Program, method and system

Abstract

To provide a system capable of proposing appropriate farm work to an agricultural worker, in order to suppress the emission of greenhouse gases.SOLUTION: A program is executed by a system 1 having a processor 31 and configured to make a proposal about management of paddy field for an agricultural worker, the program causing the processor 31 to execute the steps of: acquiring farm field information including soil components of paddy fields; specifying appropriate farm work for suppressing greenhouse gases to be produced from the paddy fields, based on the acquired farm field information; and outputting the specified appropriate farm work to a worker terminal 10.SELECTED DRAWING: Figure 8

Description

Technical Field

[0001] The present disclosure relates to programs, methods, and systems.

Background Art

[0002] Recently, systems have been provided to assist in reducing the emissions of greenhouse gases, which are considered to contribute to global warming, in the agricultural field. For example, the following patent documents disclose support systems for reducing the emissions of greenhouse gases from paddy fields by farmers. In this system, the amount of reduction in the emissions of methane gas, which is a greenhouse gas, is calculated using methane suppression cultivation parameters for estimating the amount of methane gas emissions.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the conventional system, it has not been possible to propose what farmers should do in order to suppress the generation of greenhouse gases.

[0005] An object of the present disclosure is to provide a system that can propose appropriate farming operations to farmers in order to suppress the generation of greenhouse gases.

Means for Solving the Problems

[0006] One aspect of the present disclosure is a program executed by a system having a processor and making a proposal regarding the management of paddy fields performed by farmers. The processor is caused to execute steps of: acquiring field information including soil components of a paddy field; identifying appropriate farming operations for suppressing the generation of greenhouse gases from the paddy field based on the acquired field information; and outputting the identified appropriate farming operations to a worker terminal.

Advantages of the Invention

[0007] According to the present disclosure, it is possible to propose appropriate farming operations to farmers for suppressing the generation of greenhouse gases.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2A

Figure 2B

Figure 3

Figure 4

Figure 5A

Figure 5B

Figure 5C

Figure 6A

Figure 6B

Figure 6C

Figure 7A

Figure 7B

Figure 7C

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Mode for Carrying Out the Invention

[0009] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. In the following description, the same parts are denoted by the same reference numerals. Their names and functions are also the same. Therefore, detailed descriptions thereof will not be repeated.

[0010] <1. Configuration of System 1> Hereinafter, the configuration of a farm work support system 1 (hereinafter simply referred to as system 1) according to an embodiment of the present invention will be described.

[0011] (1-1) Overall Configuration First, the overall configuration of system 1 will be described with reference to FIG. 1. As shown in FIG. 1, system 1 is a system that proposes appropriate farming operations to farmers in order to suppress the generation of greenhouse gases (e.g., methane gas) from paddy fields (fields) in rice cultivation. By performing the farming operations proposed by system 1, farmers can effectively suppress the generation of methane gas from paddy fields.

[0012] Here, farming operations include various operations performed to manage paddy fields in rice cultivation. For example, the following are included in farming operations. · Water level management operations in paddy fields · Spraying operations of methane-suppressing fertilizers on paddy fields · Straw removal operations after harvesting Note that farming operations include various operations performed to manage paddy fields, not limited to the above examples. The "methane-suppressing fertilizer" referred to in the present disclosure includes, for example, not only fertilizers such as calcium cyanamide, but also materials such as soil improvers, biostimulant-based materials, enzyme materials, or iron-containing materials.

[0013] FIG. 1 is a diagram showing the overall configuration of system 1. As shown in FIG. 1, system 1 includes a worker terminal 10, a manager terminal 20, a management server 30, and a sensor 40.

[0014] The worker terminal 10 is an information processing device operated by a user (farmer) who performs farming operations using system 1. The worker terminal 10 is realized by a portable tablet terminal, a smartphone, or a stationary PC (Personal Computer), a laptop PC, etc. corresponding to system 1. The worker terminal 10 is connected to the network 80.

[0015] The manager terminal 20 is an information processing device operated by a manager who manages the maintenance and operation of system 1. The manager terminal 20 is realized by a stationary PC (Personal Computer), a laptop PC, or a tablet terminal, a smartphone, etc. corresponding to system 1. The manager terminal 20 is connected to the network 80.

[0016] The management server 30 is a server device that performs various operations described later and provides various types of information related to agricultural work support to the operator terminal 10 via the network 80. The management server 30 includes various computers such as a personal computer, a server computer (for example, a Web server, an application server, a database server, or a combination thereof). In the present embodiment, the management server 30 will be described by taking as an example a cloud server that makes one or more virtualized servers available via a network.

[0017] The sensor 40 is a measuring device that senses the state of the field. The sensor 40 can communicate with the management server 30 via the network 80 by wireless communication. The sensor 40 senses the state of the field by a remote operation of the operator terminal 10 by an agricultural worker or according to a preset measurement frequency. The information sensed by the sensor 40 includes, for example, the following. That is, a plurality of sensors 40 may be installed in the field. · Soil components of the field · Temperature and humidity of the field · Temperature of the soil in the field · Properties of the field

[0018] Also, the sensor 40 may be a camera that photographs the state of the field. In this case, the sensor 40 periodically photographs the state of the field and transmits it to the management server 30. For example, when the field is a paddy field, a plant marker may be grown as a mark of the state change of the paddy field. The appearance of the plant marker changes according to the increase or decrease of specific molecules contained in the soil. The sensor 40 may periodically photograph the state of the plant marker.

[0019] (1-2) Hardware configuration of the operator terminal 10 Next, with reference to FIG. 2A, the hardware configuration of the worker terminal 10 will be described. FIG. 2A is a diagram showing the hardware configuration of the worker terminal 10. As shown in FIG. 2A, the worker terminal 10 includes a processor 11, a memory 12, a storage 13, a communication IF (Interface) 14, an input device 15, and an output device 16. Since the configuration of the administrator terminal 20 is generally common to that of the worker terminal 10, its description will be omitted.

[0020] The worker terminal 10 is communicably connected to the management server 30 via the network 80. The worker terminal 10 is connected to the network 80 by communicating with communication devices such as a radio base station 81 compatible with communication standards such as 5G and LTE (Long Term Evolution), and a wireless LAN router 82 compatible with wireless LAN (Local Area Network) standards such as IEEE (Institute of Electrical and Electronics Engineers) 802.11.

[0021] The processor 11 is hardware for executing an instruction set described in a program stored in the storage 13, and is composed of an arithmetic unit, registers, peripheral circuits, and the like.

[0022] The memory 12 is for temporarily storing programs and data processed by programs and the like, and is a volatile memory such as a DRAM (Dynamic Random Access Memory), for example.

[0023] The storage 13 is a storage device for storing programs and data, and is, for example, a flash memory or an HDD (Hard Disc Drive). The programs stored in the storage 13 include, for example, the following programs. ·Program of the OS (Operating System) ·Program of an application (such as a web browser) for executing information processing

[0024] The data stored in the storage 13 includes, for example, the following data. · Database referred to in information processing · Data obtained by executing information processing (execution result of information processing)

[0025] The communication IF 14 is an interface for inputting and outputting signals so that the operator terminal 10 can communicate with an external device.

[0026] The input device 15 is an input device for receiving input operations from the user (for example, a pointing device such as a touch panel, a touch pad, a mouse, etc., a keyboard, etc.).

[0027] The output device 16 is an output device (display, speaker, etc.) for presenting information to the user.

