WO2023090433A1 - Agrochemical composition, information processing device, and computer program - Google Patents

Abstract

The present invention relates to an agrochemical composition, an information processing device, and a computer program.

Description

Agrochemical composition, information processing device and computer program

The present invention relates to an agrochemical composition, an information processing device and a computer program.

Currently, a wide variety of pesticide formulations developed for paddy rice are on the market. Such agrochemical formulations include, for example, herbicides, insecticides and fungicides.

Examples of herbicides include initial agents that are sprayed before the emergence of weeds, before sowing rice seeds or transplanting, and immediately after sowing or transplanting; A large number of chemicals have been developed and marketed according to the active ingredient and the appropriate time of application, such as late-stage agents and late-stage agents that are applied in the middle to late stages of paddy rice growth to control weeds that could not be controlled and weeds that are difficult to control. As insecticides and fungicides, seed treatment agents, box application agents, Honda application agents and the like have been developed and marketed according to the characteristics of the active ingredients.

From the viewpoint of efficient control, mixtures containing multiple active ingredients have been developed, and by using such mixtures, various diseases, pests and/or weeds can be efficiently controlled. . On the other hand, it is not always the case that the products on the market match the conditions of diseases, pests, and/or weeds that are specific to the field, and in some cases, more active ingredients than necessary are being sprayed, resulting in a burden on the environment. is concerned. In view of the current situation, applying an appropriate amount of an agrochemical formulation containing a single or multiple active ingredients according to field conditions will lead to a reduction in the environmental load.

In addition, if the disease, pest and/or weed situation in the field cannot be accurately grasped, it is impossible to select an appropriate chemical, and it may not be possible to completely control the disease, pest and/or weed. In order to control diseases, pests and/or weeds that could not be done, additional chemical agents will be sprayed, which may increase the labor, cost and environmental load of the producer. In addition, fields that are not adequately controlled for diseases, pests and/or weeds can lead to poor crop plant growth and reduced yields. In other words, it is essential for efficient farming to apply an appropriate chemical at the right time and in the required amount.

Conventionally, an unmanned flying device operates a unit that injects a liquid agent at a location determined by a processing unit based on the result of analysis of an image of farmland captured by a camera (Patent Reference 7). However, this technique does not select an appropriate chemical according to disease damage, insect pests and/or weeds in paddy fields.

From the perspective of efficient application of chemicals, it is an effective means to select multiple pesticide formulations containing a single active ingredient, mix them in appropriate amounts, and apply them in one go. However, there are various dosage forms of agricultural chemical formulations such as granules, emulsions, flowable formulations and wettable granules, and there are some problems when they are mixed and used. For example, (1) pesticide formulations that can be diluted and sprayed (emulsions, flowables, wettable granules, etc.) are formulations optimized for each active ingredient, and composition are different from each other, the application of a mixture prepared by mixing releases more chemical substances, which are formulation auxiliary ingredients, into the environment. In addition, (2) when a plurality of selected pesticide formulations are mixed, changes in the physical and chemical properties of the diluent In some cases, spraying becomes difficult due to spray nozzle clogging due to sedimentation and aggregation. In order to avoid these problems, it is necessary to develop formulations that use common auxiliary ingredients for active ingredients with various physical and chemical properties.

Furthermore, from the viewpoint of efficient application of agricultural chemicals to a field, for example, when the field is a paddy field, it is effective to apply the agricultural chemical locally and use the water from the paddy field to spread the active ingredient over the entire paddy field. be. Several techniques have already been proposed for active ingredient diffusion. For example, as a paddy rice herbicide, a flowable agent with excellent diffusivity that can be applied from the ridge without dilution (Patent Document 1), a jumbo agent that throws floating granules packed in water-soluble film from the ridge (Patent Document 1). 2), etc., have been developed and sold. Furthermore, some formulations for topical application contain a dispersant so that the active ingredient can sufficiently diffuse in water after application ( Patent Documents 4, 5 and 6). In addition, as an application method, wettable application of water dispersible granules has been proposed (Patent Document 3). However, many of the pesticides used for these are mixtures prepared by mixing a plurality of pesticide formulations, which is not preferable from the viewpoint of the aforementioned environmental load. In addition, as an insecticide, a surf agent has been developed that spreads the active ingredient by dropping it on the surface of water and spreading an oil film. unfavorable from this point of view.

Furthermore, when multiple pesticide formulations containing a single active ingredient are selected and mixed in an appropriate amount for application, it is important to ensure the diffusion of the pesticide formulation using paddy water to distribute the active ingredient throughout the paddy field. important to spread

Japanese Patent Publication No. 7-47522 Japanese Patent No. 2957751 JP 2010-083869 A JP 2011-126786 A JP-A-2002-338403 JP 2012-077097 A International Publication No. 2020/225278

The purpose of the present invention is to provide an agrochemical composition, an information processing device and a computer program.

An agricultural chemical composition according to one aspect is defined as "a liquid agricultural chemical composition containing the following components (a) and (b1), or a solid agricultural chemical composition containing the following components (a) and (b2):
(a) at least one active ingredient selected from the group consisting of an active ingredient having an insecticidal effect, an active ingredient having a fungicidal effect and an active ingredient having a herbicidal effect;
(b1) 1 to 200 g/L of an anionic dispersant;
(b2) 1-20% w/w of an anionic dispersant”.

An information processing device according to one aspect is defined as "comprising at least one processor, wherein the at least one processor detects at least one damage occurring in a specific area included in a target area where paddy rice is cultivated." Acquiring type information indicating the type and amount information indicating the amount of each of the at least one harm that occurred in the specific area, and spraying the chemical to the specific area based on the type information and the amount information and determining the amount of each of the plurality of pesticide compositions.

A method according to one aspect is described as "a method executed by at least one processor executing computer readable instructions, wherein for a specified area included in a target area in which paddy rice is grown, acquiring type information indicating the type of at least one harm and amount information indicating the amount of each of the at least one harm that occurred in the specific area; and based on the type information and the amount information, a step of determining a plurality of pesticide compositions constituting a chemical agent to be applied to a specific area, and the amount of each of the plurality of pesticide compositions."

A computer program according to one aspect provides, when executed by at least one processor, "type information indicating at least one type of damage that has occurred in a specific area included in a target area where paddy rice is cultivated. and obtaining amount information indicating the amount of each of the at least one harm that occurred in the specific area, and based on the type information and the amount information, a plurality of chemicals constituting the chemical to be sprayed in the specific area functioning the at least one processor to determine a pesticide composition and an amount of each of the plurality of pesticide compositions.

An information processing apparatus according to another aspect is "a target area in which seedlings grown from a nursery box in which rice seeds are sown directly or seeded with rice seeds are transplanted. obtaining type information indicating the type of at least one harm that occurred in the specific region, and amount information indicating the amount of each of the at least one harm that occurred in the specific region; A plurality of pesticide compositions constituting chemical agents applied to rice seeds directly sown in the specific area or seeds sown in nursery boxes for transplanting seedlings to the specific area, based on the type information and the amount information. and determining the amount of each of said plurality of pesticide compositions.

According to another aspect, a method is described as "a method executed by at least one processor executing computer readable instructions, wherein seedlings grown from nursery boxes directly seeded with rice seeds or seeded with rice seeds are Type information indicating the type of at least one damage that occurred in the specific region, and amount information indicating the amount of each of the at least one damage that occurred in the specific region, with respect to the specific region included in the target region to be transplanted. and, based on the type information and the amount information, a chemical to be applied to the rice seed directly sown in the specific area or the seed rice sown in a nursery box for transplanting seedlings to the specific area. determining the constituent plurality of pesticide compositions and the amount of each of the plurality of pesticide compositions.

A computer program according to another aspect is "a specific area included in a target area in which seed rice is directly sown or seedlings grown from a nursery box in which seed rice is sown by being executed by at least one processor are transplanted. obtain type information indicating the type of at least one harm that occurred in the specific region, and amount information indicating the amount of each of the at least one harm that occurred in the specific region, and obtain the type information and the amount Based on the information, a plurality of agrochemical compositions constituting a chemical agent applied to the seed directly sown in the specific area or the seed sown in the nursery box for transplanting the seedlings to the specific area; the at least one processor to determine the amount of each of the pesticidal compositions.

According to the present invention, an agrochemical composition, an information processing device and a computer program can be provided.

FIG. 1 is a block diagram showing an example of the overall configuration of a determination system according to one embodiment. FIG. 2 is a block diagram showing an example of the hardware configuration of the information processing device 10A installed in the server device 10, the mobile spraying device 20 and the terminal device 30 in the determination system shown in FIG. FIG. 3 is a flow diagram showing an example of operations performed by the decision system 1 shown in FIG. FIG. 4 is a flow diagram specifically showing an example of a part (ST100) of the operations executed by the determination system 1 shown in FIG. FIG. 5 is a schematic diagram conceptually showing an example of information generated using a learning model by the information processing device 10A in the determination system shown in FIG. FIG. 6 is a schematic diagram showing an example of a zone determination method executed by the information processing device 10A in the determination system shown in FIG. FIG. 7 is a flow diagram specifically showing an example of a part (ST200) of the operations executed by the determination system 1 shown in FIG. FIG. 8 is a block diagram showing an example of the hardware configuration of the mobile spraying device 20 shown in FIG. FIG. 9 is a flowchart specifically showing an example of a part (ST300) of the operations executed by the decision system 1 shown in FIG. FIG. 10 is a flow diagram illustrating another example of operations performed by the decision system 1 shown in FIG. FIG. 11 is a flowchart specifically showing an example of a part (ST1000) of the operations executed by decision system 1 shown in FIG. FIG. 12 is a flow diagram specifically showing an example of a part (ST2000) of the operations executed by decision system 1 shown in FIG. FIG. 13 is a diagram showing application locations of an agricultural chemical composition by drone spraying. FIG. 14 is a diagram showing the relationship between the input amount of an anionic dispersant and heat generation.

Hereinafter, section <1> mainly describes a system for preparing a drug by mixing an agricultural chemical composition, and sections <2> and <3> describe an agricultural chemical composition that can be prepared by this system and the like. Methods of controlling diseases, pests, and/or weeds, etc., in which the systems, etc., can be used are described.

<1> Determination system for determining a plurality of agricultural chemical compositions to be mixed Hereinafter, various embodiments of the present invention will be described with reference to the accompanying drawings. In addition, the same reference numerals are attached to common components in the drawings. Also, it should be noted that components depicted in one drawing may be omitted in another drawing for convenience of explanation. Furthermore, it should be noted that the attached drawings are not necessarily drawn to scale.

The various systems, methods and devices described herein should not be construed as limited in any way. In practice, the present disclosure is directed to each of the various disclosed embodiments, combinations of these various embodiments with each other, and combinations of portions of these various embodiments with each other. All novel features and aspects are addressed. The various systems, methods, and apparatus described herein are not limited to any particular aspect, particular feature, or combination of such particular aspects and particular features, The articles and methods described herein do not claim that one or more particular advantages exist or that any problem is solved. Moreover, various features or aspects of the various embodiments described herein, or portions of such features or aspects, may be used in combination with each other.

Although the operations of some of the various methods disclosed herein have been described in a particular order for convenience, the description in such a manner is such that the particular order follows a particular order. It should be understood to include rearranging the order of the above operations unless otherwise required by the text. For example, operations described sequentially are in some cases permuted or performed concurrently. Furthermore, for purposes of brevity, the accompanying drawings do not illustrate the various ways in which the various features and methods described herein can be used with other features and methods.

Any theories of operation, scientific principles or other theoretical statements presented herein in connection with the disclosed devices or methods are provided for better understanding and to limit the technical scope. not intended to be. The devices and methods in the appended claims are not limited to devices and methods that operate according to methods described by such theory of operation.

Any of the various methods disclosed herein can be implemented using a plurality of computer-executable instructions stored on one or more computer-readable media and executed on a computer. can be The one or more media are non-transitory computer-readable storage media, such as, for example, at least one optical media disc, volatile memory components, or non-volatile memory components. obtain. Here, the plurality of volatile memory components includes, for example, DRAM or SRAM. The plurality of non-volatile memory components also includes, for example, hard drives and solid state drives (SSDs). Further, the computer includes any computer available on the market, including, for example, smartphones and other mobile devices having computing hardware.

Any of such computer-executable instructions for implementing the techniques disclosed herein may be generated and used during implementation of the various embodiments disclosed herein. Any data may be stored on one or more computer-readable media (eg, non-transitory computer-readable storage media). Such computer-executable instructions may, for example, be part of a separate software application, or may be accessed or downloaded via a web browser or other software application (such as a remote computing application). can be part of a software application that is Such software may be implemented, for example, in a network environment, either on a single local computer (eg, as a process running on any suitable computer available on the market) or using one or more network computers. (eg, the Internet, a wide area network, a local area network, a client-server network (such as a cloud computing network), or other such network).

For clarity, only certain selected aspects of various software-based implementations are described. Other details that are well known in the art are omitted. For example, the technology disclosed herein is not limited to any particular computer language or program. For example, the techniques disclosed herein may be implemented by software written in C, C++, Java, or any other suitable programming language. Similarly, the technology disclosed herein is not limited to any particular computer or type of hardware. Certain details of suitable computers and hardware are well known and need not be described at length here.

Further, various such software-based embodiments (e.g., including computer-executable instructions for causing a computer to perform any of the various methods disclosed herein) can be uploaded, downloaded, or accessed remotely by any suitable communication means. Such suitable means of communication include, for example, the Internet, World Wide Web, intranets, software applications, cables (including fiber optic cables), magnetic communications, electromagnetic communications (including RF communications, microwave communications, infrared communications), Including electronic communication or other such means of communication.

