WO2018232845A1 - Intelligent agricultural management method and system - Google Patents

Abstract

The present invention relates to a smart agriculture management method and system, the method comprising: monitoring soil nutrient data and moisture data; acquiring historical weather data and predicted weather data; acquiring historical price data; comparing the nutrient data with a nutrient content standard value and comparing the moisture data with a moisture content standard value; processing and analysing the historical price data of the crop and the historical weather data, and combining the predicted weather data to obtain a crop price trend prediction result; and, on the basis of the crop price trend prediction result, controlling the crop harvesting time. The system comprises: a control centre, a soil monitoring module, a weather information acquisition module, and a price acquisition module. In addition to monitoring the condition of the crop itself, the present invention also takes into consideration the price trend of the crop and, by means of analysing the main factors influencing the crop price, finds a correlation between the crop price and said factors, and thereby predicts the price trend of the crop and, on this basis, helps farmers control the harvest time.

Description

Intelligent agricultural management method and system Technical field

The present invention relates to the field of Internet of Things, and in particular to an intelligent agricultural management method and system.

Background technique

Since the reform and opening up, Chinese society has continued to develop, and the economic, military, science and technology fields have maintained a good growth trend. As the world's most populous country, China's population is rising. It is conservatively estimated that the population has now exceeded 1.4 billion. Such a large population provides productivity backing for social construction, but it also poses enormous challenges. Solving the problem of food and clothing for one-fifth of the world's population is the foundation of all development.

With the application of science and technology in agriculture, agriculture has gradually grown from small-scale farmland cultivation to large-scale farm planting. In the prior art, whether it is small-scale planting or large-scale farm planting, most of them are decided by farmers to manage, such as the type of crops, the amount of fertilizer applied, and the timing of harvesting, etc., which are controlled by farmers according to subjective judgments. The benefits depend to a large extent on the experience of farmers. However, subjective experience will inevitably be less rigorous. In order to carry out more scientific management of agricultural production, the industry urgently needs to find another agricultural management model to scientifically manage agricultural production, so that farmers no longer "see the sky for dinner." ".

Summary of the invention

In order to solve the above technical problems, the present invention provides an intelligent agricultural management method and system.

In a first aspect, the present invention provides an intelligent agricultural management method, the method specifically comprising the steps of:

S1. Real-time monitoring of soil nutrient data and moisture data;

S2. Obtain historical weather data and forecast weather data of the region;

S3. Obtain historical price data of crops;

S4. Pre-set the nutrient content standard value and the moisture content standard value, compare the nutrient data and the nutrient content standard value, and output the alarm information when the nutrient data is less than the nutrient content standard value, compare the moisture data and the moisture content standard value, when the moisture data is smaller than the moisture content Output alarm information when the standard value is used;

S5. Processing the historical price data of the crop and the historical weather data, and combining the predicted weather data to obtain the crop price trend prediction result;

S6. Control the timing of harvesting crops based on crop price trend projections.

The invention provides an intelligent agricultural management method, which monitors soil nutrient data and moisture data in real time and compares with preset standard values of nutrient content and moisture content, and outputs an alarm when the nutrient data is less than the standard value of nutrient content. When the data is lower than the standard value of moisture content, the alarm is output, and the amount of fertilizer and the amount of irrigation can be adjusted in time. Control nutrients and moisture in the most suitable range for crop growth, It is more scientific and reliable than empirically controlling the amount of fertilizer applied and the amount of irrigation. It saves fertilizer and saves water, and is more conducive to crop growth. In addition, based on the historical weather data of the region and the historical price data of the crops, the crop price trend is predicted by a large enough big data base, and the time of harvesting crops is controlled according to the crop price trend forecast, and the crop is controlled in the price curve. The highest point of entry into the market, through scientific management methods to get farmers out of the fate of "seeing the sky to eat."

Further, after obtaining the predicted weather data of the local area, the method further includes controlling the adjustment of the recent irrigation amount according to the predicted weather data, and specifically includes the following steps:

Monitor soil moisture data in real time;

Real-time monitoring of water vapor content in the air;

Obtained predicted weather data for the region, the predicted weather data including predicted rainfall;

The water vapor content and predicted weather data in the air are quantified into irrigation amounts;

The amount of irrigation is adjusted in conjunction with the quantitative irrigation amount and soil moisture data.

In the above embodiment, when the moisture data monitored in real time is low, it can be judged that the crop needs irrigation to ensure water absorption, and the water vapor content and the predicted rainfall in the air are obtained before the irrigation, and the water vapor content in the air and the predicted rainfall are obtained. The amount of analysis is quantified into the amount of irrigation, combined with the quantitative irrigation amount and the moisture data monitored in real time, and the irrigation amount is appropriately adjusted. Both water vapour content and predicted rainfall in the air may provide potential irrigation. When water vapour content is high and/or predicted weather data indicates that there is rainfall in the near future, irrigation can be reduced, when water vapour content is low and/or weather data is predicted. If there is no rain in the near future, it can be irrigated normally. In this way, we can make full use of nature, save water resources, and achieve efficient irrigation.

In a second aspect, the present invention provides an intelligent agricultural management system comprising:

a soil monitoring module for monitoring soil nutrient data and moisture data in real time;

a weather information acquisition module, configured to obtain historical weather data and predicted weather data of the region through the Internet;

a price information acquisition module for obtaining historical price data of crops via the Internet;

The control center is pre-set with a standard value of nutrient content and a standard value of moisture content, the control center receives nutrient data and moisture data of the soil; the control center compares the nutrient data and the nutrient content standard value, when the nutrient data is less than the standard value of the nutrient content When the alarm information is output, the farmers are reminded to adjust the amount of fertilizer; the control center compares the water data and the water content standard value, and outputs an alarm message when the water data is less than the standard value of the moisture content, reminding the farmers to adjust the irrigation amount;

The control center is connected to the soil monitoring module, the weather information acquisition module and the price information acquisition module respectively;

The control center processes the historical price data of the analyzed crops and the historical weather data of the region, and combines the predicted weather data to obtain the crop price trend prediction result, and controls the time of harvesting the crop according to the crop price trend prediction result.

The invention provides an intelligent agricultural management system, which comprises a soil monitoring module and weather information acquisition. Take the module, the price information acquisition module and the control center. The soil monitoring module, the weather information acquisition module, and the price information acquisition module respectively obtain nutrient data and moisture data of the soil, historical weather data and predicted weather data of the region, and historical price data of the crop, and the control center determines whether it needs to be adjusted based on the above data. The amount of fertilizer applied and the amount of irrigation, more importantly, is to analyze the forecast results of crop price trends, control the time of harvesting crops, and control the timing of crops entering the market through scientific methods, thereby increasing farmers' income.

