JP2022167693A - Feature quantity determination system, feature quantity determination method, and server - Google Patents

Abstract

To determine the feature quantity that contributes to harvest information as an object, from the harvest information such as the harvest amount and environmental information obtained by a sensor.SOLUTION: Provided is a feature quantity determination system in which a sensor terminal, a server, and a terminal device are communicably connected. The sensor terminal includes: a sensor that measures a plurality of pieces of environmental information regarding a farm field at which the sensor terminal is placed; and a sensor terminal transmission unit that transmits farm field information and the plurality of pieces of environmental information. The terminal device includes: an input unit that inputs harvest information regarding the harvest amount and the quality of the harvested product for each farm field; a communication unit that receives the feature quantity for each farm field; and an output unit that can output the feature quantity for each farm field. The server includes: a receiving unit that receives the farm field information, the plurality of pieces of environmental information, and the harvest information; a determination unit that determines a feature quantity correlated with at least one of the harvest amount and the quality of the harvested product for each farm field based on the plurality of pieces of environmental information and the harvest information over a predetermined period; and a transmission unit that transmits the feature quantity for each farm field.SELECTED DRAWING: Figure 1

Description

The present invention relates to a feature quantity determination system, a feature quantity determination method, and a server.

BACKGROUND ART Until now, an agricultural management system for assisting management of crops or fields has been known (for example, Patent Literature 1). The agricultural management system described in Patent Literature 1 measures the environmental information of a field, transmits the environmental information to a server, and associates an evaluation value indicating the performance value of crops harvested in the past with the environmental information during the growing period. Based on the current environment information, environment compatibility information indicating the environment necessary for harvesting crops with a predetermined evaluation value is created, and the environment compatibility information is transmitted to the mobile terminal.

However, in the conventional agricultural management system, there is a problem that it is difficult to determine which of the plurality of environmental information contributes to the yield of agricultural products.

JP 2017-46613 A

A feature amount determination system according to an embodiment of the present disclosure aims to determine a feature amount that contributes to target harvest information from environmental information obtained by a sensor and harvest information such as a harvest amount.

A feature amount determination system according to an embodiment of the present disclosure is a feature amount determination system in which a sensor terminal, a server, and a terminal device are communicably connected, and the sensor terminal is installed in a plurality of environments related to a field. It has a sensor that measures information, and a sensor terminal transmission unit that transmits field information and a plurality of environmental information about the field, and the terminal device is an input for inputting harvest information regarding the harvest amount and the quality of the harvest for each field. a communication unit that receives the feature amount for each field; and an output unit that can output the feature amount for each field. The server receives field information, a plurality of environmental information, and harvest information. a receiving unit, a determining unit that determines a feature quantity correlated with at least one of a harvest amount and quality of a harvested product for each field based on a plurality of pieces of environmental information and harvest information over a predetermined period, and features of each field and a transmitting unit for transmitting the quantity.

In the feature quantity determination system according to an embodiment of the present disclosure, the determination unit calculates a correlation coefficient with at least one of the harvest amount and the quality of the harvest for each of the plurality of environmental information, and a correlation higher than a predetermined threshold Environmental information having a number may be determined as a feature amount.

In the feature amount determination system according to an embodiment of the present disclosure, the determination unit determines a predetermined number of months, a predetermined number of days, or a predetermined time period as a predetermined period, and based on the value of the environment information for each predetermined period , the correlation coefficient may be calculated.

In the feature value determination system according to an embodiment of the present disclosure, the determination unit includes, during a predetermined period, the highest value, the lowest value, the average value, the number of counts based on a predetermined threshold value, the difference percentile, the environmental information measured by the sensor terminal Alternatively, the correlation coefficient may be calculated using the standard deviation as the value of the environment information for the predetermined period.

In the feature quantity determination system according to an embodiment of the present disclosure, the plurality of environmental information may be temperature, relative humidity, saturation difference, or CO ₂ concentration.

A feature amount determination method according to an embodiment of the present disclosure is a feature amount determination method in a system in which a sensor terminal, a server, and a terminal device are communicably connected, wherein the sensor terminal includes a plurality of The terminal device inputs harvest information regarding the yield and quality of harvested products for each field, and the server, based on a plurality of environmental information and harvest information over a predetermined period, for each field, A characteristic value having a correlation with at least one of the harvest amount and the quality of the harvested product is determined, and the terminal device outputs the characteristic value for each field.

A server according to an embodiment of the present disclosure is a server communicably connected to a sensor terminal and a terminal device, and receives field information about a field in which the sensor is installed and a plurality of environmental information from the sensor terminal, a receiving unit that receives harvest information on the yield and quality of harvest for each field from a terminal device; It is characterized by having a determination unit that determines a feature amount having a correlation with at least one, and a transmission unit that transmits the feature amount for each field.

According to the feature amount determination system according to an embodiment of the present disclosure, it is possible to determine a feature amount that contributes to target harvest information from environmental information obtained by a sensor and harvest information such as a harvest amount.

