Harvesting support system, processor, and computer program

Abstract

To provide a technique of predicting when to harvest fruits.SOLUTION: A harvesting support system 1 of the present disclosure includes: a first measurement device 2 for measuring the quality of fruits grown in a farm F; and a management server 8. The management server 8 has a processing unit 32 for executing processing of acquiring a plurality of different types of quality values on the basis of output of the first measurement device 2, acquiring plural pieces of time-series data of the different types of quality values stored in time sequence, and determining a prediction period of time as a time predicted to be the right time to harvest fruits, on the basis of the plural pieces of time-series data.SELECTED DRAWING: Figure 5

Description

Technical Field

[0001] The present disclosure relates to a harvesting support system, a processing device, and a computer program.

Background Art

[0002] Patent Document 1 discloses a measuring device that irradiates an object to be measured, such as a fruit, with light and obtains quality values such as the sugar content and acidity of the object to be measured by spectroanalyzing the transmitted light.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] According to the above measuring device, the current quality of the fruit can be grasped, but the future quality state cannot be grasped. Therefore, it is possible to determine whether the current state of the fruit is suitable for harvesting. However, when the current state of the fruit has not yet reached a state suitable for harvesting, it is not possible to predict the appropriate harvesting period, such as how long it will take for the state of the fruit to reach a state suitable for harvesting.

Means for Solving the Problems

[0005] The harvesting support system according to the present disclosure includes a measuring device that measures the quality of fruits cultivated in a field, and a processing device. The processing device includes a processing unit that executes a first process of acquiring a plurality of types of quality values based on the output of the measuring device, a second process of acquiring a plurality of time-series data in which each of the plurality of types of quality values is accumulated in time series, and a third process of obtaining a predicted period predicted to be the appropriate harvesting period of the fruit based on the plurality of time-series data.

Effects of the Invention

[0006] According to the present disclosure, it is possible to predict the appropriate harvesting time of fruits.

Brief Description of the Drawings

[0007]

Figure 1

Figure 2

Figure 3

Figure 4A

Figure 4B

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Figure 19

DETAILED DESCRIPTION OF THE INVENTION

[0008] First, the content of the embodiment will be listed and described. [Summary of the Embodiment]

[0009] (1) The harvest support system according to the present disclosure includes a measuring device that measures the quality of fruits cultivated in a field, and a processing device. The processing device performs a first process of acquiring a plurality of types of quality values based on the output of the measuring device, a second process of acquiring a plurality of time-series data obtained by accumulating each of the plurality of types of quality values in time series, and a third process of obtaining a predicted period predicted to be the appropriate harvest time of the fruits based on the plurality of time-series data. The processing device includes a processing unit that executes the processes.

[0010] According to the above configuration, it is possible to predict a plurality of types of quality values using a plurality of time-series data, and based on the predicted plurality of types of quality values, it is possible to obtain a predicted period predicted to be the appropriate harvest time. As a result, the predicted period can be output as a prediction result of the appropriate harvest time of the fruits.

[0011] (2) In the harvest support system of (1) above, the third process preferably includes a process of obtaining predicted quality values of each of the plurality of types of quality values based on the plurality of time-series data, a process of obtaining environmental prediction information indicating environmental prediction in the field, and a process of obtaining the predicted period based on the environmental prediction information and the plurality of predicted quality values. In this case, in addition to the predicted quality value of the fruit, the predicted period can be obtained by taking into account the environmental prediction information of the field.

[0012] (3) Further, in the harvesting support system of the above (2), when the environmental prediction information includes a predicted value indicating a predicted environmental state, the process of obtaining the predicted period includes obtaining a first period in which the plurality of predicted quality values satisfy a predetermined condition, and obtaining a second period determined to be a harvestable environmental state based on a comparison result between the predicted value and a predetermined threshold value, and a process of obtaining the predicted period based on the first period and the second period. It is preferable to include. In this case, the predicted period can be appropriately obtained based on the relationship between the appropriate period in the quality value and the appropriate period in the environment.

[0013] (4) Further, in the harvesting support system of the above (3), the process of obtaining the predicted period based on the first period and the second period preferably includes a process of setting the overlapping period in which the first period and the second period overlap as the predicted period. In this case, an appropriate period in the environment and the quality value can be set as the predicted period.