[0028] (1-3) Functional configuration of the operator terminal 10 Next, with reference to FIG. 2B, the functional configuration of the operator terminal 10 will be described. FIG. 2B is a diagram showing the functional configuration of the operator terminal 10. As shown in FIG. 2B, the operator terminal 10 includes an antenna 111, a wireless communication unit 101, a storage unit 102, a control unit 103, an operation reception unit 104, a position information sensor 105, and a camera 106.

[0029] The operator terminal 10 also has functions and configurations not shown in FIG. 2B (for example, a battery for holding power, a power supply circuit for controlling the supply of power from the battery to each circuit, etc.). As shown in FIG. 2B, each block included in the operator terminal 10 is electrically connected by a bus or the like.

[0030] The antenna 111 radiates the signal emitted by the operator terminal 10 as radio waves. Also, the antenna 111 receives radio waves from space and supplies the received signal to the wireless communication unit 101.

[0031] The wireless communication unit 101 performs modulation / demodulation processing and the like for transmitting and receiving signals via the antenna 111 so that the operator terminal 10 can communicate with other wireless devices.

[0032] The wireless communication unit 101 is a communication module including a tuner, an RSSI (Received Signal Strength Indicator) calculation circuit, a CRC (Cyclic Redundancy Check) calculation circuit, a high-frequency circuit, and the like. The wireless communication unit 101 performs modulation / demodulation and frequency conversion of the wireless signals transmitted and received by the operator terminal 10, and supplies the received signals to the control unit 103.

[0033] The operation reception unit 104 has a mechanism for receiving the input operations of the user. Specifically, the operation reception unit 104 is configured as a touch screen and includes a touch sensing device 1041 and a display 1042.

[0034] The touch sensing device 1041 receives the input operations of the user of the operator terminal 10. The touch sensing device 1041 detects the contact position of the user on the touch panel, for example, by using a capacitance type touch panel. The touch sensing device 1041 outputs a signal indicating the contact position of the user detected by the touch panel to the control unit 103 as an input operation.

[0035] The display 1042 displays data such as images, videos, and texts according to the control of the control unit 103. The display 1042 is realized by, for example, an LCD (Liquid Crystal Display) or an organic EL (Electro-Luminescence) display.

[0036] The position information sensor 105 is a sensor that detects the position of the operator terminal 10, and is, for example, a GPS (Global Positioning System) module. The GPS module is a receiving device used in a satellite positioning system. In the satellite positioning system, signals from at least three or four satellites are received, and based on the received signals, the current position of the operator terminal 10 equipped with the GPS module is detected.

[0037] The camera 106 is a device that receives light by a light receiving element and outputs it as a photographed image.

[0038] The storage unit 102 is composed of, for example, a flash memory or the like, and stores data and programs used by the operator terminal 10. The storage unit 102 stores at least user information 1021, field images 1022, and various programs (not shown).

[0039] The user information 1021 is information regarding the user who uses the operator terminal 10. The user information 1021 includes account information (user ID and password for identifying the user) that is required to be input when the user logs in to the system 1 by the operator terminal 10. In addition, the user information 1021 may include various information regarding the attributes of the user registered when the user installs a predetermined application on the operator terminal 10 in order to use the system 1.

[0040] The user ID may be a customer ID issued to the user. The user ID may be a user account of a service that provides various functions such as mail, video call, calendar, storage, document creation, spreadsheet creation, and news distribution in the form of SaaS (Software as a Service) (including services for corporations).

[0041] The field image 1022 is image data of the field captured using the operator terminal 10. As the image data of the field, in addition to those captured by the operator himself / herself, image data periodically captured by the operator terminal 10 fixed at a specific position is also included.

[0042] The control unit 103 reads the program stored in the storage unit 102 and executes the instructions included in the program to control the operation of the operator terminal 10. The control unit 103 is, for example, an application pre-installed in the operator terminal 10. By operating according to the program, the control unit 103 functions as an input reception unit 1031, a transmission / reception unit 1032, a photographing unit 1033, a storage processing unit 1034, and a display control unit 1035.

[0043] The input reception unit 1031 performs a process of receiving a user's input operation on the input device 15 such as the touch-sensing device 1041.

[0044] The transmission / reception unit 1032 performs a process for the operator terminal 10 to transmit and receive data to and from an external device such as the management server 30 according to a communication protocol.

[0045] The photographing unit 1033 performs a process of activating the camera 106 and photographing the field as the subject in response to an operation from the farmer.

[0046] The storage processing unit 1034 performs a process of storing the data received by the operator terminal 10 and the data obtained by performing calculations according to the program in the storage unit 102. For example, the storage processing unit 1034 controls the storage process of the captured image in the storage unit 102.

[0047] The display control unit 1035 performs a process of presenting the information to the user by displaying the information on the display 1042. The display control unit 1035 has a function as a web browser, and the management server 30 accesses the information output to the logical line (TCP connection) with the worker terminal 10 and performs a process (rendering) of displaying it on the display 1042 of the worker terminal 10.

[0048] (1-4) Hardware configuration of the management server 30 Next, with reference to FIG. 1, the hardware configuration of the management server 30 will be described. As shown in FIG. 1, the management server 30 includes a processor 31, a memory 32, a storage 33, a communication IF 34, and an input / output IF 35.

[0049] The processor 31 is hardware for executing an instruction set described in a program stored in the storage 33, and is composed of an arithmetic unit, a register, a peripheral circuit, and the like.

[0050] The memory 32 is for temporarily storing a program and data processed by the program, etc., and is a volatile memory such as a DRAM (Dynamic Random Access Memory).

[0051] The storage 33 is a storage device for storing programs and data, and is, for example, a flash memory or an HDD (Hard Disc Drive). The programs stored in the storage 33 include, for example, the following programs. · Program of the OS (Operating System) · Program of an application that executes information processing (for example, a web browser)

[0052] The data stored in the storage 33 includes, for example, the following data. · Database referred to in information processing · Data obtained by executing information processing (that is, the execution result of information processing)

[0053] The communication IF 34 is an interface for inputting and outputting signals for the management server 30 to communicate with external devices.

[0054] The input / output IF 35 functions as an interface with an input device for receiving input operations via the worker terminal 10 and the administrator terminal 20, and an output device for presenting information to the worker terminal 10 and the administrator terminal 20.

[0055] (1-5) Functional configuration of the management server 30 Next, with reference to FIG. 3, the functional configuration of the management server 30 will be described. FIG. 3 is a diagram showing the functional configuration of the management server 30. As shown in FIG. 3, the management server 30 exhibits functions as a communication unit 301, a storage unit 302, and a control unit 303.

[0056] The communication unit 301 performs processing for the management server 30 to communicate with external devices.

[0057] The storage unit 302 stores data and programs used by the management server 30. The storage unit 302 stores, for example, the following data. · User database (User DB) 3021 · Field database (Field DB) 3022 · Work history database (Work history DB) 3023 · Sensor database (Sensor DB) 3024 · Soil component database (Soil component DB) 3025 · Weather history database (Weather history DB) 3026 · Yield prediction database (Yield prediction DB) 3027 · Yield history database (Yield history DB) 3028 · Occurrence prediction database (Occurrence prediction DB) 3029 · Agricultural operation specific model 3041 · Yield prediction model 3042 · Occurrence prediction model 3043

[0058] The user DB 3021 is a database that manages information about farmers who use the system 1 to receive support for agricultural work. Details of the data structure of the user DB 3021 will be described later.

[0059] The field DB 3022 is a database that manages information about the fields operated by farmers. Details of the data structure of the field DB 3022 will be described later.

