united states terrestrial satellite) data, and the like.

Illustratively, fig. 2 provides an exemplary framework diagram of a farm intelligence system, and as shown in fig. 2, the data sources obtained by the farm intelligence system based on the multi-source data monitoring device include: the system comprises the monitoring data of the Internet of things, remote sensing image data, meteorological data, other data and the like. The monitoring data of the internet of things can be acquired through a small-sized meteorological station, a soil moisture sensor, water quality detection equipment, insect pest situation monitoring equipment, a camera and the like. The image data includes satellite data, unmanned aerial vehicle data, and the like. The meteorological data includes pattern forecast, temporary forecast, disaster warning, and the like.

The data communication is carried out among different devices of the farm intelligent system through networks, and the communication modes are various, such as an edge computing gateway, a 3G/4G/5G network, a LoRa network, a Wi-Fi network, an NB-IoT network, Bluetooth (Bluetooth) and the like.

As shown in fig. 2, the digital agriculture engine for implementing farm intelligence based on data sources may include at least one of the following functions: the system comprises a remote sensing intelligent monitoring platform, an agricultural meteorological disaster early warning platform, an intelligent Internet of things management platform and a space-time position information service platform. The remote sensing intelligent monitoring platform mainly realizes the functions of land parcel identification, crop identification, growth monitoring, yield estimation and the like based on remote sensing data. The agricultural meteorological disaster early warning platform mainly achieves the functions of accurate meteorological service, forecast of phenological period, early warning of disaster forecast, early warning of plant diseases and insect pests and the like. The intelligent Internet of things management platform mainly achieves the functions of equipment management, equipment control, data recovery, data monitoring and control and the like. The space-time position information service platform mainly realizes the functions of agricultural machinery management, positioning supervision, path regulation, command scheduling and the like.

As shown in fig. 2, the farm intelligent system further includes an agricultural knowledge graph engine, which implements a farm task adjustment function based on agricultural knowledge graph information. The agricultural knowledge map information can comprise a regional germplasm resource map, a plant nutrition management map, a phenological period and farming operation map, a pest control map, a disaster risk monitoring map, an agricultural resource map and the like. The regional germplasm resource map contains information of types, variety advantageous regions, variety characteristics and the like of different crop varieties. The plant nutrition management map comprises information such as fertilizer types, ingredient ratios and fertilizer use amounts required by different crop growth. The phenological period and farming operation map comprises information such as crop phenological period monitoring, farming operation types, farming operation standards (such as execution conditions) and the like. The pest control map includes information on types of pests, occurrence periods of different types of pests, control measures, and the like. The disaster risk monitoring map comprises information such as disaster types, disaster occurrence periods and prevention measures. The agricultural resource map comprises information of climate resources, soil resources and other resources.

As shown in fig. 2, the farm-oriented intelligent system can provide a plurality of intelligent services to the outside, including farm decision intelligent question answering, farm early warning pushing and the like, wherein the farm decision intelligent question answering relates to knowledge question answering in various aspects such as intelligent water and fertilizer management, growing season farm management, pest control and the like. The farm work early warning pushing can push pushing of information in various aspects such as meteorological disasters, plant diseases and insect pests, real-time monitoring data and the like.

In addition, as shown in fig. 2, the farm intelligent system may provide one or more farm intelligent functions in the forms of a farm SAAS (Software as a Service), APP/H5 push, open API, and the like.

The farming intelligent system shown in fig. 2 can be applied to a plurality of application scenarios such as field planting, digital orchard, facility agriculture and the like.

The method for intellectualization of farming provided by the application can be used for acquiring real-time monitoring data in the current growing season of planted crops in real time according to yield estimation requests of users on the target plots in the current growing season of the planted crops, historical monitoring data are used for acquiring complete monitoring data of the current growing season for a time interval of the current growing season which cannot be covered by the real-time monitoring data, and based on the complete monitoring data of the current growing season and a yield estimation model, the yield estimation of the crops is realized; furthermore, based on the currently obtained estimated yield and the historical yield information of the crops, when the estimated yield is determined to meet the low yield condition, a first farming task for the target plot is issued according to the real-time monitoring data and the agricultural knowledge map information, the crop yield is improved by adjusting the farming task in time, and the method is more intelligent and can obviously improve the crop yield.

The following describes the technical solutions of the present application and how to solve the above technical problems with specific embodiments. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.

Fig. 3 is a flowchart of a method for farm work intelligence according to an embodiment of the present disclosure. The method for farm affair intellectualization provided by the embodiment can be particularly applied to farm affair intellectualized control equipment. The control device may be a mobile terminal such as a smart phone and a tablet computer, or may also be a personal computer, a server, a cloud computing device, and the like, which is not specifically limited herein.

As shown in fig. 3, the method comprises the following specific steps:

step S101, responding to a yield estimation request of a target plot, and acquiring real-time monitoring data of the target plot in the current growing season of planted crops and historical monitoring data corresponding to a time interval of the current growing season uncovered by the real-time monitoring data.

The target land parcel can be any land parcel in a preset area range. One plot refers to a region for planting the same crop, and may be a region in a farm, or a region in a county, a city, or even a larger regional area.

The farm-oriented intelligent system can be used for intelligently managing one or more plots within a preset area range, the plots can be set and adjusted by a user according to the actual planting scene of crops, and information such as the size, the shape and the type of the planted crops of a target plot is not specifically limited. The preset area range refers to the maximum area range which can be managed by the farm intelligent system and can be set and adjusted according to actual application scenes.

In this embodiment, for any target plot, in the current growing season of the crop planted in the target plot, the control device for intelligent farming may automatically obtain real-time monitoring data of the target plot in the current growing season based on the yield estimation request of the user for the target plot, and may obtain corresponding historical monitoring data for the time interval of the current growing season not covered by the real-time monitoring data. The real-time monitoring data and the historical monitoring data cover the whole growing season of the crop.

The data acquisition frequency of the real-time monitoring data and the historical monitoring data can be acquired once a day, once every two days, once every several hours and the like, and can be set and adjusted according to the actual scene needs, and the frequency is not specifically limited here.

For example, the data collection frequency may be once per day, i.e., the real-time monitoring data and the historical monitoring data are day-by-day monitoring data.

Illustratively, for example, a user submits a yield assessment request for a target plot on day 1 of a grouting period of a crop, the control device for farm intelligence obtains real-time monitoring data from the beginning of the planting time of the crop to day 1 of the grouting period (if the real-time monitoring data for the current day has not been generated, the real-time monitoring data is obtained by the day 1 before the grouting period), and for a time interval from the beginning of day 2 of the grouting period (if the real-time monitoring data for the current day has not been generated, the day 1 of the grouting period) to the expected maturity time of the crop, obtains historical monitoring data from day 2 of the grouting period of the crop to the same period as the maturity time of the crop in a historical growing season in which the target plot is planted with the same type of crop.

The obtained real-time monitoring data and historical monitoring data are used for crop yield estimation and farm work adjustment, and can comprise various types of data such as meteorological data, remote sensing data and the like.

And S102, determining the estimated yield of the target plot in the current growing season according to the real-time monitoring data, the historical monitoring data and the estimated yield model of the target plot.

After the real-time monitoring data of the target plot in the current growing season of the planted crops and the historical monitoring data corresponding to the time interval of the current growing season which is not covered by the real-time monitoring data are obtained, the growth information of the crops planted in the target plot, the meteorological information of the target plot and the like can be analyzed according to the real-time monitoring data and the historical monitoring data, the pre-established estimated yield model of the target plot is combined for estimating the yield of the crops, and the estimated yield of the target plot in the current growing season is determined.

