TR2021019195A2 - ARTIFICIAL INTELLIGENCE BASED FORECAST DECISION SUPPORT SYSTEM IN DISEASE, PEST AND WEED FIGHTING - Google Patents

Abstract

The invention relates to an artificial intelligence-based predictive decision support system (A) in the control of diseases, pests and weeds, which is used to economically protect plants from the damage of diseases, pests and weeds that limit plant production, and thus to increase agricultural production and improve their quality.

Description

DESCRIPTION ARTIFICIAL INTELLIGENCE IN DISEASE, PEST AND WEED CONTROL BASED FORECAST DECISION SUPPORT SYSTEM Technical Area Artificial intelligence-based predictive decision making in invention, disease, pest and weed control It's about the support system.

In particular, the invention is a disease limiting crop production. harmful and weeds To protect crops economically from their damage and to increase agricultural production in this way. Diseases, pests and weeds used to improve the quality of It is about artificial intelligence based prediction decision support system.

Invention Background Today, people's food is at the forefront of the issues that countries focus on the most. needs are met. Despite all efforts, the world population is increasing, the surface area of the world is not increasing. Besides, erosion, new Agricultural areas for reasons such as the opening of settlements, industrial facilities and roads is gradually decreasing. Since it is not possible to increase the amount of land, modern increase in the amount of product obtained from unit area using techniques and inputs necessity arises. Among the ways to increase the yield, irrigation, suitable soil cultivation, fertilization, improvement, appropriate harvest, formation of producer associations, Besides mechanization, the application of modern plant protection methods takes place. takes. Due to diseases, pests and weeds in agricultural areas in our country a decrease in productivity occurs. This is both in the income of our producers and It causes serious losses in the gross national product in our country. so the plant implementation of the protection work correctly, at the right time and with the right diagnosis. it is essential. Countries buy agro-industrial products to meet their food needs. against his situation. Herbal products and various substances of plant origin country, so plants and herbal products soon cross national borders. it is dispersed all over the world.

There is a rapid and large-scale exchange of plants in the world today. This As a result, plant and plant product parts are far away in a short time. disperses. Along with these, very dangerous diseases, harmful and weeds disperses. If no action is taken, clean countries and regions will become harmful in a short time. infected with factors. These factors, which took a long time to spread, Today, their transmission and distribution takes place in a short time.

Since any non-economic application has no place in modern plant protection, Today, the aim of agricultural struggle is to keep the product and quality within the limits of economy. is to increase. As it is known, economy includes the most basic values of our age.

The concept of economy in modern plant protection, besides the protection of the environment and health, With conscious and controlled practices, new problems, for example new pests, diseases or is working to prevent weed species from becoming dominant.

Diseases, pests and weeds in agricultural areas are important in yield. causes significant losses and decreases the profitability of the market by decreasing the product quality. decreases. Diseases, pests and weeds of which the producer is sometimes very well acquainted. Agricultural engineers, consultants, who are mixing and working in the field, and pests have difficulty in making a full diagnosis. Producers unconsciously spray disease, harmful and weeds, and As a result, they cannot get the desired product. unconsciously applied plant protection products harm the soil, water resources, natural flora, animals and plants. gives. Producers are mostly in the neighboring parcel without asking the agricultural engineers. They imitate the drug application and apply pesticides unnecessarily.

Regarding the subject in the Chinese patent application numbered CN107942302 in the literature explains the estimation system and method. The system consists of a radar, a database and, in turn, consists of a connecting host. Radar illuminates a detected sea area and The radar stores sea clutter data in its database. host, a data preprocessing module, a robust predictive model modeling module, an intelligent optimization module, a sea clutter prediction module, a segregation model update module, and a result Includes display module. According to the invention, the chaotic characteristics of radar sea clutter As for the radar sea clutter data, reconstructed, reconstructed data is subjected to non-linear fitting and to create an intelligent forecasting model Invasive weed optimization method is introduced for radar sea clutter. invention, artificial intrusive weed optimization that avoids factors and has high intelligence It provides an intelligent radar sea clutter forecasting system and method based on the algorithm.” The application referred to relates to a radar system on invasive weed in the seas. Radar An intelligent forecasting model based on data on the chaotic features of sea clutter. forms.

In the patent application numbered CN111387169 in the literature, explains the module, a multi-jet path based on artificial intelligence technology and relates to the field of machinery. Multiple spray paths based on artificial intelligence technology, targeted precision sorting module with controlled spray interval, especially It is applied to smart field sorting of a large number of crops in the agricultural field. Module, Used for multiple types of transport platforms and quick snap-on mounting can be provided.