[0060] The work history DB 3023 is a database that manages the history of various agricultural operations carried out by farmers as field management. Details of the data structure of the work history DB 3023 will be described later.

[0061] The sensor DB 3024 is a database that manages information about the sensors 40 installed in the fields. Details of the data structure of the sensor DB 3024 will be described later.

[0062] The soil component DB 3025 is a database that manages information about the soil components detected from the fields. Details of the data structure of the soil component DB 3025 will be described later.

[0063] The weather history DB 3026 is a database that manages the history of the weather around the fields. Details of the data structure of the weather history DB 3026 will be described later.

[0064] The yield prediction DB 3027 is a database that manages information about the yield prediction results. Details of the data structure of the yield prediction DB 3027 will be described later.

[0065] The yield history DB 3028 is a database that manages information about the actual yield. Details of the data structure of the yield history DB 3028 will be described later.

[0066] The generation prediction DB 3029 is a database that manages information about the generation prediction of methane gas from the fields. Details of the data structure of the generation prediction DB 3029 will be described later.

[0067] The specific agricultural operation model 3041 is obtained by causing a machine learning model to perform machine learning according to a model learning program based on learning data. For example, in the present embodiment, the specific agricultural operation model 3041 is learned to output the content of appropriate agricultural operations (hereinafter referred to as operation proposal information) for suppressing the generation of methane gas from the input field information. The specific agricultural operation model 3041 is constructed by an administrator and stored in advance in the storage unit 302 of the management server 30. The specific agricultural operation model 3041 is relearned by the administrator as needed.

[0068] The learning data of the specific agricultural operation model 3041 uses, for example, field information as input data and operation proposal information for suppressing the generation of methane gas as correct output data. The operation proposal information includes the following information. · Type of agricultural operation · Method of agricultural operation (including specific aspects such as procedures and equipment to be used) · Recommended time to perform agricultural operations

[0069] The specific agricultural operation model 3041 according to the present embodiment is, for example, a composite function with parameters in which a plurality of functions are combined. The composite function with parameters is defined by a combination of a plurality of adjustable functions and parameters. The specific agricultural operation model 3041 according to the present embodiment may be any composite function with parameters that satisfies the above requirements, but is, for example, a multi-layer neural network model (hereinafter referred to as a "multi-layer network"). The specific agricultural operation model 3041 using a multi-layer network has an input layer, an output layer, and at least one intermediate layer or hidden layer provided between the input layer and the output layer. The specific agricultural operation model 3041 is assumed to be used as a program module that is part of artificial intelligence software.

[0070] As the multilayer network according to this embodiment, for example, a deep neural network (DNN) which is a multilayer neural network targeted for deep learning can be used. As the DNN, for example, a convolution neural network (CNN) targeted for images may be used.

[0071] The yield prediction model 3042 is obtained by causing a machine learning model to perform machine learning according to a model learning program based on learning data. For example, in this embodiment, the yield prediction model 3042 is learned to output a predicted value of the growth state of paddy rice in the field for the input field information. The predicted value of the growth state includes the following information. · Growth state (predicted growth curve) for each unit period · Predicted yield at the harvest time

[0072] The yield prediction model 3042 is constructed by the administrator and stored in advance in the storage unit 302 of the management server 30. The yield prediction model 3042 is re-learned by the administrator as necessary. The learning data of the yield prediction model 3042 uses, for example, field information as input data, and for the input field information, the growth state of paddy rice in the field is used as correct answer output data.

[0073] The yield prediction model 3042 according to this embodiment is, for example, a composite function with parameters in which a plurality of functions are combined. The composite function with parameters is defined by a combination of a plurality of adjustable functions and parameters. The yield prediction model 3042 according to this embodiment may be any composite function with parameters that satisfies the above requirements, but is, for example, a multi-layer neural network model (hereinafter referred to as a "multi-layer network"). The yield prediction model 3042 using a multi-layer network has an input layer, an output layer, and at least one intermediate layer or hidden layer provided between the input layer and the output layer. The yield prediction model 3042 is assumed to be used as a program module that is part of artificial intelligence software.

[0074] The generation prediction model 3043 is a mathematical model that predicts the amount of methane generated, constructed from the relationship between the state of soil components and the amount of methane generated. FIG. 4 is a diagram showing the relationship between soil components used for methane generation prediction and methane generation. As shown in FIG. 4, it is known that there is a certain relationship between the change in the concentration of soil components and the amount of methane gas generated.

[0075] In the illustrated example, for example, when the oxidation-reduction potential (Eh value) decreases over time and falls below -0.1 volts, a significant increase in the generation of methane gas is observed. On the other hand, it is confirmed that almost no methane gas is generated when the oxidation-reduction potential is 0 volts or more. Based on this, it can be said that appropriate farming operations for suppressing the generation of methane gas include operations that slow down the change in the oxidation-reduction potential of paddy fields. By slowing down the change in the oxidation-reduction potential of paddy fields, the generation of methane gas can be suppressed.

[0076] In other words, appropriate farming operations for suppressing the generation of methane gas include operations for maintaining the oxidation-reduction potential of paddy fields at the target potential. FIG. 14 shows an example of maintaining the oxidation-reduction potential of paddy fields at the target potential by appropriately performing the water supply operation W2 to the paddy fields and the drainage operation W1 from the paddy fields. In FIG. 14, the horizontal axis is the time axis during the cultivation period, and the vertical axis is the oxidation-reduction potential (Eh value) of the paddy fields. When the drainage operation W1 from the paddy fields is performed, the soil of the paddy fields approaches the oxidized state, so the oxidation-reduction potential increases. When the water supply operation W2 to the paddy fields is performed, the soil of the paddy fields approaches the reduced state, so the oxidation-reduction potential decreases. Therefore, as shown in FIG. 14, when the water supply operation W2 to the paddy fields and the drainage operation W1 from the paddy fields are performed at appropriate timings, the oxidation-reduction potential of the paddy fields is controlled to maintain the target potential as in the graph G1. On the other hand, when appropriate management is not performed, as shown by the graph G2 (dashed-two dotted line), the oxidation-reduction potential of the paddy fields may deviate significantly from the target potential. Here, the target potential may have a certain width. In the example of FIG. 14, the range (hatched area) of not less than the lower limit value V1 (for example, "-150 mV") and not more than the upper limit value V2 (for example, "+200 mV") is defined as the "target potential". Also, the target potential is not limited to a fixed value and may be variable.

[0077] In addition, a certain relationship is also recognized between the transition of the pH value of the soil and other component concentrations and the transition of the methane generation amount. The generation prediction model 3043 focuses on the relationship between the states of these soil components and the methane generation amount, and is constructed as a rule-based mathematical model that defines the predicted methane generation amount based on the values of the soil components. The generation prediction model 3043 is constructed by the administrator and is stored in advance in the storage unit 302 of the management server 30. The generation prediction model 3043 is updated with parameters that configure the mathematical model by the administrator as needed.

[0078] The control unit 303 exhibits functions as various modules when the processor 31 of the management server 30 performs processing according to a program. The control unit 303 exhibits functions as a transmission / reception control module 3031, an acquisition module 3032, a specification module 3033, a prediction module 3034, and an output module 3036.

[0079] The transmission / reception control module 3031 controls the process in which the management server 30 transmits and receives signals to and from an external device according to a communication protocol.

[0080] The acquisition module 3032 acquires the information transmitted from the farmer terminal 10A in response to the operation of the farmer. Further, the acquisition module 3032 acquires the sensing results transmitted from various sensors 40. The acquisition module 3032 stores the acquired various information in a predetermined storage area (each database) in the storage unit 302.