And S103, issuing a first farming task for the target plot according to the estimated yield of the target plot in the current growing season, the historical yield information of crops, the real-time monitoring data and the agricultural knowledge map information.

After the crop estimation is carried out to determine the estimated yield of the target plot in the current growing season, whether the current estimated yield is low or not can be analyzed and judged according to the current estimated yield and the historical yield information of the crop; and if the current estimated yield is low, determining that the estimated yield meets a low-yield condition, analyzing the reason causing the low yield of the target plot according to the real-time monitoring data, and generating and issuing a first farming task for the target plot according to the agricultural knowledge map information aiming at the reason causing the low yield of the target plot so as to improve the crop yield of the target plot by executing the first farming task for the target plot.

In addition, when the estimated yield is normal or higher, the reason for the higher estimated yield of the target plot can be analyzed according to the real-time monitoring data, and other farming tasks for the target plot are generated and issued, so that the crop yield of the target plot is further improved by executing the farming tasks for the target plot.

The low-yield condition may be set and adjusted according to an actual application scenario, and is not specifically limited herein.

Alternatively, the low yield condition may be an average of the predicted yields below the historical yield of the same type of crop planted in the target plot.

Alternatively, the low yield condition may be that the predicted yield is lower than the average of the historical yields of the same kind of crops planted in the target plot, and the difference between the predicted yield and the average of the historical yields of the same kind of crops planted in the target plot is greater than a preset threshold. The preset threshold value can also be set and adjusted according to the actual application scene.

The agricultural knowledge map information is a knowledge map constructed based on a knowledge base in the agricultural field, covers the adaptation area of the known crops, and information such as pest control, illumination, soil, moisture and the like, and relevant knowledge such as conditions, opportunities and the like for carrying out various agricultural tasks, supports the inquiry function of the agricultural knowledge, and can guide agricultural production by using the existing knowledge.

Illustratively, the agricultural knowledge base map information may include a regional germplasm resource map, a plant nutrition management map, a phenological period and farming operation map, a pest control map, a disaster risk monitoring map, an agricultural resource map, and the like. The regional germplasm resource map contains information of types, variety advantageous regions, variety characteristics and the like of different crop varieties. The plant nutrition management map comprises information such as fertilizer types, ingredient ratios and fertilizer use amounts required by different crop growth. The phenological period and farming operation map comprises information such as crop phenological period monitoring, farming operation types, farming operation standards (such as execution conditions) and the like. The pest control map includes information on types of pests, occurrence periods of different types of pests, control measures, and the like. The disaster risk monitoring map comprises information such as disaster types, disaster occurrence periods and prevention measures. The agricultural resource map comprises information of climate resources, soil resources and other resources.

In the step, the reason causing the low yield of the target plot is analyzed based on the real-time monitoring data, the agricultural knowledge map information is inquired according to the reason causing the low yield of the target plot, the farming tasks which need to be executed for improving the yield of the target plot aiming at the reason causing the low yield of the target plot are obtained, the first farming tasks for the target plot are issued, and the crop yield of the target plot is improved by executing the first farming tasks for the target plot.

In the embodiment, real-time monitoring data of a target land block to be estimated in the current growing season of planted crops are obtained at any time in one growing season of the crops based on an estimation request, corresponding historical monitoring data are obtained for a time interval uncovered by the real-time monitoring data, the real-time monitoring data and the historical monitoring data cover the whole growing season of the crops, and the estimation of the crops is carried out according to the real-time monitoring data, the historical monitoring data and an estimation model of the target land block to determine the estimation yield of the target land block in the current growing season, so that the estimation of the crops can be dynamically carried out in real time in the whole growing season; and issuing a first farming task for the target plot according to the estimated yield of the target plot in the current growing season, the historical yield information of the crops, the real-time monitoring data and the agricultural knowledge map information, so that when the estimated yield is low, farming operation can be performed on the target plot with the estimated yield in time, and the crop yield of the target plot can be greatly improved.

Fig. 4 is a flowchart of a method for crop yield assessment according to another embodiment of the present application. On the basis of the embodiment of the method corresponding to fig. 3, in this embodiment, the real-time monitoring data includes weather live data, weather forecast data, and real-time remote sensing data, and the historical monitoring data includes historical weather data and historical remote sensing data, and the estimated yield of the target plot in the current growing season is determined by combining the weather data and the remote sensing data and using the yield estimation model of the target plot, so as to realize the dynamic crop yield estimation of the target plot. By utilizing the advantages of continuous space and dynamic time change of satellite remote sensing data, the problem that monitoring data is expanded from point (single-point sampling data) to point (single-point estimation) to surface (continuous space monitoring data) and surface (large-area field crop estimation) can be effectively solved, and the spatial continuity of a crop estimation model is improved. The meteorological data also has spatial continuity and time continuity, and the yield advance prediction and dynamic prediction can be completed by utilizing the predictable characteristics of the meteorological data.

The crop yield estimation method provided by the embodiment is a sub-processing flow of the intelligent farm affairs method. As shown in fig. 4, the specific steps of crop yield estimation are as follows:

step S201, in response to the request for estimating production of the target parcel, obtaining parcel information of the target parcel.

In this embodiment, the plot information of each plot is preset and stored, wherein each plot is used for planting a crop. The plot information in the system may change with the re-planting of the crop at different times.

The plot information may include crop planting parameter information and an area range corresponding to the plot.

The crop planting parameter information includes at least one of: crop species, crop variety, seeding time, planting density, planting area.

Step S202, acquiring real-time monitoring data of a target plot in the current growing season of the planted crops and historical monitoring data corresponding to a time interval of the current growing season, which is not covered by the real-time monitoring data, according to the plot information of the target plot; the real-time monitoring data comprises live meteorological data, meteorological forecast data and real-time remote sensing data, and the historical monitoring data comprises historical meteorological data and historical remote sensing data.

In this embodiment, the collected monitoring data includes meteorological data and remote sensing data, and the meteorological data and the remote sensing data both have spatial continuity and temporal continuity.

Because the monitoring data has spatial continuity and time continuity, after the land parcel information of the target land parcel to be estimated is obtained, the real-time monitoring data in the area range corresponding to the target land parcel and with the monitoring time in the current growing season can be obtained according to the land parcel information of the target land parcel, and the real-time monitoring data of the target land parcel in the current growing season of the planted crops can be obtained.

And for the time interval which is not covered by the real-time monitoring data, acquiring the synchronous historical monitoring data of the same time interval in the historical growth season of the same kind of crops planted in the previous target plot, wherein the real-time monitoring data and the historical monitoring data can cover the whole growth season of the crops.

The collected real-time monitoring data comprises real weather data, weather forecast data and real-time remote sensing data, because the recent weather forecast data is closer to the real weather data of the current year compared with the historical weather data of the same period in the previous year. And for the time interval not covered by the weather live data and the weather forecast data, acquiring the historical weather data in the same period, and improving the accuracy of monitoring data so as to improve the precision of crop yield estimation.

Optionally, the farm-oriented intelligent control device may obtain weather-related live data such as temperature, humidity, wind speed, wind direction, illuminance, rainfall, carbon dioxide, atmospheric pressure and the like from the internet-of-things environment sensing device; weather forecast data published by the weather bureau can also be acquired, and the data comprises the following data: temperature, precipitation, relative humidity, weather phenomena, wind speed, wind direction, disaster forecast, etc. In addition, an imminent weather forecast extrapolated from an imminent radar can also be acquired.