1. Overview of Determination System FIG. 1 is a block diagram showing an example of the overall configuration of a determination system according to one embodiment. As shown in FIG. 1, the determination system 1 can include, for example, at least one server device 10, at least one mobile application device 20, and at least one terminal device 30. As shown in FIG. These devices 10 , 20 , 30 are interconnectable via network 2 .

Although FIG. 1 shows only one server device 10 as at least one server device 10 as an example, it is also possible to use a plurality of server devices 10 . Also, although FIG. 1 shows only one mobile application device 20 as at least one mobile application device 20 as an example, it is also possible to utilize a plurality of mobile application devices 20. . Similarly, although FIG. 1 shows only one terminal device 30 as at least one terminal device 30 as an example, a plurality of terminal devices 30 may be used.

Network 2 is limited to mobile phone networks, wireless networks, fixed phone networks, the Internet, intranets, local area networks (LAN), wide area networks (WAN), and/or Ethernet networks. can be included without The wireless network is limited to RF connections via, for example, Bluetooth®, WiFi (such as IEEE 802.11a/b/n), WiMax, cellular, satellite, laser, infrared, etc. can be included without

The server device 10 is a device equipped with an information processing device (not shown). Such a server device 10 can be, for example, a web server, cloud server, personal computer, workstation, supercomputer, or the like.

The mobile spraying device 20 is equipped with an information processing device (not shown) and is controlled by this information processing device to spray chemicals. Such a mobile spraying device 20 may be a traveling spraying device (eg, a spraying device that travels on the ground or the surface of water) or a flying spraying device (eg, a drone-type spraying device).

The terminal device 30 is a device equipped with an information processing device (not shown). Such a terminal device 30 may be a smart phone, a feature phone, a mobile phone, a portable information terminal, a personal computer, a tablet, or the like.

In the determination system shown in FIG. 1, to put it briefly, the server device 10 determines at least one Type information indicative of the type of harm and quantity information indicative of the amount of each of the at least one harm that occurred in the particular area may be received and obtained from various devices. Such various devices may include mobile application devices 20, terminal devices 30, and/or other devices (not shown) connectable to network 2. FIG.

Furthermore, based on the type information and amount information received in this way, server device 10 selects a plurality of pesticide compositions that make up the chemical agent to be sprayed on the specific area, and the amount of each of the plurality of pesticide compositions. can be determined. Such determination can be executed by an information processing device (not shown) installed in the server device 10 . Note that such a determination is made in place of or in addition to the information processing device mounted on the server device 10, the information processing device (not shown) mounted on the mobile spraying device 20, the information mounted on the terminal device 30 It can also be executed by a processing device (not shown) and/or an information processing device (not shown) installed in another device connectable to the network 2 . To achieve this, the device making the decision may receive type and quantity information from other devices (10, 20, 30, etc.) via network 2. FIG. Alternatively, the device making the determination may receive the type and quantity information, such as via a user interface provided on the device.

Furthermore, as an option, the mobile spraying device 20 can prepare a drug by mixing the amounts determined as described above for each of the plurality of pesticide compositions determined as described above. Alternatively, mobile application device 20 may obtain the prepared drug itself from a preparation device (not shown) that is also capable of such preparation. As a result, the mobile spraying device 20 moves to the specific area (a certain area in the field) in the target area (a field or the like), and sprays the chemical to the paddy rice existing in the specific area. can be done.

2. Configuration of Information Processing Device Installed in Server Device 10, etc. The server device 10, the mobile spraying device 20 and the terminal device 30 can be equipped with the information processing device 10A. FIG. 2 is a block diagram showing an example of the hardware configuration of the information processing device 10A installed in the server device 10, the mobile spraying device 20, and the terminal device 30 in the determination system according to one embodiment.

As shown in FIG. 2, the information processing device 10A mainly includes a central processing unit 11, a main storage device 12, an input/output interface device 13, an input device 14, an auxiliary storage device 15, and an output device 16. , can be included. These devices are connected to each other by data buses and/or control buses.

The central processing unit 11 is one processor called "CPU (Central Processing Unit)". The central processing unit 11 can perform operations on the instructions and data stored in the main memory 12 and store the results of the operations in the main memory 12 . Furthermore, the central processing unit 11 can control the input device 14, the auxiliary storage device 15, the output device 16, and the like through the input/output interface device 13. FIG. Information processor 10A may include one or more such central processing units 11 .

The main storage device 12 is referred to as "memory" and stores instructions and data received from the input device 14, the auxiliary storage device 15 and the network 400 via the input/output interface device 13, and the operation results of the central processing unit 11. can be memorized. The main memory device 12 may include, but is not limited to, RAM (Random Access Memory), ROM (Read Only Memory), and/or flash memory.

The auxiliary storage device 15 is a storage device having a larger capacity than the main storage device 12. The secondary storage device may store instructions and data (computer programs) that make up, for example, an operating system and certain applications. This specific application is executed by the information processing device 10A mounted on the server device 10 (or the mobile spraying device 20 or the terminal device 30), so that the information processing device 10 as a whole becomes the server device 10 (or mobile application). It can function as the spraying device 20 and the terminal device 30). Furthermore, the auxiliary storage device 15 can be controlled by the central processing unit 11 to transmit these instructions and data (computer programs) to the main storage device 12 via the input/output interface device 13 . Auxiliary storage device 15 can include, but is not limited to, a magnetic disk device and/or an optical disk device.

The input device 14 is a device that takes in data from the outside, and can include at least one sensor, touch panel, button, keyboard and/or mouse, etc. without being limited to these. It should be noted that the at least one sensor can include, for example, an RGB camera, a multispectral camera, a hyperspectral camera, and/or a high wavelength spectrum camera.

The output device 16 can include, but is not limited to, a display device, a touch panel and/or a printer device.

In such a hardware configuration, the central processing unit 11 sequentially loads instructions and data (computer programs) constituting a specific application stored in the auxiliary storage device 15 into the main storage device 12, and loads them. It can operate on instructions and data. Thereby, the central processing unit 11 controls the input device 14 and/or the output device 16 via the input/output interface device 13, or also controls other devices (e.g. , server device 10, mobile spraying device 20 and/or terminal device 30).

The information processing device 10A can also include one or more microprocessors and/or a graphics processing unit (GPU), etc. instead of or together with the central processing unit 11.

3. Operation of Decision System (Part 1)
Next, a specific example of operations performed by the determination system 1 having the above configuration will be described with reference to FIG. FIG. 3 is a flow diagram showing an example of operations performed by the decision system 1 shown in FIG.

As shown in FIG. 3, the operations performed by the decision system 1 are, broadly speaking, the step of obtaining information about a region of interest (or a specific region included in the region of interest) (hereinafter referred to as "ST") 100; , ST200 for determining a plurality of pesticide compositions that make up the drug, and the amount of each pesticide composition, based on the information obtained in ST100. Furthermore, optionally, the operation performed by the determination system 1 is to distribute the chemical prepared by mixing each of the plurality of pesticide compositions determined in ST200 in the determined amount to the region of interest (or region of interest). and ST 300 that distributes to a specific area included in the ST 300 .
Specific examples of each of ST100, ST200, and ST300 will be sequentially described below.

3-1. Operation Executed in ST100 FIG. 4 is a flow diagram specifically showing an example of a part (ST100) of the operations executed by the decision system 1 shown in FIG.
Here, the target area refers to an area in which paddy rice is cultivated (including, for example, an area in which seedlings are transplanted and/or an area in which seed rice is directly sown). It can be a partial area and/or multiple fields. Harm refers to disease damage occurring in the target area (or paddy rice grown in the target area), pests occurring in the target area (or paddy rice grown in the target area), and/or weeds occurring in the target area. , including but not limited to.

First, in ST102, the information processing device 10A can acquire an image of the target area. Such an image may be, for example, an image acquired by the mobile spraying device 20 or the like capturing an image of the target region from above the target region (such an image is sent to the information processing device 10A via the network 2). may be sent). In another example, such an image may be an image obtained by a user located in a building, helicopter, aircraft, etc., capturing this target area using a camera, which is the input device 14 such as the terminal device 30. (Such images can be transmitted to the information processing device 10A via the network 2). In yet another example, such an image may be an image acquired by the information processing device 10A via the network 2 from some device (such as a server device that provides images of aerial photographs taken across the country).

In ST104, the information processing apparatus 10A inputs the image acquired in ST102 to the learned learning model, thereby determining which pixel included in the image has which damage or which damage has occurred. You can identify whether it has occurred or not.

Such a trained learning model performs machine learning (particularly deep learning), including an input layer, an output layer, and a plurality of hidden layers arranged between the input layer and the output layer. It can be a possible learning model. Each of these learning models is composed of an image (input data) of a rice plant in which a certain damage has occurred, and a pixel (one or more pixels) in the image in which the damage has occurred. Pre-learning is performed using information (output data) indicating whether or not there is, and a large number (for example, tens of thousands or more) of teacher data. Such a learning model has a large number of coefficients used in the learning model so as to reduce the error between the data output when the input data of each teacher data is input and the output data of the teacher data. Learning can be performed by optimizing.

In the first example, the information processing device 10A can have such a learned learning model. In a second example, the information processing device 10A receives (acquires), via the network 2, such a learned learning model stored in a device different from the device on which the information processing device 10A is mounted. be able to. In a third example, the information processing device 10A transmits images via the network 2 to such a learned learning model stored in a device different from the device in which the information processing device 10A is installed. By transmitting, the output data of this learning model can be received (obtained).

By inputting an image into such a learned learning model, the information processing apparatus 10A can acquire information indicating which damage has occurred in which pixel in the image from this learning model. can.

FIG. 5 is a schematic diagram conceptually showing an example of information generated by the information processing device 10A using the learning model in the determination system shown in FIG. For simplicity of explanation, FIG. 5 shows an example of information generated for each of a very small portion of the unit area in the target area by inputting an image of the target area into the learning model. It is shown.

FIG. 5 shows only six unit areas 120A to 120I as an example. Each unit area can be represented by arbitrary pixels, but in this example it can be represented by 25 pixels (5 pixels×5 pixels). Each unit area presents a square in this example, but may present any shape such as a polygon, a circle, an oval, a trapezoid, or a rhombus in another example.

For each unit area, each pixel can be associated with information specific to the damage that occurred at the position corresponding to that pixel. For example, focusing on the unit area 120A, the position corresponding to the pixel 120A1 is associated with information "1" specific to the first damage that occurred at this position. Here, as an example, each location corresponding to a total of 10 pixels may be associated with information "1" specific to the first harm that occurred at this location. The first type of damage is disease damage occurring in the target area (or paddy rice grown in the target area), pests occurring in the target area (or paddy rice grown in the target area), and weeds occurring in the target area. is one of us.

Also, the location corresponding to pixel 120A2 may be associated with information "null" specific to the event that no harm has occurred at this location in one example, but in another example there is nothing at this location. Specific information such as “0” can be associated with an event that no harm has occurred.

Further, for example, focusing on the unit area 120G, the position corresponding to the pixel 120G1 is associated with information "4" specific to the fourth damage that occurred at this position. Here, as an example, each location corresponding to a total of 5 pixels may be associated with information "4" specific to the fourth harm that occurred at this location. The fourth type of harm is disease damage occurring in the target area (or paddy rice grown in the target area), pests occurring in the target area (or paddy rice grown in the target area), and weeds occurring in the target area. is one of us.

Also, the position corresponding to pixel 120G2 is associated with information "5" specific to the fifth damage that occurred at this position. Here, as an example, each location corresponding to a total of three pixels may be associated with information "5" specific to the fifth harm that occurred at this location. The fourth type of harm is disease damage occurring in the target area (or paddy rice grown in the target area), pests occurring in the target area (or paddy rice grown in the target area), and weeds occurring in the target area. is one of us.

Furthermore, the position corresponding to pixel 120G3 is associated with information "6" specific to the sixth damage that occurred at this position. Here, as an example, each location corresponding to a total of two pixels may be associated with information "6" specific to the sixth harm that occurred at this location. The sixth type of harm is disease damage occurring in the target area (or paddy rice grown in the target area), pests occurring in the target area (or paddy rice grown in the target area), and weeds occurring in the target area. is one of us.

Furthermore, the location corresponding to pixel 120G4 may in one example be associated with the information "null" specific to the event that no harm has occurred at this location, while in another example Specific information such as “0” can be associated with an event that no harm has occurred.

Other unit areas will not be described in detail, but the concept is the same as that described for the unit areas 120A and 120G.

Returning to FIG. 4, in ST106, the information processing apparatus 10A uses the information output from the learning model in ST104 (for example, the information illustrated in FIG. 5) for each of the plurality of unit regions included in the target region. It is possible to acquire and store (for example, in the auxiliary storage device 15) "unit type information" that indicates at least one type of damage that has occurred in the unit area.

Focusing on the example shown in FIG. 4, for the unit area 120A, the information processing apparatus 10A sets information "1" indicating the type of damage that has occurred in the unit area 120A (information "1" corresponding to the first damage). ) can be acquired as unit type information. For each of the unit areas 120B and 120C, the information processing apparatus 10A can also acquire information "1" indicating the type of damage that has occurred in this unit area as unit type information.

Further, information processing apparatus 10A sets information "2" and information "3" (information "2" and information "3" corresponding to the second damage) indicating the type of harm that occurred in unit area 120D for unit area 120D. Information "3") corresponding to the damage of the unit can be acquired as the unit type information. The information processing apparatus 10A can also acquire information "2" and information "3" indicating the type of harm that has occurred in each of the unit areas 120E and 120F as unit type information.