[0081] Based on the acquired field information, the specification module 3033 specifies work proposal information for suppressing the generation of methane gas and generates the work proposal information. Specifically, the specification module 3033 inputs the field information into the farming operation specific model 3041 to acquire an appropriate farming operation output from the farming operation specific model 3041.

[0082] In response to an instruction operation by the farmer on the worker terminal 10, the prediction module 3034 calculates a predicted value of the growth state of paddy rice in the field based on the field information. Specifically, the prediction module 3034 inputs the field information to the yield prediction model 3042 to acquire the predicted value of the growth state output from the yield prediction model 3042. The prediction module 3034 stores the acquired predicted value of the growth state in the yield prediction DB 3027.

[0083] The prediction module 3034 also predicts the generation of methane gas. The prediction module 3034 predicts the generation of methane gas at present or in the future by inputting the value of the soil component of the field into the generation prediction model 3043.

[0084] The aggregation module 3035 calculates the expected amount of methane gas reduction that is expected to be reduced by the implementation of agricultural operations. Based on the calculated expected amount of methane gas reduction, the aggregation module 3035 performs at least one of applying for carbon credits and calculating the carbon footprint. The aggregation module 3035 uses the expected reduction amount to create application information that conforms to a predetermined application form for review by a carbon credit certification agency.

[0085] The output module 3036 outputs various types of information obtained by the executed processing in response to the operation of the agricultural operator. The output module 3036 outputs, for example, the following information. · Work proposal information · Information stored in each database

[0086] In addition, the output module 3036 transmits the carbon credit application information created by the aggregation module 3035 to the carbon credit certification agency.

[0087] (1-6) Data structure Next, an example of the data structure of each database stored in the storage unit 302 of the management server 30 will be described with reference to FIGS. 5 to 7.

[0088] (1-6-1) User DB3021 FIG. 5A is a diagram showing an example of the data structure of the user DB3021. As shown in FIG. 5A, the user DB3021 stores information about users who use the system 1 as agricultural operators. The user DB3021 records a new record by the user registration operation at the start of using the system 1 by the agricultural operator.

[0089] The user DB3021 includes an item "user ID", an item "name", an item "personal information", and an item "affiliated organization".

[0090] In the item "User ID", user identification information that can identify a user who uses System 1 as a farm worker is stored.

[0091] In the item "Name", information regarding the name of the user corresponding to the User ID is stored.

[0092] In the item "Personal Information", various personal information regarding the user corresponding to the User ID is stored. The personal information includes, for example, the following. · The user's age, gender, date of birth, login password, etc · The user's address, contact information, etc

[0093] In the item "Affiliated Organization", the name of the organization such as an agricultural cooperative to which the user corresponding to the User ID belongs is stored. Note that if the user does not belong to any organization, the item "Affiliated Organization" may be blank.

[0094] Note that the structure of the User DB3021 shown in FIG. 5A is merely an example, and the User DB3021 may include columns for storing other data items.

[0095] (1-6-2) Field DB3022 FIG. 5B is a diagram showing an example of the data structure of the Field DB3022. As shown in FIG. 5B, the User DB3021 stores information regarding the fields managed by the user who is a farm worker. The Field DB3022 records new records by an input operation from the farm worker.

[0096] The Field DB3022 includes an item "Field ID", an item "Location Information", an item "Field Area", an item "Administrator ID", an item "Crop Cultivation Status", an item "Topographical Information", and an item "Field Image".

[0097] In the item "Field ID", field identification information that can identify the field is stored.

[0098] In the item "Location Information", the location information of the field corresponding to the Field ID is stored.

[0099] In the item "field area", the area of the field corresponding to the field ID is stored.

[0100] In the item "administrator ID", the user ID of the user corresponding to the administrator of the field corresponding to the field ID is stored.

[0101] In the item "cropping status", the cropping status of the field corresponding to the field ID is stored.

[0102] In the item "topographic information", the topographic information of the field corresponding to the field ID is stored.

[0103] In the item "field image", the image information of the field corresponding to the field ID is stored.

[0104] Note that the structure of the field DB3022 shown in Fig. 5B is merely an example, and the field DB3022 may include columns for storing other data items.

[0105] (1 - 6 - 3) Work history DB3023 Fig. 5C is a diagram showing an example of the data structure of the work history DB3023. As shown in Fig. 5C, the work history DB3023 stores the history of the agricultural operations performed by the farmer for field management. New records are recorded in the work history DB3023 through the input by the farmer.

[0106] The work history DB3023 includes an item "work ID", an item "field ID", an item "work name", an item "work content", and an item "work time".

[0107] In the item "work ID", the identification information of the work that can identify the agricultural work performed by the farmer is stored.

[0108] In the item "field ID", the identification information of the field where the agricultural work corresponding to the work ID was performed is stored.

[0109] In the item "work name", the name of the agricultural work corresponding to the work ID is stored.

[0110] In the item "work content", the content of the agricultural work corresponding to the work ID is stored. The content of the agricultural work includes the following information. · Specific procedures of the agricultural work · Number of times of the agricultural work · Scope where the agricultural work was carried out · Name of chemicals such as fertilizers used in the agricultural work

[0111] In the item "working time", information regarding the time when the agricultural work corresponding to the work ID was carried out is stored.

[0112] Note that the structure of the work history DB3023 shown in Fig. 5C is merely an example, and the work history DB3023 may include columns for storing other data items.

[0113] (1-6-4) Sensor DB3024 Fig. 6A is a diagram showing an example of the data structure of the sensor DB3024. As shown in Fig. 6A, the sensor DB3024 stores information regarding the sensor 40 installed in the field. When the sensor 40 is installed in the field, a new record is recorded based on the input by the agricultural worker in the sensor DB3024.

[0114] The sensor DB3024 includes the item "sensor ID" and the item "field ID".

[0115] In the item "sensor ID", the identification information of the sensor 40 that can identify the sensor 40 installed in the field is stored.

[0116] In the item "field ID", the identification information of the field where the sensor 40 corresponding to the sensor ID is installed is stored.

[0117] Note that the structure of the sensor DB3024 shown in Fig. 6A is merely an example, and the sensor DB3024 may include columns for storing other data items.

[0118] (1-6-5) Soil component DB3025 Figure 6B is a diagram showing an example of the data structure of the soil component DB3025. As shown in Figure 6B, the soil component DB3025 stores information on soil components detected by the sensor 40 from the field. The soil components include at least the oxidation-reduction potential of paddy soil and the content of specific molecules related to the oxidation-reduction state. When the sensing result by the sensor 40 is transmitted to the management server 30, a new record is recorded in the soil component DB3025.

[0119] The soil component DB3025 includes an item "measurement ID", an item "sensor ID", an item "measurement date and time", and an item "soil component data".

[0120] In the item "measurement ID", identification information of the sensing result that can identify the sensing result of measuring the soil component is stored.

[0121] In the item "sensor ID", identification information of the sensor 40 that obtained the sensing result corresponding to the measurement ID is stored.

[0122] In the item "measurement date and time", the date and time when the sensing result corresponding to the measurement ID was obtained is stored.