1 is a diagram illustrating an example of a schematic configuration of a feature quantity determination system according to an embodiment of the present disclosure; FIG. It is a figure which shows an example of schematic structure of a sensor terminal. It is a figure which shows an example of schematic structure of a terminal device. It is a figure which shows an example of a schematic structure of a server. It is a figure which shows an example of the operation sequence of the feature-value determination system which concerns on one Embodiment of this disclosure. FIG. 4 is a diagram showing an example of a flowchart for explaining operation procedures of the feature quantity determination system according to an embodiment of the present disclosure; 4 is a graph showing an example of the relationship between the monthly average of the maximum CO ₂ concentration in all days and the yield of the target crop. 4 is a table showing an example of the relationship between the CO ₂ concentration in each month and the correlation coefficient with respect to the yield. FIG. 10 is a graph showing an example of the relationship between the highest value of saturation in the daytime and the yield of target crops; FIG. It is a table|surface which shows an example of the relationship between the saturation difference in each month, and the correlation coefficient with respect to a return yield. 4 is a table showing an example of the relationship between relative humidity in each month and a correlation coefficient with respect to yield. 4 is a table showing an example of the relationship between the temperature in each month and the correlation coefficient with respect to the yield. 2 is a table showing an example of the relationship between standard deviations of CO ₂ concentration, saturation, relative humidity, and temperature in each month and correlation coefficients with respect to yield. 2 is a table showing an example of the relationship between CO ₂ concentration, saturation, relative humidity, and temperature in each month and the maximum value of the correlation coefficient with respect to yield.

A feature quantity determination system, a feature quantity determination method, and a server according to an embodiment of the present disclosure will be described below with reference to the drawings. However, it should be noted that the technical scope of the present invention is not limited to those embodiments, but extends to the invention described in the claims and equivalents thereof.

FIG. 1 shows an example of a schematic configuration of a feature quantity determination system according to an embodiment of the present disclosure. The feature quantity determination system 100 has one or more sensor terminals 10, a terminal device 20, and a server 30, which are communicably connected. The feature determination system 100 further includes a relay device 40 that receives information from one or more sensor terminals 10 , and the terminal device 20 , server 30 and relay device 40 are connected by a communication network 50 .

The feature value determination system 100 accumulates or manages environmental information of the field 60 in accordance with a request from a user who manages the field 60 where crops are grown. The environmental information is data indicating environmental factors such as measured temperature, relative humidity, saturation, or CO ₂ concentration.

One or a plurality of sensor terminals 10 are installed for each of the plurality of fields 60, and each sensor terminal 10 has a sensor unit that measures environmental factors. In the field 60, target crops are grown and harvested. The relay device 40 may accumulate environmental information transmitted from one or more sensor terminals 10 and transmit the accumulated environmental information to the server 30 . Alternatively, it may be transmitted directly from the sensor terminal 10 to the server 30 .

First, the sensor unit connected to the sensor terminal 10 measures environmental factors such as temperature, relative humidity, saturation, or CO ₂ concentration. Next, the sensor terminal 10 acquires and accumulates environmental information indicating the environmental factors of the field 60 measured by the sensor unit from the sensor unit at predetermined measurement intervals. The predetermined measurement cycle is, for example, 10 minutes, but may be arbitrarily set by the user who manages the farm field 60 or the administrator of the feature quantity determination system 100 or the like.

Next, the sensor terminal 10 transmits the accumulated environmental information to the relay device 40 at a predetermined transmission cycle. The predetermined transmission period may be the same period as the measurement period or a period longer than the measurement period. Note that the sensor terminal 10 may directly transmit the environmental information to the server 30 at predetermined intervals.

Next, the relay device 40 receives environmental information transmitted from one or a plurality of sensor terminals 10 at a predetermined transmission cycle, accumulates the received environmental information, and converts the accumulated environmental information of each sensor terminal 10 into a predetermined is transmitted to the server 30 at the server transmission cycle of . The server transmission cycle is, for example, one hour, but may be arbitrarily set by the administrator of the feature quantity determination system 100 or the like.

Next, the server 30 receives the transmitted current environmental information of the field 60 . In each of the plurality of fields 60, the server 30 associates and stores harvest information regarding the yield and quality of the crop harvested in each field 60 with environmental information during the growing period in which the crop was grown. . The harvest information may include at least one of a plurality of evaluation values corresponding to the yield of the harvested crops and a plurality of evaluation values corresponding to the quality of the harvested crops. Also, the harvest information regarding the harvest amount and the quality of the harvested product may be set by a farmer who harvested the crop, a specific evaluator, or the like. The quality of crops may include shape, size, sugar content, content of various vitamins, content of various minerals, evaluation value of taste, and the like.