[0014] (5) Immediately after the period that is not the second period, the state of the field may not be good due to rainfall or the like. In this regard, in the harvesting support system of the above (4), the process of obtaining the predicted period based on the first period and the second period further includes a process of providing at least a one-day interval between the period that is not the second period and the predicted period when there is a period that is not the second period immediately before the overlapping period. Thereby, the predicted period can be obtained while avoiding the timing when the state of the field is not good.

[0015] (6) In any one of the harvesting support systems of the above (2) to (5), the environmental prediction information may include at least one of weather information and disease risk information regarding the disease of the fruit.

[0016] (7) Further, in the harvesting support system of (4) above, the process of obtaining the prediction period based on the first period and the second period may include a process of setting, as the prediction period, the day in the second period that is closest to the first period when there is no overlapping period between the first period and the second period. In this case, the prediction period can be set at a timing when a plurality of prediction quality values are close to a predetermined condition within the second period.

[0017] (8) Further, in the harvesting support system of (4) above, the process of obtaining the prediction period may further include a process of outputting the plurality of prediction quality values to the outside when the first period does not exist. In this case, a plurality of prediction quality values can be provided to the operator as information necessary for determining the prediction period.

[0018] (9) Further, in any one of the harvesting support systems of (1) to (8) above, the measuring device includes a first measuring unit that measures the quality of the fruit and a second measuring unit that measures the quality of the fruit with a configuration different from that of the first measuring unit, and the first process may include a process of obtaining the plurality of types of quality values when the quality of the fruit is measured by the first measuring unit based on scaling data indicating a correlation between the output of the first measuring unit and a plurality of reference quality values based on the output of the second measuring unit. In this case, if the measurement accuracy of the second measuring unit is higher than that of the first measuring unit, the output of the first measuring unit can be corrected to correspond to the quality value of the second measuring unit having a higher measurement accuracy than the first measuring unit, and the quality measurement accuracy can be easily increased.

[0019] (10) In the harvesting support system of (1) or (9) above, the fruit preferably includes grapes. For determining the appropriate harvesting time of grapes, a plurality of quality values are considered. Therefore, this embodiment can be suitably used for determining the appropriate harvesting time of grapes.

[0020] (11) Further, in the harvesting support system according to the above (1) or (10), it is preferable that the plurality of types of quality values include at least any two of the sugar content, acidity, pH, and polyphenol content.

[0021] (12) From another perspective, the present disclosure is a processing device that performs processing to support the harvesting of fruits cultivated in a field. This processing device includes a process of acquiring a plurality of types of quality values based on the output of a measuring device that measures the quality of fruits cultivated in the field, a process of acquiring a plurality of time-series data obtained by accumulating each of the plurality of types of quality values in time series, and a process of obtaining a predicted period predicted to be the appropriate harvesting time of the fruits based on the plurality of time-series data.

[0022] (13) From another perspective, the present disclosure is a computer program for causing a computer to execute processing to support the harvesting of fruits cultivated in a field. This computer program causes the computer to perform a step of acquiring a plurality of types of quality values based on the output of a measuring device that measures the quality of the fruits, a step of acquiring a plurality of time-series data obtained by accumulating each of the plurality of types of quality values in time series, and a step of obtaining a predicted period predicted to be the appropriate harvesting time of the fruits based on the plurality of time-series data.

[0023] [Details of Embodiment] Hereinafter, preferred embodiments will be described with reference to the drawings. Note that at least a part of each of the embodiments described below may be arbitrarily combined.

[0024] [Regarding the Overall Configuration of the Harvesting Support System] FIG. 1 is a diagram showing an example of the overall configuration of a harvesting support system according to an embodiment. In FIG. 1, the harvesting support system 1 has a function of measuring the quality values of fruits of fruit trees cultivated in the field F. Further, the harvesting support system 1 has a function of obtaining a predicted period predicted to be the appropriate harvesting time of the fruits. The field F of this embodiment is, for example, a vineyard for cultivating grapes that are the raw material for wine. Therefore, a plurality of trees T are cultivated in the field F. The plurality of trees T are fruit trees and are grape trees. The plurality of trees T are cultivated in a plurality of rows. The harvest support system 1 has a function of measuring the quality value of the grape fruits that grow on the tree T. More specifically, the harvest support system 1 obtains the quality value of the fruit by analysis using near-infrared light. The quality value of the fruit is a value based on various components representing the quality of the fruit. The quality value includes the sugar content, acidity, pH, polyphenols, etc.