[0123] In the item "soil component data", the value of the soil component is stored as the sensing result corresponding to the measurement ID. Examples of the soil component data include the following. · Oxidation-reduction potential: A value indicating the oxidation-reduction potential of the soil · pH value: A value indicating the acidity or alkalinity of the soil · Content of methane-producing bacteria: The amount of methane-producing bacteria contained in the soil · Nitrogen content: The concentration of nitrogen in the soil · Phosphorus content: The concentration of phosphorus in the soil · Potassium content: The concentration of potassium in the soil · Organic matter content: The concentration of organic matter in the soil · Inorganic matter content: The concentration of inorganic substances such as iron and manganese

[0124] Note that the structure of the soil component DB3025 shown in FIG. 6B is merely an example, and the soil component DB3025 may include columns in which other data items are stored. Further, as the soil component, the content of components other than the above may be included.

[0125] For example, the soil component DB3025 may include soil analysis results. The soil analysis results are values obtained by performing various analyses on the collected soil samples and measuring the contents of nutrients, minerals, organic substances, etc. As the analysis results, in addition to the same evaluation items as the above sensing results, soil particle distribution, water retention capacity, salt absorption amount, and electrical conductivity are included.

[0126] Also, for example, the soil component DB3025 may refer to the values in the database of soil information publicly disclosed by research institutions related to agriculture and divert any data items as new columns.

[0127] (1-6-6) Weather history DB3026 FIG. 6C is a diagram showing an example of the data structure of the weather history DB3026. As shown in FIG. 6C, the weather history DB3026 stores the weather history of the field. The weather history DB3026 has new records recorded when the acquisition module 3032 of the management server 30 periodically acquires the weather history from an external weather information system. Note that the weather information may be acquired by the sensor 40.

[0128] The weather history DB3026 includes an item "Observation ID", an item "Observation location", an item "Observation date", and an item "Weather information".

[0129] In the item "Observation ID", identification information of the observation result that can identify the weather observation result is stored.

[0130] In the item "Observation location", information on the location where the observation corresponding to the observation ID was performed is stored.

[0131] In the item "Observation date", the date when the observation corresponding to the observation ID was performed is stored.

[0132] The content of the observation corresponding to the observation ID is stored in the item "weather information". The content of the observation includes, for example, the following. · Type of weather · Precipitation · Temperature, humidity · Wind speed, wind direction · Information on other external environments of the field

[0133] Note that the structure of the weather history DB3026 shown in FIG. 6C is merely an example, and the weather history DB3026 may include columns in which other data items are stored.

[0134] (1-6-7) Yield prediction DB3027 FIG. 7A is a diagram showing an example of the data structure of the yield prediction DB3027. As shown in FIG. 7A, the yield prediction DB3027 stores predicted values of the growth state of paddy rice in the field. When the management server 30 performs a yield prediction in response to an instruction from a farmer, a new record is recorded in the yield prediction DB3027.

[0135] The yield prediction DB3027 includes an item "yield prediction ID", an item "field ID", an item "prediction date", an item "predicted growth state", and an item "predicted yield".

[0136] The item "yield prediction ID" stores identification information of a prediction result that can identify the yield prediction.

[0137] The item "field ID" stores identification information of the field that is the target of the prediction corresponding to the yield prediction ID.

[0138] The item "prediction date" stores the date on which the prediction corresponding to the yield prediction ID was made.

[0139] The item "predicted growth state" stores the predicted value corresponding to the yield prediction ID. The predicted value includes a predicted growth curve in which the predicted values of the growth state for each evaluation date are connected.

[0140] In the item "predicted yield", the predicted value of the yield obtained as the prediction result corresponding to the yield prediction ID is stored. The predicted value of the yield is defined by the growth state when the evaluation date is set as the planned harvest date.

[0141] Note that the structure of the yield prediction DB3027 shown in FIG. 7A is merely an example, and the yield prediction DB3027 may include columns for storing other data items.

[0142] (1-6-8) Yield history DB3028 FIG. 7B is a diagram showing an example of the data structure of the yield history DB3028. As shown in FIG. 7B, the yield history DB3028 stores the actual value of the final yield in the field. When the yield history DB3028 receives an input operation of the yield after harvest from the farmer via the operator terminal 10, a new record is recorded.

[0143] The yield history DB3028 includes an item "harvest ID", an item "field ID", an item "harvest date", an item "harvested product", and an item "yield".

[0144] In the item "harvest ID", the identification information of the harvest operation that can identify the yield achievement is stored.

[0145] In the item "field ID", the identification information of the field where the harvest operation corresponding to the harvest ID was performed is stored.

[0146] In the item "harvest date", the date when the harvest operation corresponding to the harvest ID was performed is stored.

[0147] In the item "harvested product", the name of the crop harvested by the harvest operation corresponding to the harvest ID is stored.

[0148] In the item "yield", the actual value of the yield (harvest amount) in the harvest operation corresponding to the harvest ID is stored.

[0149] Note that the structure of the yield history DB 3028 shown in FIG. 7B is merely an example, and the yield history DB 3028 may include columns in which other data items are stored.

[0150] (1-6-9) Generation prediction DB 3029 FIG. 7C is a diagram showing an example of the data structure of the generation prediction DB 3029. As shown in FIG. 7C, the generation prediction DB 3029 stores predicted values of methane gas generation from the field. When the generation prediction of methane gas is performed in response to an instruction from a farmer, a new record is recorded in the generation prediction DB 3029.

[0151] The generation prediction DB 3029 includes an item “generation prediction ID”, an item “field ID”, an item “prediction date”, and an item “generation prediction value”.

[0152] In the item “generation prediction ID”, identification information of the methane gas generation prediction that can identify the generation prediction result is stored.

[0153] In the item “field ID”, identification information of the field that is the target of the generation prediction corresponding to the generation prediction ID is stored.

[0154] In the item “prediction date”, the date on which the generation prediction corresponding to the generation prediction ID was performed is stored.

[0155] In the item “generation prediction value”, the predicted value of methane gas generation obtained by the generation prediction corresponding to the generation prediction ID is stored. The generation prediction value includes a predicted generation time and a predicted generation amount.

[0156] Note that the structure of the generation prediction DB 3029 shown in FIG. 7C is merely an example, and the generation prediction DB 3029 may include columns in which other data items are stored.

[0157] <2. Outline of the Embodiment> Next, with reference to FIG. 8, an outline of an embodiment of the system 1 will be described. FIG. 8 is a diagram showing an outline of an embodiment of the system 1.

[0158] As shown in Fig. 8, as a conventional method for water management in paddy fields, in order to suppress the generation of methane from paddy fields, "mid-drying", which drains water from the paddy field during a part of the rice-growing period, has been carried out. However, regarding the period (mid-drying period) for draining water from the paddy field when performing mid-drying, clear judgment criteria have not yet been established. Against this background, the extent to which the mid-drying period affects subsequent yields varies depending on individual specific variables for each field, such as the soil components of the field, the weather history, and the work history on the field. For this reason, it is difficult to establish uniform and quantitative judgment criteria for an appropriate mid-drying period.

[0159] Therefore, when performing mid-drying, farmers set the mid-drying period within a range assumed not to have an adverse effect on yields, using their own past experience and advice from those around them. For this reason, in a situation where there is no basis to conclude that the set mid-drying period has no adverse effect on yields, nor is there a basis to conclude that methane gas generation is sufficiently suppressed, there has been a current situation where farmers routinely perform mid-drying.

[0160] Therefore, in System 1, the working time and the mid-drying period of an appropriate mid-drying period are proposed using field information including soil components to suppress the generation of methane gas. As a result, it is expected to optimize the farming operations for suppressing the generation of methane gas including mid-drying.

[0161] In addition, the farming operations proposed by System 1 are not limited to mid-drying. For example, the timing and details of the application work of methane suppression fertilizers for suppressing the generation of methane gas may also be proposed. As a result, effective application of methane suppression fertilizers can be carried out. The processing of such System 1 will be described in detail below.