Further, the plurality of soil monitoring modules are evenly distributed in the soil of the monitored area, and the soil monitoring module and the control center are wirelessly networked through Bluetooth or ZigBee or WiFi, and the soil monitoring module only transmits the collected data. Nutrient data and moisture data without receiving any information, the soil monitoring module is powered by battery or solar energy; the control center simultaneously receives nutrient data and moisture data sent by a plurality of soil monitoring modules and performs unified analysis and processing.

In the above embodiment, in order to accurately and efficiently monitor the soil nutrient data and moisture data in real time, a plurality of soil monitoring modules are uniformly disposed in the soil of the monitored area. The control center analyzes the nutrient data and moisture data based on the data collected by the individual soil monitoring modules, but the data collected by all soil monitoring modules. When a soil monitoring module stops working, data is faulty, and transmission is not smooth, the large data collected by other soil monitoring modules can still be comprehensively collected, so the data of a single soil monitoring module does not affect the entire system. Make an impact. Secondly, due to the large number of soil monitoring modules, if the network is wired, it will undoubtedly increase the cost greatly. Therefore, the wireless monitoring network between the soil monitoring module and the control center simplifies the system and reduces the system. Outgoing support is conducive to large-scale deployment of soil monitoring modules. Once again, the wireless networking will bring power problems and cannot be directly charged through the power line. Therefore, the soil monitoring module is powered by battery or solar energy, so that the soil monitoring module can perform data collection more independently without relying on system power supply. .

DRAWINGS

1 is an architectural diagram of an intelligent agricultural management system of the present invention;

2 is a structural diagram of a network of a control center and a soil monitoring module of the present invention;

3 is a schematic flow chart of an intelligent agricultural management method according to the present invention;

4 is a schematic diagram of interaction between nutrient data and moisture data for monitoring soil according to the present invention;

Figure 5 is a schematic flow chart of precise control of fertilization amount and irrigation amount according to the present invention;

6 is a schematic flow chart of obtaining a crop price trend prediction result according to the present invention;

FIG. 7 is a schematic flow chart of modifying the rainfall correlation factor α, the wind level correlation factor β, and the temperature correlation factor γ according to the present invention.

Detailed ways

In the following description, for purposes of illustration and not limitation, Specific details such as mouth, technology, etc., in order to understand the present invention. However, it will be apparent to those skilled in the art that the present invention may be practiced in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, circuits, and methods are omitted so as not to obscure the description of the invention.

As shown in FIG. 1, FIG. 1 is an architectural diagram of an intelligent agricultural management system according to the present invention. An intelligent agricultural management system includes a control center 1, a soil monitoring module 2, a weather information acquisition module 3, and a price information acquisition module 4. The control center 1 is connected to the soil monitoring module 2, the weather information acquiring module 3, and the price information acquiring module 4, respectively, and the meaning of the above "connected" is understood to include the physical connection and the transmission direction of the signal.

The roles of each module are:

The soil monitoring module 2 is configured to monitor nutrient data and moisture data of the soil in real time, that is, nutrient data and moisture data of the collected and sent soil; the weather information acquiring module 3 is configured to obtain historical weather data of the region through the Internet and Forecasting weather data; the price information obtaining module 4 is configured to obtain historical price data of the crop through the Internet;

The control center 1 is pre-set with a nutrient content standard value and a moisture content standard value, the control center 1 receives nutrient data and moisture data of the soil; the control center 1 compares the nutrient data and the nutrient content standard value, when the nutrient data is smaller than When the nutrient content standard value is output, an alarm is issued to remind the farmers to adjust the fertilization amount; the control center 1 compares the water data and the water content standard value, and outputs an alarm when the moisture data is smaller than the water content standard value, reminding the farmers to adjust the irrigation amount.

The control center 1 is connected to the soil monitoring module 2, the weather information acquiring module 3, and the price information acquiring module 4, respectively;

The control center 1 processes the historical price data of the analyzed crops and the historical weather data of the region, and combines the predicted weather data to obtain the crop price trend prediction result, and controls the time of harvesting the crop according to the crop price trend prediction result.

As shown in FIG. 3, FIG. 3 is a schematic flowchart of a smart agricultural management method according to the present invention. An intelligent agricultural management method corresponding to an intelligent agricultural management system, comprising the steps of:

S1. Real-time monitoring of soil nutrient data and moisture data;

S2. Obtain historical weather data and forecast weather data of the region;

S3. Obtain historical price data of crops;

S4. Pre-set the nutrient content standard value and the moisture content standard value, compare the nutrient data and the nutrient content standard value, and output the alarm information when the nutrient data is less than the nutrient content standard value, compare the moisture data and the moisture content standard value, when the moisture data is smaller than the moisture content Output alarm information when the standard value is used;

S5. Processing the historical price data of the crop and the historical weather data, and combining the predicted weather data to obtain the crop price trend prediction result;

S6. Control the timing of harvesting crops based on crop price trend projections.

In this embodiment, in combination with the intelligent agricultural management system, the principle of the intelligent agricultural management method is: The soil monitoring module 2 monitors the nutrient data and the moisture data reflecting the real-time condition of the soil according to a certain sampling frequency, acquires the historical weather data and the predicted weather data of the region through the weather information acquiring module 3, and acquires the history of the crop through the price information acquiring module 4. Price data, which is implemented in parallel in three steps, aims to collect data that is closely related to agricultural management. In the present invention, the idea of intellectual property management of intelligent agriculture is embodied in three aspects: 1. The standard value of nutrient content and the standard value of moisture content are preset in the control center 1, and the soil monitoring module 2 obtains nutrient data and moisture data of the soil. Send to the control center 1, the control center 1 compares the nutrient data and the nutrient content standard value, compares the water data and the moisture content standard value, when the nutrient data is less than the nutrient content standard value and when the moisture data is less than the moisture content standard value, the alarm is output, the farmers according to The alarm controls the amount of fertilizer applied and the amount of irrigation. 2. The Control Center 1 analyzes the predicted weather data of the area, and outputs an alarm when weather warning occurs, and applies the meteorological information issued by the Meteorological Bureau directly to the system. 3. The control center 1 analyzes the historical price data of the crops and the historical weather data of the region, and outputs the forecast results of the crop price trends. The farmers can control the time of harvesting the crops according to the forecast results of the crop price trends, and issue information when the crop prices are in an upward trend. Remind farmers to harvest in time, try to make the crops enter the market at the highest point of the predicted price; when the crop price is in a downward trend, it can send a message to remind the farmers to suspend the harvest, try to avoid the crop entering the market at the low price of the forecast price, from the perspective of price Best harvest time. It should be noted that the growth of the crop is a natural process, and the present embodiment only analyzes the time for controlling the harvested crop from an economic point of view.