Optionally, the farm affair intelligent control device can also obtain soil condition data of soil moisture, nutrients, fertility, soil temperature and humidity from the internet of things environment sensing device, and the soil condition data is used for analyzing the reason of low yield and/or the reason of poor crop growth and evaluating the execution effect of the farm affair task.

Optionally, the farm intelligent control device may further obtain remote sensing data of the multi-source satellite, and specifically may include at least one of the following: high-branch satellite data, high-view satellite data, sentinel satellite data, Landsat (United states terrestrial satellite) data, and the like.

Optionally, the farm intelligent control device may also obtain historical climate data, such as historical 30-year climate data, mainly for obtaining historical climate data at the site level, when needed. The climate data elements include: average temperature, highest temperature, lowest temperature, effective accumulated temperature, accumulated precipitation, wind speed, sunshine hours, relative humidity, relative soil water content and the like.

Optionally, the farm-oriented intelligent control device may acquire and store real-time monitoring data, may generate a monitoring index trend graph of the current growth season for each acquired monitoring index, and supports display of the monitoring index trend graph for the user to view.

In addition, any one of real-time monitoring data, plot information and the like acquired by the control equipment for intelligent farm affairs supports the functions of displaying and checking data.

Through the steps S201-S202, the real-time monitoring data of the target plot in the current growing season of the planted crops and the historical monitoring data corresponding to the time interval of the current growing season which is not covered by the real-time monitoring data are obtained in response to the yield estimation request of the target plot.

After the real-time monitoring data of the target plot in the current growing season of the planted crops and the historical monitoring data corresponding to the time interval of the current growing season uncovered by the real-time monitoring data are obtained, through the steps S203-S205, the estimated yield of the target plot in the current growing season is determined according to the real-time monitoring data, the historical monitoring data and the estimated yield model of the target plot.

And S203, determining key vegetation index factors of the target land in the current growing season according to the real-time remote sensing data and the historical remote sensing data, and determining key meteorological factors of the target land in the current growing season according to the weather live data, the weather forecast data and the historical meteorological data.

In this embodiment, the obtained monitoring data mainly includes meteorological data and remote sensing data, and the agricultural related information at the site level, including crop growth data, and the like of the target site, can be determined by analyzing the remote sensing data. The crop growth data can truly reflect the growth condition of crops, and is an important data basis for crop estimation. The vegetation index is information which can better reflect the growth condition of crops.

The meteorological data are important factors influencing the growth and the final yield of crops, the meteorological data and the remote sensing data are combined to construct a yield estimation model, the crop yield estimation is carried out, the monitoring data at different periods in the growing season are iterated in real time, the crop yield estimation can be carried out for multiple times dynamically in the growing season, and the prediction of meteorological forecast data can be utilized to advance the yield estimation time.

The key vegetation index factors and the key meteorological factors are a plurality of vegetation index factors and a plurality of meteorological factors which are determined based on a large amount of historical data and have the greatest influence on the yield of crops planted in the target plot when the estimated yield model of the target plot is constructed.

In the step, according to the real-time remote sensing data and the historical remote sensing data of the crops planted in the target plot in the current growing season, a key vegetation index factor of the target plot in the current growing season can be calculated and determined; calculating key meteorological factors of the target plot in the current growing season according to weather live data, weather forecast data and historical meteorological data of crops planted in the target plot in the current growing season; and inputting the key vegetation index factor and the key meteorological factor as important yield estimation parameters into a yield estimation model for crop yield estimation.

In addition, land data (such as planting area of the land) and crop species data can be determined according to the remote sensing data.

Alternatively, after years (or multiple growing seasons) of remote sensing data are accumulated, the growth vigor grading of the crops can be determined based on the remote sensing data of the same period in different years (or different growing seasons), and according to the growth vigor indexes of the same period in different years (or different growing seasons) of the same crops planted in the same plot, a crop growth monitoring grading map of the plot in the period is generated, so that the growth conditions of the crops between the years (or different growing seasons) can be compared.

Further, in response to a user's viewing operation of the crop growth monitoring graded map of any plot (for example, when inquiring about the crop growth situation of the same period between different ages of the plot, or by clicking a corresponding control displayed on the front-end interface, etc.), the crop growth monitoring graded map of the plot is displayed.

Optionally, for the remote sensing data of one growing season (or one year), the growth information of the crops at different time points can be determined according to the remote sensing data acquired in real time at different time points of the growing season, so as to generate a crop growth process curve.

Further, in response to a user's viewing operation of the crop growth process curve of any plot in any year (for example, when the crop growth condition of a certain year in the plot is queried, or when a corresponding control displayed on the front-end interface is clicked, etc.), the crop growth process curve of the plot in the corresponding year is displayed.

And S204, determining the estimated yield of the target land in the current growing season according to the key vegetation index factor and the key meteorological factor of the target land in the current growing season and the estimated yield model of the target land, and outputting the estimated yield of the target land in the current growing season.

After obtaining the key vegetation index factor and the key meteorological factor of the target land in the current growing season, inputting the key vegetation index factor and the key meteorological factor into a yield estimation model of the target land, and estimating the yield of crops through the yield estimation model to obtain the estimated yield of the target land in the current growing season.

In this embodiment, the yield estimation model of the target plot is established based on actual monitoring data and actual yield data of the target plot in each historical growth season of the target crop during planting of the target crop in the target plot in a preset historical time period for the first crop yield estimation in the current growth season, and the yield estimation model may be used multiple times in the current growth season subsequently to dynamically estimate the yield of the target plot based on the latest real-time monitoring data.

Optionally, after determining the estimated yield of the target plot in the current growing season, the estimated yield of the target plot in the current growing season may be output through the front-end page.

In addition, the estimated yield of any land in the current growing season can be displayed through the front-end page based on the query operation of the user.

For example, if the estimation request is the first estimation request of the target parcel in the current growing season, after the parcel information of the target parcel is acquired in step S201, before the estimated yield of the target parcel in the current growing season is determined by using the estimation model in step S204, the estimation model of the target parcel in the current growing season may be established through the following steps S205 to S209.

And S205, determining the target crop currently planted in the target plot according to the plot information of the target plot.

In this embodiment, when historical data used by the estimation model is established, related data of target crops of the same type are planted in the same target plot.

In the step, according to the plot information of the target plot, the target crop currently planted in the target plot is determined, so as to obtain historical data required for building the estimation model.

And S206, acquiring actual monitoring data and actual yield data of the target plot in each historical growth season of the target crop during the period of planting the target crop in the target plot in the preset historical time period.

The preset historical time period can be set and adjusted according to the requirements of the actual application scene. For example, the preset historical period may be a period of time of approximately 5 years, that is, historical data of approximately 5 years is obtained for building the estimated production model.

In this step, the historical data used to build the valuation model includes actual monitored data and actual yield data for a plurality of historical growing seasons in which the target crop is planted in the target plot. The actual monitoring data comprises meteorological data and crop growth related data. The weather data may include, among other things, weather data and weather-live data.

Optionally, if the farm-oriented intelligent system has a certain data accumulation, that is, the preset historical time period has corresponding real-time monitoring data, the actual monitoring data acquired in this step may be the real-time monitoring data in the historical time period, including the actual meteorological data and the actual remote sensing data.

Optionally, if the farm-oriented intelligent system does not have data accumulation, that is, there is no real-time monitoring data corresponding to the preset historical time period, the single-point sampling data in the preset historical time period obtained in this step may also determine, based on the single-point sampling data, a plurality of vegetation index factors and a plurality of meteorological factors of the target plot in each development period of the historical growth season.