The server 30 determines a feature quantity correlated with at least one of the harvest amount and the quality of the harvested product for each field, based on a plurality of pieces of environmental information and harvest information over a predetermined period. Here, a correlation coefficient between at least one of the harvest amount and the quality of the harvested product may be calculated for each of the plurality of pieces of environmental information, and environmental information having a correlation coefficient higher than a predetermined threshold value may be determined as the feature amount.

The server 30 determines the feature amount for each field. First, the server 30 calculates correlation coefficients between various measurement items included in the environmental information and the harvested amount based on the relationship between the current environmental information and at least one of the harvested amount and quality. Then, the server 30 extracts from the current environmental information measurement items whose absolute value of correlation coefficient with a predetermined harvest amount is greater than a predetermined threshold. For example, if the current environmental information is temperature, relative humidity, saturation, or _CO2 concentration, calculate the correlation coefficient between these measurement items and the yield, and the absolute value of the correlation coefficient is Decide on a large measurement item. Similarly, for the quality of crops, the correlation coefficient between the temperature, relative humidity, saturation difference, or _CO2 concentration and the quality evaluation value is calculated, and the measurement item with the large absolute value of the correlation coefficient is determined. do.

Next, the server 30 transmits to the terminal device 20 of the user who manages the farm field 60 information about the measurement item having a large correlation coefficient with the yield or quality of the crop in the farm field 60 . Then, the user who manages the farm field 60 manages the farm field 60 according to the displayed measurement item with a large correlation coefficient.

As described above, the feature value determination system 100 can manage environmental information suitable for the environmental factors unique to each field 60, and therefore can manage an environment suitable for growing crops in each field 60. FIG.

Although the case where the field 60 is a vinyl house will be described, it is not limited to such an example, and may be a facility such as a factory capable of controlling the environment. Although FIG. 1 shows an example in which three fields 60 are provided, the number of fields 60 is not limited to such an example, and the number of fields 60 may be one, two, or four or more. good too.

Next, the sensor terminal 10 included in the feature quantity determination system 100 according to an embodiment of the present disclosure will be described. FIG. 2 shows an example of a schematic configuration of the sensor terminal 10. As shown in FIG. The sensor terminal 10 has a sensor section 11 , a sensor terminal transmission section 12 , a GPS section 13 , a sensor connection section 14 , a sensor terminal control section 15 and a sensor terminal storage section 16 . connected by

The sensor unit 11 measures a plurality of environmental information regarding the field 60 in which it is set. A plurality of environmental information are, for example, temperature, relative humidity, saturation, or _CO2 concentration. However, the environment information is not limited to such an example, and other measurement information may be included in the environment information.

The sensor unit 11 has a temperature sensor for measuring temperature, a relative humidity sensor for measuring relative humidity, a saturation sensor for measuring saturation, and a CO ₂ concentration sensor for measuring CO ₂ concentration. . However, it is not limited to such an example, and other sensors may be included. For example, the sensor unit 11 includes a soil temperature sensor for measuring soil temperature, a soil moisture sensor for measuring soil moisture content, a solar radiation sensor for measuring solar radiation, and a soil sensor for measuring soil electrical conductivity. At least one of an EC (Electrical Conductivity) sensor, a soil pH sensor for measuring soil pH, a dew point temperature sensor, a water level sensor, a water temperature sensor, a wind direction sensor, and a wind speed sensor may be included.

The temperature is the temperature in the field 60 where the sensor terminal 10 is installed, and the unit is Celsius [°C].

The relative humidity is the ratio of the amount of water vapor in the field 60 where the sensor terminal 10 is installed and the amount of saturated water vapor at the temperature at that time, expressed as a percentage.

The saturation difference is an index indicating how much more water vapor can enter in the air of a certain temperature and humidity in the field 60 where the sensor terminal 10 is installed, and is the free space of water vapor per cubic meter of air. Expressed in grams. The saturation sensor can calculate the saturation D by applying the temperature and relative humidity included in the environment information to the following equations (1) to (3). In formulas (1) to (3), the unit of temperature T is Celsius [°C], the unit of relative humidity R is percent [%], and the unit of saturation D is gram/cubic meter [g/m ³ ].

Water vapor pressure = 6.1078 x 10 ^ ((7.5 x T/(T + 237.3))) (1)
Saturated water vapor volume = 217 x water vapor pressure / (T + 273.15) (2)
D = (100-R) x Saturated water vapor volume/100 (3)

It is known that the water status of plants is more strongly affected by saturation than by relative humidity. For example, when the saturation difference is small, the humidity is high, and even if the stomata of the leaves of the crop are open, the amount of transpiration is small. On the other hand, when the saturation difference is moderate, the stomata open and transpiration occurs vigorously. If the saturation difference is further increased, it may become dry and the pores may close.

The CO ₂ concentration is the concentration of carbon dioxide (CO ₂ ) in field 60 where sensor terminal 10 is installed. A CO ₂ concentration sensor can measure the concentration of CO ₂ by detecting the CO ₂ absorption wavelength. It is generally known that an increase in CO ₂ concentration increases the yield of agricultural crops.