[0162] <3. Operation of System 1> Next, the processing by System 1 will be described.

[0163] (3-1) Identification process of appropriate farming operations First, the specific process of identifying appropriate farming operations by the system 1 will be described. FIG. 9 is a flowchart showing the specific process of identifying appropriate farming operations by the system 1.

[0164] As shown in FIG. 9, in the specific process of identifying appropriate farming operations, the operator terminal 10 receives an instruction operation for a farming operation proposal from the farmer (step S101). Specifically, the farmer operates the operator terminal 10 at an arbitrary timing to input a proposal instruction for the farming operation to be performed to suppress the generation of methane gas. For example, this operation is performed when the farmer considers when to carry out mid-season drought. The proposal instruction for the farming operation includes the identification information of the target field. The operator terminal 10 transmits the proposal instruction for the farming operation to the management server 30.

[0165] Thereafter, the management server 30 receives the instruction for the farming operation proposal (step S201). Specifically, the transmission / reception control module 3031 of the management server 30 receives the proposal instruction for the farming operation transmitted from the operator terminal 10. The transmission / reception control module 3031 of the control unit 303 inputs the received proposal instruction for the farming operation to the acquisition module 3032.

[0166] Thereafter, the management server 30 acquires the field information (step S202). Specifically, the acquisition module 3032 of the management server 30 refers to and acquires the field information regarding the field targeted by the instruction from among the field information stored in the field DB 3022. The acquisition module 3032 inputs the acquired field information to the identification module 3033.

[0167] Thereafter, the management server 30 identifies appropriate farming operations (step S203). Specifically, the identification module 3033 of the management server 30 inputs the field information input from the acquisition module 3032 to the farming operation identification model 3041 to acquire work proposal information regarding appropriate farming operations. The work proposal information includes, for example, the following information. · The implementation time of the drainage work during mid-season drought · The mid-season drought period · The implementation time of the water supply work during mid-season drought · Timing and amount of applying methane-suppressing fertilizer

[0168] After that, the management server 30 outputs the identified farming work (step S204). Specifically, the output module 3036 of the management server 30 outputs the work proposal information obtained by the identification module 3033 to the worker terminal 10.

[0169] After that, the worker terminal 10 presents the identified farming work to the farmer (step S102). Specifically, the worker terminal 10 presents the work proposal information transmitted from the management server 30 to the farmer by displaying it on the display 1042. By checking the work proposal information displayed on the display 1042, the farmer can check the work content and the time to be carried out for the appropriate farming work to suppress the generation of methane gas. In this way, in the system 1, it is possible to propose appropriate farming work to the farmer to suppress the generation of methane gas. Thus, the specific process of identifying appropriate farming work by the system 1 is completed.

[0170] (3-2) Application process for carbon credits Next, the application process for carbon credits by the system 1 will be described. Fig. 10 is a flowchart showing the application process for carbon credits by the system 1. In this process, a process of calculating the expected reduction amount of methane gas expected to be reduced by the implementation of appropriate farming work and a process of applying for carbon credits based on the calculated expected reduction amount are performed.

[0171] As shown in Fig. 10, in the application process for carbon credits, first, the farmer inputs the work performance to the worker terminal 10 (step S111). Specifically, the farmer inputs the work performance when carrying out farming work according to the work proposal information output from the system 1 or when carrying out farming work different from the work proposal information. The worker terminal 10 transmits the input work performance to the management server 30.

[0172] After that, the management server 30 receives the work results (step S211). Specifically, the transmission / reception control module 3031 of the management server 30 receives the work results transmitted from the worker terminal 10 and stores them in the work history DB 3023.

[0173] In system 1, steps S111 and S211 are repeatedly performed throughout the entire rice cultivation period. That is, when the farmer performs the farming operations proposed by system 1, the farmer inputs the work results.

[0174] After that, for example, after harvesting paddy rice, the farmer operates the worker terminal 10 to input an application instruction for carbon credits. Specifically, the farmer applies for carbon credits as the achievement of methane gas reduction through the annual rice cultivation. Note that the application for carbon credits may be made collectively after the harvest of paddy rice, or may be made for each operation. Also, the application for carbon credits may be made by an application agency that has received a request from the farmer, by operating another terminal device that is communicably connected to the management server 30 via the network 80.

[0175] After that, the management server 30 calculates the expected amount of methane gas reduction (step S212). Specifically, the prediction module 3034 of the management server 30 predicts the generation of methane gas. The prediction module 3034 compares the predicted generation amount of methane gas predicted from the soil components before performing the farming operations included in the work proposal information with the predicted generation amount of methane gas predicted from the soil components after performing the farming operations included in the work proposal information. Thereby, the prediction module 3034 calculates the expected amount of methane gas reduction.

[0176] After that, the management server 30 applies for carbon credits (step S213). Specifically, the aggregation module 3035 of the management server 30 creates application information for carbon credits using the calculated expected methane gas reduction and information regarding the work actually performed by the farmer on the farmland. The application information includes the following information. · Information identifying the farmer (name, address, etc.) · Information identifying the farmland (address, location, etc.) · Details of the farming operations actually carried out · Expected amount of methane gas reduction due to the farming operations · Other information necessary for the review required by the certification body

[0177] Thus, the application process for carbon credits by System 1 is completed. In this way, in System 1, based on the farming operations carried out by the farmer, the expected amount of methane gas reduction can be calculated and an application for carbon credits can be made. This can save the effort involved in the farmer's application for carbon credits.

[0178] <4. Variation> A variation of this embodiment will be described. In the following description, for the same configurations and the same processes as those in the foregoing embodiment, detailed descriptions thereof will be omitted.

[0179] (4-1) First Variation: Specific Process for Identifying Appropriate Farming Operations Using Yield Prediction In System 1 according to the first variation, not only farmland information but also yield prediction is used to identify appropriate farming operations. First, the yield prediction by System 1 will be described.

[0180] (4-1-1) Yield Prediction Process FIG. 11 is a flowchart showing the yield prediction process by System 1. As shown in FIG. 11, in the yield prediction process, the operator terminal 10 receives an instruction operation for yield prediction from the farmer (step S121). Specifically, the farmer operates the operator terminal 10 at an arbitrary timing to input a yield prediction instruction. The operator terminal 10 transmits the yield prediction instruction to the management server 30.

[0181] After that, the management server 30 receives a yield prediction instruction (step S221). Specifically, the transmission / reception control module 3031 of the management server 30 receives the yield prediction instruction transmitted from the operator terminal 10. The transmission / reception control module 3031 of the control unit 303 inputs the received yield prediction instruction to the acquisition module 3032.

[0182] After that, the management server 30 acquires field information (step S222). Specifically, the acquisition module 3032 of the management server 30 refers to and acquires the field information regarding the field targeted by the instruction from among the field information stored in the field DB 3022. The acquisition module 3032 inputs the acquired field information to the prediction module 3034.

[0183] After that, the management server 30 calculates a yield prediction value (step S223). Specifically, the prediction module 3034 of the management server 30 inputs the field information input from the acquisition module 3032 to the yield prediction model 3042 to obtain a yield prediction value. The yield prediction value is stored in the yield prediction DB 3027.

[0184] After that, the management server 30 outputs the yield prediction value to the operator terminal 10 (step S224). Specifically, the output module 3036 of the management server 30 outputs the yield prediction value acquired by the prediction module 3034 toward the operator terminal 10.

