Method for analyzing monitoring data on basis of crop growth knowledge base

Abstract

The present invention relates to a method for analyzing monitoring data on the basis of a crop growth knowledge base. By means of establishing a crop growth knowledge base, and according to model data of the knowledge base, performing data analysis and calculation on collected agricultural monitoring data that includes humidity data, temperature data, carbon dioxide data, illumination intensity data and soil nutrient parameters in terms of farmland soil and air, and abnormal events of crop growth are discovered in a timely manner; and on the basis of the abnormal events, matching is performed to obtain corresponding solutions, and feedback is provided after manual confirmation of the events, and thus the model data of the crop growth knowledge base is continuously adjusted and improved, thereby continuously improving the accuracy of an analysis result, such that abnormal events can be discovered and handled in a timely manner, which can not only save on labor costs of manual inspection, but can also improve the production yield of crops.

Description

A monitoring data analysis method based on crop growth knowledge base Technical Field

[0001] The present invention relates to a monitoring data analysis method based on a crop growth knowledge base, belonging to the technical field of application of smart agricultural management. Background Art

[0002] my country has been a major agricultural nation since ancient times. Whether in terms of rural population, agricultural land, or the crucial role of agriculture in my country's survival and development, my country is destined to become a major and powerful agricultural nation worldwide. Modern agriculture has become a key pillar industry driving the sustainable development of my country's economy. Smart agriculture applies IoT technology to traditional agriculture, employing sensors and software to control agricultural production through mobile or computer platforms, making traditional agriculture more intelligent. Smart agriculture fully leverages the advances of modern information technology, integrating computer and network technologies, IoT technologies, audio and video technologies, wireless communications technologies, and expert knowledge to achieve intelligent management through visual remote diagnosis, remote control, and disaster warning. Smart agriculture has become a major development direction for the modern agricultural industry, offering a modern agricultural production method with high efficiency, high productivity, and high added value.

[0003] With the continuous development of the Internet of Things (IoT), it is now possible to monitor crop growth environments by continuously collecting data on farmland air, light, soil, and other factors. However, accurately detecting anomalies in this massive amount of data and taking appropriate measures to mitigate the damage these anomalies may cause to crop growth presents a significant technical challenge. Summary of the Invention

[0004] The purpose of the present invention is to solve the above problems and provide a monitoring data analysis method based on a crop growth knowledge base. By establishing a crop growth knowledge base, the collected farmland soil and air humidity, temperature, carbon dioxide, light intensity data, and soil parameter agricultural monitoring data are analyzed according to the knowledge base, and abnormal events in farmland are discovered. Solutions are matched from the knowledge base based on the abnormal events, and then the alarm notification interface is called to notify the relevant person in charge of the abnormal events and solutions through emails, text messages, etc. The person in charge will feed back the inspection results to the knowledge base for updating and improvement through actual inspections. By continuously adjusting the crop growth knowledge base, the accuracy of the analysis results is continuously improved, abnormal events can be discovered in a timely manner and correct responses can be made, which not only saves labor costs, but also improves the efficiency of supervision of the farmland crop growth environment.

[0005] The crop growth knowledge base model is constructed to structurally represent the knowledge related to the crop growth environment, including the construction of a crop growth abnormality event knowledge base and a crop growth abnormality solution knowledge base.

[0006] The construction of the crop growth abnormal event knowledge base, whose knowledge base model includes crop type, growth time, growth location, normal range information of humidity in farmland soil and air, normal range information of temperature, normal range information of carbon dioxide, normal range information of light intensity, normal range information of soil nutrient parameters, and abnormal event information.

[0007] The construction of the crop growth abnormality solution knowledge base includes a knowledge base model including crop types, abnormal event information and treatment measure information.

[0008] The abnormal event analysis analyzes and calculates the monitoring data collected in real time based on the constructed crop growth knowledge base model to calculate whether the monitoring data is within the normal range. If the monitoring data is not within the correct indicator range, abnormal events in the crop growth process are discovered.