In this embodiment, the most important function of the control center 1 is to collect historical price data of crops and historical weather data of the region and perform processing analysis to predict future crop price trends and output crop price trend prediction results. Farmers can grasp the harvest time of crops according to crop maturity and crop price trend forecasting results, control crops to enter the market at the highest point of the price curve, and increase farmers' income through scientific management methods.

The control center 1 is a device with data analysis and processing functions, intelligent decision-making and intelligent control. Unlike the control center 1, the soil monitoring module 2 has only data acquisition and transmission functions. Correspondingly, in the S1, the nutrient data and the moisture data of the soil are monitored in real time by a device having only data acquisition and transmission functions. In the agricultural Internet of Things, not all devices are smart devices like the Control Center 1, and more are data acquisition devices at the edge. In the present embodiment, the soil monitoring module 2 monitors the nutrient data and moisture data of the soil in real time through sensors. As a monitoring device, the sensors in the soil monitoring module 2 can sense nutrient and moisture information in the soil and output nutrient data and moisture data in the form of signals. Due to the large number of soil monitoring modules 2, and the various soil monitoring modules 2 have very simple and efficient transmission and reception requirements, only a small amount of data is needed to reflect the real-time conditions of the soil.

The weather information acquisition module 3 is configured to acquire historical weather data, real-time weather data, and predicted weather data of the region. In this embodiment, the weather information acquisition module 3 does not have to have an analysis or storage function, and only needs to obtain data of the weather bureau through the Internet. Of course, in some cases, The weather information acquisition module 3 is set to be the same smart device as the control center 1. The weather information acquisition module 3 can be a soft device implemented by a computer program, and the purpose thereof is only to take historical weather data, real-time weather data and predicted weather data of the local area through the Internet. Historical weather data is the weather information of the past year or years of the region, including the date and daily corresponding rainfall, wind size, temperature, etc.; real-time weather data is mainly used to combine real-time crop prices, and the rainfall-related factor α in the later period. The wind level correlation factor β and the air temperature correlation factor γ are used as a reference for correction; and the predicted weather data is used to obtain crop price trend prediction results according to the correlation, for example, the predicted weather data in the next half month includes the daily date and daily Corresponding rainfall, wind power, temperature, etc., according to the relevant relationship, can wait until the corresponding forecasted crop price per day, and further obtain the crop price trend forecast result.

The price of crops is susceptible to weather factors, and the weather, seasonality, rainfall, wind size, temperature, etc. have the most significant impact on crop prices. The weather information acquisition module 3 obtains the historical weather data of the region, and then obtains the price weather correlation relationship through the control center 1 analysis, and further combines the predicted weather data and the price weather correlation relationship to obtain the crop price trend prediction result.

Compared with other traditional agricultural internet of things systems that only focus on the growth and maturity of crops, the innovation of this intelligent agricultural management system is that it has more attention than basic functions such as real-time monitoring of crop growth and maturity. The price trend of crops. Through the analysis of the main factors affecting crop prices, the correlation between crop prices and various factors is sought to predict the price trend of crops. The traditional agricultural Internet of Things system can only produce crops better. This intelligent agricultural management system can also help farmers control harvest time and increase income.

In addition, this intelligent agricultural management method and system can accurately control the amount of fertilizer and irrigation. The specific steps are:

The control center 1 is pre-set with a nutrient content standard value and a moisture content standard value, and the control center 1 receives nutrient data and moisture data of the soil;

The control center 1 compares the real-time nutrient data and the nutrient content standard value, and outputs alarm information when the real-time nutrient data is less than the nutrient content standard value, prompting the farmers to adjust the fertilization amount;

The control center 1 compares the real-time moisture data and the moisture content standard value, and outputs an alarm message when the real-time moisture data is smaller than the water content standard value, reminding the farmers to adjust the irrigation amount.

The above steps are mainly embodied in S4, pre-set the standard value of nutrient content and the standard value of moisture content, compare the nutrient data and the standard value of nutrient content, and output alarm information when the nutrient data is less than the standard value of nutrient content, and compare the standard values of moisture data and moisture content. Outputs an alarm message when the moisture data is less than the moisture content standard value.

Further, in S4, when comparing the nutrient data and the nutrient content standard value and the contrast water data and the moisture content standard value, the difference between the nutrient data and the nutrient content standard value and the difference between the moisture data and the moisture content standard value are also calculated, according to The difference values are the amount of fertilization and the amount of irrigation, respectively, and the time limit for fertilization and the time limit for irrigation are separately output. Correspondingly, the control center compares nutrient data and nutrient content When the quasi value and the contrast water data and the moisture content standard value are calculated, the difference between the nutrient data and the nutrient content standard value and the difference between the moisture data and the water content standard value are also calculated, and the fertilization amount and the irrigation amount are respectively output according to the difference, and respectively Output fertilization time limit and irrigation time limit. For example, when the nutrient data is slightly smaller than the standard value of the nutrient content, a smaller amount of fertilization is output, and a larger fertilization time limit is output; when the nutrient data is much smaller than the standard value of the nutrient content, a larger amount of fertilization is output, and the output is smaller. Fertilization time limit.

Each crop has its own unique characteristics, and the demand for nutrients and water varies from crop to crop. Use big data to quantify the nutrient and water needs of crops. For specific crops, a standard value of nutrient content and a standard value of moisture content are set in the control center 1 in advance. Taking grapes as an example, different nutrients have different nutrient content standard values. Grapes have a greater need for phosphorus and less nitrogen. After quantifying these requirements, the standard value of phosphorus is set in the control center 1 in advance. 0.35, the standard value of nitrogen content is 0.15; at the same time, the grape has higher requirements on moisture, and the standard value of moisture content in the control center 1 is 0.28 in advance. The control center 1 receives the nutrient data and moisture data of the soil. When the nutrient data of phosphorus is lower than 0.35, the output alarm alerts the farmers to supplement the phosphate fertilizer in time; when the nutrient data of nitrogen is lower than 0.15, the output alarm reminds the farmers to supplement the nitrogen fertilizer in time; When the data is below 0.28, an alarm is output to remind farmers to irrigate in time. According to the characteristics of different crops, scientifically define different standard values and water content standard values, and collect nutrient data and water data in the soil in real time to accurately control the nutrient content and water content in the soil.