Optionally, if the farm-oriented intelligent system has a small amount of data accumulation, that is, a part of time intervals in the preset historical time period have corresponding real-time monitoring data, the real-time monitoring data of the part of time intervals in the step and the single-point sampling data of other parts.

And S207, determining a vegetation index factor and a meteorological factor of the target plot in each development period of the historical growing seasons according to the actual monitoring data of each historical growing season.

Illustratively, the vegetation index factor includes at least: normalized vegetation index (NDVI), Enhanced Vegetation Index (EVI), greenness index (GDVI), environmentally optimized vegetation index (HJVI).

The meteorological factors at least include: cumulative rainfall, average temperature, maximum temperature, lowest temperature, average radiation.

In this embodiment, the vegetation index factors of different developmental stages are used as different vegetation index factors, and the meteorological factors of different developmental stages are used as different meteorological factors. The number and the type of the vegetation index factors and the number and the type of the meteorological factors can be set and adjusted according to the requirements of actual application scenes, and are not particularly limited.

Illustratively, a crop may include 5 developmental stages within one growing season as follows: seeding period, jointing period, flowering-heading period, grouting period and maturation period; 4 vegetation index factors for each development period were determined, for a total of 4 × 5=20 vegetation index factors, 5 meteorological factors for each development period were determined, for a total of 5 × 5=25 meteorological factors, and for a total of 45 influencing factors.

And S208, determining key vegetation index factors and key meteorological factors which seriously affect the yield of the target crops by adopting a principal component analysis method according to the vegetation index factors and the meteorological factors of the target plots in each development period of each historical growth season and actual yield data.

After determining the vegetation index factors and meteorological factors of the target plot in each development period of each historical growth season, establishing a statistical relationship among the yield, the meteorological factors and the vegetation index factors by combining actual yield data. And screening out the key factors which have the greatest influence on the yield by utilizing a statistical method and a principal component analysis method to obtain a plurality of key vegetation index factors and a plurality of key meteorological factors.

For example, the screened key meteorological factors may include temperature, rainfall, radiation; screened key vegetation index factor

And S209, establishing a relation model of the estimated yield, the key vegetation index factors and the key meteorological factors to obtain an estimated yield model of the target land parcel.

After the key vegetation index factor and the key meteorological factor which have the greatest influence on the yield are screened out, a relation model of the estimated yield, the key vegetation index factor and the key meteorological factor is established, and an estimated yield model of the target land parcel is obtained.

The established assessment model comprehensively considers meteorological factors and vegetation index factors, and establishes the assessment model of the key meteorological factors, the key vegetation index factors and the crop yield through the screened key meteorological factors (such as temperature, rainfall and radiation) and the key vegetation index factors.

Illustratively, the valuation model can be expressed as:

Yield=ƒ( ME_index，RS_index )

the Yield of the crops is a function of the key meteorological factor ME _ index and the key vegetation index factor RS _ index, and an equation of the Yield and the key factors (including the key meteorological factor and the key vegetation index factor) is constructed by

To build an assessment model.

In practical application, different meteorological data of different plots are different, and the growth vigor of crops reflected by vegetation index factors when different crops are planted in the same plot is different, so that when the crops are estimated, an estimated production model of a target plot in a current growing season is established based on historical data of the target plot planted with the target crop according to the target crop currently planted in the target plot. Multiple crop assessments can be performed during the current growing season using the same assessment model.

In the embodiment, during the period of planting the target crop in the target plot in the preset historical time period, the actual monitoring data and the actual yield data of the target plot in each historical growth season of the target crop are calculated, the vegetation index factor and the meteorological factor of the target plot in each development period of the historical growth season are calculated, the key vegetation index factor and the key meteorological factor which seriously affect the yield of the target crop are screened out by adopting a principal component analysis method based on the actual yield data, a relation model of the estimated yield, the key vegetation index factor and the key meteorological factor is established, the estimated yield model of the target plot is obtained, the yield model is used in the current whole growth season, the crop yield can be dynamically estimated for multiple times according to the real-time monitoring data collected in real time, the accuracy of the crop estimation can be improved, the closer to the crop maturity, the longer the time covered by the real-time monitoring data for the estimation is, the closer to the real conditions of crop growth in the current growing season, the closer to the real yield the yield estimation result is, the more accurate the yield estimation result is. On the basis, after the crops are dynamically estimated every time, according to the estimated yield and the historical yield information of the crops, when the estimated yield is determined to meet the low yield condition, a first farming task for a target plot can be issued according to real-time monitoring data and agricultural knowledge map information, the crop yield is improved by adjusting the farming task in time, and the method is more intelligent and can obviously improve the crop yield.

In an optional implementation manner, the farm intelligent control device further provides an electronic map function, and a user can circle a plot on a displayed map and input related information of the plot through the client device, so that the intelligent degree of the farm intelligent system is improved.

Illustratively, before performing crop assessment, as shown in fig. 5, the method for farm intelligence may further include the following steps:

and S301, displaying the map in the preset area range.

In this embodiment, the farm-oriented intelligent control device displays a map in a preset area range through the client, and supports a user to circle a plot on the displayed map and enter plot information.

The preset area range refers to the maximum area range which can be managed by the farm intelligent system, and can be set and adjusted according to actual application scenes.

The farm-oriented intelligent system can be used for intelligently managing one or more plots within a preset area range, the plots can be set and adjusted by a user according to the actual planting scene of crops, and information such as the size, the shape and the type of the planted crops of a target plot is not specifically limited.

One plot refers to a region for planting the same crop, and may be a region in a farm, or a region in a county, a city, or even a larger regional area.

The plot information comprises an area range corresponding to the plot and crop planting parameter information of the plot.

The crop planting parameter information of the land comprises at least one of the following items: crop species, crop variety, seeding time, planting density, planting area.

Step S302, responding to the plot circling operation on the map, taking the land in the area range defined by the plot circling operation as a plot, acquiring the input crop planting parameter information of the plot, and storing the plot information of the plot, wherein the plot information comprises the crop planting parameter information and the area range.

In this embodiment, a user can perform a parcel circling operation on a displayed map through a client, and can circle a map area on the map, the map area forms a parcel corresponding to an area on the ground, and the area on the ground corresponding to the map area is used as an area range corresponding to the parcel, so that an intelligent parcel circling function of the parcel is realized in the intelligent farming system. Further, after a parcel is defined, the user can edit parcel information of the parcel through the client, and enter or update the parcel information.

Optionally, in response to the operation of circling the parcel on the map, creating a parcel according to the area range circled by the parcel circling operation, and storing the area range corresponding to the parcel, where the area range corresponding to the parcel is the area range circled by the parcel circling operation. And acquiring the crop planting parameter information of the plot input by a user through a client, and storing the crop planting parameter information of the plot.

Optionally, the crop planting parameter information of the land can be entered by filling in a form. Illustratively, a land parcel information input interface is displayed through the client, a form to be filled in is provided on the interface, the content of the form comprises crop planting parameter information of a land parcel, and the crop planting parameter information of the land parcel is filled in through the form.

In addition, after a land parcel is created, the area range corresponding to the land parcel of the land parcel and/or the crop planting parameter information of the land parcel can be dynamically adjusted through the provided front end page.

Optionally, based on the map function, one or more agricultural production areas are also supported to be defined on the map, and one or more plots may be included in each agricultural production area. For example, the agricultural management area may be a digital agricultural production base (or a farm) that may include a plurality of plots therein.

Alternatively, based on the map function, the user may find any agricultural production area or any parcel on the displayed map by searching or moving the map, and inquire, browse, and edit the related information of any agricultural production area or any parcel through the front-end page.