[0185] After that, the operator terminal 10 presents the specified farming work to the farmer (step S122). Specifically, the operator terminal 10 presents the yield prediction value transmitted from the management server 30 to the farmer by displaying it on the display 1042. The farmer can confirm the predicted yield value by checking the yield prediction value displayed on the display 1042. In addition, the farmer can confirm the predicted value of the transition of the growth state until the future harvest by checking the predicted growth curve included in the yield prediction value. In this way, in the system 1, the yield prediction value can be provided to the farmer. Thus, the yield prediction process by the system 1 ends.

[0186] (4-1-2) Specific process for identifying appropriate farming operations using yield prediction Next, the specific process for identifying appropriate farming operations using yield prediction will be described. FIG. 12 is a flowchart showing the specific process for identifying appropriate farming operations by the system 1 according to the first modification. As shown in FIG. 12, in this process, in addition to the field information, the use of yield prediction is different from the above-described embodiment.

[0187] In the system 1 according to the first modification, the farming operation identification model 3041 is trained to output work proposal information for the input field information and yield prediction. At this time, for example, the field information and the yield prediction are used as input data, and the work proposal information for suppressing the generation of methane gas is used as the correct output data in the learning data. That is, in this case, it is to identify appropriate farming operations for suppressing the generation of methane from paddy fields while maintaining the good growth state of rice. Therefore, the mid-drying period that has no adverse effect on the yield can be accurately estimated.

[0188] Regarding steps S131 to S232 shown in FIG. 12, since they are the same as the processing shown in FIG. 9, the description thereof will be omitted. And in the system 1 according to the first modification example, after the acquisition of field information (step S232), the acquisition of yield prediction (step S233) is performed. Specifically, the acquisition module 3032 of the management server 30 refers to the yield prediction DB 3027 and acquires the yield prediction value. The acquisition module 3032 inputs the acquired yield prediction value to the identification module 3033.

[0189] After that, the management server 30 identifies an appropriate farming operation (step S234). Specifically, the identification module 3033 of the management server 30 inputs the field information and the yield prediction value input from the acquisition module 3032 to the farming operation identification model 3041, thereby acquiring work proposal information regarding an appropriate farming operation. Regarding the subsequent processing, since it is the same as the processing shown in FIG. 9, the description thereof will be omitted. In this way, the processing for identifying an appropriate farming operation by the system 1 according to the first modification example is completed.

[0190] (4-2) Second Modification Example: Identification Processing of Appropriate Farming Operations Using Methane Generation Prediction In the system 1 according to the second modification example, not only field information but also the prediction of methane gas generation is used to identify an appropriate farming operation. FIG. 13 is a flowchart showing the identification processing of an appropriate farming operation by the system 1 according to the first modification example. As shown in FIG. 13, in this processing, in addition to field information, the use of the prediction of methane gas generation is different from the above-described embodiment.

[0191] In the system 1 according to the second modification example, the farming operation identification model 3041 is trained to output work proposal information for the input field information and the prediction of methane gas generation. At this time, the learning data uses, for example, the field information and the prediction of methane gas generation as input data, and the work proposal information for suppressing the generation of methane gas as correct output data. That is, in this case, based on the prediction of the generation time of greenhouse gases from paddy fields, the implementation time of mid-drying is specified. Therefore, it is possible to propose appropriate content as the implementation time and period of mid-drying.

[0192] Regarding steps S141 to S242 shown in FIG. 13, since they are the same as the processing shown in FIG. 9, the description thereof will be omitted. And in the system 1 according to the second modification example, after acquiring the field information (step S242), acquisition of methane generation prediction (step S243) is performed. Specifically, the acquisition module 3032 of the management server 30 refers to the generation prediction DB and acquires the methane generation prediction value. The acquisition module 3032 inputs the acquired methane generation prediction value to the specification module 3033.

[0193] After that, the management server 30 specifies an appropriate farming operation (step S244). Specifically, the specification module 3033 of the management server 30 inputs the field information and the methane generation prediction value input from the acquisition module 3032 to the farming operation specification model 3041, thereby acquiring operation proposal information regarding an appropriate farming operation. Since the subsequent processing is the same as the processing shown in FIG. 9, the description thereof will be omitted. In this way, the processing for specifying an appropriate farming operation by the system 1 according to the second modification example is completed.

[0194] <5. Other Modification Examples> The following describes other modification examples.

[0195] In the above embodiment, methane gas has been described as an example of the greenhouse gas, but this is not the only case. That is, the system 1 may propose an appropriate farming operation for the purpose of reducing greenhouse gases other than methane gas.

[0196] In the above embodiment, rice has been described as an example of the crop grown in the field, but this is not the only case. That is, the system 1 may propose an appropriate farming operation for the purpose of reducing greenhouse gases for fields growing crops other than rice.

[0197] In addition, in the step of obtaining field information, the detection of the content of specific molecules contained in the soil of the field may be obtained. The detection of the increase or decrease in the content of such specific molecules may be performed using the appearance information of the plant markers. The appearance information of the food markers refers to the growth status of the food markers, the color of the leaves, etc., and for example, the observation results of farmers are periodically input. As the appearance information, image data of the food markers may be used. Thereby, even without directly measuring the soil components, the change in the soil components can be detected based on the change in the plant markers. Also, in the step of obtaining field information, the measurement result of the content of methane-producing bacteria in paddy fields may be obtained. Thereby, the accuracy of predicting the generation of methane gas can be improved.

[0198] In addition, in System 1, the predicted amount of greenhouse gas generation in the following year calculated from the results of field management work carried out after the harvest in the previous year in the field may be obtained and used for specifying appropriate farming operations. The field management work includes, for example, the operation of mowing the straw left in the field.

[0199] Also, in System 1, yield prediction may be performed using field information and weather history. In this case, the yield prediction model 3042 is learned to output a predicted value of the growth state of paddy rice in the field for the input field information and weather history. At this time, for the learning data, for example, the field information and weather history are used as input data, and for the input field information, the growth state of paddy rice in the field is used as the correct output data.

[0200] Also, in the above embodiment, the field information based on the sensing result obtained by the sensor 40 is used, but this is not the limit. The field information may refer to the soil information for each region publicly disclosed by research institutions related to agriculture, obtain the field information related to the fields managed by farmers, and specify the above-described work proposal information.

[0201] As described above in detail for the embodiments of the present invention, the scope of the present invention is not limited to the above embodiments. Also, various improvements and modifications are possible for the above embodiments without departing from the gist of the present invention. Further, the above embodiments and modified examples can be combined or a part thereof can be omitted.

[0202] <6. Supplementary Note> The matters described in the embodiments and modified examples are supplemented below.

[0203] (Supplementary Note 1) A program executed by a system having a processor and making a proposal regarding the management of paddy fields performed by farmers, wherein the processor is caused to acquire field information including the soil components of the paddy field; specify appropriate farming operations for suppressing the generation of greenhouse gases from the paddy field based on the acquired field information; and output the specified appropriate farming operations to the operator terminal. A program for causing the above to be executed.

[0204] (Supplementary Note 2) In the step of specifying the appropriate farming operations, a learned model constructed by machine learning using the field information as input data and learning data having the appropriate farming operations as correct output data for the input of the field information is used to specify the appropriate farming operations. The program according to Supplementary Note 1.

[0205] (Supplementary Note 3) The soil components include the oxidation-reduction potential of the paddy field. In the step of acquiring the field information, the measurement result of the oxidation-reduction potential of the paddy field is acquired. The appropriate farming operations include operations for slowing down the change in the oxidation-reduction potential of the paddy field, in other words, operations for maintaining the oxidation-reduction potential of the paddy field at a target potential. The program according to Supplementary Note 1 or 2.