In addition, the intelligent agriculture management method and system can also provide weather warning. The control center 1 receives the predicted weather data acquired by the weather information acquisition module 3, and outputs an alarm when a weather warning occurs. Weather factors are one of the most influential factors in agriculture. If the weather changes cannot be accurately controlled and prepared in time, agricultural production will be largely controlled by the weather. Taking rice as an example, typhoon has a great influence on rice, especially near the harvested rice. When the typhoon hits, the rice ear will be knocked down. Therefore, it is extremely important for agricultural production to keep an eye on the weather. In the embodiment, the weather information acquisition module 3 obtains the predicted weather data of the region from the weather bureau, and outputs an alarm in time when the typhoon warning occurs, so as to obtain more preparation time for the farmers.

As shown in FIG. 2, FIG. 2 is a structural diagram of the network of the control center 1 and the soil monitoring module 2 of the present invention. The intelligent agriculture management system further includes a plurality of forwarding nodes 5, the soil monitoring module 2 includes a soil nutrient sensor for monitoring soil nutrient data in real time, and the soil moisture sensor for real time Monitor soil moisture data.

The soil nutrient sensor and the soil moisture sensor are buried under the soil beside the crop root system, so that the environment of the soil monitoring module 2 is as close as possible to the actual environment of the crop, and the data collected by the soil monitoring module 2 can more accurately reflect the crop. status.

The soil monitoring module 2 is connected to the control center 1 through the forwarding node 5, and the soil nutrient sensor and the soil moisture sensor periodically send data to the forwarding node 5, and the forwarding node 5 receives the nutrient data of the soil nutrient sensor and the moisture data of the soil moisture sensor. And send the nutrient data and moisture data to the control center 1.

The soil monitoring module 2, the forwarding node 5 and the control center 1 respectively constitute a three-tier architecture of the agricultural Internet of Things. The soil monitoring module 2 is the front-end data acquisition device of the agricultural Internet of Things, which has a large number, a simple data structure and is not suitable for the traditional Internet protocol. In the entire agricultural IoT architecture, the soil monitoring module 2 only needs to continuously collect and send nutrient data and moisture data. The accuracy and security of data required by traditional Internet protocols can be ignored in the agricultural Internet of Things. More attention is paid to the number of samples sampled, ie the number of soil monitoring modules 2 and whether the entire area is covered. Since the soil monitoring module 2 is not suitable for the traditional Internet protocol, the current Internet of Things is still based on the traditional Internet to varying degrees. Therefore, the forwarding node 5 and the control center 1 still follow the traditional Internet protocol. The forwarding node 5 provides the data transmission and gateway functions of the traditional Internet, that is, performs protocol conversion, and the networking protocol of the front-end soil monitoring module 2 and the networking protocol of the traditional Internet. The Control Center 1 provides data analysis, integrated control, and human-machine interface functions. In this way, a bridge between the agricultural Internet of Things and the traditional Internet can be established to provide a basis for the realization of the agricultural Internet of Things.

In the network architecture of the intelligent agriculture management system, the soil monitoring module 2, as the front end of the system, only needs to have data acquisition and transmission functions, and does not need to have data receiving and processing functions. This is due to the large number of soil monitoring modules 2, which are only used to monitor the nutrient data and moisture data of the soil in real time, so the cost of configuring the data receiving or processing function of the soil monitoring module 2 is much greater than the effect. On the other hand, the front end of the system does not need to have data receiving and processing functions, and there are disadvantages to a certain extent, because this will greatly increase the pressure of the subsequent control center 1 to process data. Therefore, between the control center 1 and the soil monitoring module 2 are connected by a forwarding node 5 having the ability to receive, process and forward data, which can be forwarded before the nutrient data and moisture data are forwarded to the control center 1. Pretreatment is performed. Pre-processing includes intelligent closure and cropping of nutrient data and moisture data, checking for complete data, discarding corrupted data and redundant data, and specifying the direction of data transfer. In this embodiment, the setting of the forwarding node 5 optimizes the structure of the system, so that the front end and the back end are more closely connected, and the efficiency of data collection, transmission, and processing is improved.

As shown in FIG. 4, FIG. 4 is a schematic diagram of interaction between nutrient data and moisture data for monitoring soil according to the present invention. In the S1, real-time monitoring of soil nutrient data and moisture data specifically includes:

The first layer network device 20 collects nutrient data and moisture data of the soil, and transmits the collected nutrient data and moisture data to the second layer network device 50 in a broadcast form;

The second layer network device 50 preprocesses the data after receiving the nutrient data and the moisture data, and transmits the preprocessed nutrient data and moisture data to the layer 3 network device 10.

The first layer network device 20 corresponds to the soil monitoring module 2, the second layer network device 50 corresponds to the forwarding node 5, and the third layer network device 10 corresponds to the control center 1. In this embodiment, real-time monitoring of soil nutrient data and moisture data specifically includes:

The soil monitoring module 2 collects nutrient data and moisture data of the soil and broadcasts it to the form. The forwarding node 5 sends the collected nutrient data and moisture data; the soil monitoring module 2 does not have the data processing function, and can only perform simple data collection and transmission; and the soil monitoring module 2 passes between the collection and forwarding node 5 and the control center 1 In the wireless mode networking, after collecting the nutrient data and the moisture data, the soil monitoring module 2 transmits the collected data in the form of a broadcast.

Forwarding the nutrient data and the moisture data received by the node 5, pre-processing the data, and transmitting the pre-processed nutrient data and moisture data to the control center 1; the functions of the forwarding node 5 include forwarding data and pre-processing the data, specifically This includes intelligent closure and cropping of nutrient data and moisture data, checking for complete data, discarding corrupted data and redundant data, and specifying the direction of data transfer. Since the soil monitoring module 2 does not have the data processing function, if all the data collection work is performed by the control center 1, the management center 1 will be greatly burdened, and the data processing efficiency is low. Therefore, the nutrient data and the moisture data are put. Before being sent to the control center 1, the forwarding node 5 performs pre-processing to help share the pressure of the control center 1 and improve the data processing efficiency of the entire system.