Further, based on the map function, when the crop estimation is needed, the user can select any land on the displayed map to estimate the crop. The user can select any land parcel as a target land parcel to be estimated and submit an estimation request for the target land parcel.

Step S303, in response to a plot selection operation on the displayed map, determines the selected plot as a target plot.

Optionally, based on the map function, the user may find any parcel on the displayed map by searching or moving the map, and select any parcel as the target parcel to be estimated. The farming intelligent control device determines the selected parcel as a target parcel in response to a parcel selection operation on the displayed map.

And step S304, responding to the determined estimated production operation of the target plot, and determining that an estimated production request of the target plot is received.

After selecting any parcel, the user can submit a yield assessment request for the selected parcel by triggering a determined yield assessment control provided by the page. The farm-oriented intelligent control device determines that a yield estimation request for the target plot is received in response to the determination of the yield estimation operation for the target plot.

Further, responding to a yield estimation request of the target plot, acquiring real-time monitoring data of the target plot in the current growing season of the planted crops and historical monitoring data corresponding to a time interval of the current growing season, which is not covered by the real-time monitoring data, by the intelligent control equipment for the farm; and determining the estimated yield of the target plot in the current growing season according to the real-time monitoring data, the historical monitoring data and the estimated yield model of the target plot.

In an optional embodiment, after completing crop estimation once, as shown in fig. 6, according to the estimated yield of the target plot in the current growing season and the historical yield information of the crop, if it is determined that the estimated yield satisfies the low yield condition, a first farming task for the target plot is issued according to the real-time monitoring data and the agricultural knowledge map information, which may specifically be implemented by the following steps:

step S401, according to the estimated yield of the target plot in the current growing season and the historical yield information of the crops, if the estimated yield is determined to meet the low-yield condition, according to the real-time monitoring data, determining first reason information causing the low yield of the target plot in the current growing season.

After the sequential crop estimation is finished, the estimated yield of the target plot in the current growing season is determined, whether the estimated yield of the current target plot is normal or not is judged by comparing the estimated yield of the target plot in the current growing season with the historical yield information of the target crop, and whether the estimated yield is low compared with the yield in the past year or not is determined, namely whether the estimated yield meets the low-yield condition or not is determined.

In the growth process of crops, the crop diseases and insect pests, meteorological disasters and improper operation of farm works cause soil moisture content, improper nutrients and the like, which all result in the reduction of the crop yield.

When the estimated yield of the target plot in the current growing season meets the low-yield condition, judging which period is abnormal in the crop growing process through a big data analysis technology according to the real-time monitoring data, so that the estimated yield is low.

Optionally, determining, according to the real-time monitoring data, first cause information causing low yield of the target plot in the current growing season, including at least one of: determining abnormal information of the soil condition of the target plot, determining pest and disease information of the target plot, and determining weather disaster information occurring in the range of the target plot in the current growing season.

Optionally, the real-time monitoring data includes live soil data of the target plot, and according to the live soil data of the target plot, if it is determined that the live soil of the target plot is abnormal, abnormal information of the live soil of the target plot is determined.

Wherein the soil condition data may include at least one of: soil moisture content, nutrients, fertility, soil temperature and humidity and the like. According to the soil condition data of the target land, multiple soil parameters of the target land can be determined, whether each soil parameter meets the generation requirement of the current crop or not is analyzed according to the growth stages of multiple crops planted in the target land, and abnormal soil parameters which cannot meet the generation requirement of the current crop are determined, so that abnormal information of the soil condition of the target land is determined.

Further, through step S402, based on the abnormal information of the soil condition of the target plot and the agricultural knowledge map information, a farming task for adjusting the abnormal soil parameters of the soil may be generated to improve the abnormal soil parameters of the soil, so as to meet the growth needs of the crops and increase the crop yield.

For example, if it is determined that the soil of the target plot has a low content of a nutrient (e.g., nitrogen, phosphorus, potassium, etc.) based on the soil condition data of the target plot, a farming task may be generated that provides the nutrient content of the target plot, such as applying a fertilizer rich in the nutrient, spraying a nutrient solution rich in the nutrient, etc.

Optionally, the real-time monitoring data includes real-time remote sensing data of the target plot, the real-time remote sensing data is analyzed, and if it is determined that the target plot has plant diseases and insect pests, plant disease and insect pest information of the target plot is determined.

By processing the real-time remote sensing data, whether the crop planted in the target plot sends the plant diseases and insect pests or not can be identified, and information such as specific types of the plant diseases and insect pests can be identified.

Further, through step S402, based on the pest information and the agricultural knowledge map information of the target plot, a farming task for treating the pest occurring in the target plot may be generated, so as to reduce the influence of the pest on the growth of the crop and improve the crop yield.

Optionally, the real-time monitoring data includes weather live data and weather forecast data, and according to the weather live data and the weather forecast data, if it is determined that a weather disaster occurs within a range where the target land parcel is located in the current growing season, the weather disaster information occurring within the range where the target land parcel is located in the current growing season is determined.

By analyzing the weather live data and the weather forecast data, whether a weather disaster occurs in the range of the target land parcel in the current growing season or not and specific information such as the type of the weather disaster can be determined.

Further, in step S402, based on the information of the meteorological disaster and the information of the agricultural knowledge map, which occur within the range of the target plot in the current growing season, a farming task for improving the growing environment of the target plot crop in response to the meteorological disaster can be generated, so as to reduce the influence of the meteorological disaster on the crop growth and improve the crop yield.

For example, if it is determined that the target land is recently drought according to the weather live data and the weather forecast data, a farming task, such as land irrigation, for increasing the moisture content of the target land can be generated to reduce the influence of drought on the growth of crops and increase the yield of crops.

Optionally, after determining that the estimated yield meets the low-yield condition and determining first reason information causing low yield of the target plot in the current growing season according to the real-time monitoring data, farm early warning information including weather disaster information, pest and disease information, soil condition abnormal information and the like can be pushed in a preset mode.

And S402, determining a first farming task for the target plot according to the first reason information and the agricultural knowledge map information.

In the step, the reason causing the low yield of the target plot is analyzed and determined based on the real-time monitoring data, the agricultural knowledge map information is inquired according to the reason causing the low yield of the target plot, the agricultural tasks required to be executed for improving the yield of the target plot aiming at the reason causing the low yield of the target plot are obtained, the first agricultural tasks for the target plot are issued, and the crop yield of the target plot is improved by executing the first agricultural tasks for the target plot.

In this embodiment, the first farming task refers to a farming task performed on a target plot for improving crop yield when the estimated yield is low based on the crop yield estimation result.

And S403, issuing a first farming task.

After the first farming task of the target plot is automatically generated according to the first reason information and the agricultural knowledge map information, the first farming task can be automatically issued.

In practical application, the farming task can be executed only when multiple factors such as weather, soil, crops and the like meet the execution conditions of the farming task. For example, fertilization should not be performed before heavy rain, and irrigation should not be performed at too high a soil moisture (e.g., immediately after heavy rain, after a flood disaster, etc.).

Optionally, before issuing the first farming task, it is determined that the target plot satisfies the execution condition of the first farming task. The execution conditions of different farming tasks can be different, and the execution conditions of the farming tasks can be determined by inquiring the agricultural knowledge map information.

In an optional implementation manner, after the first farming task is issued, the execution effect of the first farming task can be determined according to real-time monitoring data collected in real time.

Specifically, real-time monitoring data after a first farming task is executed on a target plot is acquired; determining the execution effect information of the first farming task according to the real-time monitoring data after the first farming task is executed on the target plot; and outputting the execution effect information of the first farming task.