[0025] The harvest support system 1 includes a measuring device 5, an agricultural machine 6, a management server 8, a management terminal 10, and a weather information server 7. The measuring device 5 includes a first measuring device 2 (first measuring unit) and a second measuring device 4 (second measuring unit). The first measuring device 2 and the second measuring device 4 are mounted on the agricultural machine 6. The first measuring device 2 and the second measuring device 4 are devices for measuring the quality of the fruit. The first measuring device 2 and the second measuring device 4 have a function of acquiring spectral information in the near-infrared region included in the reflected light and transmitted light of the fruit. The spectral information in the near-infrared region includes information indicating the quality value of the fruit. Therefore, the first measuring device 2 and the second measuring device 4 output the spectral information in the near-infrared region as the quality measurement result. The first measuring device 2 and the second measuring device 4 will be described in detail later. The harvest support system 1 further includes a manipulator 12. The manipulator 12 has a function of moving the second measuring head 26 (described later) that the second measuring device 4 has.

[0026] The agricultural machine 6, the management server 8, and the management terminal 10 are connected to be communicable with each other via a public network NW such as the Internet. The agricultural machine 6 has, for example, a communication function by a mobile communication system. The agricultural machine 6 is connected to the public network NW via a radio base station BS of the mobile communication system.

[0027] The management server 8 has a function of performing a process of obtaining a quality value of fruits based on the outputs of the first measuring device 2 and the second measuring device 4. The management terminal 10 is a terminal operated by the operator 14 of the harvesting support system 1. The management terminal 10 has a function of receiving an operation on the harvesting support system 1 by the operator 14, and also has a function of outputting the quality value and the like obtained by the management server 8 to the operator 14. The weather information server 7 collects and stores weather information issued from the Japan Meteorological Agency or the like. The weather information includes weather prediction information. The weather prediction information includes sunny / rainy prediction, predicted precipitation amount, predicted temperature, and predicted humidity for a period of about one week to ten days. The weather information server 7 provides necessary information to the management server 8 and the management terminal 10 in response to requests from the management server 8 and the management terminal 10.

[0028] The agricultural machine 6 is, for example, a tractor. The agricultural machine 6 can travel within the field F. The agricultural machine 6 can travel between rows of a plurality of trees T in the field F and can approach all the trees T in the field F. The agricultural machine 6 can also travel through the field F by manual driving by an operator's operation, or can travel within the field F by automatic driving based on a control command from the management server 8 or a control command from the management terminal 10 based on an input from the operator 14.

[0029] FIG. 2 is a block diagram showing the in-vehicle network of the agricultural machine 6. The agricultural machine 6 has an in-vehicle network 6a compliant with a communication standard such as CAN (Controller Area Network). The in-vehicle network 6a includes a control device 18, an input / output device 19, and a communication device 20.

[0030] The communication device 20 has a function as a mobile terminal in a mobile communication system. Therefore, the communication device 20 performs wireless communication with the radio base station BS. The control device 18 is an ECU (Electronic Control Unit) that controls the traveling system and the working system of the agricultural machine 6. Based on the operator's driving operation, the control device 18 controls each part of the agricultural machine 6. The control device 18 is connected to the public network NW via the communication device 20. Therefore, the control device 18 is communicably connected to the management server 8 and the management terminal 10. The control device 18 exchanges necessary information with the management server 8 and the management terminal 10 via the public network NW. When the agricultural machine 6 is capable of autonomous driving, the control device 18 controls cameras, sensors, the drive system, and the steering system around the agricultural machine 6 based on control commands and the like from the management server 8 and the management terminal 10, and performs processes for executing autonomous driving. The input / output device 19 has a function of receiving the operator's operation and a function of outputting information and the like to the operator.

[0031] In addition, the in-vehicle network 6a is connected to the first measurement device 2, the second measurement device 4, and the manipulator 12. The first measurement device 2, the second measurement device 4, and the manipulator 12 are connected to the public network NW by the communication device 20. Therefore, the first measurement device 2, the second measurement device 4, and the manipulator 12 are communicably connected to the management server 8 and the management terminal 10. Thereby, the first measurement device 2, the second measurement device 4, and the manipulator 12 can provide necessary information to the management server 8 and the management terminal 10. In addition, the first measurement device 2, the second measurement device 4, and the manipulator 12 can be controlled by the management server 8 and the management terminal 10.