The control center 1 receives and processes the pre-processed nutrient data and moisture data, and can control the forwarding node 5 to receive the nutrient data and the moisture data collected by the specific soil monitoring module 2 as needed; for example, when it is necessary to pay attention to the real-time condition of the soil in a certain area The nutrient data and moisture data of the soil collected by the soil monitoring module 2 in the region may be marked as interested. As shown in FIG. 4, the layer 3 network device 10 receives the nutrient data and moisture data of interest through the layer 2 network device.

The forwarding node 5 receives the nutrient data and moisture data collected by the specific soil monitoring module 2 while ignoring the nutrient data and moisture data collected by the other soil monitoring modules 2. Only accept the data of interest, can process the data more strongly, and improve the efficiency of data processing.

It should be particularly noted that the soil monitoring module 2 transmits the nutrient data and the moisture data collected to the soil by means of broadcasting, and can be transferred to other forwarding nodes 5 that are working normally when some forwarding nodes 5 cannot transmit data for various reasons. Guarantee the reliability of the system. In addition, since the data frame of the soil monitoring module 2 is very small and carries only the most important information, the use of the broadcast form does not affect the operation and maintenance cost of the entire system.

The soil nutrient sensor and the soil moisture sensor monitor the soil nutrient data and moisture data according to a specific sampling frequency, that is, the soil nutrient sensor and the soil moisture sensor continuously work continuously, and continuously monitor the soil nutrient data and moisture data. The specific sampling frequency specifically refers to data collection every one hour or two hours, and then the collected nutrient data and moisture data are sent. The specific sampling frequency is set for the soil nutrient sensor and the soil moisture sensor to balance cost and data validity. Soil nutrient data and moisture data do not change from time to time. If soil nutrient sensors and soil moisture sensors are working at all times, the data is of low effectiveness and the cost of equipment is high. As the number increases, such conditions become more and more obvious. Therefore, data collection is performed every hour or two, which is a good balance between cost and data availability.

Preferably, the soil nutrient sensor and the soil moisture sensor are disposed in the monitored farmland, and the monitored farmland is divided into a plurality of small areas. The data frames collected by the soil nutrient sensor and the soil moisture sensor include a transmission pointing code, an address code, and sensing data. The number of front-end devices in the Internet of Things is huge. Considering the overhead and efficiency of data, soil nutrient sensors and soil moisture sensors only carry the most useful information for this system.

The above data frame can meet the basic requirements of the agricultural Internet of Things, wherein the transmission pointing code records the data transmission direction, that is, which forwarding node 5 sends data; the address code records the location of the soil nutrient sensor or the soil moisture sensor; Then, it is nutrient data or moisture data, such as nutrient data of phosphorus and nitrogen in the above embodiment, and the nutrient data and moisture data corresponding to each location can be visually analyzed by combining the address code and the sensing data.

As shown in FIG. 5, FIG. 5 is a schematic flow chart of accurately controlling the amount of fertilizer applied and the amount of irrigation according to the present invention. The monitored farmland is divided into multiple small areas and the data frames collected by the soil nutrient sensor and the soil moisture sensor include the transmission pointing code, the address code and the sensing data, which can be used to precisely control the amount of fertilizer and the amount of irrigation, including:

S401. The monitored farmland is divided into several small areas; the soil nutrient sensor and the soil moisture sensor both have a certain monitoring radius, so the small area division of the monitored farmland can be realized by setting the soil nutrient sensor and the soil moisture sensor at intervals. .

S402. Real-time monitoring of nutrient data and moisture data of soil in multiple small areas; the process of collecting data by each soil nutrient sensor and soil moisture sensor is a process of monitoring nutrient data and moisture data of soil in each small area.

S403. Compare the nutrient data and nutrient content standard values of multiple small areas, compare the water data and water content standard values of multiple small areas; generally, nutrients and water are distributed along the soil, so when some When the local nutrient data or moisture data is not in the acceptable range, the nutrient data or moisture data of a region adjacent to this place is usually not in the acceptable range. Combined with the address code and sensing data of the soil nutrient sensor and the soil moisture sensor, the Control Center 1 can analyze which areas require fertilization or irrigation.

S404. Screen out a small area where the nutrient data is smaller than the standard value of the nutrient content, and screen out a small area where the moisture data is smaller than the standard value of the moisture content;

S405. Output an alarm to precisely control the amount of fertilizer applied and the amount of irrigation in each small area. The control center 1 can display the nutrient and water status of each small area to the farmers through maps, such as using the form of rainfall distribution map in the weather forecast to intuitively realize human-computer interaction, and the farmers obtain information based on the information obtained from the control center 1. Fertilize or irrigate to achieve precise control of fertilization and irrigation.

The Internet of Things has a similar place to the traditional Internet, but in many ways, there is still a fundamental difference between the two. The traditional Internet is concerned with the accuracy and reliability of data, while the Internet of Things is a lossy, intermittent network with low requirements for accuracy and reliability. In the field of Internet of Things, in most cases, the number of samples is high, and there is no need to sacrifice high cost to maintain accurate data. Sex. In this embodiment, the data collected by each soil nutrient sensor and soil moisture sensor is "small data", and the data collected by all soil nutrient sensors and soil moisture sensors is "big data", when a single "small data" When there is a timeout or packet loss, it will not affect "big data". As long as the sample is added, the "inaccuracy" and "unreliability" of the Internet of Things data can be overcome.

Preferably, after obtaining the predicted weather data of the local area, the method further comprises controlling the adjustment of the recent irrigation amount according to the predicted weather data, specifically comprising the following steps:

Monitor soil moisture data in real time;

Real-time monitoring of water vapor content in the air;

Obtained predicted weather data for the region, the predicted weather data including predicted rainfall;

The water vapor content and predicted weather data in the air are quantified into irrigation amounts;

Adjust the amount of irrigation by combining the amount of irrigation and the moisture data of the soil.

As shown in FIG. 6, FIG. 6 is a schematic flow chart of obtaining a crop price trend prediction result according to the present invention. In the S5, the process of obtaining the crop price trend prediction result specifically includes:

S501. Organizing historical price data of the crop, the historical price data of the crop including the crop price Y of each day in the past period of time;

S502. Obtain historical weather data of the region, where the historical weather data includes rainfall A, wind level B, and temperature C of each day in the past period of time;

S503. Set up a price-related model, and analyze the rainfall correlation factor α, the wind level correlation factor β and the temperature correlation factor γ according to the price correlation model, and obtain the price weather correlation relationship Y=αA+βB+γC;

S504. Obtain predicted weather data of the region, and predict the price of the crop by combining the price weather correlation relationship Y=αA+βB+γC to obtain the predicted crop price;

S505. Compare crop prices with crop prices for each day in the past, and export crop price trend forecasts.