The sensor terminal transmission unit 12 transmits agricultural field information and a plurality of environmental information regarding the agricultural field 60 . The field information may include at least one of field identification information, field area information, and field position information. The sensor terminal transmission unit 12 has a communication interface circuit including an antenna whose sensitivity band is mainly 920 [MHz], and connects the sensor terminal 10 to the relay device 40 . The sensor terminal transmission unit 12 uses a specific channel to perform radio communication with the relay device 40 based on a specific low-power radio system or the like. Note that the frequency band of wireless communication performed between the sensor terminal transmission unit 12 and the relay device 40 is not limited to the frequency band described above. The sensor terminal transmission unit 12 transmits the environment information supplied from the sensor unit 11 to the relay device 40 .

The sensor terminal storage unit 16 has, for example, a semiconductor memory. The sensor terminal storage unit 16 stores driver programs, operating system programs, data, etc. used for processing in the sensor terminal control unit 15 . For example, the sensor terminal storage unit 16 stores, as driver programs, a wireless communication device driver program that controls the sensor terminal transmission unit 12, a GPS driver program that controls the GPS unit 13, a sensor driver program that controls the sensor unit 11, and the like. . The sensor terminal storage unit 16 also stores, as an operating system program, a radio control program for executing a specific low-power radio system or the like. The sensor terminal storage unit 16 also stores environmental information indicating the environmental factors measured by the sensor unit 11 as data.

The GPS unit 13 has a GPS circuit including an antenna whose sensitive band is mainly the 1.5 [GHz] band, and receives GPS signals from GPS satellites. The GPS unit 13 decodes GPS signals and acquires time information and the like. Next, the GPS unit 13 calculates the pseudoranges from the GPS satellites to the sensor terminal 10 based on the time information or the like, and solves the simultaneous equations obtained by substituting the pseudoranges to determine whether the sensor terminal 10 exists. Detect location (latitude, longitude, altitude, etc.). Then, the GPS unit 13 associates the position information indicating the detected position with the acquired time information, and periodically outputs the information to the sensor terminal control unit 15 .

The sensor connection section 14 includes a sensor terminal that connects with the sensor section 11 and connects with the sensor section 11 for measuring one or more types of environmental factors.

The sensor unit 11 includes various sensors for measuring environmental factors such as temperature, relative humidity, saturation, and _CO2 concentration. However, the sensor unit 11 is not limited to such examples, and the sensor unit 11 measures environmental factors such as soil temperature, soil moisture content, amount of solar radiation, soil electrical conductivity, soil pH, wind direction and wind speed, dew point temperature, water level, and water temperature. may include various sensors for For example, the sensor unit 11 includes at least a temperature sensor for measuring temperature, a humidity sensor for measuring relative humidity, a saturation sensor for measuring saturation, and a CO ₂ sensor for measuring CO ₂ concentration. Contains any one. However, the sensor unit 11 is not limited to such an example, and includes a soil temperature sensor for measuring soil temperature, a soil moisture sensor for measuring soil moisture content, a solar radiation sensor for measuring solar radiation, and a soil At least one of a soil EC sensor for measuring electrical conductivity, a soil pH sensor for measuring soil pH, a wind direction sensor and wind speed sensor, a dew point temperature sensor, a water level sensor, a water temperature sensor, etc. may be included.

The sensor terminal control unit 15 has one or more processors and their peripheral circuits. The sensor terminal control unit 15 comprehensively controls the overall operation of the sensor terminal 10, and is, for example, a CPU. The sensor terminal control unit 15 controls the sensor unit 11, the sensor terminal transmitting unit 12, the GPS It controls the operation of the unit 13 and the like. The sensor terminal control unit 15 executes processing based on programs (driver program, operating system program, etc.) stored in the sensor terminal storage unit 16 .

Next, the terminal device 20 included in the feature quantity determination system 100 according to an embodiment of the present disclosure will be described. FIG. 3 shows an example of a schematic configuration of the terminal device 20. As shown in FIG. The terminal device 20 has an input section 21 , a communication section 22 , an output section 23 , a terminal control section 24 and a terminal storage section 25 , which are connected by a bus 26 .

The input unit 21 inputs harvest information regarding the harvest amount and the quality of the harvest for each field. The input unit 21 may be any device as long as it is possible to input data to the terminal device 20, and may be, for example, a keyboard, mouse, touch panel, keypad, or the like. The operator of the terminal device 20 can use these devices to input information such as letters and numbers. The input unit 21 generates a signal corresponding to the input operation when the operator performs an input operation. The generated signal is input to the terminal controller 24 as an operator's instruction.

The communication unit 22 receives the feature amount for each field from the server 30 . The communication unit 22 has a communication interface circuit and connects the terminal device 20 to the communication network 50 (see FIG. 1). The communication unit 22 supplies the data received from the server 30 to the terminal control unit 24 .