[0206] (Supplementary Note 4) The soil component includes the content of specific molecules related to the redox state of the paddy field. In the step of acquiring the field information, the program according to any one of Appendices 1 to 3, which acquires the detection of the content of the specific molecule.

[0207] (Appendix 5) The detection of the increase or decrease in the content of the specific molecule is performed using the appearance information of a plant grown in the paddy field and whose appearance changes according to the increase or decrease in the specific molecule, according to the program described in Appendix 4.

[0208] (Appendix 6) The soil component includes the content of methane-producing bacteria in the paddy field. In the step of acquiring the field information, the program according to any one of Appendices 1 to 5, which acquires the measurement result of the content of methane-producing bacteria in the paddy field.

[0209] (Appendix 7) The agricultural work includes the water supply work to the paddy field and the drainage work from the paddy field, according to the program described in any one of Appendices 1 to 6.

[0210] (Appendix 8) In the step of specifying the appropriate agricultural work, the program according to Appendix 7, which specifies the implementation time of the agricultural work based on the prediction of the generation time of the greenhouse gas from the paddy field based on the input field information.

[0211] (Appendix 9) The agricultural work includes the spraying work of methane-suppressing fertilizer to the paddy field, according to the program described in any one of Appendices 1 to 8.

[0212] (Appendix 10) To the processor, Based on the input field information, further execute the step of predicting the growth state of rice including the predicted yield at the harvest stage. In the step of identifying the appropriate farming operation, based on the input field information and the predicted growth information indicating the growth state of the paddy rice, an appropriate farming operation is identified to suppress the generation of methane from the paddy field while maintaining the good growth state of the paddy rice, according to the program described in any one of Appendices 1 to 9.

[0213] (Appendix 11) To the processor, further execute the step of obtaining the predicted generation amount of the greenhouse gas based on the field information, In the step of identifying the appropriate farming operation, based on the input field information and the obtained predicted generation amount of the greenhouse gas, an appropriate farming operation is identified to suppress the generation of the greenhouse gas from the paddy field, according to the program described in any one of Appendices 1 to 10.

[0214] (Appendix 12) To the processor, further execute the step of calculating the expected reduction amount of the greenhouse gas that is expected to be reduced by the implementation of the identified appropriate farming operation, Based on the calculated expected reduction amount, apply for carbon credits, according to the program described in any one of Appendices 1 to 11.

[0215] (Appendix 13) A method executed by a system having a processor and making a proposal regarding the management of a paddy field performed by a farmer, wherein the processor obtains field information including the soil components of the paddy field based on an operation from an operator terminal; identifies an appropriate farming operation to suppress the generation of the greenhouse gas from the paddy field based on the obtained field information; outputs the identified farming operation to the operator terminal; and executes.

[0216] (Appendix 14) A system having a processor and making proposals regarding the management of paddy fields performed by farmers, wherein the processor a module that acquires field information including the soil components of the paddy field based on an operation from an operator terminal; a module that identifies appropriate farming operations for suppressing the generation of greenhouse gases from the paddy field based on the acquired field information; and a module that outputs the identified farming operations to the operator terminal A system comprising:

[0217] (Appendix 15) One aspect of the present disclosure is a program executed by a system having a processor and making proposals regarding the management of paddy fields performed by farmers, the processor performing, based on an operation from an operator terminal, the step of acquiring field information including the soil components of the paddy field, the step of identifying appropriate farming operations for suppressing the generation of greenhouse gases from the paddy field based on the acquired field information, and the step of outputting the identified appropriate farming operations to the operator terminal.

Industrial Applicability

[0218] The present invention is applicable to the field of farming support systems.

Explanation of Signs

[0219] 1 Farming support system 10 Operator terminal 20 Administrator terminal 30 Management server 31 Processor 32 Memory 33 Storage 34 Communication IF 35 Input / output IF 301 Communication unit 302 Storage unit 303 Control unit 40 Sensor 80 Network

Claims

1. A program executed by a system that has a processor and makes proposals regarding the management of paddy fields performed by farmers, wherein the processor performs a step of acquiring field information including the soil components of the paddy field, performs a step of identifying appropriate farming operations for suppressing the generation of greenhouse gases from the paddy field based on the acquired field information, performs a step of outputting the identified appropriate farming operations to a worker terminal A program that causes the above to be executed.

2. In the step of identifying the appropriate farming operations, a learned model constructed by machine learning using the field information as input data and learning data having the appropriate farming operations as correct output data for the input of the field information is used to identify the appropriate farming operations. The program according to claim 1.

3. The soil components include the oxidation-reduction potential of the paddy field, In the step of acquiring the field information, the measurement result of the oxidation-reduction potential of the paddy field is acquired, The appropriate farming operations include operations for maintaining the oxidation-reduction potential of the paddy field at a target potential. The program according to claim 1.

4. The soil components include the content of specific molecules related to the oxidation-reduction state of the paddy field, In the step of acquiring the field information, the detection of the content of the specific molecules is acquired. The program according to claim 1.

5. The detection of the increase or decrease in the content of the specific molecules is performed using the appearance information of plants grown in the paddy field and whose appearance changes according to the increase or decrease of the specific molecules. The program according to claim 4.

6. The soil components include the content of methane-producing bacteria in the paddy field, In the step of acquiring the field information, the measurement result of the content of the methane-producing bacteria in the paddy field is acquired. The program according to claim 1.

7. The farming operations include a water supply operation to the paddy field and a drainage operation from the paddy field. The program according to claim 1.

8. In the step of identifying the appropriate farming operations, the implementation timing of the farming operations is identified based on the prediction of the generation timing of the greenhouse gases from the paddy field based on the input field information. The program according to claim 7.

9. The farming operations include a spraying operation of methane-suppressing fertilizer to the paddy field. The program according to claim 1.

10. To the processor, Further execute a step of predicting the growth state of paddy rice including the predicted yield at the harvest stage based on the input field information. In the step of identifying the appropriate farming operation, based on the input field information and the predicted growth information indicating the predicted growth state of the paddy rice, identify an appropriate farming operation for suppressing the generation of methane from the paddy field while maintaining the good growth state of the paddy rice. The program according to claim 1.

11. Cause the processor to Further execute a step of obtaining a predicted amount of greenhouse gas generation based on the field information. In the step of identifying the appropriate farming operation, based on the input field information and the obtained predicted amount of greenhouse gas generation, identify an appropriate farming operation for suppressing the generation of the greenhouse gas from the paddy field. The program according to claim 1.

12. Cause the processor to Further execute a step of calculating an expected reduction amount of the greenhouse gas that is expected to be reduced by the implementation of the identified appropriate farming operation. Based on the calculated expected reduction amount, perform at least one of applying for carbon credits and calculating a carbon footprint. The program according to claim 1.

13. A method executed by a system having a processor and making a proposal regarding the management of paddy fields performed by farmers, wherein the processor Obtains field information including the soil components of the paddy field. Based on the obtained field information, identifies an appropriate farming operation for suppressing the generation of greenhouse gas from the paddy field. Outputs the identified farming operation to the operator terminal. And execute.

14. A system having a processor and making a proposal regarding the management of paddy fields performed by farmers, wherein the processor A module for obtaining field information including the soil components of the paddy field. A module for identifying an appropriate farming operation for suppressing the generation of greenhouse gas from the paddy field based on the obtained field information. A module for outputting the identified farming operation to the operator terminal. And comprises.

Images