[0009] The solution to the abnormal event is to query and match corresponding processing measures from a knowledge base of crop growth abnormality solutions according to the abnormal event.

[0010] The abnormal event alarm is to notify the relevant person in charge of the abnormal crop growth event and the treatment measures through email, text message, etc.

[0011] The feedback of the knowledge base is improved. Feedback is provided after manual confirmation of abnormal events. If it is a true abnormal event, it is handled according to the corresponding processing measures; if it is not an abnormal event, it is fed back to the crop growth abnormal event knowledge base, and the crop growth abnormal knowledge base is continuously adjusted and improved.

[0012] The beneficial effects of this invention lie in: by establishing and continuously improving a crop growth knowledge base and continuously monitoring farmland monitoring data through an abnormal event detection algorithm, abnormal events in crop growth can be proactively identified and expert solutions can be provided. This not only allows for immediate identification of problems but also allows for accurate and effective treatment, thereby improving crop growth efficiency and yield. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] FIG1 is a schematic diagram of the overall structure of the present invention.

[0014] FIG2 is a data flow diagram of the knowledge base establishment in the present invention.

[0015] FIG3 is a flow chart of an abnormal event analysis algorithm in the present invention.

[0016] FIG4 is a flow chart of the knowledge base feedback improvement process in the present invention. DETAILED DESCRIPTION

[0017] The present invention will be further described below with reference to specific drawings and embodiments.

[0018] As shown in the overall structural diagram of Figure 1, it is a schematic diagram of the overall structure of the monitoring data analysis method based on the crop growth knowledge base. In order to achieve the timely discovery and correct handling of abnormal events in the growth of crops in farmland, and improve the efficiency and yield of crop growth. The present invention includes the construction of a crop growth knowledge base model, abnormal event analysis, and knowledge base feedback improvement. By establishing a crop growth knowledge base, the collected humidity, temperature, carbon dioxide, light intensity data, and soil parameter agricultural monitoring data in the farmland soil and air are analyzed according to the knowledge base, and abnormal events in farmland are discovered. Solutions are matched from the knowledge base based on the abnormal events, and then the alarm notification interface is called to notify the relevant person in charge of the abnormal events and solutions through emails, text messages, etc. The person in charge will feed back the inspection results to the knowledge base for updating and improvement through actual inspections. By continuously adjusting the crop growth knowledge base, the accuracy of the analysis results is continuously improved, and abnormal events can be discovered in a timely manner and responded to correctly.

[0019] As shown in the data flow diagram for knowledge base establishment in Figure 2, the crop growth knowledge base model is constructed to structure knowledge related to the crop growth environment, including the construction of a knowledge base for abnormal crop growth events and a knowledge base for solutions to abnormal crop growth. Domain knowledge data is collected from experts in the agricultural field, including growth time, humidity, temperature, carbon dioxide, light intensity data in farmland soil and air, soil nutrient parameters, abnormal events, and treatment measures. This data is converted into model data for the abnormal crop growth event knowledge base and the abnormal crop growth solution knowledge base through a data processing program and stored in a database, providing data support for abnormal event analysis and solution queries.

[0020] As shown in the flowchart of the abnormal event analysis algorithm in Figure 3, the abnormal event analysis analyzes and calculates the real-time monitoring data collected based on the constructed crop growth knowledge base model to determine whether the monitoring data is within the normal range. If the monitoring data is not within the correct indicator range, abnormal events in the crop growth process can be discovered. The specific calculation steps are as follows:

[0021] Get all monitoring data collected in the last n minutes;

[0022] Load the crop growth abnormal event knowledge base model data based on crop type and collection time;

[0023] Determine whether the air and soil temperatures are within the normal range of the knowledge base model, record whether the temperature is within the range and any abnormal data information, and continue execution;

[0024] Determine whether the air and soil humidity are within the normal range of the knowledge base model, record whether the humidity is within the range and any abnormal data information, and continue execution;

[0025] Determine whether the light intensity is within the normal range of the knowledge base model, record whether the light intensity is within the range and abnormal data information, and continue to execute;