The output unit 23 outputs the feature amount for each field. The output unit 23 may be any device as long as it can output moving images, still images, and the like. The output unit 23 may be, for example, a touch panel display device, a liquid crystal display, an organic EL display, or the like. The output unit 23 may display a moving image corresponding to the moving image data supplied from the terminal control unit 24, a still image corresponding to the still image data, and the like.

The terminal control unit 24 has one or more processors and their peripheral circuits. The terminal control unit 24 comprehensively controls the overall operation of the terminal device 20, and is, for example, a CPU. The terminal control unit 24 controls the communication unit 22 and the output unit 23 so that various processes of the terminal device 20 are executed in an appropriate procedure according to the programs stored in the terminal storage unit 25 and the operation of the input unit 21. and other operations. The terminal control unit 24 executes processing based on programs (driver program, operating system program, application program, etc.) stored in the terminal storage unit 25 . Also, the terminal control unit 24 can execute a plurality of programs (application programs, etc.) in parallel.

The terminal storage unit 25 has, for example, a semiconductor memory. The terminal storage unit 25 stores driver programs, operating system programs, application programs, data, and the like used for processing in the terminal control unit 24 . For example, the terminal storage unit 25 stores, as driver programs, a communication device driver program for controlling the communication unit 22, an input device driver program for controlling the input unit 21, an output device driver program for controlling the output unit 23, and the like. The terminal storage unit 25 also stores a connection control program and the like as operating system programs. The terminal storage unit 25 also stores, as application programs, a web browser program for acquiring and displaying web pages, an e-mail program for sending and receiving e-mails, and the like. The computer program may be installed in the terminal storage unit 25 from a computer-readable portable recording medium such as CD-ROM, DVD-ROM, etc. using a known setup program or the like.

Next, the server 30 included in the feature quantity determination system 100 according to an embodiment of the present disclosure will be described. FIG. 4 shows an example of a schematic configuration of the server 30. As shown in FIG. The server 30 has a receiving section 31 , a determining section 32 , a transmitting section 33 , a server control section 34 and a server storage section 35 , which are connected by a bus 36 .

The receiving unit 31 receives field information, a plurality of pieces of environmental information, and harvest information. The receiver 31 has a communication interface circuit for connecting the server 30 to the communication network 50 . The receiving unit 31 receives data from the sensor terminal 10 transmitted from the relay device 40 and data transmitted from the terminal device 20 , and supplies the received data to the server control unit 34 .

The determination unit 32 determines a feature quantity correlated with at least one of the yield and the quality of the harvested product for each field based on a plurality of pieces of environmental information and harvested information over a predetermined period. A feature amount is environmental information measured by the sensor terminal 10 during a predetermined measurement period, and is information that correlates with at least one of the yield and the quality of the harvest.

The determination unit 32 calculates a correlation coefficient with at least one of the harvest amount and the quality of the harvested product for each of the plurality of pieces of environmental information, and determines environmental information having a correlation coefficient whose absolute value is higher than a predetermined threshold value as a feature amount. You can Whether or not the feature quantity has a correlation with the harvest information may be determined by calculating the magnitude of the correlation coefficient and determining whether or not the absolute value of the calculated correlation coefficient is greater than a predetermined threshold.

The determination unit 32 may determine a predetermined number of months, a predetermined number of days, or a predetermined period of time as the predetermined period, and calculate the correlation coefficient based on the value of the environment information for each predetermined period. For example, in the case of crops grown in winter, the environmental information acquisition period may be four months from November to February of the following year. Also, the predetermined number of days for calculating the average value of the environmental information may be the number of days in a month or the number of days in a week. Also, the time period for acquiring the environment information may be 24 hours a day, or may be a predetermined time period within the day.

The determination unit 32 determines the maximum value, minimum value, average value, count number based on a predetermined threshold value, percentile difference, or standard deviation of the environmental information measured by the sensor terminal 10 during a predetermined period of time. A correlation coefficient may be calculated as the value of . A specific method of calculating the correlation coefficient will be described later.

The transmission unit 33 transmits the feature amount for each field to the terminal device 20 . The transmitter 33 has a communication interface circuit for connecting the server 30 to the communication network 50 . The transmission unit 33 may transmit the data regarding the feature quantity to the terminal device 20 via the communication network 50 .

The server control unit 34 has one or more processors and their peripheral circuits. The server control unit 34 comprehensively controls the overall operation of the server 30, and is, for example, a CPU. The server control unit 34 controls the operation of the receiving unit 31, the determining unit 32, and the transmitting unit 33 so that various processes of the server 30 are executed in an appropriate procedure according to the programs and the like stored in the server storage unit 35. Control. The server control unit 34 executes processing based on programs (driver program, operating system program, application program, etc.) stored in the server storage unit 35 . Also, the server control unit 34 can execute a plurality of programs (application programs, etc.) in parallel.