The device is suitable for field weeding of a large number of field crops at different growth cycles. suitable. According to the device, a slightly convolutional neural network for recognizing weed information so that agent type selection, target spray parameters and flows, pressure, for automatic optimization of spray head angles and settling zone planning the foundations have been laid. A multi-channel target spray unit can be used to capture different types of wild can spray different types of herbicides on grass, a synchronous belt slide table, weed spray nozzles for precise target spraying on weeds. moves transversely and a spray interval can be adjusted according to the following. foreign the size of the weed groups, thanks to the targeted spray system, the pesticide use can be reduced, pollution to an ecological environment can be reduced and operating efficiency can be developed effectively.” statements are included.

In the aforementioned patent application, the device is used in a wide variety of fields in different growth cycles. only according to the species characteristics designed for field selection of plants. It works according to growth differences. Different types of weeds on different It is designed as an agricultural machine that can spray all kinds of herbicides.

It's just about weed.

Again, in the patent application numbered CN109676624 in the literature, aims. Field target detection robot platform, a vehicle body and an artificial consists of an intelligence system group, where the vehicle body is a frame platform, a walking and steering system, a double-wing vision mechanism and an intelligent control system. consists of system. A wheel hub in the power, drive and steering system supplied by the engine. platform to perform a routing function. A stepper motor is used to control the direction of feed. Above Based on the aforementioned, field crops and weeds in the artificial intelligence system collection of information and the determination of the detected plants by transmitting this information to the computer. and a camera in the double-wing sight mechanism is used for its classification.

The intelligent control system in the vehicle body, the walking and steering system and a Used to control the steering system. Meanwhile, the vehicle body, artificial intelligence subject to speed adjustment and progressive change of direction according to the instructions of the system. In the mentioned application, it is related to an area target detection robot and it is related to field plant and foreign collecting weed information and transmitting this information to the computer used for detection and classification. Just the camera through the plant It takes the image and sends it to a computer in the center.

Because of the disadvantages mentioned above, disease, pest and weed Introducing a new predictive decision support system based on artificial intelligence need has been felt.

Disclosure of the Invention Starting from this position of the technique, the aim of the invention is to eliminate the existing disadvantages. A new artificial intelligence-based method in the control of diseases, pests and weeds that removes predictive decision support system.

Another object of the invention is to control disease, pest and weeds that limit crop production. by protecting plants economically from their damage and by increasing agricultural production in this way. is to put forward a system that increases the production quality.

Another purpose of the invention. our farmers both as a struggle and economically. automatic regional information on most troublesome diseases, pests and weeds mapping as well as agricultural engineers and farmers can benefit from and is to present an application that you can use.

Another object of the invention is the end user (agricultural engineers and farmers) regional mapping and forecasting as data expands to reveal a dynamic system Explanation of Figures Figure - 1 Artificial intelligence in the control of diseases, pests and weeds, which is the subject of the invention A schematic view of a predictive decision support system Reference Numbers A- Artificial Intelligence Based Prediction in Disease, Pest and Weed Control Decision Support System Disease, Pest and Weed Formations Diseased Fruit/Vegetable Application Raw Data Artificial Intelligence Engine 9753:“93539 Learned Database 7. Master Databases 8. Classified Data 9. Expert Pool .Feedback Unit Detailed Description of the Invention In this detailed description, the innovation subject of the invention is only intended for a better understanding of the subject. It is explained with examples that will not have any limiting effect on the subject.

The invention is responsible for the damage of diseases, pests and weeds that limit crop production. to protect plants economically and in this way to increase agricultural production and quality artificial in the control of diseases, pests and weeds used to raise It is an intelligence-based prediction decision support system (A) and its feature is; disease, pest and foreign whether weed formations (1) and/or diseased fruit/vegetables (2) are photographed or not. analysis and image detection, the detected image is processed by image processing. creating raw data (4) by uploading it to the application (3), raw data of the incoming photos sending the data (4) to a central server where the artificial intelligence engine (5) runs, disease, pest and weed occurrences present in the main databases (7) (1) and analyzed with deep learning trained with a learned database (6) and the subject classified data with data processing technique in software with the determinations of experts (8) means that the artificial intelligence engine (5), which includes the artificial intelligence-based system; The images uploaded in the main databases (7) are analyzed in the algorithmic analysis module. artificial intelligence model data learned by classified data (8) is obtained and the learned artificial intelligence model obtained The process of registering the classified data (8) that has data in the learned database (6) is characterized by containing the steps.

In Figure - 1, the subject of the invention is artificial in the control of disease, pest and weed. A schematic view of the intelligence-based predictive decision support system (A) is pictured.