In practical application, crop yield estimation can be performed once at intervals (such as two weeks, one week, 20 days and the like), when the estimated yield is determined to be low according to a yield estimation result, reasons causing the estimated yield to be low are analyzed timely, and a first farming task is automatically generated and issued to improve the crop yield. The interval time between two crop estimations can be set and adjusted according to the crop species and the development period in the actual application scene, and is not particularly limited herein.

In an optional implementation mode, by the farm intelligent system, the crop growth of the target land can be monitored at any time in the current growing season, and the farm task can be timely adjusted based on the crop growth, so that the farm intelligent system is more intelligent.

Specifically, according to a preset monitoring strategy, second real-time monitoring data of the target plot in the current growing season of the planted crops can be analyzed based on the second real-time monitoring data, crop growth information of the target plot is generated when the crops grow poorly, a second farming task is automatically issued under appropriate conditions, and the growth of the crops planted in the target plot is promoted by executing the second farming task on the target plot.

As shown in fig. 7, the method for farm intelligence may further include the following steps:

step S501, in the current growing season of the crops planted in the target plot, second real-time monitoring data of the target plot in the current growing season of the crops planted in the target plot are obtained according to a preset monitoring strategy, and the second real-time monitoring data comprise second weather live data, second weather forecast data and second real-time remote sensing data.

In this embodiment, for convenience of description, real-time monitoring data for crop yield estimation and crop growth monitoring are distinguished, the second real-time monitoring data is used for real-time monitoring data for crop growth monitoring, and the first real-time monitoring data is used for real-time monitoring data for crop yield estimation.

If the first real-time monitoring data and the second real-time monitoring data are real-time monitoring data acquired at the same time and are used for crop yield estimation and crop growth monitoring, the first real-time monitoring data and the second real-time monitoring data are completely the same data.

If the first real-time monitoring data and the second real-time monitoring data are real-time monitoring data acquired at different moments, the first real-time monitoring data and the second real-time monitoring data are not identical.

The preset monitoring strategy is configured with the crop growth of the monitoring target plot and adjusts the farming task time and rule based on the crop growth. For example, according to a preset monitoring strategy, a crop growth analysis may be performed periodically, or at intervals, based on real-time monitoring data, and a farming task may be adjusted based on the crop growth.

The obtaining manner of the second real-time monitoring data is consistent with that of the first real-time monitoring data, which is specifically referred to in the above steps S201 to S202, and is not described herein again.

And S502, according to the second real-time remote sensing data, performing growth analysis on crops planted in the target plot, and determining current crop growth information of the target plot.

The obtained second real-time monitoring data comprise second real-time remote sensing data, and the agricultural related information of the plot level, including crop growth data, crop growth data and the like of the target plot, can be determined by analyzing the remote sensing data. The crop growth data can truly reflect the growth condition of crops, and is an important data basis for crop estimation.

The crop growth information may be information such as crop growth grading, crop growth index, and the like. The vegetation index is a part of the crop growth index that can better reflect the growth conditions of crops. Common vegetation indices such as normalized vegetation index (NDVI), Enhanced Vegetation Index (EVI), greenness index (GDVI), environmentally optimized vegetation index (HJVI), and the like.

In this embodiment, the remote sensing data of the land parcel is processed to determine the crop growth information of the corresponding land parcel, which can be implemented by any existing method capable of implementing similar functions, and is not described herein again.

And S503, according to the current crop growth information of the target plot, if the current crop growth information of the target plot meets the growth potential difference condition, determining second reason information causing the growth potential difference of the crops planted in the target plot according to the second real-time monitoring data.

After determining the current crop growth information of the target plot, whether the current growth of crops planted in the target plot is deviated or not can be determined by judging whether the current crop growth information of the target plot meets the growth difference condition or not.

Optionally, the growth condition may be that the growth information of the crops is greater than or equal to the corresponding growth information threshold, the growth information thresholds corresponding to different types of the crop growth information may be different, and may be set and adjusted according to an actual application scenario, which is not specifically limited herein.

Alternatively, the growth potential difference condition may be that the crop growth potential information is lower than the average value of the same-period historical growth potential information of the same type of crops planted in the target plot.

Optionally, the growth potential difference condition may be that the crop growth potential information is lower than an average value of the same-period historical growth potential information of the same type of crops planted in the target plot, and a difference value from the average value of the same-period historical growth potential information is greater than a set threshold. The set threshold value can also be set and adjusted according to the actual application scene.

In the growth process of crops, the crops have diseases and insect pests, meteorological disasters, improper operation of farm works, soil moisture content, improper nutrients and the like, and the growth vigor of the crops is poor.

In an optional embodiment, the determining, according to the second real-time monitoring data, second cause information causing a difference in growth potential of crops planted in the target block includes at least one of: determining abnormal information of the soil condition of the target plot, determining pest and disease information of the target plot, and determining weather disaster information occurring in the range of the target plot in the current growing season.

Optionally, the second real-time monitoring data includes live soil data of the target plot, and according to the live soil data of the target plot, if it is determined that the live soil of the target plot is abnormal, abnormal information of the live soil of the target plot is determined.

Optionally, the second real-time remote sensing data is analyzed, and if it is determined that the target plot has a pest, pest information of the target plot is determined.

Optionally, according to the second weather live data and the second weather forecast data, if it is determined that a weather disaster occurs within the range of the target parcel in the current growing season, determining weather disaster information occurring within the range of the target parcel in the current growing season.

And step S504, determining a second farming task for the target plot according to the second reason information and the agricultural knowledge map information.

In the step, the reason which causes the crop growth potential difference planted in the target plot is analyzed and determined based on the real-time monitoring data, the agricultural knowledge map information is inquired according to the reason of the crop growth potential difference planted in the target plot, the agricultural task which needs to be executed for improving the growth of the crops in the target plot aiming at the reason of the crop growth potential difference planted in the target plot is obtained, the second agricultural task for the target plot is issued, and the growth of the crops in the target plot is improved by executing the second agricultural task for the target plot.

In this embodiment, the second farming task refers to a farming task performed on a target plot for improving the growth of crops when it is determined that the growth of crops is poor based on the crop growth monitoring result.

And step S505, issuing a second farming task.

And after the second farming task of the target plot is automatically generated according to the second reason information and the agricultural knowledge map information, the second farming task can be automatically issued.

Optionally, before issuing the second farming task, it is determined that the target plot satisfies the execution condition of the second farming task.

In an optional implementation manner, after the second farming task is issued, the execution effect of the second farming task can be determined according to the real-time monitoring data.

Specifically, real-time monitoring data after a second farming task is executed on a target plot is acquired; determining the execution effect information of the second farming task according to the real-time monitoring data after the second farming task is executed on the target plot; and outputting the execution effect information of the second farming task.

In practical application, the crop growth condition can be monitored once at intervals in the whole growing season of crops, the reason causing the poor growth condition of the crops is analyzed in time when the poor growth condition of the crops is determined according to the crop growth condition monitoring result, and a second farming task is automatically generated and issued to improve the growth condition of the crops. The interval time between two crop growth monitoring can be set and adjusted according to the crop species and the development period of the crop in the actual application scene, and is not specifically limited here.