Next, an operation sequence of the feature quantity determination system 100 according to an embodiment of the present disclosure will be described. FIG. 5 shows an example of an operation sequence of the feature quantity determination system 100 according to an embodiment of the present disclosure.

First, the sensor terminal 10 measures a plurality of pieces of environmental information about the field 60 (S101). Here, as environmental information, the temperature, relative humidity, saturation difference, or CO ₂ concentration measured by the sensor unit 11 during a predetermined period will be described as an example. However, environmental information is not limited to this information.

Next, the sensor terminal 10 transmits agricultural field information and a plurality of pieces of environmental information regarding the agricultural field 60 to the server 30 (S102).

Next, the terminal device 20 inputs the harvest information regarding the harvest amount and the quality of the harvest for each field (S103). The input harvest information is transmitted to the server 30 by the communication unit 22 of the terminal device 20 .

Next, the server 30 receives farm field information, a plurality of environmental information, and harvest information (S104).

Next, the server 30 determines a feature quantity correlated with at least one of the harvest amount and the quality of the harvested product for each field based on a plurality of pieces of environmental information and harvest information over a predetermined period (S105). The server 30 transmits the feature amount for each field to the terminal device 20 .

Next, the terminal device 20 receives the feature amount for each field from the server 30 (S106).

Next, the terminal device 20 outputs the feature amount for each field (S107).

As described above, based on a plurality of pieces of environmental information and harvest information over a predetermined period, the terminal device 20 outputs a feature amount correlated with at least one of the yield and the quality of the harvest for each field. be. According to the feature amount output to the terminal device 20, it is possible to set the conditions for growing crops.

Next, operation procedures of the feature quantity determination system 100 according to an embodiment of the present disclosure will be described. FIG. 6 shows an example of a flowchart for explaining the operation procedure of the feature quantity determination system 100 according to an embodiment of the present disclosure.

First, in step S<b>201 , the sensor terminal 10 measures a plurality of environmental information regarding the farm field 60 . Specifically, the sensor unit 11 of the sensor terminal 10 installed in the field 60 measures temperature, relative humidity, saturation difference, or CO ₂ concentration in a predetermined period. For example, the predetermined time period may be "all day", measured over a 24-hour period, or "day", measured during a predetermined period of the day, eg, from 10:00 to 14:00. The environmental information may be data on one farm field spanning a plurality of years, or may be data on a plurality of farm fields spanning a plurality of years. Alternatively, the environmental information may be data for a single year regarding multiple fields.

Next, in step S<b>202 , the terminal device 20 inputs harvest information regarding the yield and quality of the harvest for each field 60 .

As the harvest information related to the amount of harvest, "yield" may be used. Yield is the amount of crops harvested per 1 acre (about 10 ares) of field. Data on yield per unit area may be used instead of yield per area.

Harvest information related to the quality of agricultural products includes "appearance" such as shape and color, "taste" such as taste, aroma and texture, "nutrition" such as minerals and vitamins, and "functionality" such as dietary fiber and pigments. may be information about However, it is not limited to these information, and other information may be included in the harvest information regarding quality.

Next, in step S203, the server 30 determines a feature quantity correlated with at least one of the harvest amount and the quality of the harvested product for each field 60 based on a plurality of environmental information and harvest information over a predetermined period. .

FIG. 7 shows a graph 301 representing an example of the relationship between the monthly average value of the maximum CO ₂ concentration in all days and the yield of the target crop. In the graph 301, the horizontal axis is the “maximum daily CO ₂ concentration (average)”, which is the monthly average of the maximum CO ₂ concentration in all days, and the vertical axis is the “return yield”.

Graph 301 plots data from multiple fields over multiple years. It can be seen from the graph 301 that the yield is positively correlated with the daily maximum CO ₂ concentration (average).

Here, if the daily maximum CO ₂ concentration (average) is _xi , the yield is _yi , and the average values of _xi and _yi are X and Y, the correlation coefficient _Rxy is given by the following equation (4): Desired. Note that n is the number of data on the daily maximum CO ₂ concentration (average).

Moreover, the regression line y is calculated|required by the following formulas (5) by the least-squares method.

In this case, a and b are represented by the following formulas (6) and (7), respectively.

From the regression line shown in FIG. 7, it can be seen that the value of the daily maximum CO ₂ concentration (average) must be greater than or equal to Cave in order to obtain a predetermined surface yield Yth.

Moreover, the standard deviation S _e of the yield is represented by the following equation (8).

In step S203, the determining unit 32 of the server 30 calculates a regression line indicating a positive or negative correlation between the harvest information and the environmental information, and calculates the absolute value of the correlation coefficient R _xy related to the calculated regression line. is equal to or greater than a predetermined threshold value, it is determined that there is a specific correlation between the harvest information and the environmental information.

Next, in step S<b>204 , the terminal device 20 outputs feature amounts for each field 60 .