The subject of the invention is artificial intelligence-based control in the control of diseases, pests and weeds. predictive decision support system (A), disease, pest and weed occurrences (1), diseased fruit/vegetable (2), app (3), raw data (4), artificial intelligence engine (5), learned database (6), master databases (7) and classified data (8). is occurring.

Disease, pest and weed occurrences selected in the application of the invention (1) and The image detected by photographing or analyzing the diseased fruit/vegetable (2), The raw data (4) is created by uploading it to the application (3) with image processing. Moreover Diseases in the main databases of the Ministry of Agriculture and Forestry and Universities (7), harmful and weed photographs are also used.

The raw data (4) of the incoming photographs are stored in a centralized location where the artificial intelligence engine (5) works. sent to the server, the disease, harmful and weed occurrences (1) with deep learning trained with a learned database (6) are analyzed and the data processing technique in the software is determined with the determinations of the subject experts. It is recorded as (8) classified data.

Analysis of new images within the system with the artificial intelligence engine (5) are carried out and controlled by experts. Artificial intelligence based system including artificial intelligence engine (5); images uploaded in the main databases (7), artificially learned by analyzing and detecting differences in the algorithmic analysis module The classified data (8) which is the intelligence model data is obtained and the obtained learned classified data (8) to learned database (6), which is artificial intelligence model data is recorded.

The main databases (7) operate in relational and no-sql (unrelated) architecture and It is being prepared for data retention. Images in the mentioned artificial intelligence engine (5) computer-vision (computerized) which is included in the processing artificial intelligence algorithm module. It analyzes it by working with vision) algorithms and artificial intelligence algorithms. Artificial CNN with evolving neural networks to find the best result in the development process of intelligence Algorithm methods are used.

Artificial intelligence-based prediction in disease, pest and weed control, which is the subject of the invention decision support system (A), both disease, pest and weed in agricultural production Species and genus that can detect their occurrence (1) as well as diseased fruit/vegetables (2) Databases learned with deep learning software system trained with differences (6) using computer-vision algorithms and artificial intelligence engine It will analyze by working with (5) based artificial intelligence algorithms.

Claims (1)

CLIENTS The invention is an artificial intelligence-based prediction decision support system (A) in the control of diseases, pests and weeds, which is used to economically protect plants from the damage of diseases, pests and weeds that limit plant production, and thus to increase agricultural production and improve their quality. disease, pest and weed formations (1) and/or diseased fruit/vegetables (2) are photographed or analyzed and images are determined, the image is uploaded to the application (3) by image processing and raw data (4) is created, belonging to the incoming photographs Sending the raw data (4) to a central server running the artificial intelligence engine (5), analyzing the disease, pest and weed occurrences available in the main databases (7) (1), and deep learning trained with the learned database (6), and the analysis of the subject matter experts. recording as classified data (8) with the data processing technique in the software with its determinations, artificial intelligence engine (5), which includes the artificial intelligence-based system; By analyzing the images uploaded in the main databases (7) in the algorithmic analysis module and detecting the differences, classified data (8) which is the learned artificial intelligence model data is obtained. is characterized by containing the steps. It is an artificial intelligence-based prediction decision support system (A) in the control of diseases, pests and weeds in accordance with claim 1, and its feature is; The use of disease, pest and weed photos in the main databases of the Ministry of Agriculture and Forestry and Universities (7) includes the process step. It is an artificial intelligence-based prediction decision support system (A) in the control of diseases, pests and weeds in accordance with any of the above claims, and its feature is; It includes the process step of preparing the main databases (7) for Big Data holding by working in relational (relational) and no-sql (unrelated) architecture. It is an artificial intelligence-based prediction decision support system (A) in the control of diseases, pests and weeds in accordance with any of the above claims, and its feature is; It includes the processing step of analyzing by working with computer-vision algorithms and artificial intelligence algorithms included in the image processing artificial intelligence algorithm module in the artificial intelligence engine (5). . It is an artificial intelligence-based prediction decision support system (A) in the control of diseases, pests and weeds in accordance with any of the above claims, and its feature is; The use of evolving neural networks and CNN Algorithm methods to find the best result in the development process of artificial intelligence includes the process step. . It is an artificial intelligence-based prediction decision support system (A) in the control of diseases, pests and weeds in accordance with any of the above claims, and its feature is; computer-vision (computer vision) using databases (6) learned with a deep learning software system trained with species and breed differences that can detect both disease, pest and weed formations (1) and diseased fruits/vegetables (2) in agricultural production algorithms and artificial intelligence engine (5)-based artificial intelligence algorithms by working with the analysis process includes the step.