In an alternative embodiment, a growing season of crops planted in a target plot may include a plurality of development periods such as a seeding period, a heading period, a flowering-heading period, a filling period, a maturation period, etc., during the first development periods such as the seeding period, the heading period, etc., real-time monitoring data for crop yield estimation is short in coverage time interval, the crop yield estimation result accuracy is relatively low, crop yield estimation can be performed once at intervals from the flowering-heading period or the filling period of the crops, crop yield can be dynamically performed from the flowering-heading period or the filling period, and an agricultural task is automatically adjusted to improve and adjust the agricultural task. Furthermore, according to each estimated yield result, when the estimated yield is determined to be low, the reason causing the estimated yield to be low is timely analyzed, and the first farming task is automatically generated and issued, so that the farming task is automatically adjusted when the estimated yield is low, and the crop yield can be improved.

The crop growth monitoring can run through the whole growing season, crop growth monitoring is carried out once at intervals in the whole growing season of crops, when the poor crop growth is determined according to crop growth monitoring results, the reason causing the poor crop growth is analyzed timely, a second farming task is automatically generated and issued, the crop growth can be improved timely when the crop growth is poor, and therefore the crop yield can be improved.

Through crop yield estimation and crop growth monitoring, the risk in the planting process is traced back, a suggested farm task for guaranteeing the crop yield is output, the farm task and risk prediction are communicated, the farm task is automatically generated, farm production is better served, a crop yield estimation result and a crop growth monitoring result are used as the input of the farm task, and the crop yield can be better guaranteed through farm operation.

Fig. 8 is a schematic structural diagram of a farm-oriented intelligent device according to an embodiment of the present application. The farm-oriented intelligent device provided by the embodiment of the application can execute the processing flow provided by the method embodiment of the farm-oriented intelligent device. The intelligent device of farming affairs that this application embodiment provided is applied to intelligent controlgear of farming affairs, as shown in fig. 8, intelligent device 80 of farming affairs includes: a data acquisition module 801, a crop assessment module 802, and a farming treatment module 803.

Specifically, the data obtaining module 801 is configured to, in response to a yield estimation request for a target plot, obtain real-time monitoring data of the target plot in a current growing season of a planted crop, and historical monitoring data corresponding to a time interval of the current growing season which is not covered by the real-time monitoring data.

And a crop estimation module 802, configured to determine an estimated yield of the target plot in the current growing season according to the real-time monitoring data, the historical monitoring data, and an estimation model of the target plot.

And the farming processing module 803 is used for issuing a first farming task for the target plot according to the estimated yield of the target plot in the current growing season, the historical yield information of crops, the real-time monitoring data and the agricultural knowledge map information.

Optionally, the data obtaining module is further configured to: responding to a yield estimation request of a target plot, and acquiring plot information of the target plot; acquiring real-time monitoring data of the target plot in the current growing season of the planted crops and historical monitoring data corresponding to a time interval of the current growing season, which is not covered by the real-time monitoring data, according to the plot information of the target plot; the real-time monitoring data comprises live meteorological data, meteorological forecast data and real-time remote sensing data, and the historical monitoring data comprises historical meteorological data and historical remote sensing data.

Optionally, the data obtaining module is further configured to: determining key vegetation index factors of the target land in the current growing season according to the real-time remote sensing data and the historical remote sensing data, and determining key meteorological factors of the target land in the current growing season according to weather live data, weather forecast data and historical meteorological data; determining the estimated yield of the target land parcel in the current growing season according to the key vegetation index factor and the key meteorological factor of the target land parcel in the current growing season and the estimated yield model of the target land parcel; and outputting the estimated yield of the target plot in the current growing season.

Optionally, the farm intelligence device may further include:

an assessment model building module for: determining a target crop currently planted in the target plot according to the plot information of the target plot; acquiring actual monitoring data and actual yield data of a target plot in each historical growth season of the target crop during the period of planting the target crop in the target plot within a preset historical time period, wherein the actual monitoring data comprises actual meteorological data and actual remote sensing data; determining vegetation index factors and meteorological factors of the target plot in each development period of the historical growth seasons according to actual monitoring data of each historical growth season; determining key vegetation index factors and key meteorological factors which seriously affect the yield of target crops by adopting a principal component analysis method according to the vegetation index factors and meteorological factors of the target plots in each development period of each historical growth season and actual yield data; and establishing a relation model of the estimated yield, the key vegetation index factors and the key meteorological factors to obtain an estimated yield model of the target land parcel.

Optionally, the farm intelligence device may further include:

the land parcel information management module is used for: displaying a map within a preset area range; in response to the land parcel circling operation on the map, taking the land in the region range circled by the land parcel circling operation as a land parcel, and acquiring the input crop planting parameter information of the land parcel; and storing the plot information of the plot, wherein the plot information comprises crop planting parameter information and an area range.

Optionally, the data obtaining module is further configured to: determining the selected parcel as a target parcel in response to a parcel selection operation on the displayed map; and responding to the determined estimated production operation of the target plot, determining that an estimated production request of the target plot is received, and acquiring the plot information of the target plot.

Optionally, the farming treatment module is further configured to: according to the estimated yield of the target plot in the current growing season and the historical yield information of the crops, if the estimated yield is determined to meet the low-yield condition, determining first reason information causing the low yield of the target plot in the current growing season according to the real-time monitoring data; determining a first farming task for the target plot according to the first reason information and the agricultural knowledge map information; and issuing a first farming task.

Optionally, determining, according to the real-time monitoring data, first cause information causing low yield of the target plot in the current growing season, including at least one of:

the real-time monitoring data comprises real soil data of the target land, and according to the real soil data of the target land, if the real soil data of the target land is abnormal, abnormal information of the real soil data of the target land is determined;

the real-time monitoring data comprise real-time remote sensing data of the target plot, the real-time remote sensing data are analyzed, and if the target plot is determined to suffer from plant diseases and insect pests, the plant diseases and insect pests information of the target plot is determined;

and the real-time monitoring data comprises weather live data and weather forecast data, and according to the weather live data and the weather forecast data, if weather disasters are determined to occur within the range of the target land parcel in the current growing season, determining weather disaster information occurring within the range of the target land parcel in the current growing season.

Optionally, the farm intelligence device may further include:

a crop growth monitoring module for: in the current growing season of crops planted in the target plot, acquiring second real-time monitoring data of the target plot in the current growing season of the planted crops according to a preset monitoring strategy, wherein the second real-time monitoring data comprises second weather live data, second weather forecast data and second real-time remote sensing data; and according to the second real-time remote sensing data, carrying out growth analysis on crops planted in the target plot, and determining the current crop growth information of the target plot.

The farming treatment module is further configured to: according to the current crop growth information of the target plot, if the current crop growth information of the target plot meets the growth potential difference condition, determining second reason information causing the growth potential difference of the crops planted in the target plot according to second real-time monitoring data; determining a second farming task for the target plot according to the second reason information and the agricultural knowledge map information; and issuing a second farming task.

Optionally, determining second cause information causing a difference in the growth potential of the crops planted in the target block according to the second real-time monitoring data, wherein the second cause information includes at least one of the following:

the second real-time monitoring data comprise real soil data of the target land, and according to the real soil data of the target land, if the real soil data of the target land is abnormal, abnormal information of the real soil data of the target land is determined;

analyzing the second real-time remote sensing data, and if determining that the target plot has plant diseases and insect pests, determining the plant disease and insect pest information of the target plot;

and according to the second weather live data and the second weather forecast data, if it is determined that the weather disaster happens in the range of the target land parcel in the current growing season, determining weather disaster information in the range of the target land parcel in the current growing season.

Optionally, the farming treatment module is further configured to: before any specific farming task is issued, determining that a target plot meets the execution condition of the specific farming task; wherein the specific farming tasks include a first farming task and a second farming task.