Further, the information processing apparatus 10A, regarding the unit area 120G, sets the information "4", the information "5", and the information "6" (information corresponding to the fourth harm " 4”, information “5” corresponding to the fifth harm, and information “6” corresponding to the sixth harm) can be acquired as the unit type information. The information processing apparatus 10A can also acquire information "4", information "5", and information "6" indicating the type of harm that occurred in the unit region 120H as the unit type information for the unit region 120H.

Furthermore, for the unit region 120I, the information processing apparatus 10A acquires information “null” (or “0” or the like) indicating an event in which no harm has occurred in this unit region 120I as unit type information. be able to.

In one example, the information processing device 10A can acquire unit type information for all unit regions included in the target region. It is also possible to obtain unit type information for each unit area (one or more unit areas).

Furthermore, in another example, the information processing device 10A can acquire "type information" indicating at least one type of damage that has occurred in the specific area included in the target area. For example, when the target area is one agricultural field and the specific area is a partial area included in this one agricultural field, the information processing device 10A It is also possible to obtain type information indicating the type of at least one harm that occurred. In this case, the information processing apparatus 10A can acquire the type information by searching information associated with each pixel forming the partial area in the information acquired from the learning model in ST104. . For example, when the specific area is an area configured by the unit areas 120D and 120G, the information processing device 10A displays information "2" and information "3" indicating the type of harm that occurred in these unit areas. , information “4”, information “5” and information “6” can be obtained as type information.

The information identifying the target area and the information identifying the specific area in the target area may be input by the user via the input device 14 of the information processing device 10A and acquired by the information processing device 10A, for example.

Returning to FIG. 4, next, in ST108, the information processing apparatus 10A uses the information output from the learning model in ST104 (for example, the information illustrated in FIG. 5) to determine each of the plurality of unit regions included in the target region. , the amount of at least one harm caused in this unit area can be determined. As a result, the information processing apparatus 10A acquires unit amount information indicating at least one amount of harm that has occurred in each of the plurality of unit areas included in the target area (for example, stores the unit amount information in the auxiliary storage device 15). ) can be stored.

Focusing on the example shown in FIG. 4, the information processing apparatus 10A determines that the unit area 120A has ten pieces of information "1" indicating the type of damage that has occurred in the unit area 120A. 10” (information indicating that there are “10” pieces of information “1” corresponding to the first harm/information indicating that the density of information “1” is “10”) is acquired as unit amount information. can do. Information processing apparatus 10A also sets information "1-10" indicating that there are 10 pieces of information "1" indicating the type of harm that has occurred in unit area 120B and 120C to each of unit areas 120B and 120C. It can be obtained as information.

Further, the information processing apparatus 10A sets the information "2-4" indicating that there are four pieces of information "2" indicating the type of damage that has occurred in the unit area 120D (the second damage is information indicating that there are "4" pieces of corresponding information "2"/information indicating that the density of information "2" is "4") and information indicating the type of harm that occurred in this unit area 120D " Information "3-6" indicating that there are six "3" (Information indicating that there are "6" pieces of information "3" corresponding to the third harm/The density of the information "3" is "6" information indicating that it is) can be acquired as the unit amount information. Information processing apparatus 10A also stores information "2-4" indicating that there are four pieces of information "2" indicating the type of harm that has occurred in each of unit areas 120E and 120F, and information "2-4" indicating that unit area 120D Information "3-6" indicating that there are six pieces of information "3" indicating the type of harm that occurred in the above can be obtained as unit amount information.

Furthermore, information processing apparatus 10A, for unit area 120G, sets information "4-5" indicating that there are five pieces of information "4" indicating the type of harm that occurred in unit area 120G, Information “5-3” indicating that there are three pieces of information “5” indicating the type of harm that has occurred, and information “5-3” indicating that there are two pieces of information “6” indicating the type of harm that has occurred in this unit area 120G. can be acquired as the unit amount information. Information processing apparatus 10A also sets information "4-5" indicating that there are five pieces of information "4" indicating the type of harm that occurred in unit area 120H, Information "5-3" indicating that there are three pieces of information "5" indicating the type of damage, and indicating that there are two pieces of information "6" indicating the type of damage that occurred in this unit area 120H. Information "6-2" can be obtained as unit amount information.

In one example, the information processing apparatus 10A can acquire unit class information for all unit regions included in the target region. It is also possible to obtain unit amount information for each of the unit areas (one or more unit areas).

Furthermore, in another example, the information processing device 10A can also acquire "amount information" indicating the amount of at least one damage that has occurred in the specific area included in the target area. For example, when the target area is one agricultural field and the specific area is a partial area included in this one agricultural field, the information processing device 10A It is also possible to obtain quantity information indicating the quantity of at least one harm that has occurred. In this case, the information processing apparatus 10A can acquire the type information by searching information associated with each pixel forming the partial area in the information acquired from the learning model in ST104. . For example, when the specific area is an area composed of the unit area 120D and the unit area 120G, the information processing device 10A can acquire the following information as amount information.
・Information “2-4” indicating that there are four pieces of information “2” indicating the type of harm that occurred in these unit areas
・Information “3-6” indicating that there are six pieces of information “3” indicating the type of harm that occurred in these unit areas
・Information “4-5” indicating that there are five pieces of information “4” indicating the type of harm that occurred in these unit areas
・Information “5-3” indicating that there are three pieces of information “5” indicating the type of harm that occurred in these unit areas
・Information “6-2” indicating that there are two pieces of information “6” indicating the type of damage that has occurred in these unit areas

Returning to FIG. 4 again, until now, as an embodiment, the information processing apparatus 10A acquires unit type information (or type information) in ST104 and ST106 via ST102, and acquires unit amount information (or amount information) in ST108. information) has been described. However, in another embodiment, information processing apparatus 10A acquires unit type information (or type information) in ST106 without going through ST102 and ST104, and acquires unit amount information (or amount information) in ST108. It is also possible to obtain Specifically, for example, the information processing device 10A acquires unit type information (or type information) from some device via the network 2 in ST106, and acquires unit type information (or type information) from some device via the network 2 in ST108. , it is also possible to obtain unit amount information (or amount information). In this case, the certain device may be another information processing device capable of acquiring (generating) this information by executing the processing shown in ST102 to ST108, or It may be another information processing device that can acquire (generate) these pieces of information by executing arbitrary processing other than the processing.

Next, as an option, in ST110, the information processing device 10A can determine at least one zone from the target area using the unit type information and the unit amount information (or the type information and the amount information).
Here, it can be said that a zone is a plurality of unit areas that are common or substantially common in the type of harm that has occurred and the amount of harm that has occurred.

A zone determination method executed by the information processing device 10A will be described with reference to FIG. FIG. 6 is a schematic diagram showing an example of a zone determination method executed by the information processing device 10A in the determination system shown in FIG. This FIG. 6 is expressed in correspondence with FIG. 5 referred to above.

First, focus on the unit area 120A. Ten pieces of information "1" are present in the unit area 120A. That is, the single type information regarding the unit area 120A has information "1", and the unit amount information regarding the unit area 120A has information "1-10". The information processing apparatus 10A retrieves the unit type information and the unit amount information regarding the other unit regions, so that the unit type information regarding each of the unit regions 120B and 120C has only the information "1", and the unit region It can be identified that the unit quantity information for each of 120B and unit area 120C both have only the information "1-10". In other words, the information processing device 10A can identify that the unit areas 120A, 120B, and 120C are common to each other in terms of both the type of harm that has occurred and the amount of harm that has occurred. As a result, the information processing device 10A can determine an area including all of the unit areas 120A, 120B, and 120C as the first zone 130. FIG.

Next, focus on the unit area 120D. In the unit area 120D, there are four pieces of information "2" and six pieces of information "3". That is, the single type information regarding the unit area 120D has the information "2" and the information "3", and the unit amount information regarding the unit area 120D has the information "2-4" and the information "3-6". Information processing apparatus 10A searches for unit type information and unit amount information regarding other unit regions, and finds that unit type information regarding each of unit region 120E and unit region 120F includes only information “2” and information “3”. and that the unit quantity information for each of unit area 120E and unit area 120F both have information "2-4" and information "3-6" only. That is, the information processing device 10A can identify that the unit areas 120D, 120E, and 120F are common to each other in terms of both the type of harm that has occurred and the amount of harm that has occurred. As a result, the information processing device 10A can determine a region including all of the unit regions 120D, 120E, and 120F as the second zone 131. FIG.

Next, focus on the unit area 120G. In the unit area 120G, five pieces of information "4" exist, three pieces of information "5" exist, and two pieces of information "6" exist. That is, the single-type information about the unit area 120G has information "4", information "5" and information "6", and the unit amount information about the unit area 120G has information "4-5", information "5-3" and It has information "6-2". The information processing device 10A retrieves the unit type information and the unit amount information regarding the other unit regions, and finds that the unit type information regarding the unit region 120H has only the information "4", the information "5" and the information "6". , that the unit quantity information for the unit area 120H has only the information '4-5', the information '5-3' and the information '6-2'. That is, the information processing apparatus 10A can identify that the unit areas 120G and 120H are common to each other in terms of both the type of harm that has occurred and the amount of harm that has occurred. As a result, the information processing device 10A can determine a region including all of the unit regions 120G and 120H as the third zone 132. FIG.

In the example shown in FIG. 6, the information processing device 10A identifies a plurality of areas that are "common" in terms of the type of harm that has occurred and the amount of harm that has occurred, and includes all of the plurality of areas thus identified. A region can be defined as a zone. However, in another embodiment, the information processing device 10A identifies a plurality of regions that are "substantially common" in the type of harm caused and the amount of harm caused, and the entirety of the plurality of thus identified regions. The containing area can also be determined as a zone.

Here, "substantially common" means not only the case where the type of harm caused in a certain unit area completely matches the type of harm caused in another unit area, but also the case where the kind of harm caused in another unit area A case in which the type of harm caused in the unit area and the type of harm caused in the other unit area are similar (both types can be regarded as substantially the same) may also be included.

In addition, "substantially common" means only when the amount (density) of harm caused in a certain unit area and the amount (density) of harm caused in another unit area completely match. and the error between the amount (density) of harm caused in a certain unit area and the amount (density) of harm caused in another unit area is an arbitrary predetermined value or less (both amounts can be regarded as substantially the same).

Returning to FIG. 4, next, in ST112, the information processing device 10A generates zone information indicating each zone (one or more zones) determined in ST110 and stores it (for example, in the auxiliary storage device 15). can be done.

Specifically, focusing on the example shown in FIG. 6, the information processing apparatus 10A indicates that the first zone 130 is an area including the unit areas 120A, 120B, and 130C. The indicated zone information can be generated and stored. Further, for the second zone 131, the information processing device 10A can generate and store zone information indicating that the second zone 131 is an area including the unit areas 120D, 120E, and 130F. Similarly, for the third zone 132, the information processing device 10A can generate and store zone information indicating that the third zone 132 is an area including the unit areas 120G and 120H.

As will be described later, by using such zone information, the mobile spraying device 20 can distribute a plurality of agrochemical compositions determined corresponding to the zone to each agrochemical composition determined corresponding to the zone. amount of the mixed agent can be applied to the zone.

Note that the information processing apparatus 10A can also execute the processing in ST110 and ST112 (FIG. 4) described above in ST200 (FIG. 3).

3-2. Operation Executed in ST200 FIG. 7 is a flow diagram specifically showing an example of a part (ST200) of the operations executed by the decision system 1 shown in FIG. The information processing device 10A can perform the operation shown in FIG. 7 for each specific area included in the target area or each zone included in the target area. Of course, the information processing device 10A can also perform the operation shown in FIG. 7 for any one specific area included in the target area or any one zone included in the target area.

First, in ST202, the information processing device 10A outputs type information indicating at least one damage that has occurred in a specific area (for example, one farm field or a partial area included in one farm field) and the identification information. Amount information can be obtained that indicates the amount of each of the at least one harm that occurred in the area. Such information has already been obtained and written by the information processing apparatus 10A in ST106 and ST108.

Here, when the zone determined in ST110 (see FIG. 4) is used as the specific area, the information processing device 10A acquires the zone information stored in ST112 (see FIG. 4) corresponding to the zone. Then, unit type information and unit amount information corresponding to each unit area identified by this zone information can be obtained.

Next, in ST204, the information processing device 10A can acquire various types of information to be input to the learned first learning model or the learned first decision tree model. Specifically, the information processing device 10A can acquire information (1) to information (5) shown below.

(1) Soil information on the type of soil in a specific area (zone) (2) Harm occurrence information on damage that has occurred in the past in a specific area (zone) (3) Information on seeds buried in the soil in a specific area (zone) Seed burial information (4) Pest prevalence information on the prevalence of chemical-resistant pests in specific areas (zones) (5) Weather forecast information on predicted meteorological data for the cultivation period of paddy rice in specific areas (zones)

Information (1), ie, soil information, can be, for example, information indicating (identifying) the type of soil (sand, clay, etc.) in a specific area (zone). This information (1) can be used in consideration of the possibility that the type of soil in a specific area (zone) affects the damage that occurs in that soil, the speed and timing of the growth of this damage, and the like.

Information (2), ie, harm occurrence information, can be information indicating (identifying) harm that occurred in the past in a specific area (zone). This information (2) can be used in view of the fact that harm that has already occurred in the past in a particular area (zone) is likely to occur in the same particular area (zone) now as well.