Weather is a key factor affecting crop prices. Therefore, the present invention analyzes crop price trend prediction results based on historical price data of crops and historical weather data in the region. Firstly obtain historical price data and historical weather data, establish a price-related model through mathematical modeling, and then analyze the rainfall correlation factor α, wind level correlation factor β and temperature-related factor γ according to multiple linear regression analysis methods. The relationship between crop prices and weather, combined with forecasting weather data, can be used to predict crop prices. Through the above steps, the relationship between price and weather is mathematically expressed, which ensures the accuracy of the prediction results and provides a scientific basis for agricultural management.

The soft system corresponding to the above-described processing analysis process for the historical price data of the crop and the historical weather data of the region includes the price data unit 11, the weather data unit 12, the model building unit 13, the price forecasting unit 14, the trend predicting unit 15, and the correction. Unit 16.

The price data unit 11 is for organizing historical price data of the crop, the historical price data of the crop including the crop price Y of each day in the past period of time. Crop historical price data For the basis of price forecasting, the specific time period in the past is specifically the past few months or years. The greater the time span of a particular time period, the more accurate the subsequent crop price trend predictions. The format of the historical price data of the crop is (date, price). Taking the price of corn as an example, the historical price data of corn can be (2013.03.02, 10).

The weather data unit 12 is for processing historical weather data of the local area, including historical rainfall A, wind level B, and temperature C for each day in the past period of time. Similarly, the control center 1 also has means for processing real-time weather data and predicted weather data, the principle of which is the same as the weather data unit 12 for processing historical weather data. The format of historical weather data is (date, rainfall, wind level, temperature), such as (2013.03.02,150,3,22).

The model forming unit 13 is configured to construct a price correlation model, and analyzes the rainfall correlation factor α, the wind level correlation factor β, and the temperature correlation factor γ according to the price correlation model, and obtains a price weather correlation relationship Y=αA+βB+γC. The mathematical model is used to construct a price-related model, combined with historical price data (such as corn) and historical weather data of a certain crop, and the rainfall correlation factor α, wind level correlation factor β and temperature correlation are analyzed according to multiple linear regression analysis methods. The factor γ determines the correlation between crop prices and weather. For example, the obtained rainfall correlation factor α is 0.02, the wind level correlation factor β is 1.5, and the temperature correlation factor γ is 0.8. At this time, the correlation between the corn price and the weather can be determined as Y=0.02*A+1.5*B+ 0.8*C. The price prediction unit 14 is configured to predict the crop price based on the predicted weather data of the region and the price correlation relationship of the crop with the weather-related relationship Y=0.02*A+1.5*B+0.8*C. For example, if the weather data for a certain day is predicted to be (201X.XX.XX, 100, 1, 20), the corresponding A is 100, B is 1, and C is 20. The price of corn combined with the weather is related to Y=0.02*A+1.5. *B+0.8*C, the price of corn after the forecast of three days is 19.5.

As shown in FIG. 7, FIG. 7 is a schematic flow chart of the modified rainfall correlation factor α, the wind level correlation factor β, and the temperature correlation factor γ according to the present invention. In the S504, the real-time crop price and the real-time weather data are first acquired, the real-time weather data is the weather data of the day, the real-time crop price is the crop price of the day, and the rainfall is continuously correlated according to the predicted crop price and the actual crop price. The factor α, the wind level correlation factor β and the air temperature correlation factor γ are corrected, and the correction process specifically includes:

S5041. Obtain daily forecasted crop prices and actual crop prices for a period of time in the past;

并取

的绝对值

作为一组修正参考数；S5042. The traversal calculation yields the difference between the predicted crop price and the actual crop price per day over the past period of time.

And take

Absolute value

As a set of revised reference numbers;

S5043. Calculating an average value σ of all corrected reference numbers;

与2σ，当

小于2σ时认定当天的预测作物价格可信，否则认定当天的预测作物价格不可信。S5044. Compare the absolute value of the difference between the predicted crop price and the real-time crop price on the day

With 2σ, when

When the price is less than 2σ, it is determined that the forecasted crop price on the day is credible, otherwise the forecasted crop price on the day is not credible.

S5045. When the forecasted crop price of the day is credible, it is determined that the real-time crop price of the day is highly correlated with real-time weather data, and the real-time crop price and real-time weather data of the day are included in the price-related model. And reanalyzed the rainfall correlation factor α, the wind level correlation factor β and the temperature related factor γ; when the forecasted crop price of the day is not credible, and the correlation between the real-time crop price and the real-time weather data is weak on the day, the real-time crop of the day is discarded. Price and real-time weather data, retaining the original rainfall correlation factor α, wind level correlation factor β and temperature correlation factor γ.

The trend prediction unit 15 is configured to compare the predicted crop price with the crop price of each day in the past period of time, and output the crop price trend prediction result. Using the above method to sequentially determine the predicted crop price over a period of time, the crop price trend prediction result can be obtained.

The correction unit 16 continuously corrects the rainfall correlation factor α, the wind level correlation factor β, and the temperature correlation factor γ according to the predicted crop price and the real-time crop price, and the correction unit 16 specifically includes a price comparator, a traverser, an averager, Judger and iterator.

The price comparator is used to obtain predicted crop prices and actual crop prices for each day in the past; for example, the predicted crop price is 19.5 and the real-time crop price is 20.

并取

的绝对值

作为一组修正参考数；预测作物价格为19.5、实时作物价格为20时，

为0.5，当天的修正参考数为0.5。The traversal is used to traverse the difference between the predicted crop price and the actual crop price for each day in the past period of time.

And take

Absolute value

As a set of revised reference numbers; forecast crop price is 19.5, real-time crop price is 20,

For 0.5, the corrected reference number for the day is 0.5.

The averager is used to calculate the average value σ of all modified reference numbers; the value of σ is obtained by a weighted average method, for example, the corrected reference numbers of 5 days are 0.5, 0.3, 0.2, 0.4, and 0.6, respectively, and the value of σ is 0.4. .