Optionally, the farming treatment module is further configured to: after any specific farming task is issued, acquiring real-time monitoring data after the specific farming task is executed on a target land; determining the execution effect information of the specific farming task according to the real-time monitoring data after the specific farming task is executed on the target plot; and outputting the execution effect information of the specific farming task.

The apparatus provided in the embodiment of the present application may be specifically configured to execute the scheme provided in any one of the method embodiments, and specific functions and technical effects that can be achieved are not described herein again.

The application also provides a farming intellectuality's controlgear, includes: a processor, and a memory communicatively coupled to the processor, the memory storing computer-executable instructions. The processor executes the computer execution instructions stored in the memory to implement the scheme provided by any of the above method embodiments, and the specific functions and the technical effects that can be achieved are not described herein again.

The embodiment of the present application further provides a computer-readable storage medium, where computer-executable instructions are stored in the computer-readable storage medium, and when the computer-executable instructions are executed by a processor, the computer-executable instructions are used to implement the solutions provided in any of the above method embodiments, and specific functions and technical effects that can be achieved are not described herein again.

An embodiment of the present application further provides a computer program product, where the program product includes: the computer program is stored in the readable storage medium, at least one processor of the farm-oriented intelligent control device can read the computer program from the readable storage medium, and the at least one processor executes the computer program to enable the control device to execute the scheme provided by any one of the method embodiments, so that specific functions and achievable technical effects are not described herein again.

Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.

It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims

1. A method for intellectualization of farming activities, comprising:

2. The method of claim 1, wherein the obtaining real-time monitoring data of the target plot during a current growing season of the planted crop and historical monitoring data corresponding to time intervals of the current growing season not covered by the real-time monitoring data in response to a request for yield assessment of the target plot comprises:

responding to a yield estimation request of a target plot, and acquiring plot information of the target plot;

acquiring real-time monitoring data of the target plot in the current growing season of the planted crops and historical monitoring data corresponding to a time interval of the current growing season, which is not covered by the real-time monitoring data, according to the plot information of the target plot;

the real-time monitoring data comprises live meteorological data, forecast meteorological data and real-time remote sensing data, and the historical monitoring data comprises historical meteorological data and historical remote sensing data.

3. The method of claim 2, wherein determining the estimated production of the target plot during the current growing season based on the real-time monitored data, the historical monitored data, and an estimated production model of the target plot comprises:

determining key vegetation index factors of the target land in the current growing season according to the real-time remote sensing data and the historical remote sensing data, and determining key meteorological factors of the target land in the current growing season according to the weather live data, weather forecast data and historical weather data;

determining the estimated yield of the target land parcel in the current growing season according to the key vegetation index factor and the key meteorological factor of the target land parcel in the current growing season and the estimated yield model of the target land parcel;

and outputting the estimated yield of the target plot in the current growing season.

4. The method as claimed in claim 2, wherein if the estimation request is a first estimation request of the target parcel in the current growing season, after obtaining the parcel information of the target parcel, further comprising:

determining a target crop currently planted in the target plot according to the plot information of the target plot;

acquiring actual monitoring data and actual yield data of the target plot in each historical growth season of the target crop during the period of planting the target crop in the target plot within a preset historical time period, wherein the actual monitoring data comprises actual meteorological data and actual remote sensing data;

determining vegetation index factors and meteorological factors of the target plot in each development period of the historical growing seasons according to actual monitoring data of each historical growing season;

determining key vegetation index factors and key meteorological factors which seriously affect the yield of the target crops by adopting a principal component analysis method according to the vegetation index factors and meteorological factors of the target plots in each development period of each historical growth season and actual yield data;

and establishing a relation model of the estimated yield, the key vegetation index factors and the key meteorological factors to obtain an estimated yield model of the target land parcel.

5. The method according to any one of claims 1-4, further comprising:

displaying a map within a preset area range;

in response to the land parcel circling operation on the map, taking land in the area range circled by the land parcel circling operation as a land parcel, and acquiring input crop planting parameter information of the land parcel;

and storing the plot information of the plot, wherein the plot information comprises crop planting parameter information and an area range.

6. The method of claim 5, wherein obtaining the parcel information for the target parcel in response to a request for valuation of the target parcel comprises:

determining the selected parcel as the target parcel in response to a parcel selection operation on the displayed map;

and responding to the determined estimated production operation of the target plot, determining that an estimated production request of the target plot is received, and acquiring the plot information of the target plot.

7. The method of claim 1, wherein the issuing a first farming task for the target plot based on the predicted yield of the target plot over the current growing season, the historical yield information of the crop, the real-time monitoring data, and the agricultural knowledge-map information comprises: according to the estimated yield of the target plot in the current growing season and the historical yield information of the crops, if the estimated yield is determined to meet a low-yield condition, determining first reason information causing low yield of the target plot in the current growing season according to the real-time monitoring data;

determining a first farming task for the target plot according to the first reason information and the agricultural knowledge map information;

and issuing the first farming task.

8. The method according to claim 7, wherein the determining first cause information causing the low yield of the target plot in the current growing season according to the real-time monitoring data comprises at least one of:

the real-time monitoring data comprise live soil data of the target land, and according to the live soil data of the target land, if the fact that the live soil of the target land is abnormal is determined, abnormal information of the live soil of the target land is determined;

and the real-time monitoring data comprises weather live data and weather forecast data, and according to the weather live data and the weather forecast data, if it is determined that the weather disaster happens in the range of the target land parcel in the current growing season, the weather disaster information in the range of the target land parcel in the current growing season is determined.

9. The method of claim 1, further comprising:

in the current growing season of the crops planted in the target land block, acquiring second real-time monitoring data of the target land block in the current growing season of the crops planted in the target land block according to a preset monitoring strategy, wherein the second real-time monitoring data comprises second weather live data, second weather forecast data and second real-time remote sensing data;

according to the second real-time remote sensing data, carrying out growth analysis on crops planted in the target plot, and determining current crop growth information of the target plot;

according to the current crop growth information of the target plot, if the current crop growth information of the target plot meets a growth potential difference condition, determining second reason information causing the growth potential difference of the crops planted in the target plot according to the second real-time monitoring data;

determining a second farming task for the target plot according to the second reason information and the agricultural knowledge map information;

and issuing the second farming task.

10. The method of claim 9, wherein determining second cause information for a difference in growth potential of crops planted in the target block based on the second real-time monitoring data comprises at least one of:

the second real-time monitoring data comprise live soil data of the target land, and according to the live soil data of the target land, if the fact that the live soil of the target land is abnormal is determined, abnormal information of the live soil of the target land is determined;

analyzing the second real-time remote sensing data, and if determining that the target plot has plant diseases and insect pests, determining plant disease and insect pest information of the target plot;

and according to the second weather live data and the second weather forecast data, if it is determined that the weather disaster happens within the range of the target land parcel in the current growing season, determining weather disaster information which happens within the range of the target land parcel in the current growing season.

11. The method of claim 7 or 9, further comprising:

before any specific farming task is issued, determining that the target plot meets the execution condition of the specific farming task;

wherein the specific farming task comprises a first farming task and a second farming task.

12. The method of claim 11, further comprising, after issuing any of said specific farming tasks:

acquiring real-time monitoring data after the specific farming task is executed on the target land;

determining the execution effect information of the specific farming task according to the real-time monitoring data after the target plot executes the specific farming task;

and outputting the execution effect information of the specific farming task.

13. An intelligent farm work device, comprising:

14. A farming intellectualized control apparatus, comprising: a processor, and a memory communicatively coupled to the processor;

the memory stores computer-executable instructions;

the processor executes computer-executable instructions stored by the memory to implement the method of any of claims 1-12.