Information (3), ie, seed burial information, may be information indicating (identifying) seeds (weed seeds) buried in a specific area (zone). Considering that when a certain seed is buried in a specific area (zone), there is a high possibility that weeds corresponding to that seed will still grow in the same specific area (zone), this information ( 3) can be used.

Information (4), pest prevalence information, indicates (identifies) which pests with resistance to agents (fungicides, insecticides and/or herbicides) are currently prevalent in a particular area (zone). ) information. If a harm with a certain resistance is currently prevalent in an area that includes a specific area (zone), the possibility that such a harm with such resistance will still occur in the same specific area (zone). This information (5) can be used in view of the high .

Information (5), i.e., weather forecast information, indicates (identifies) weather data (temperature, humidity, weather, and/or precipitation, etc.) predicted for the period of rice cultivation in a specific zone. can be information. Considering the possibility that these meteorological data during the period of paddy rice cultivation in a specific zone (zone) will affect the damage that occurs in the same specific zone (zone) and the speed and timing of the growth of this damage, This information (5) can be used.

The above information can be obtained by the user using the menu screen displayed on the output device (display, etc.) 16 of the information processing device 10A and using the input device 14 (keyboard, mouse, touch panel, etc.) of the information processing device 10A. It may be information to be input by using.

Next, in ST206, the information processing apparatus 10A selects at least one of the information acquired in ST202 (type information and amount information) and the information acquired in ST204 (that is, information (1) to information (5) (at least one of the above) into the learned first learning model or the learned first decision tree model to obtain the following information (6) to information (8) can be done.

(6) Predictive information on the type and amount of harm that will occur in a specific area (zone) (7) Predictive information on the growth of the harm that will occur in the specific area (zone) information on phytotoxicity

Information (6), ie, harm occurrence prediction information, can literally be information indicating (identifying) the type of harm that will occur in a specific area (zone) and the amount of this harm.

The information (7), that is, the damage growth prediction information, indicates (identifies) at what timing (at what speed and at what time) the damage shown in the information (6) will occur. can be information.

Information (8), ie, phytotoxicity information, can be information indicating (identifying) what kind of phytotoxicity (side effects, etc.) will occur in a specific area (zone).

A first learning model (such as a machine learning/deep learning model with an input layer, multiple hidden layers, and an output layer) and a first decision tree model each contain type information, quantity information, and information ( Learning is performed in advance using 1) to information (5) (input data) and information (6) to information (8) (output data) and a large number (for example, tens of thousands or more) of teacher data. Such a first learning model or first decision tree model reduces the error between the data output when the input data in each teacher data is input and the output data in the teacher data, Learning can be performed by optimizing a number of coefficients (or a number of parameters) used in the first learning model or first decision tree model.

In the first example, the information processing device 10A can have such a trained first learning model and a trained first decision tree model. In a second example, the information processing device 10A stores such a learned first learning model and a learned first decision tree stored in a device different from the device on which the information processing device 10A is mounted. The model can be received (obtained) via the network 2 . In a third example, the information processing device 10A stores such a learned first learning model or a learned first decision tree stored in a device different from the device in which this information processing device 10A is mounted. By transmitting necessary information (for example, at least one of information (1) to information (5)) to the model via the network 2, the first learning model or the first Information (6) to Information (8), which are output data of the decision tree model, can be received (obtained).

Next, in ST208, information processing apparatus 10A inputs information (6) to information (8) acquired in ST206 to the second learned model or the second learned decision tree model. , information (9) and information (10) shown below can be obtained and stored (eg, in the auxiliary storage device 15).

(9) Information indicating (identifying) a plurality of pesticide compositions constituting a chemical sprayed in a specific area (zone) (10) Indicating the amount of each of the plurality of pesticide compositions indicated in information (9) (identifying) information

Further, as an option, information processing apparatus 10A inputs information (6) to information (8) acquired in ST206 to the second learned model or the second learned decision tree model, In addition to information (9) and information (10), at least one of information (11) and information (12) shown below can also be acquired and stored (for example, in auxiliary storage device 15).

(11) Optimal continuous processing information regarding the optimal method of continuously applying (processing) the drug mixed according to information (9) and information (10) (12) Mixed according to information (9) and information (10) Optimal treatment time information on the best time to spray (treat) the chemical

Information (11), i.e., optimum continuous processing information, is the method (for example, a method of continuously spraying the medicine every two weeks, etc.) that is mixed according to information (9) and information (10). It can be information that indicates (identifies) whether it is best to disseminate (process) at .

Information (12), i.e., optimal treatment timing information, indicates at what time (for example, March) it is optimal to spray (treat) the medicine mixed according to information (9) and information (10). can be information indicating (identifying) the

Such a second learning model and a second decision tree model each include information (6) to information (8) (input data), information (9) to information (12) (output data), Learning is performed in advance using a large number (for example, tens of thousands or more) of teacher data. Such a second learning model or second decision tree model reduces the error between the data output when the input data in each teacher data is input and the output data in the teacher data, Learning can be performed by optimizing a number of coefficients (or a number of parameters) used in the second learning model or second decision tree model.

In the first example, the information processing device 10A can have such a trained second learning model and a trained second decision tree model. In a second example, the information processing device 10A stores such a learned second learning model and a learned second decision tree stored in a device different from the device on which the information processing device 10A is mounted. The model can be received (obtained) via the network 2 . In a third example, the information processing device 10A stores such a learned second learning model or a learned second decision tree stored in a device different from the device on which the information processing device 10A is mounted. By transmitting necessary information (for example, information (6) to information (8)) to the model via the network 2, the output data of this second learning model or second decision tree model Certain information (9) to information (12) can be received (obtained).

In ST208, information processing apparatus 10A displays the acquired information (9) and information (10) (further information (11) and/or information (12)) to the user via output device 16. is also possible.

Next, in ST210 as an option, the information processing device 10A can acquire various types of information to be input to the learned third learning model or the learned third decision tree model. Specifically, the information processing apparatus 10A can acquire information (13) and “at least one” of information (14) to information (16) shown below.

(13) Information on the general effects of drugs against harm indicated by the above information (6) (Prediction information on occurrence of harm) (14) Information on the types and effects of drugs used in the past in a specific area (zone) ( 15) Information on the composition of the soil in the specified area (zone) (16) Information on the water holding capacity of the specified area (zone)

Information (13) may be information indicating (identifying) an effect commonly known as the effect of a drug on the harm indicated by information (6).

The information (14) can be information indicating (identifying) the type of drug actually used in the past in a specific area (zone) and the effect actually obtained in the past for that drug. Even if a drug is known to have a generally high (or low) efficacy against a particular harm, it may be possible that the drug has actually been used in a specific area (zone) in the past. In spite of this, there may be facts such as the drug not being able to exert a sufficient effect (or being able to exert a sufficient effect). In view of such cases, this information (14) can be used.

The information (15) can be information indicating (identifying) the composition of the soil in a specific area (zone). This information (15) can be used given the high likelihood that the composition of the soil in a particular area (zone) will affect the efficacy of the pesticide composition applied to this area of interest.

The information (16) may be information indicating (identifying) the water retention capacity of a specific area (zone). This information (16) can be used given the high likelihood that the water retention capacity of a particular area (zone) will affect the efficacy of an agrochemical composition applied to this area of interest.

The above information can be obtained by the user using the menu screen displayed on the output device (display, etc.) 16 of the information processing device 10A and using the input device 14 (keyboard, mouse, touch panel, etc.) of the information processing device 10A. It may be information to be input by using.

Next, in ST212 as an option, information processing apparatus 10A learns the information acquired in ST210, that is, information (13) and at least one of information (14) to information (16). By inputting to the third learning model or the learned third decision tree model, the following information (9) and information (10) described above are acquired and stored (for example, in the auxiliary storage device 15) can be done. In this case, information (13) may be essential information.

(9) Information indicating a plurality of agricultural chemical compositions that constitute the chemical sprayed in a specific area (zone) (10) Information indicating the amount of each of the plurality of agricultural chemical compositions indicated in information (9)

Further, as an option, information processing apparatus 10A converts the information acquired in ST210, that is, information (13) and at least one of information (14) to information (16) into a learned third By inputting to the learning model or the learned third decision tree model, in addition to the following information (9) and information (10) described above, at least one of information (11) and information (12) can be acquired and stored (for example, in the auxiliary storage device 15). In this case, information (13) may be essential information.

(9) Information indicating a plurality of agricultural chemical compositions constituting the chemical sprayed in a specific area (zone) (10) Information indicating the amount of each of the plurality of agricultural chemical compositions indicated in information (9) (11) Optimal continuous processing information on the optimal method of continuously spraying (processing) the drug mixed according to information (9) and information (10) (12) Spraying the drug mixed according to information (9) and information (10) Best time to process information about the best time to (process)

A third learning model (a machine learning/deep learning model with an input layer, multiple hidden layers, an output layer, etc.) and a third decision tree model each contain information (13) to information (16) ( Input data), information (9) to information (12) (output data), and a large number (for example, tens of thousands or more) of teacher data are used for pre-learning. Such a third learning model or third decision tree model reduces the error between the data output when the input data in each teacher data is input and the output data in the teacher data, Learning can be performed by optimizing a number of coefficients (or a number of parameters) used in the third learning model or third decision tree model.

In the first example, the information processing device 10A can have such a learned third learning model and a learned third decision tree model. In a second example, the information processing device 10A stores such a learned third learning model and a learned third decision tree stored in a device different from the device in which this information processing device 10A is mounted. The model can be received (obtained) via the network 2 . In a third example, the information processing device 10A uses such a learned third learning model or a learned third decision tree stored in a device different from the device on which the information processing device 10A is mounted. By transmitting necessary information (for example, information (13) to information (16)) to the model via the network 2, the output data of this third learning model or third decision tree model Certain information (9) to information (12) can be received (obtained).

In ST212, the information processing apparatus 10A displays the acquired information (9) and information (10) (further information (11) and/or information (12)) to the user via the output device 16. is also possible.

In ST208 described above, the information processing device 10A identifies the plurality of pesticide compositions that constitute the chemical sprayed in the specific area and the amount of each pesticide composition by the information (9) and the information (10), respectively. can do. At this point, the information processing apparatus 10A can achieve a prima facie purpose. However, by executing ST210 and ST212 as the options described above, information processing apparatus 10A converts information (13) and at least one of information (14) to information (16) into learned information. Information (9) and information (10) based on these information can be obtained by inputting to the third learning model or the learned third decision tree model. That is, the information processing device 10A, based on the information (13) and at least one of the information (14) to the information (16), configures the chemical to be sprayed in the specific area, and the plurality of pesticide compositions , and the amount of each pesticide composition can be obtained. As a result, the user receives information (9) and information (10) (further information (11) and/or information (12)) indicated to information processing apparatus 10A in ST208, and information (11) and/or information (12) indicated to information processing apparatus 10A in ST212. Two types of information can be recognized as options, including information (9) and information (10) (and also information (11) and/or information (12)).

3-3. Operations performed in ST300 In this ST300, the mobile spraying device 20 sprays a chemical agent prepared by mixing each pesticide composition determined in ST200 in the determined amount to a specific area (or zone). can do.
Before describing the operations performed in ST300, first, the hardware configuration of mobile spraying device 20 will be briefly described with reference to FIG.

FIG. 8 is a block diagram showing an example of the hardware configuration of the mobile spraying device 20 shown in FIG. As shown in FIG. 8, the mobile spraying device 20 includes the information processing device 10A described above, a drive source 21 and a drive mechanism 22 for moving the mobile spraying device 20, and a current position of the mobile spraying device 20. A GPS (Global Positioning System) unit 23 that acquires position information, a plurality of tanks 24 each containing a unique agricultural chemical composition, and a plurality of agricultural chemical compositions in any of these multiple tanks 24 are mixed. It may include a preparation device 25 for preparing the medicament and one or more nozzles 26 for dispensing the medicament supplied from the preparation device 25 .

The drive source 21 can be an engine and/or a motor that can generate a drive force for moving the mobile spraying device 20 and provide it to the drive mechanism 22 under the control of the information processing device 10A. .

The drive mechanism 22 is an arbitrary mechanism that converts the drive force supplied from the drive source 21 into the propulsion force of the mobile spraying device 20, and includes gears, shafts, tires, caterpillars, and/or propellers. can include, without limitation, The drive mechanism 22 is also an arbitrary mechanism for controlling the moving direction and/or moving speed of the mobile spraying device 20 under the control of the information processing device 10A. and/or may include, without limitation, ladders and the like.

Under the control of the information processing device 10A, the GPS unit 23 can provide the information processing device 10A with position information regarding the current position of the mobile spraying device 20 using well-known GPS technology.

Each of the plurality of tanks 24 can contain an agrochemical composition unique to that tank among the plurality of agrochemical compositions.

The preparation device 25 can be coupled to each of the plurality of tanks 24 via pipes, valves and sensors that the preparation device 25 has. The preparation device 25 is controlled by the information processing device 10A to obtain a plurality of agricultural chemical compositions from a plurality of tanks among the plurality of tanks 24 and mix them to prepare a drug.

Specifically, the preparation device 25 may have a valve that is provided in a pipe that connects the preparation device 25 and each of the plurality of tanks 24 and that can be opened and closed under the control of the information processing device 10A. can. The preparation device 25 opens the valve designated by the information processing device 10A, and can measure the amount of the agricultural chemical composition passing through the valve with a sensor. The preparation device 25 can return the valve to the closed state when the amount of the agricultural chemical composition measured by this sensor reaches the amount specified by the information processing device 10A. As a result, the preparation device 25 designates (determines) the agricultural chemical composition contained in any one of the plurality of tanks 24 designated (determined) by the information processing device 10A. The drug can be prepared by taking and mixing the required amount.