[0032] 〔Regarding the first measurement device 2 and the second measurement device 4〕 FIG. 3 is a block diagram showing an example of the first measurement device 2. As described above, the first measurement device 2 is a device that measures the quality of fruits and outputs spectral information in the near-infrared region as a measurement result of the quality. The first measurement device 2 receives the reflected light from the fruit and outputs spectral information obtained by spectroscopically analyzing the received reflected light. Note that the spectral information refers to information indicating the relationship between the wavelength and the light intensity in the near-infrared region.

[0033] As shown in FIG. 3, the first measurement device 2 includes a first measurement head 22 and a first control unit 24. The first measurement head 22 includes, for example, a hyperspectral camera. The hyperspectral camera is a spectroscopic camera having a plurality of detection wavelength bands capable of detecting the intensity of light. The first measurement head 22 (hyperspectral camera) has a plurality of detection wavelength bands in the near-infrared region. The first measurement head 22 images a predetermined imaging region to acquire a two-dimensional image. That is, the first measurement head 22 receives the reflected light when the object existing in the imaging region is irradiated with sunlight and acquires a two-dimensional image. The pixels constituting this two-dimensional image have information indicating the light intensity of a plurality of detection wavelength bands as luminance. Therefore, the image acquired by the first measurement head 22 has spectral information in the near-infrared region for each pixel. Hereinafter, the image acquired by the first measurement head 22 is also referred to as a spectral image. In this way, the first measurement head 22 can acquire spectral information in the near-infrared region in units of the imaging region.

[0034] The first measurement head 22 is used to image the grape fruit K which is the object to be measured. The first measurement head 22 is a camera capable of imaging a two-dimensional image. Therefore, when imaging the fruit K with the first measurement head 22, a predetermined first interval D1 is provided between the first measurement head 22 and the grape fruit K. In the present embodiment, the grape fruit K refers to a cluster including a plurality of fruit grains k1. The imaging region A of the first measurement head 22 when the first interval D1 is provided has a size capable of imaging a plurality of fruits K scattered on the branches and leaves of one tree T. Therefore, the spectral image imaged by the first measurement head 22 includes a plurality of fruits K. The first measurement head 22 outputs a spectral image in which a plurality of fruits K are imaged. That is, the first measurement head 22 receives the reflected light from the plurality of fruits K and outputs a spectral image.

[0035] The first measurement head 22 provides the captured spectral image to the first control unit 24. The first control unit 24 is connected to the communication device 20 of the agricultural machine 6. The first control unit 24 has a function of controlling the first measurement head 22 based on control commands and the like given from the management server 8 or the management terminal 10. Further, the first control unit 24 has an input unit (not shown) for receiving operation inputs, and also has a function of controlling the first measurement head 22 based on the operation inputs of the operator. In addition, the first control unit 24 transmits the spectral image provided from the first measurement head 22 to the management server 8. That is, the spectral image acquired by the first measurement head 22 is provided to the management server 8 as the output (measurement result) of the first measurement device 2.

[0036] FIG. 4A is a block diagram showing an example of the second measurement device 4. As described above, the second measurement device 4 is a device that measures the quality of the fruit K, and outputs spectral information in the near-infrared region as a quality measurement result. The second measurement device 4 irradiates the fruit K with light, receives the transmitted light that has passed through the fruit K, and outputs spectral information obtained by spectro-analyzing the transmitted light.

[0037] As shown in FIG. 4A, the second measurement device 4 includes a second measurement head 26, a light source 27, a spectroscope 28, and a second control unit 30. The second measurement head 26 has a light projecting unit 26a and a light receiving unit 26b. The light projecting unit 26a and the light source 27 are connected by an optical fiber. The light source 27 is, for example, a halogen lamp. The light from the light source 27 is guided through the optical fiber to the light projecting unit 26a of the second measurement head 26. The light projecting unit 26a irradiates the fruit K, which is the object to be measured, with the light from the light source 27.

[0038] The light receiving unit 26b receives the transmitted light that has passed through the fruit K. The transmitted light received by the light receiving unit 26b is generated when the light from the light projecting unit 26a irradiates the fruit K. The light receiving unit 26b and the spectroscope 28 are connected by an optical fiber. The transmitted light received by the light receiving unit 26b is guided to the spectroscope 28 through the optical fiber.