与2σ，当

小于2σ时认定当天的预测作物价格可信，否则认定当天的预测作物价格不可信；例如某天的预测作物价格和实时作物价格之差的绝对值

为0.7时，认定这天的的预测作物价格可信，当某天的预测作物价格和实时作物价格之差的绝对值

为0.8以上时，认定这天的预测作物价格不可信。The determiner is used to compare the absolute value of the difference between the predicted crop price and the real-time crop price of the day.

With 2σ, when

When less than 2σ, the forecasted crop price on the day is believed to be credible, otherwise the forecasted crop price on the day is deemed untrustworthy; for example, the absolute value of the difference between the predicted crop price and the real-time crop price of a certain day

At 0.7, the forecasted crop price for this day is believed to be credible, when the absolute value of the difference between the predicted crop price and the real-time crop price for one day

When it is 0.8 or more, it is determined that the predicted crop price of this day is not credible.

The iterator is used to adopt or discard the real-time crop price and real-time weather data of the day. When the forecast crop price of the day is credible, it is determined that the real-time crop price of the day is highly correlated with the real-time weather data, and the real-time crop price and real time of the day are The weather data is included in the price-related model and reanalyzed the rainfall correlation factor α, the wind level correlation factor β and the temperature-related factor γ; when the forecasted crop price on the day is not credible, it is determined that the correlation between the real-time crop price and the real-time weather data on that day is weak. The real-time crop price and real-time weather data of the day are discarded, and the original rainfall correlation factor α, the wind level correlation factor β, and the temperature correlation factor γ are retained. It is simply understood that when the predicted crop price and the real-time crop price are too different, it is considered that the price data and weather data of that day have no reference value, are not retained and are not used for subsequent price forecasting; when the forecast crop price and the real-time crop price are not much different At that time, it was considered that the price data and weather data of that day had reference value, which was retained and used as historical data for subsequent price forecasting.

The reader should understand that in the description of this specification, reference is made to the terms "one embodiment", "some The description of the embodiments, the "examples", the "specific examples", or "some examples" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiments or examples are included in at least one embodiment or example of the invention. In the present specification, the schematic representation of the above terms is not necessarily to the same embodiment or example, and the specific features, structures, materials or features described may be suitable in any one or more embodiments or examples. In addition, those skilled in the art can combine and combine the different embodiments or examples described in the specification and the features of the different embodiments or examples, without being contradicted.

A person skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working process of the device and the unit described above can refer to the corresponding process in the foregoing method embodiment, and details are not described herein again.

In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the device embodiments described above are merely illustrative. For example, the division of cells is only a logical function division. In actual implementation, there may be another division manner. For example, multiple units or components may be combined or integrated. Go to another system, or some features can be ignored or not executed.

The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the embodiments of the present invention.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

An integrated unit, if implemented in the form of a software functional unit and sold or used as a standalone product, can be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention contributes in essence or to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium. A number of instructions are included to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the various embodiments of the present invention. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like. .

The above is only the specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any equivalent modification or can be easily conceived by those skilled in the art within the technical scope of the present disclosure. Such modifications or substitutions are intended to be included within the scope of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims (10)

An intelligent agricultural management method, characterized in that the method comprises the following steps: S1. Real-time monitoring of soil nutrient data and moisture data; S2. Obtain historical weather data and forecast weather data of the region; S3. Obtain historical price data of crops; S4. presetting the nutrient content standard value and the moisture content standard value, comparing the nutrient data and the nutrient content standard value, and outputting alarm information when the nutrient data is less than the nutrient content standard value, comparing the moisture data and The moisture content standard value, outputting alarm information when the moisture data is less than the moisture content standard value; S5. Processing and analyzing historical price data of the crop and the historical weather data, and combining the predicted weather data to obtain a crop price trend prediction result; S6. Controlling the time to harvest the crop based on the crop price trend prediction. The intelligent agricultural management method according to claim 1, wherein in the S1, monitoring the nutrient data and the moisture data of the soil in real time comprises: S101. Collecting nutrient data and moisture data of the soil; S102 transmitting the nutrient data and moisture data in a broadcast form; S103. Pre-processing the nutrient data and moisture data, the pre-processing comprising intelligently closing and cutting the nutrient data and moisture data, checking whether the data is complete, discarding damaged data, discarding redundant data, and specifying Transmission direction. The intelligent agriculture management method according to claim 1, wherein the S4 further comprises precisely controlling the amount of fertilizer applied and the amount of irrigation, specifically comprising: S401. Divide the monitored farmland into a plurality of small areas; S402. Real-time monitoring of nutrient data and moisture data of the soil in the plurality of small areas; S403. Comparing the nutrient data and the nutrient content standard value of the plurality of small regions, comparing the moisture data and the moisture content standard value of the plurality of small regions; S404. Screen out a small area where the nutrient data is smaller than the standard value of the nutrient content, and screen out a small area where the moisture data is smaller than the standard value of the moisture content; S405. Output an alarm to precisely control the amount of fertilizer applied and the amount of irrigation in each small area. The intelligent agriculture management method according to any one of claims 1 to 3, wherein the process of obtaining a crop price trend prediction result in the S5 includes: S501. Organizing historical price data of the crop, the historical price data of the crop includes a crop price Y of each day in a past period of time; S502. Obtain historical weather data of the region, where the historical weather data includes rainfall A, wind level B, and temperature C of each day in the past period of time; S503. Establish a price-related model, and analyze the rainfall correlation factor α, the wind level correlation factor β and the temperature correlation factor γ according to the price correlation model, and obtain the price weather correlation relationship. Y=αA+βB+γC; S504. Obtaining predicted weather data of the region, and combining the price weather correlation relationship Y=αA+βB+γC to predict the price of the crop, and obtaining the predicted crop price; S505. Compare crop prices with crop prices for each day in the past, and export crop price trend forecasts. The intelligent agriculture management method according to claim 4, wherein in S504, real-time crop prices and real-time weather data are first acquired, and the real-time weather data is weather data of the day, and the real-time crop price is The crop price of the day, based on the predicted crop price and the actual crop price, continuously corrects the rainfall correlation factor α, the wind level correlation factor β and the temperature correlation factor γ. The correction process specifically includes: S5041. Obtain daily forecasted crop prices and actual crop prices for a period of time in the past; S5042. The traversal calculation yields the difference between the predicted crop price and the actual crop price per day over the past period of time.