[0026] Determine whether the air carbon dioxide concentration is within the normal range of the knowledge base model, record whether the air carbon dioxide concentration is within the range and abnormal data information, and continue to execute;

[0027] Determine whether the soil nutrient parameter data is within the normal range, record whether the soil nutrient parameters are within the range and abnormal data information, and continue to execute;

[0028] If all monitoring indicator data are within the normal range, the abnormal event analysis process ends; if any monitoring indicator data is not within the normal range of the knowledge base model, the abnormal event is matched from the crop growth abnormal event knowledge base based on the recorded abnormal indicator data.

[0029] According to the abnormal events, solution information is matched from the crop growth abnormality solution knowledge base.

[0030] Call the alarm notification interface to notify the relevant person in charge of abnormal event information and solution information through email, text message, etc.

[0031] As shown in the knowledge base feedback improvement flow chart in Figure 4, upon receiving an abnormal event alert, relevant operators conduct on-site verification in the fields. After manually confirming the abnormal event, this information is fed back to the knowledge base of abnormal crop growth events. If a true abnormal event is detected on-site, the action is taken according to the notification's instructions. If a false abnormal event is detected on-site, the information is fed back to the knowledge base. This continuous feedback helps adjust and improve the model data in the knowledge base of abnormal crop growth events, thereby continuously improving the accuracy of abnormal event detection.

Claims

1. A monitoring data analysis method based on a crop growth knowledge base, characterized in that: The method includes: by constructing a crop growth model knowledge base, analyzing the abnormal events of the farmland monitoring data collected in real time and actively discovering the abnormal events, matching solutions from the knowledge base according to the abnormal events, and then calling the alarm notification interface to notify the relevant person in charge of the abnormal events and solutions by sending emails, text messages, etc. The person in charge will feed back the inspection results to the knowledge base through actual inspection visits for continuous updating and improvement.

2. The monitoring data analysis method based on the crop growth knowledge base according to claim 1, characterized in that: The crop growth knowledge base model is constructed to structurally represent the knowledge related to the crop growth environment, including the construction of a crop growth abnormal event knowledge base and a crop growth abnormal solution knowledge base.

3. The monitoring data analysis method based on the crop growth knowledge base according to claim 1, characterized in that: The construction of the crop growth abnormal event knowledge base, whose knowledge base model includes crop types, growth time, growth location, normal range information of humidity in farmland soil and air, normal range information of temperature, normal range information of carbon dioxide, normal range information of light intensity, normal range information of soil nutrient parameters, and abnormal event information.

4. The monitoring data analysis method based on the crop growth knowledge base according to claim 1, characterized in that: The construction of the crop growth abnormality solution knowledge base, the knowledge base model includes crop types, abnormal event information and treatment measure information.

5. The monitoring data analysis method based on the crop growth knowledge base according to claim 1, characterized in that: The abnormal event analysis analyzes and calculates the monitoring data collected in real time based on the constructed crop growth knowledge base model to calculate whether the monitoring data is within a normal range. If the monitoring data is not within the correct indicator range, abnormal events in the crop growth process are discovered.

6. The monitoring data analysis method based on the crop growth knowledge base according to claim 1, characterized in that: The solution to the abnormal event is to query and match corresponding processing measures from a knowledge base of crop growth abnormality solutions according to the abnormal event.

7. The monitoring data analysis method based on the crop growth knowledge base according to claim 1, characterized in that: The abnormal event alarm is to notify the relevant person in charge of the abnormal crop growth event and the treatment measures through email, text message, etc.

8. The monitoring data analysis method based on the crop growth knowledge base according to claim 1, characterized in that: The feedback of the knowledge base is improved, and feedback is provided after manual confirmation of abnormal events. If it is a true abnormal event, it is handled according to corresponding processing measures; if it is not an abnormal event, it is fed back to the knowledge base of abnormal crop growth events, and the knowledge base of abnormal crop growth is continuously adjusted and improved.

Images