Each of the one or more nozzles 26 is coupled to the brewing device 25 . Each nozzle 26 can be controlled by the information processing device 10A to spray (spray) the medicine supplied from the preparation device 25 .

Next, operations performed by the mobile spraying device 20 having the above configuration will be described with reference to FIG. FIG. 9 is a flowchart specifically showing an example of a part (ST300) of the operations executed by the decision system 1 shown in FIG.

First, in ST302, the information processing device 10A loads (acquires) the plurality of agricultural chemical compositions determined in ST200 and the amount of each agricultural chemical composition for the specific region (or each zone) from the auxiliary storage device 15. can do.

Next, in ST304, the information processing device 10A can acquire position information indicating the position of the specific area (or each zone). In one example, this positional information includes the positional information (of the target region) given to the image by the device that captured the image of the target region in ST102, and the specific region (each region) for the target region derived from this image. Zones) relative positional relationship and. In another example, this position information can be obtained by the information processing apparatus 10A by being input by the user via the input device 14 of the information processing apparatus 10A at arbitrary timing.

Next, in ST306, the information processing device 10A can first use the GPS unit 23 to acquire current position information indicating the current position of the mobile spraying device 20. Furthermore, based on the current position thus obtained and the position of the specific area (or each zone) obtained in ST304, information processing apparatus 10A determines the movement route (positions corresponding to a plurality of points to be sequentially passed through). information) can be determined. Such travel routes can be determined, for example, using techniques utilized in well-known navigation systems. Here, in the case of spraying the chemical over multiple zones, the information processing device 10A can determine the movement route so as to pass through all of the multiple unit areas included in each zone. For example, in the example shown in FIG. 6, the first zone 130 passes through all of the unit regions 120A, 120B, and 120C, and the second zone 131 passes through all of the unit regions 120D, 120E, and 120F. As for the third zone 132, a movement route can be determined so as to pass through all of the unit areas 120G and 120H.

In ST308, the information processing device 10A can control the drive source 21 and the drive mechanism 22 to start moving the mobile spraying device 20. Further, information processing apparatus 10A can control drive source 21 and drive mechanism 22 to move mobile spraying apparatus 20 along the movement route determined in ST306. This can be achieved by controlling drive source 21 and/or drive mechanism 22 so that the current position of mobile spraying device 20 provided from GPS unit 23 follows the movement route determined in ST306.

In ST310, the information processing device 10A, for example, in a state approaching the specific region (or each zone), the plurality of pesticide compositions determined corresponding to the specific region (or each zone), each of the determined The preparation device 25 can be controlled to mix only the amount of the pesticidal composition. As a result, the preparation device 25 performs the above-described operation to mix a plurality of pesticide compositions determined for the specific region (or each zone) by the determined amount of each pesticide composition, thereby Agents can be prepared that correspond to specific regions (or each zone).

Furthermore, the information processing device 10A instructs to open the nozzles when the difference between the current position of the mobile spraying device 20 and the position of the specific region (or each zone) becomes equal to or less than a threshold. A signal can be sent to the nozzle 26 to Thereby, the nozzle 26 can spray (jet) the medicine supplied from the preparation device 25 .

Furthermore, the information processing device 10A instructs to open the nozzles while the difference between the current position of the mobile spraying device 20 and the position of the specific region (or each zone) is equal to or less than the threshold. A signal can continue to be sent to the nozzle 26 to do so. As a result, the mobile spraying device 20 can spray chemicals corresponding to the specific area while it is in a position corresponding to the position of the specific area (or each zone).

Thereafter, the information processing device 10A instructs to close the nozzles when the difference between the current position of the mobile spraying device 20 and the position of the specific region (or each zone) exceeds the threshold. A signal can be sent to the nozzle 26 to This allows the nozzle 26 to stop ejecting the medicine.

In the case where the mobile spraying device 20 sprays chemicals on multiple specific areas (or multiple zones), ST308 and ST310 may be executed sequentially for each specific area (each zone).

It should be noted that the operations performed by the information processing device 10A on the specific region described above can be applied to the operations performed on the zones by the information processing device 10A.

4. Operation of Decision System (Part 2)
So far, the aspect (first aspect) of determining the amount of a plurality of agricultural chemical compositions to be contained in the chemical agent to be sprayed in a specific area (or zone) included in the target area (first aspect). , have explained. However, this first aspect is a treatment (applied ) is similarly applicable to the aspect (second aspect) of determining a plurality of pesticide compositions to be contained in the pesticide and the amount of each pesticide composition. In this Section 4, the target area refers to the area where the seed is directly sown and/or the area where the seedlings grown from the nursery box in which the seed is sown is transplanted. It can be a partial area and/or multiple fields.

In the following, in order to avoid redundant description, only the parts of the second mode that differ from the above-described first mode will be briefly described with reference to FIG. FIG. 10 is a flow diagram illustrating another example of operations performed by the decision system 1 shown in FIG.

As shown in FIG. 10, the operations performed by decision system 1 are, broadly speaking, ST1000 of obtaining information about a region of interest (or a specific region included in the region of interest); rice seed directly sown in the target area (or a specific area included in the target area) or seed rice sown in nursery boxes for transplanting seedlings to this target area (or specific area). may include a plurality of pesticide compositions that make up the drug, and an ST2000 that determines the amount of each pesticide composition. Furthermore, optionally, the operation performed by the determination system 1 is to apply a drug prepared by mixing each of the plurality of pesticide compositions determined in ST2000 in a determined amount to a region of interest (or region of interest). ST3000 that treats the seed directly sown in the target area (or the specific area included in the target area) or the seed sown in the nursery box for transplanting the seedlings to this target area (or the specific area).

First, focus on the ST1000. FIG. 11 is a flowchart specifically showing an example of a part (ST1000) of the operations executed by decision system 1 shown in FIG. The operation shown in FIG. 11 lacks ST102 and ST104 shown in FIG.

ST1002 corresponds to ST106 shown in FIG. However, in ST1002, for each of a plurality of unit areas included in the target area, the "unit type information" indicating at least one type of damage that has occurred in this unit area is actually collected in relation to the unit area, for example. It can be the information of the past (last year etc.) that was made. In one example, such unit type information may be input by the user via the input device 14 of the information processing apparatus 10A and acquired by the information processing apparatus 10A. In another example, such unit type information can be acquired by the information processing device 10A via the network 2 from any other device (server device or the like) that collects and stores such information.

ST1004 corresponds to ST108 shown in FIG. However, in ST1004, for each of the plurality of unit areas included in the target area, the "unit amount information" indicating the amount of each of at least one harm that occurred in this unit area is, for example, actually can be information obtained in In one example, such unit amount information may be input by the user via the input device 14 of the information processing device 10A and acquired by the information processing device 10A. In another example, such unit type information can be acquired by the information processing device 10A via the network 2 from any other device (server device or the like) that collects and stores such information.

ST1006 and ST1008 correspond to ST110 and ST112 shown in FIG. 4, respectively.

Returning to FIG. 10, next focus on ST2000. FIG. 12 is a flow diagram specifically showing an example of a part (ST2000) of the operations executed by decision system 1 shown in FIG.

ST2002 to ST2006 respectively correspond to ST204 to ST208 shown in FIG. In the following, ST2002 to ST2006 will be described with reference to FIG. 7 only with respect to the points different from those described above.

In ST2002, the information processing device 10A can acquire the following information (1) to information (5) to be input to the trained first learning model or the trained first decision tree model.

(1) Soil information on the type of soil in a specific area (zone) (2) Harm occurrence information on damage that has occurred in the past in a specific area (zone) (3) Chemical-resistant damage in a specific area (zone) (4) Weather forecast information on forecasted meteorological data for the period during which paddy rice is cultivated in a specific area (zone).

These information (1) to information (4) respectively correspond to information (1), information (2), information (4) and information (5) described above in relation to ST204.

Next, in ST2004, information processing apparatus 10A converts at least one of the information acquired in ST2002 (that is, at least one of information (1) to information (4)) to the learned third The following information (5) to information (7) can be obtained by inputting into one learning model or the first learned decision tree model.

(5) Predictive information on the type and amount of harm that will occur in a specific area (zone) (6) Predictive information on the growth of the harm that will occur in the specific zone (7) Chemical injury that will occur in the specific zone information on phytotoxicity

These information (5) to information (7) respectively correspond to information (6) to information (8) described above in relation to ST206.

A first learning model (such as a machine learning/deep learning model having an input layer, multiple hidden layers, and an output layer) and a first decision tree model each contain information (1) to information (4) ( Input data), information (5) to information (7) (output data), and a large number (for example, tens of thousands or more) of teacher data are used for pre-learning. Such a first learning model or first decision tree model reduces the error between the data output when the input data in each teacher data is input and the output data in the teacher data, Learning can be performed by optimizing a number of coefficients (or a number of parameters) used in the first learning model or first decision tree model.

Next, in ST2006, information processing apparatus 10A inputs information (5) to information (7) acquired in ST2004 to the learned second learning model or the learned second decision tree model. , information (8) and information (9) shown below can be obtained and stored (for example, in the auxiliary storage device 15).

(8) Information indicating a plurality of pesticide compositions that make up the chemical applied to the seed directly sown in the specific area (or information indicating a plurality of agricultural chemical compositions that constitute the drug)
(9) information indicating the amount of each of the plurality of pesticide compositions indicated in information (8);

Such a second learning model and a second decision tree model each include information (5) to information (7) (input data), information (8) to information (9) (output data), Learning is performed in advance using a large number (for example, tens of thousands or more) of teacher data. Such a second learning model or second decision tree model reduces the error between the data output when the input data in each teacher data is input and the output data in the teacher data, Learning can be performed by optimizing a number of coefficients (or a number of parameters) used in the second learning model or second decision tree model.

Returning to FIG. 10 again, in ST3000, a chemical agent can be prepared by mixing a plurality of pesticide compositions determined for the specific area (zone) in ST2000 by the amount of each pesticide composition determined. In one example, the agent thus prepared is applied to rice seeds that are directly sown in specific areas (zones). The seed rice treated in this manner is sown in a specific area (zone). In another example, the drug thus prepared is applied to rice seeds, and the treated rice seeds are sown in nursery boxes. After that, the seedlings grown in this nursery box are transplanted to a specific area (zone).

It should be noted that the operations performed by the information processing device 10A on the specific region described above can be applied to the operations performed on the zones by the information processing device 10A.

As described above, according to the various embodiments disclosed in the present application, for a chemical to be sprayed in a specific area (zone) included in a target area where paddy rice is cultivated, a plurality of pesticide compositions that constitute the chemical and the amount of each pesticide composition can be determined at any time. In addition, for the rice seed directly sown in the specific area (zone) included in the target area, or the seed rice sown in the nursery box for transplanting the seedlings to this specific area (zone), this chemical agent can be determined at any timing.

5. Modified Example In the example described with reference to FIG. 4, the case where ST102 to ST112 can be executed by the same information processing apparatus 10A has been described. However, ST102 to ST112 are the information processing device 10A mounted on the mobile spraying device 20, the information processing device 10A mounted on the terminal device 30, the information processing device 10A mounted on the server device 10, and/or the network. 2 can be shared by any other device (other server device, etc.). In this case, the devices that share and execute ST102 to ST112 can transmit necessary information via the network 2 to the device that executes the next process. This is equally applicable to the example described in connection with FIG.

In the example described with reference to FIG. 7, the case where ST202 to ST212 can be executed by the same information processing device 10A has been described. However, ST202 to ST212 are the information processing device 10A mounted on the mobile spraying device 20, the information processing device 10A mounted on the terminal device 30, the information processing device 10A mounted on the server device 10, and/or the network. 2 can be shared by any other device (other server device, etc.). In this case, the devices that share and execute ST202 to ST212 can transmit necessary information via the network 2 to the device that executes the next process. This is equally applicable to the example described in connection with FIG.

In the above, the case where a chemical agent is prepared by mixing a plurality of agricultural chemical compositions has been described. However, the technology disclosed in the present application determines only one pesticide composition from among a plurality of pesticide compositions, and when preparing a drug using only the determined amount of the selected one pesticide composition is equally applicable to
In this case, for example, information (9) and information (10) used in the learning model described in ST208 can be changed as follows.
(9) Information indicating one agricultural chemical composition that constitutes a chemical sprayed in a specific area (zone) (10) Information indicating the amount of one agricultural chemical composition indicated in information (9) "Information indicating a plurality of pesticide compositions" used in the learning model can be replaced with "information indicating one pesticide composition", and "information indicating the amount of each of a plurality of pesticide compositions" can be replaced with " information indicating the amount of one pesticide composition”.

The inventors have confirmed that there is a correlation between the data input to each learning model described in the present application and the data output from this learning model, and as a result, such data in each learning data was adopted.

As will be readily appreciated by a person of ordinary skill in the art having the benefit of this disclosure, the various examples described above can be used in suitable combinations in various patterns with each other, unless inconsistency is created.

<2> Agrochemical composition The agricultural chemical composition according to the present invention is a liquid agricultural chemical composition containing the following components (a) and (b1), or a solid agricultural chemical composition containing the following components (a) and (b2). :
(a) at least one active ingredient selected from the group consisting of an active ingredient having a herbicidal effect, an active ingredient having an insecticidal effect and an active ingredient having a fungicidal effect;
(b1) 1-200 g/L of an anionic dispersant;
(b2) 1-20% w/w of an anionic dispersant.