As described above, the correlation coefficient between the daily maximum CO ₂ concentration (average) and the yield can be calculated. Similarly, the results of calculating the maximum value and average value of CO ₂ concentration for all days and daytime for a plurality of months will be described.

FIG. 8 shows a table 401 representing an example of the relationship between the CO ₂ concentration in each month and the correlation coefficient for the yield. The count number is the number of times the measured value exceeds or falls below a predetermined threshold.

In FIG. 8, environment information with a correlation coefficient equal to or greater than a predetermined first threshold is indicated by a dark shaded portion 4011, and environment information with a correlation coefficient smaller than the first threshold but equal to or greater than a predetermined second threshold is displayed. Information is indicated by light shaded area 4012 . From the example shown in FIG. 8, it can be seen that the highest CO ₂ concentration in all days contributes to the yield. From this result, the manager of the farm field 60 can recognize that it is important to manage the CO ₂ concentration over a predetermined period (for example, from November to February). Further, from the regression line shown in FIG. 7, it is possible to calculate the value of the CO ₂ concentration that should be set in order to obtain a predetermined yield.

Next, the correlation between the harvest information and the environmental information will be described when attention is focused on saturation as the environmental information. FIG. 9 shows a graph 302 representing an example of the relationship between the highest value of saturation in the daytime and the yield of the target crop. In the graph 302, the horizontal axis is the "daily maximum saturation difference (daytime)", which is the monthly maximum value of the saturation difference in the daytime, and the vertical axis is the "recovery".

Graph 302 plots data for multiple fields over multiple years. From the graph 302, it can be seen that the yield has a negative correlation with the daily maximum saturation (daytime). Also, from the graph 302, it can be seen that the daily maximum saturation difference (daytime) should be set to a predetermined value Smax or less in order to obtain a predetermined yield Yth.

FIG. 10 shows a table 402 representing an example of the relationship between the saturation in each month and the correlation coefficient with respect to the yield. A difference percentile is a value that indicates the rate of change over time when a change is made by a given amount in a given period of time. In general, for example, rapid temperature changes are considered undesirable because they stress crops.

In FIG. 10, the environment information whose correlation coefficient is greater than or equal to the predetermined first threshold is indicated by a dark shaded portion 4021, and the environment information whose correlation coefficient is less than the first threshold but greater than or equal to the predetermined second threshold. Information is indicated by light shaded area 4022 . From the example shown in FIG. 10, it can be seen that the saturation difference value in November contributes to the yield. From this result, the manager of the farm field 60 can recognize that the management of the saturation gap is important in November. Further, the saturation difference value to be set to obtain a predetermined yield can be calculated from the regression line shown in FIG.

Next, the correlation between the harvest information and the environmental information when focusing on the relative humidity as the environmental information will be described. FIG. 11 shows a table 403 representing an example of the relationship between the relative humidity in each month and the correlation coefficient with respect to the yield.

In FIG. 11, the environment information whose correlation coefficient is equal to or greater than the predetermined first threshold is indicated by a dark shaded portion 4031, and the environment information whose correlation coefficient is less than the first threshold but equal to or greater than the predetermined second threshold is Information is indicated by light shaded area 4032 . From the example shown in FIG. 11, it can be seen that the lowest values of relative humidity in November and December contribute to the yield. From this result, the manager of the farm field 60 can recognize that it is important to manage the minimum value of relative humidity in November and December.

Next, the correlation between the harvest information and the environmental information will be described when attention is paid to the temperature as the environmental information. FIG. 12 shows a table 404 showing an example of the relationship between the temperature in each month and the correlation coefficient with respect to the yield.

In FIG. 12, the environment information whose correlation coefficient is greater than or equal to the predetermined first threshold is indicated by a dark shaded portion 4041, and the environment information whose correlation coefficient is less than the first threshold but is greater than or equal to the predetermined second threshold. Information is indicated by light shaded area 4042 . From the example shown in FIG. 12, it can be seen that the highest and average temperatures in November contribute to the yield. From this result, the manager of the farm field 60 can recognize that it is important to manage the maximum and average temperatures in November.

Next, a description will be given of the effects of changes in environmental information over a predetermined period on harvest information such as yield and quality of harvested products. FIG. 13 shows a table 405 showing an example of the relationship between standard deviations of CO ₂ concentration, saturation, relative humidity, and temperature in each month and correlation coefficients with respect to yield. Here, the standard deviation is an index that indicates variations in environmental information within a given month.

In FIG. 13, the environment information whose correlation coefficient is equal to or greater than the predetermined first threshold is indicated by a dark shaded portion 4051, and the environment information whose correlation coefficient is less than the first threshold but equal to or greater than the predetermined second threshold. Information is indicated by light shaded area 4052 . From the example shown in FIG. 13, the highest and average values of the standard deviation of saturation, the highest standard deviation of temperature, and the highest standard deviation of CO ₂ concentration in December contributed to the yield. It is understood that From this result, the manager of the farm field 60 can recognize that it is important to manage changes in saturation and temperature in November and changes in CO ₂ concentration in December.