And take

Absolute value

As a set of revised reference numbers; S5043. Calculating an average value σ of all corrected reference numbers; S5044. Compare the absolute value of the difference between the predicted crop price and the real-time crop price on the day

With 2σ, when

When less than 2σ, the forecasted crop price on the day is deemed to be credible, otherwise the forecasted crop price on the day is not credible; S5045. When the forecasted crop price of the day is credible, it is determined that the real-time crop price of the day is highly correlated with real-time weather data, and the real-time crop price and real-time weather data of the day are included in the price correlation model and the rainfall correlation factor α, wind power is re-analyzed. The rank correlation factor β and the temperature correlation factor γ; when the forecast crop price of the day is not credible, and the correlation between the real-time crop price and the real-time weather data is weak on the day, the real-time crop price and real-time weather data of the day are discarded, and the original rainfall is retained. Correlation factor α, wind level correlation factor β and temperature correlation factor γ. An intelligent agricultural management system, comprising: a soil monitoring module for monitoring soil nutrient data and moisture data in real time; a weather information acquisition module, configured to obtain historical weather data and predicted weather data of the region through the Internet; a price information acquisition module for obtaining historical price data of crops via the Internet; The control center is pre-set with a standard value of nutrient content and a standard value of moisture content, the control center receiving nutrient data and moisture data of the soil; the control center comparing the nutrient data with the standard value of the nutrient content, When the nutrient data is less than the standard value of the nutrient content, an alarm message is output to remind the farmer to adjust the amount of fertilization; the control center compares the moisture data with the standard value of the moisture content, when the moisture data is less than the standard value of the moisture content When the alarm message is output, the farmers are reminded to adjust the amount of irrigation; The control center is respectively connected to the soil monitoring module, the weather information acquiring module and the price information acquiring module; The control center processes and analyzes historical price data of the crop and historical weather data of the local area, and combines the predicted weather data to obtain a crop price trend prediction result, and controls the time of harvesting the crop according to the crop price trend prediction result. . The intelligent agricultural management system according to claim 6, further comprising a plurality of forwarding nodes, wherein the soil monitoring module comprises a soil nutrient sensor and a soil moisture sensor, wherein the soil nutrient sensor is used for real-time monitoring of soil Nutrient data, the soil moisture sensor is used to monitor soil moisture data in real time; The soil nutrient sensor and the soil moisture sensor are buried under the soil beside the crop root system; The soil nutrient sensor and the soil moisture sensor are connected to the control center through the forwarding node; The soil nutrient sensor and the soil moisture sensor monitor nutrient data and moisture data of the soil according to a specific sampling frequency; The soil nutrient sensor and the soil moisture sensor periodically send data to the forwarding node, and the forwarding node receives nutrient data of the soil nutrient sensor and moisture data of the soil moisture sensor, and the nutrient data and The moisture data is sent to the control center; The soil monitoring module monitors the nutrient data and the moisture data of the soil in real time, and specifically includes: The soil nutrient sensor and the soil moisture sensor respectively collect nutrient data and moisture data of the soil; The soil monitoring module transmits the nutrient data and moisture data to the forwarding node in a broadcast form; The forwarding node pre-processes the nutrient data and the moisture data, the pre-processing includes intelligently closing and cutting the nutrient data and the moisture data, checking whether the data is complete, discarding the damaged data, and discarding the redundant data. And specify the direction of the transfer. The intelligent agricultural management system according to claim 6, wherein the monitored farmland is divided into a plurality of small areas, and the fertilization amount and the irrigation amount are precisely controlled through a small area, and specifically includes: The soil monitoring module monitors nutrient data and moisture data of the soil in the plurality of small areas in real time; The control center compares the nutrient data and the nutrient content standard value of the plurality of small regions, and compares the moisture data and the moisture content standard value of the plurality of small regions; The control center screens out a small area where the nutrient data is smaller than the standard value of the nutrient content, and screens out a small area where the moisture data is smaller than the standard value of the moisture content; The control center outputs an alarm to precisely control the amount of fertilizer applied and the amount of irrigation in each small area. An intelligent agricultural management system according to any one of claims 6-9, wherein the control center comprises: a price data unit for arranging historical price data of the crop, the historical price data of the crop including a crop price Y of each day in a past period of time; a weather data unit for processing historical weather data of the area, the historical weather data including rainfall A, wind level B and temperature C of each day in the past period of time; The model building unit is used to construct a price-related model, and according to the price correlation model, the rainfall correlation factor α, the wind level correlation factor β and the temperature correlation factor γ are analyzed, and the price weather correlation relationship Y=αA+βB+γC is obtained; a price prediction unit, configured to obtain predicted weather data of the region, and predict the price of the crop by combining the price weather correlation relationship Y=αA+βB+γC to obtain a predicted crop price; The trend forecasting unit is used to compare the predicted crop price with the crop price of each day in the past period of time, and output the crop price trend forecast result. The intelligent agricultural management system according to claim 9, wherein the price information acquisition module acquires a real-time crop price, and the weather information acquisition module acquires real-time weather data of the local area, wherein the real-time weather data is the same day. The weather control data further includes a correction unit that continuously corrects the rainfall correlation factor α, the wind level correlation factor β, and the temperature correlation factor γ according to the predicted crop price and the actual crop price, the correction unit Specifically includes: a comparator, a traverser, an averager, a determiner, and an iterator; a price comparator for obtaining forecasted crop prices and actual crop prices for each of the past period of time; A traversal that is used to traverse the difference between the predicted crop price and the actual crop price for each of the past period of time.

And take

Absolute value

As a set of revised reference numbers; An averager for calculating an average value σ of all corrected reference numbers; Judger for comparing the absolute value of the difference between the predicted crop price and the real-time crop price for the day

With 2σ, when

When less than 2σ, the forecasted crop price on the day is deemed to be credible, otherwise the forecasted crop price on the day is not credible; An iterator that uses or discards real-time crop prices and real-time weather data for the day. When the forecasted crop price for the day is credible, it is determined that the real-time crop price of the day is highly correlated with real-time weather data, and the real-time crop price and real time of the day are The weather data is included in the price-related model and reanalyzed the rainfall correlation factor α, the wind level correlation factor β and the temperature-related factor γ; when the forecasted crop price on the day is not credible, it is determined that the correlation between the real-time crop price and the real-time weather data on that day is weak. The real-time crop price and real-time weather data of the day are discarded, and the original rainfall correlation factor α, the wind level correlation factor β, and the temperature correlation factor γ are retained.

Images