The agrochemical composition according to the present invention may contain one or more of the aforementioned active ingredients, and may also contain one or more of anionic dispersants.

As described above, by mixing the anionic dispersant at a specific content, it is possible to ensure sufficient dispersibility of the agricultural chemical composition in the field. As a result, it is possible to reduce the phytotoxicity caused by topical application and the burden on the environment caused by the active ingredients and auxiliary ingredients.

When the agricultural chemical composition is a liquid agricultural chemical composition, the dosage form is, for example, an aqueous suspension or an oily suspension. Specific formulations of the liquid pesticide composition include, for example, a flowable formulation (SC: suspension concentrate).

When the agricultural chemical composition is a solid agricultural chemical composition, the dosage form is, for example, a wettable powder and granules. Specific dosage forms of the solid pesticide composition include, for example, wettable granules (WG: water dispersible granules) and floating granules. In one aspect, the solid pesticidal composition is a wettable powder having at least one of self-diffusing and floating properties. By having such properties, it is possible to uniformly control pests and weeds in a field to which the agricultural chemical has been sprayed.

(a) Active ingredient The agrochemical composition according to the present invention is selected from the group consisting of (a1) an active ingredient having a herbicidal effect, (a2) an active ingredient having an insecticidal effect, and (a3) an active ingredient having a bactericidal effect. At least one.

(a1) Herbicidal Active Ingredient Examples of herbicidal active ingredients include tefuryltrione, triafamone, fentrazamide, clomeprop, oxadiazone, ipfencarbazone, caffenstrol, indanophan, fenoxasulfone, mefenacet, butachlor, and pretilachlor. , fenquinotrione, benzobicyclon, sulcotrione, mesotrione, pyrazolate, benzofenap, pyrimisulphane, ethoxysulfuron, bensulfuron-methyl, propyrisulfuron, metazosulfuron, penoxsulam, oxadiargyl, pyraclonil, pentoxazone, florpyrauxifene Benzyl, fenoxapropethyl, cyhalofopbutyl, metamifop, cyclopyrimolate, dimethamethrin, simetryn, bentazone, oxadiclomefone, bromobutide and tetoflupyrrolimete, without limitation. The active ingredient having a herbicidal effect is at least one selected from the group consisting of these compounds.

The agrochemical composition according to the present invention may contain a plurality of active ingredients (a1) having a herbicidal effect. In a preferred embodiment, the agricultural chemical composition according to the present invention contains one or more herbicidal active ingredients (a1) selected from the group consisting of tefuryltrione, triafamone, fentrazamide, clomeprop, oxadiazon and ethoxysulfuron. .

(a2) Active ingredient with insecticidal effect Examples of active ingredients with insecticidal effect include imidacloprid, thiacloprid, dinotefuran, flupyradifron, flupyrimine, nitenpyram, clothianidin, sulfoxaflor, ethiprole, fipronil, spinosad, tetraniliprole, and chlorantranilip. These include, but are not limited to, role, cyantraniliprole, pymetrozine, triflumezopyrim, benzpyrimoxane and oxazosulfil. The active ingredient having an insecticidal effect is at least one selected from the group consisting of these compounds. The agricultural chemical composition according to the present invention may contain a plurality of active ingredients (a2) having an insecticidal effect.

(a3) Active ingredient with bactericidal effect Active ingredients with bactericidal effect include, for example, isotianil, probenazole, tricyclazole, diclobenzazox, penflufen, thifluzamide, impilfluxam, kasugamycin, validamycin, fusalide, metminostrobin, Examples include, but are not limited to, azoxystrobin and pencycuron. The active ingredient having a bactericidal effect is at least one selected from the group consisting of these compounds. The agricultural chemical composition according to the present invention may contain a plurality of active ingredients (a3) having a bactericidal effect.

When the agrochemical composition according to the present invention contains a plurality of active ingredients selected from the group consisting of the above components (a1), (a2) and (a3), the content specified for the active ingredients is the content of each active ingredient. is the total amount.

When the agricultural chemical composition according to the present invention is a liquid agricultural chemical composition, it contains, for example, 10 to 700 g/L, preferably 50 to 600 g/L, more preferably 200 to 600 g/L of active ingredient (a).

When the pesticide composition according to the present invention is a solid pesticide composition, for example, 10 to 70% w/w, preferably 50 to 60% w/w, more preferably 20 to 60% w/w active ingredient (a )including.

(b) Anionic Dispersants Anionic dispersants include, but are not limited to, for example, alkylnaphthalene sulfonic acid derivatives and lignin sulfonic acid derivatives. Anionic dispersants may be synthetic or commercially available. Commercially available alkylnaphthalene sulfonic acid derivatives of anionic dispersants include, for example, Demol SNB, Nucalgen PS-P, Nucalgen WG-101, Nucalgen BX-C, AEROSOL OS, MORWET D425, MORWET IP, SUPRAGIL WP, SUPRAGIL MNS/90, TERSPERSE 2020 and the like. Lignosulfonic acid derivatives, which are commercially available anionic dispersants, include, for example, Nucalgen RX-B, Nucalgen WG-4, BORRESPERSE CA, BORRESPERSE NA, MARASPERSE CBOS-4, POLYFON H, POLYFON T, POLYFON O, and UFOXANE 3A. , VANISPERSE CB and the like. The anionic dispersant is at least one selected from the group consisting of the aforementioned compounds.

When the agrochemical composition according to the present invention contains a plurality of anionic dispersants, the specified content of the anionic dispersants is the total content of each anionic dispersant.

When the agricultural chemical composition according to the present invention is a liquid agricultural chemical composition, it contains, for example, 1 to 200 g/L, preferably 5 to 150 g/L, more preferably 50 to 150 g/L of an anionic dispersant.

When the pesticide composition according to the present invention is a solid pesticide composition, for example, 1 to 20% w/w, preferably 5 to 20% w/w, more preferably 5 to 15% w/w of an anionic dispersant. include.

In a preferred embodiment, the agricultural chemical composition according to the present invention is designed so that the application amount of the anionic dispersant is 9 to 300 g/ha when applied to fields. By setting such an application amount, when the spray liquid after single use and mixed use is sprayed in a field, especially in a paddy field, it is possible to impart sufficient spreading performance to the agricultural chemical composition while avoiding phytotoxicity to paddy rice. In a more preferred embodiment, the agricultural chemical composition of the present invention is designed so that the application rate of the anionic dispersant is 9 to 150 g/ha when applied to fields. In a still more preferred embodiment, the agricultural chemical composition according to the present invention is designed so that the application rate of the anionic dispersant is 9 to 130 g/ha when applied to fields.

The agrochemical composition according to the present invention can ensure sufficient dispersibility even when applied topically to paddy fields, and can reduce the environmental load caused by active ingredients and/or auxiliary ingredients. In addition, since the auxiliary ingredients to be used are common, even when a plurality of the agrochemical compositions according to the present invention are mixed and applied, it is possible to reduce the environmental load caused by using more auxiliary ingredients than necessary. .

The agricultural chemical composition according to the present invention may further contain auxiliary ingredients. Auxiliary ingredients are, for example, surfactants, antifreeze agents, thickeners, preservatives, antifoam agents, safeners and carriers. Any of these auxiliary ingredients may be synthetic or commercially available.

As a surfactant, for example, a nonionic surfactant can be used. Agrochemical compositions according to the present invention may contain one or more nonionic surfactants. Examples of nonionic surfactants include polyoxyethylene-polyoxypropylene block polymers, polyalkylene oxide block polymers, polyoxyalkylene alkylphenyl ethers, polyoxyalkylene fatty acid esters, polyoxyalkylene tristyrylphenyl ethers, polyoxyalkylene alkyl Amines, polyoxyethylene alkane diols, acetylene glycol, polyoxyethylene acetylene glycol, sorbitan fatty acid esters, sucrose fatty acid esters, polyoxyalkylene sorbitan esters and glycerin fatty acid esters. Specific examples of commercially available nonionic surfactants include Surfynol 104, Surfynol 420, Surfynol 440, Nucalgen TG-310, ATLAS G 5000, DOWFAX 100N50, GENAPOL 10500, PLURONIC (registered trademark) F127, PLURONIC ( L62, PLURONIC® P105, PLURONIC® PE 6200, PLURONIC® PE 10500, SYNPERONIC PE/F 127, SOPROPHOR BSU, SOPROPHOR S/40P, STEP-FLOW 26, SYNPERONIC PE/ L 62, TERMUL 5429, ULTRARIC PE 62, ULTRARIC PE 105, Toho Chemical Co., Ltd. SORPOL T series products, various SPAN products, Mitsubishi Chemical Co., Ltd. products Ryoto Sugar Ester, Daiichi Kogyo Seiyaku Co., Ltd. DK Ester products and Kao Rheodor Co., Ltd. SP series products and the like.

Antifreeze agents include, for example, urea, glycerin, polyglycerin and polyglycerin derivatives, ethylene glycol, propanediol and propylene glycol.

Specific examples of thickeners include Gohsenol GL-05, diutan gum, Rheocrysta, FBP-34 WELAN GUM, KELZAN, KELZAN BT, KUNIPIA F, KUNIPIA G, RHODOPOL G, RHODOPOL 23, RHODOPOL 50 MC, SATIAXANE CX911, VAN GEL B, VEEGUM R, VOLCLAY HPM-20, WELAN GUM BG3810 and EXILVA.

Specific examples of antiseptics include BIOHOPE, ACTICIDE B 20, BRONOPOL, KATHON CG/ICP, PREVENTOL BIT 20 N, PREVENTOL D 2, PREVENTOL D 7 PROXEL GXL and PROXEL GXL (S).

Antifoaming agents include silicone oil and calcium stearate. Specific examples of commercially available defoaming agents include Antifoam E-20, ANTIFOAM 8830 FOOD GRADE, SAG10, SAG30, SAG1 1572, SILCOLAPSE 426R, SILCOLAPSE 432, SILCOLAPSE454, SILCOLAPSE482, SILCOLAPSE2, S ILFAR SE4 and SILFOAM Examples include SRE.

Carriers include, for example, talc, kaolin clay, silica, clay, chalk, quartz, attapulgite, montmorillonite, diatomaceous earth, calcium carbonate, resins, waxes, water, alcohols, organic solvents, mineral oils and vegetable oils. It is appropriately selected according to the dosage form of the product.

When the pesticide composition according to the present invention is a solid pesticide composition, it may further contain the following ingredients: for example, citric acid, malic acid, hydrochloric acid, sulfuric acid, sodium hydroxide, aqueous ammonia, ammonium sulfate, binding agent (e.g., starch, CMC, PVA, polyurethane, PVP, etc.), granulation/disintegration improving agent (e.g., anionic surfactant, disintegration improving agent (e.g., anionic surfactant, CMC), disintegration extender (e.g., polyacrylate) and the like.

Another aspect of the present invention relates to a method for producing an agrochemical composition. The manufacturing method comprises mixing an active ingredient (a) and an anionic dispersant (b). Specifically, the method of making the pesticidal composition is:
- A first mixing step of mixing the active ingredient (a) and the anionic dispersant (b);
- A second mixing step of adding and mixing an auxiliary component to the mixture obtained in the first mixing step.

When the agricultural chemical composition according to the present invention is a liquid agricultural chemical composition, for example, after mixing and pulverizing other ingredients such as an active ingredient, an anionic dispersant, a carrier (e.g. water) and an antifoaming agent, water and a thickener are separately added. can be prepared by adding a mixture of agents and preservatives.

When the pesticide composition according to the present invention is a solid pesticide composition, for example, an active ingredient, an anionic dispersant, a carrier (for example, talc and/or kaolin clay) and other ingredients are mixed and dry-pulverized, and then pulverized. Separately, a mixture of a liquid wetting agent and water is added, mixed and kneaded, granulated, dried and sieved. For example, when the solid pesticidal composition is a wettable powder (WG), conventional methods such as spray drying, fluid bed granulation, pan granulation, mixing with high speed mixers, and extrusion without solid inerts are used. can be prepared by a method.

In another aspect, the method for producing an agrochemical composition according to the present invention comprises
- A mixing step of mixing the active ingredient (a) and the anionic dispersant (b);
- A pulverizing step of pulverizing after the mixing step;
- A further mixing step of further adding and mixing an anionic dispersant (b) after the pulverizing step. By adding and mixing the anionic dispersant in divided portions before and after pulverization in this manner, heat generation due to pulverization of the pulverization liquid can be avoided, and the product temperature can be lowered. It is preferable to suppress heat generation due to pulverization to, for example, less than 10°C. The manufacturing method can be used for both SC and WG. Preferably, the manufacturing method can be used for SC.

The agricultural chemical composition according to the present invention may be a mixture prepared by mixing multiple agricultural chemical compositions included in the present invention. Therefore, still another aspect of the present invention relates to a method for producing an agrochemical composition, comprising mixing a plurality of the agrochemical compositions described above. When a plurality of agrochemical compositions according to the present invention are mixed, the auxiliary ingredients to be used are common, so it is possible to reduce the environmental load caused by using more auxiliary ingredients than necessary.

<3> Method for controlling diseases, pests and/or weeds Another aspect of the present invention relates to a method for controlling diseases, pests and/or weeds using the agrochemical composition described above. More specifically, it relates to a method for controlling diseases, pests and/or weeds comprising applying one or more of the agrochemical compositions described above to a field, wherein the anionic dispersant is, for example, 9 to 300 g/ha , preferably 9 to 150 g/ha, more preferably 9 to 130 g/ha. By setting the application amount within such a range, it is possible to impart sufficient spreading performance to the agricultural chemical composition when the spray solution after single use or mixed use is applied to fields, particularly paddy fields.