As described above, it can be seen that multiple pieces of environmental information contribute to yield. However, if there is too much environmental information to be managed, there is a risk that the most important environment will be insufficiently managed. Therefore, it is preferable to display the maximum value of the correlation coefficients in the plurality of environmental information for each measurement item. FIG. 14 shows a table 406 showing an example of the relationship between the CO ₂ concentration, saturation, relative humidity, and temperature in each month and the maximum value of the correlation coefficient for yield.

In FIG. 14, the environment information whose correlation coefficient is greater than or equal to the predetermined first threshold is indicated by a dark shaded portion 4061, and the environment information whose correlation coefficient is less than the first threshold but is greater than or equal to the predetermined second threshold. Information is indicated by light shaded area 4062 . From the example shown in FIG. 14, among the four types of environmental information, the CO ₂ concentration greatly contributes to the yield from December to February, followed by the saturation difference from November to February. is found to contribute significantly to From this result, the manager of the farm field 60 can recognize that the management of the CO ₂ concentration is most important from December to February, and the next most important is the management of the saturation difference from November to February. can.

As described above, according to the feature amount determination system according to the embodiment of the present disclosure, the environmental information from the sensor installed in the field and the data of the results such as the yield and quality of the agricultural products are used to determine the target results identify environmental factors that contribute to

In the above explanation, an example was explained in which the yield of agricultural products was used as the index related to results. Furthermore, even in the case where the index related to results is an index that comprehensively evaluates the yield and quality of agricultural products, the feature amount determination system according to the embodiment of the present disclosure can be applied.

10 sensor terminal 11 sensor unit 12 sensor terminal transmission unit 13 GPS unit 14 sensor connection unit 15 sensor terminal control unit 16 sensor terminal storage unit 20 terminal device 21 input unit 22 communication unit 23 output unit 24 terminal control unit 25 terminal storage unit 30 server 31 Receiving Unit 32 Determination Unit 33 Transmission Unit 34 Server Control Unit 35 Server Storage Unit 40 Relay Device 50 Communication Network 60 Field 100 Feature Determining System

Claims (7)

A feature amount determination system in which a sensor terminal, a server, and a terminal device are communicably connected,
The sensor terminal is
a sensor that measures a plurality of environmental information about the installed field;
a sensor terminal transmission unit that transmits field information about the field and the plurality of environmental information;
The terminal device
an input unit for inputting harvest information regarding the harvest amount and the quality of harvested products for each field;
a communication unit that receives the feature amount for each field;
an output unit capable of outputting the feature amount for each field,
The server is
a receiving unit that receives the field information, the plurality of environmental information, and the harvest information;
a determination unit that determines the feature amount correlated with at least one of the harvest amount and the quality of the harvested product for each field based on the plurality of environmental information and the harvest information over a predetermined period;
A transmitting unit that transmits the feature amount for each field,
A feature quantity determination system characterized by: The determination unit calculates a correlation coefficient between at least one of the harvest amount and the quality of the harvested product for each of the plurality of pieces of environmental information, and uses the environmental information having the correlation coefficient higher than a predetermined threshold value as a feature amount. 2. The feature quantity determination system of claim 1, which determines. 3. The determination unit defines a predetermined period of time as a predetermined number of months, a predetermined number of days, or a predetermined time period, and calculates the correlation coefficient based on the value of the environmental information for each predetermined period. The feature quantity determination system according to . The determination unit determines, during the predetermined period, the highest value, the lowest value, the average value, the number of counts based on a predetermined threshold value, the percentile difference, or the standard deviation of the environmental information measured by the sensor terminal. 4. The feature quantity determination system according to claim 3, wherein said correlation coefficient is calculated as an information value. The feature quantity determination system according to any one of claims 1 to 4, wherein the plurality of environmental information are temperature, relative humidity, saturation difference, or CO2 concentration. A feature amount determination method in a system in which a sensor terminal, a server, and a terminal device are communicably connected,
The sensor terminal measures a plurality of environmental information related to the installed field,
The terminal device inputs harvest information regarding the harvest amount and the quality of the harvest for each field,
The server determines a feature quantity correlated with at least one of the yield and the quality of the harvested product for each field based on the plurality of environmental information and the harvested information over a predetermined period of time;
The terminal device outputs the feature amount for each field,
A feature amount determination method characterized by: A server communicably connected to a sensor terminal and a terminal device,
a receiving unit that receives from the sensor terminal field information about the field where the sensor is installed and a plurality of environmental information, and receives harvest information about the harvest amount and the quality of the harvest for each field from the terminal device;
a determination unit that determines a feature value correlated with at least one of the harvest amount and the quality of the harvested product for each field based on the plurality of environmental information and the harvest information over a predetermined period;
A transmitting unit that transmits the feature amount for each field,
A server characterized by:

Images