Paddy rice diseases include, but are not limited to, rice blast (Pyricularia oryzae).

Examples of rice pests include, but are not limited to:
Hemiptera: Nephotettix cincticeps, Nilaparvata lugens, Laodelphax striatellus (Fallen), Sogatella furcifera (Horvath), etc.
Coleoptera: Oulema oryzae (Kuwayama), rice water weevil (Lissorhoptrus oryzophilus Kuschel), etc.

Weeds refer to plants that are undesirable for the growth of crop plants growing in a field, and "control of weeds" refers to controlling undesirable plants or regulating the growth of such plants. In a method of controlling weeds, one or more of the agrochemical compositions of the present invention are applied to weeds (e.g., monocotyledonous or dicotyledonous weeds or harmful plants such as undesirable crop plants), seeds (e.g., cereals, seeds or vegetative propagules such as tubers or shoot parts with buds) or areas where crop plants grow (eg areas under cultivation).

Examples of paddy weeds include, but are not limited to:
Dicots of the following genera: Polygonum, Rorippa, Rotala, Lindernia, Bidens, Dopatrium, Eclipta, Elatine, Gratiola, Lindernia, Ludwigia, Oenanthe, Ranunculus, Deinostema, etc.
Monocots of the following genera: Echinochloa, Panicum, Poa, Cyperus, Monochoria, Fimbristylis, Sagittaria, Genus Eleocharis, genus Scirpus, genus Alisma, genus Aneilema, genus Blyxa, genus Eriocaulon, genus Potamogeton, and the like.

More specifically, the agricultural chemical composition according to the present invention can be used, for example, for the following typical paddy field weeds:
Dicots: Rotala indica Koehne, Lindernia procumbens Philcox, Ludwigia prostrata Roxburgh, Potamogeton distinctus A. Benn, Elatine triandra Schk, Japanese parsley (Oenanthe javanica),
Monocots: Echinochloa oryzicola Vasing, Monochoria vaginalis Presl, Eleocharis acicularis L., Eleocharis Kuroguwai Ohwi, Cyperus difformis L., Cyperus serotinus Rottboel, Sagittaria pygmaea Miq), giant prickly pear (Alisma canaliculatum A. Br. et Bouche), firefly (Scirpus juncoides Roxburgh).

In the control method according to the present invention, application may be performed by any means. For example, manual application or automatic application, such as by manned or unmanned aircraft and vehicles.

Regarding the control method according to the present invention, the field is preferably a paddy field. The application is preferably application to the water surface of paddy fields, more preferably topical application to the water surface of paddy fields.

In the control method according to the present invention, the anionic dispersant is preferably applied to the field at an application rate of 9 to 250 g/ha. By setting the application amount within this range, the agricultural chemical composition can be more efficiently diffused in the field.

In addition, in the control method according to the present invention, the active ingredient is applied to fields at an application rate of, for example, 5 to 1000 g/ha, preferably 15 to 500 g/ha. In one aspect, the active ingredient is applied to the field at an application rate of 50-650 g/ha. The application amount of the active ingredient can be appropriately selected from the above range depending on, for example, the climate, the type of disease, pests and/or weeds in the field, the application period, and the like.

In the control method according to the present invention, the agricultural chemical composition to be applied is, for example, automatically selected based on field disease, pest and / or weed occurrence prediction and / or its occurrence situation, or (for example selected by the user). There may be one or more pesticide compositions that are automatically selected or selected. Automatic selection may be performed by the aforementioned information processing device.

In one aspect, in the control method according to the present invention, the agricultural chemical composition is automatically measured and applied to the field. In another aspect, a plurality of pesticide compositions are automatically measured and/or automatically mixed and applied to a field. Automatic measurement and/or automatic mixing may be performed by the information processing device 10A described above and/or the mobile spraying device 20 described above. In another embodiment that does not use the information processing device 10A and/or the mobile spraying device 20 described above, the agricultural chemical composition is applied to a field by measuring it using an instrument or device, for example, by a user, or A plurality of pesticide compositions, for example, are measured and/or mixed by a user using an instrument or device and applied to a field.

Another aspect of the present invention is a kit for use in the aforementioned method of control, the kit comprising the aforementioned pesticidal composition and a container. Preferably, the kit comprises
- a plurality of pesticide compositions as described above;
- a plurality of spatially separated containers, wherein each of the plurality of pesticide compositions is stored in each of said plurality of containers; An example of a kit according to the invention is a plurality of tanks 24 shown in FIG. According to such a kit, it is possible to appropriately select and apply an appropriate agricultural chemical composition from a plurality of candidate agricultural chemical compositions according to the conditions of the field. Such a kit may be used in combination with the information processing device 10A described above, or may be used by being incorporated in the mobile spraying device 20 described above.

The present invention further relates to the use of the aforementioned pesticidal composition for controlling diseases, pests and/or weeds. Regarding the use of the pesticide composition of the present invention, in one aspect diseases, pests and/or weeds occur in paddy fields.

INDUSTRIAL APPLICABILITY As described above, according to the present invention, it is possible to provide an agrochemical composition that exhibits excellent diffusibility, particularly excellent diffusibility in water, so that it exhibits a sufficient effect even in local application, and can be used on crops. Phytotoxicity to plants can be avoided.

Further, based on the prediction of the occurrence of diseases, pests and/or weeds and their occurrence status, two or more pesticide compositions are mixed in appropriate amounts and stably diluted according to the diseases, pests and/or weeds to be controlled. A sap can be obtained and applied to fields (eg, paddy fields). It is possible to avoid spraying excessive chemical substances into the environment by applying chemicals selected for pest control according to field conditions. Further, by combining a plurality of pesticide compositions, a pesticide composition with stable physical and / or chemical properties of the dilution liquid, and different physical and chemical properties, different diseases, pests and /or an agrochemical composition can be provided as an admixture that can control weeds at the same time. Due to its excellent diffusibility, such an agrochemical composition can spread uniformly and widely in a field (e.g., paddy field) and exhibit insecticidal, bactericidal and/or herbicidal effects when the active ingredients are mixed and applied. , diseases, insect pests and/or weeds can be controlled while avoiding the application of excessive active ingredients that impose a burden on the environment. In addition, by applying a plurality of agricultural chemical compositions within the scope of the present invention, since auxiliary ingredients are common among agricultural chemical compositions, it is possible to avoid using auxiliary ingredients more than necessary. can also reduce the environmental load.

Furthermore, by combining with an information processing device and/or a spraying device, based on the prediction of the occurrence of diseases, pests and/or weeds and the state of their occurrence, the type and application of chemicals more suitable for diseases, pests and/or weeds to be controlled. Dosage can be selected and more efficient control can be achieved.

This application is based on Japanese Patent Application No. 2021-189672 filed on November 22, 2021 entitled "Agrochemical composition, information processing device and computer program" enjoy the benefits of The entire contents of this Japanese patent application are incorporated herein by reference.

Based on the ingredients and composition shown in the table below, mix other ingredients such as water, active ingredient, dispersant and antifoaming agent, and after pulverizing, add a mixture of water, thickener and preservative separately. By mixing, pesticide compositions of Examples and Comparative Examples were prepared. In the examples, "amount applied" corresponds to "amount applied". Abbreviations in the table are as follows.

For a flowable formulation (SC: suspension concentrate), after mixing and pulverizing the active ingredient, anionic dispersant, water and other ingredients such as an antifoaming agent, add a mixture of water, thickener and preservative separately. Prepared by Water dispersible granules (WG: water dispersible granules) are made by mixing active ingredients, anionic dispersants, carriers and other ingredients, followed by dry pulverization, and then adding a mixture of a liquid wetting agent and water to the pulverized product. were mixed and kneaded, granulated, dried and sieved.

Test Example 1A
The agricultural chemical compositions of Examples 7 and 8 and the agricultural chemical compositions of Comparative Examples 1 and 2 were topically applied to paddy fields at the dosages and dosages shown in the table below. Topical application was done in a single side treatment on the short side in a 2m x 13m plot.

When the amount of anionic dispersant applied is 4 g/ha (Comparative Example 1) and 0.8 g/ha (Comparative Example 2), it is compared with 55 g/ha (Example 7) and 9.167 g/ha (Example 8). Thus, topical application (one-side treatment to the short side of a 2m x 13m plot) caused greater phytotoxicity at the application site. These results indicate that an anionic dispersant is required at least 9 g/ha or more in an agricultural chemical composition whose dosage form is a wettable powder.

Test example 1B
Next, using Example 8 and Comparative Example 2, which contained the same active ingredient triafamone but had different dosage forms and different dispersant contents, differences in the effect due to dispersibility were tested.

As shown by the above results, when triafamone was contained as an active ingredient, the pesticide composition containing 0.8 g/ha of dispersant (Comparative Example 2) had insufficient effect at a distance from the site of application. On the other hand, the agricultural chemical composition containing 9.167 g/ha of an anionic dispersant (Example 8) was able to secure sufficient effects even at a distance from the site of application.

Test example 1C
In this test example, Example 2 and Comparative Example 2 were used to test differences in phytotoxicity due to dispersibility. Example 2 and Comparative Example 2 were topically applied to paddy fields at the formulation application rates and dosages shown in the table below. Topical application was done in a single side treatment on the short side in a 1 m x 15 m plot. Both Example 2 and Comparative Example 2 are flowable formulations containing the same active ingredient triafamone, but Example 2 has a higher dispersant concentration than Comparative Example 2.

When the amount of the anionic dispersant applied to the field was 0.8 g/ha (Comparative Example 2), the local application ( Phytotoxicity at the application site was greater in the one-sided treatment to the short side of a 1 m×15 m plot. The results indicated that at least 10 g/ha of anionic dispersant was required for field application.

Test example 1D
In this test example, differences in phytotoxicity due to dispersibility were tested when a plurality of formulations were mixed. A mixture of Example 2 and Example 4 and a mixture of Comparative Example 2 and Comparative Example 3 were topically applied to paddy fields at dosages and dosages shown in the table below. Topical application was done in a single side treatment on the short side in a 1 m x 15 m plot. Both Example 2 and Comparative Example 2 are flowable formulations containing the active ingredient triafamone, but Example 2 has a higher dispersant concentration than Comparative Example 2. Both Example 4 and Comparative Example 3 are flowable formulations containing the active ingredient fentrazamide, but Example 4 has a higher dispersant concentration than Comparative Example 3.

When the total amount of the anionic dispersant applied to the field was 8.8 g/ha (Comparative Example 2+Comparative Example 3), compared with the case of 70 g/ha (Example 2+Example 4), Phytotoxicity at the application site was greater in topical application (one-sided treatment to the short side of a 1 m x 15 m plot). From this result, it was shown that 8.8 g/ha of the total applied amount of the anionic dispersant at the time of application to the field was insufficient.

Test example 2
A plurality of pesticide compositions were sprayed in fields using pesticide spraying drones, and the effects on Japanese barnyard millet, Konagi and firefly after 6 weeks of treatment were tested. Similarly, it was compared with manual pesticide spraying by humans. The pesticide composition used, the amount of formulation used, the amount of drug applied and the amount of dispersant applied are shown in the table below. In addition, in FIG. 13, the drone spray flight route is indicated by an arrow (→), and the effect investigation points are indicated by numbers 1 to 12.

From the above results, it was shown that drone spraying was as effective as manual spraying. In addition, similar formulations can be applied to different active ingredients, and no trouble has occurred even when a plurality of pesticide compositions containing at least one of these active ingredients are mixed. From the above, it was shown that sufficient effects can be obtained even by various application methods and topical application.

Test example 3
When the active ingredient, anionic dispersant, water and other ingredients such as an antifoaming agent were mixed, the relationship between the amount of the anionic dispersant added and the temperature of the pulverized liquid during the pulverization process was investigated. Specifically, in the agricultural chemical composition of Example 3, the anionic dispersant was added before and after pulverization, and the relationship between the amount of input and heat generation was examined. The results are shown in the table below and in FIG.

From the above results, it was shown that by dividing the dispersant into a predetermined amount, heat generation during pulverization of the pulverized liquid can be avoided and the product temperature can be lowered. Specifically, it was shown that when the amount of the anionic dispersant added at one time was 80 g/L or more, the temperature rose by 10°C or more after 6 minutes of pulverization.

REFERENCE SIGNS LIST 1 determination system 2 network 10 server device 20 mobile spray device 21 drive source 22 drive mechanism 23 GPS unit 24 multiple tanks 25 preparation device 26 nozzle 30 terminal device

Claims (38)

1. A liquid agrochemical composition comprising components (a) and (b1) below, or a solid agrochemical composition comprising components (a) and (b2) below:
   (a) at least one active ingredient selected from the group consisting of an active ingredient having an insecticidal effect, an active ingredient having a fungicidal effect and an active ingredient having a herbicidal effect;
   (b1) 1 to 200 g/L of an anionic dispersant;
   (b2) 1-20% w/w of an anionic dispersant.
2. The agricultural chemical composition according to claim 1, which is designed so that the application amount of the anionic dispersant is 9 to 300 g/ha when applied to fields.
3. The agricultural chemical composition according to claim 1 or 2, wherein the solid agricultural chemical composition is a wettable powder or granules.
4. The agricultural chemical composition according to any one of claims 1 to 3, wherein the solid agricultural chemical composition is a wettable powder having at least one of self-diffusion and floating properties.
5. 3. Agrochemical composition according to claim 1 or 2, wherein said liquid agrochemical composition is an aqueous suspension or an oily suspension.
6. The herbicidal active ingredients include tefuryltrione, triafamone, fentrazamide, clomeprop, oxadiazone, ipfencarbazone, caffenstrol, indanophan, fenoxasulfone, mefenacet, butachlor, pretilachlor, fenquinotrione, benzobicyclone, and sulcotrione. , mesotrione, pyrazolate, benzofenap, pyrimisulphane, ethoxysulfuron, bensulfuron-methyl, propyrisulfuron, metazosulfuron, penoxsulam, oxadiargyl, pyraclonil, pentoxazone, florpyrauxifenebenzyl, fenoxaprop-ethyl, cyhalofop-butyl , metamifop, cyclopyrimolate, dimethamethrin, simetryn, bentazone, oxadiclomefone, bromobutide and tetflupyrrolimet, at least one selected from the group consisting of, the pesticide composition according to any one of claims 1 to 5.
7. The active ingredient having an insecticidal effect is imidacloprid, thiacloprid, dinotefuran, flupyradifuron, flupyrimine, nitenpyram, clothianidin, sulfoxaflor, ethiprole, fipronil, spinosad, tetraniliprole, chlorantraniliprole, cyantraniliprole, pymetrozine, and triflumezopi. The agricultural chemical composition according to any one of claims 1 to 6, which is at least one selected from the group consisting of rim, benzpyrimoxane and oxazosulfil.
8. The active ingredient having a bactericidal effect is selected from the group consisting of isotianil, probenazole, tricyclazole, diclobenchiazox, penflufen, thifluzamide, impilfluxam, kasugamycin, validamycin, fthalide, metminostrobin, azoxystrobin and penciclon. The pesticide composition according to any one of claims 1 to 7, which is at least one of
9. The agricultural chemical composition according to any one of claims 1 to 8, wherein the anionic dispersant is at least one selected from the group consisting of alkylnaphthalenesulfonic acid derivatives and ligninsulfonic acid derivatives.
10. A method for controlling diseases, pests and/or weeds, comprising applying one or more of the agricultural chemical compositions according to any one of claims 1 to 9 to a field,
    A control method, wherein the anionic dispersant is applied to the field at an application rate of 9 to 300 g/ha.
11. The control method according to claim 10, wherein the anionic dispersant is applied to the field at an application rate of 9 to 150 g/ha.
12. The control method according to claim 10 or 11, wherein the active ingredient is applied to the field at an application rate of 50 to 650 g/ha.
13. The field is a paddy field,
    The control method according to any one of claims 10 to 12, wherein the application is topical application to the water surface of paddy fields.
14. (ia) automatically measuring the agricultural chemical composition and applying it to the field;
    (ib) automatically measuring and/or automatically mixing a plurality of the pesticide compositions and applying them to the field;
    (ii-a) metering and applying said pesticidal composition to said field, or
    (ii-b) measuring and/or mixing a plurality of the pesticide compositions and applying them to the field;
    The control method according to any one of claims 10 to 13.
15. According to any one of claims 10 to 14, the agricultural chemical composition is automatically selected or selected based on the prediction of the occurrence of diseases, pests and/or weeds in the field and/or the occurrence status thereof. Control method.
16. A plurality of agricultural chemical compositions according to any one of claims 1 to 9 and a plurality of spatially separated containers for use in the control method according to any one of claims 10 to 15 A kit comprising:
    A kit, wherein each of the plurality of pesticide compositions is stored in each of the plurality of containers.
17. Use of the agricultural chemical composition according to any one of claims 1 to 9 for controlling diseases, pests and/or weeds.
18. Use of the pesticidal composition according to claim 17, wherein said diseases, pests and/or weeds occur in paddy fields.
19. A method for producing the agricultural chemical composition according to any one of claims 1 to 9,
    A mixing step of mixing the active ingredient and the anionic dispersant;
    A pulverizing step of pulverizing after the mixing step;
    and a further mixing step of further adding and mixing the anionic dispersant after the pulverizing step.
20. A method for producing an agrochemical composition, comprising mixing a plurality of the agrochemical compositions according to any one of claims 1 to 9.
21. comprising at least one processor;
    the at least one processor
    For a specific area included in a target area where paddy rice is cultivated, type information indicating the type of at least one damage that has occurred in the specific area, and the amount of each of the at least one damage that has occurred in the specific area. get quantity information,
    Based on the type information and the amount information, a plurality of pesticide compositions that make up the chemical to be sprayed in the specific area and amounts of each of the plurality of pesticide compositions are determined;
    An information processing apparatus characterized by being configured as follows.
22. The information processing apparatus according to claim 21, wherein the at least one harm includes disease, pests, and/or weeds.
23. The information processing apparatus according to claim 21 or 22, wherein the target area includes at least one agricultural field.
24. the at least one processor;
    For each of a plurality of unit areas included in the target area, unit type information indicating the type of at least one harm that occurred in the unit area, and the amount of each of the at least one harm that occurred in the unit area. Get the unit amount information that shows,
    Using the unit type information and the unit amount information, one zone containing a plurality of unit areas that are common or substantially common in the type of harm caused and the amount of harm caused is selected from the target area. decide and
    By using the one zone as the specific area, a plurality of pesticide compositions constituting the chemical sprayed in the one zone and the amount of each of the plurality of pesticide compositions are determined;
    24. The information processing apparatus according to any one of claims 21 to 23, configured to:
25. the at least one processor;
    Using the unit type information and the unit amount information, a plurality of zones, each of which includes a plurality of unit areas, are selected from the target area, and the types of harm caused and the amount of harm caused in each zone are determined. determining a plurality of zones, including a plurality of common or substantially common unit areas;
    By using each of the plurality of zones as the specific region, a plurality of pesticide compositions constituting the chemical to be applied to each of the plurality of zones and the amount of each of the plurality of pesticide compositions are determined. ,
    25. The information processing apparatus according to claim 24, configured to:
26. the at least one processor;
    In the trained first learning model or the trained first decision tree model,
    the type information and the amount information;
    Soil information about the type of soil in the specific area, damage occurrence information about past damage that occurred in the specific area, seed burial information about seeds buried in the soil in the specific area, and resistance to chemicals in the specific area. at least one of: damage prevalence information about the prevalence of damage, and weather forecast information about weather data predicted for a period during which paddy rice is cultivated in the specific area;
    By inputting the following information, prediction information on the type and amount of damage that will occur in the specific area, prediction information on the growth of damage on the time when the damage will grow, and phytotoxicity information on the chemical damage that will occur in the specific area. and get
    By inputting the hazard occurrence prediction information, the hazard growth prediction information, and the phytotoxicity information to the learned second learning model or the learned second decision tree model, it is dispersed in the specific area. Determining the plurality of pesticide compositions that make up the drug and the amount of each of the plurality of pesticide compositions;
    26. The information processing apparatus according to any one of claims 21 to 25, configured to:
27. the at least one processor;
    In the learned third learning model or the learned third decision tree model,
    information about the general effect of the drug on the harm indicated by the harm occurrence prediction information;
    at least one of information on the types and effects of chemicals used in the past in the specific area, information on the composition of the soil in the specific area, and information on the water retention capacity of the specific area;
    to determine a plurality of pesticide compositions that make up the chemical to be sprayed on the specific area, and the amount of each of the plurality of pesticide compositions;
    27. The information processing apparatus according to claim 26, configured to:
28. [Correction under Rule 91 09.02.2023]
    A spraying device comprising the information processing device according to any one of claims 21 to 27,
    a drive source and drive mechanism for moving the spraying device;
    a plurality of tanks configured such that each tank contains a pesticide composition specific to each of said plurality of pesticide compositions;
    from a plurality of selected tanks coupled to the plurality of tanks and selected from among the plurality of tanks, measuring and obtaining the determined amount of the pesticidal composition contained in each of the selected tanks; a preparation device configured to prepare a drug by mixing substances;
    a nozzle coupled to the preparation device and configured to dispense the medicament prepared by the preparation device;
    A sparging device comprising a
29. the at least one processor;
    Acquiring first position information indicating the position of the specific area;
    Acquiring second position information indicating the current position of the spreader,
    The medicine prepared by the preparation device is to be released when the difference between the position of the specific region indicated by the first position information and the current position indicated by the second position information is equal to or less than a threshold. sending a signal to direct a signal to be dispensed from the nozzle;
    29. A distribution device according to claim 28, configured to:
30. the drug prepared by the preparation device comprises an anionic dispersant having a concentration of 1-200 g/L or 1-20% w/w;
    A spraying device according to claim 28 or claim 29, wherein the anionic dispersant is applied at an application rate of 9-300 g/ha.
31. A method performed by at least one processor executing computer readable instructions, comprising:
    For a specific area included in a target area where paddy rice is cultivated, type information indicating the type of at least one damage that has occurred in the specific area, and the amount of each of the at least one damage that has occurred in the specific area. obtaining quantity information;
    determining, based on the type information and the amount information, a plurality of pesticide compositions constituting the chemical agent to be applied to the specific area and the amount of each of the plurality of pesticide compositions;
    A method comprising:
32. by being executed by at least one processor,
    For a specific area included in a target area where paddy rice is cultivated, type information indicating the type of at least one damage that has occurred in the specific area, and the amount of each of the at least one damage that has occurred in the specific area. get quantity information,
    Based on the type information and the amount information, a plurality of pesticide compositions that make up the chemical to be sprayed in the specific area and amounts of each of the plurality of pesticide compositions are determined;
    A computer program, characterized in that it causes the at least one processor to function as such.
33. comprising at least one processor;
    the at least one processor
    Type information indicating at least one type of harm occurring in a specific area included in a target area in which seedlings grown from a nursery box in which seed rice is sown is directly sown or seedlings are transplanted, and obtaining quantity information indicating the quantity of each of the at least one harm that occurred in the specified area;
    A plurality of pesticide compositions constituting chemical agents applied to rice seeds directly sown in the specific area or seeds sown in nursery boxes for transplanting seedlings to the specific area, based on the type information and the amount information. and the amount of each of the plurality of pesticide compositions;
    An information processing apparatus characterized by being configured as follows.
34. the at least one processor;
    For each of a plurality of unit areas included in the target area, unit type information indicating the type of at least one harm that occurred in the unit area, and the amount of each of the at least one harm that occurred in the unit area. Get the unit amount information that shows,
    Using the unit type information and the unit amount information, one zone containing a plurality of unit areas that are common or substantially common in the type of harm caused and the amount of harm caused is selected from the target area. decide and
    a plurality of pesticide compositions constituting chemicals to be applied to the seed rice directly sown in the one zone or the seed rice sown in the nursery box by using the one zone as the specific region; and determining the amount of each of the plurality of pesticide compositions;
    34. An information processing apparatus according to claim 33, configured to:
35. the at least one processor;
    Using the unit type information and the unit amount information, a plurality of zones, each of which includes a plurality of unit areas, are selected from the target area, and the types of harm caused and the amount of harm caused in each zone are determined. determining a plurality of zones, including a plurality of common or substantially common unit areas;
    By using each of the plurality of zones as the specific region, a plurality of pesticide compositions constituting chemicals that are applied to the seed rice directly sown in each of the plurality of zones or the seed rice sown in the nursery box. and the amount of each of the plurality of pesticide compositions;
    35. An information processing apparatus according to claim 34, configured to:
36. the at least one processor;
    In the trained first learning model or the trained first decision tree model,
    Soil information related to the type of soil in the specific area, harm occurrence information related to damage that occurred in the past in the specific area, harm prevalence information related to the prevalence of chemical-resistant harm in the specific area, and in the specific area at least one of weather forecast information relating to forecasted weather data for the rice growing period;
    By inputting the following information, prediction information on the type and amount of damage that will occur in the specific area, prediction information on the growth of damage on the time when the damage will grow, and phytotoxicity information on the chemical damage that will occur in the specific area. and get
    In the trained second learning model or the trained second decision tree model,
    By inputting the hazard occurrence prediction information, the hazard growth prediction information, and the phytotoxicity information, a chemical to be treated for the seed rice directly sown in the specific area or the seed rice sown in the nursery box is configured. determining the plurality of pesticide compositions and the amount of each of the plurality of pesticide compositions;
    36. The information processing apparatus according to any one of claims 33 to 35, configured to:
37. A method performed by at least one processor executing computer readable instructions, comprising:
    Type information indicating at least one type of damage that has occurred in a specific area included in a target area to which seed rice is sown directly or seeds grown from a nursery box in which seed rice is sown is transplanted; and obtaining quantity information indicative of the quantity of each of the at least one harm that occurred in the specified area;
    A plurality of pesticide compositions constituting chemical agents applied to rice seeds directly sown in the specific area or seeds sown in nursery boxes for transplanting seedlings to the specific area, based on the type information and the amount information. and determining the amount of each of the plurality of pesticide compositions;
    A method comprising:
38. by being executed by at least one processor,
    Type information indicating at least one type of harm occurring in a specific area included in a target area in which seedlings grown from a nursery box in which seed rice is sown is directly sown or seedlings are transplanted, and obtaining quantity information indicating the quantity of each of the at least one harm that occurred in the specified area;
    A plurality of pesticide compositions constituting chemical agents applied to rice seeds directly sown in the specific area or seeds sown in nursery boxes for transplanting seedlings to the specific area, based on the type information and the amount information. and the amount of each of the plurality of pesticide compositions;
    A computer program, characterized in that it causes the at least one processor to function as such.

Images