[0039] Figure 4B is a cross-sectional view of the second measurement head 26. As shown in Figure 4B, the second measurement head 26 has a head body 26c. The head body 26c is an annular member formed of resin or the like. The head body 26c is fixed to the tip of the manipulator 12. Therefore, the second measurement head 26 is movable by the manipulator 12.

[0040] The light projecting unit 26a is provided on the annular tip surface 26c1 of the head body 26c. The light projecting unit 26a is annular. The light from the light source 27 is scattered inside when applied to the light projecting unit 26a and is uniformly irradiated from the light projecting unit 26a. The light from the light projecting unit 26a irradiates the fruit grains k1 of the fruit K, and transmitted light that has passed through the fruit grains k1 and reflected light reflected from the surface of the fruit grains k1 are generated. The light receiving unit 26b is provided in the hole portion 26c2 of the head body 26c. The light receiving unit 26b receives the transmitted light that has passed through the hole portion 26c2. Note that the light receiving unit 26b mainly receives transmitted light but also receives reflected light.

[0041] In the measurement of the fruit K by the second measurement device 4, since it is necessary to irradiate the fruit grains k1 of the fruit K with light by the light projecting unit 26a, it is necessary to bring the second measurement head 26 close to the fruit grains k1 of the fruit K. When measuring the fruit K by the second measurement device 4, the second measurement head 26 is arranged at the measurement position as shown in Figure 4B. The measurement position shown in Figure 4B refers to the position where the distance between the second measurement head 26 and the fruit grains k1 is the second interval D2. The second interval D2 is shorter than the first interval D1 (see Figure 3).

[0042] The second measurement head 26 is arranged at the measurement position by the manipulator 12. In this way, the manipulator 12 functions as a moving mechanism that moves the second measurement head 26 to the measurement position.

[0043] When the second measurement head 26 is arranged at the measurement position in proximity to the fruit grain k1, the fruit grain k1 is irradiated with light from the light projecting unit 26a. The light irradiated on the fruit grain k1 passes through the fruit grain k1 as shown by the arrow in FIG. 4B, and transmitted light is generated. The transmitted light passes through the hole portion 26c2 and is received by the light receiving unit 26b.

[0044] In FIG. 4A, the spectroscope 28 has a function of splitting the transmitted light and a light receiving function of converting the split spectrum into a signal. When the transmitted light received by the light receiving unit 26b is given, the spectroscope 28 outputs spectrum information obtained by splitting the transmitted light. The spectrum information output by the spectroscope 28 is given to the second control unit 30.

[0045] The second control unit 30 is connected to the communication device 20 of the agricultural machine 6. The second control unit 30 has a function of controlling the light source 27 and the spectroscope 28 based on control commands and the like given from the management server 8 or the management terminal 10. Further, the second control unit 30 has an input unit (not shown) for receiving an operation input, and also has a function of controlling the light source 27 and the spectroscope 28 based on the operation input of the operator.

[0046] Also, the second control unit 30 transmits the spectrum information given from the spectroscope 28 to the management server 8. That is, the spectrum information acquired by the spectroscope 28 is given to the management server 8 as the output (measurement result) of the second measuring device 4.

[0047] In this way, the configuration of the first measuring device 2 and the configuration of the second measuring device 4 are different in terms of the presence or absence of a spectral camera, the presence or absence of a light source, etc. Further, in the first measuring device 2, the quality of a plurality of fruits K is measured collectively, while in the second measuring device 4, the quality of one fruit grain k1 is measured. Here, the measurement accuracy as the quality value indicated by the spectral information output by the second measurement device 4 is higher than the measurement accuracy as the quality value indicated by the spectral image (spectral information) output by the first measurement device 2. In the measurement by the second measurement device 4, since the second measurement head 26 is brought close to the fruit grain k1 and spectral information is acquired from the transmitted light when irradiated with light, it is less affected by the surrounding environment. On the other hand, in the measurement by the first measurement device 2, since spectral information is acquired from the reflected light of the fruit K, it is easily affected by the surrounding environment. As a result, the measurement accuracy of the second measurement device 4 is higher than that of the first measurement device 2.

[0048] In the present embodiment, the case where the first measurement device 2 and the second measurement device 4 are mounted on the agricultural machine 6 is shown, but it is not limited thereto. The first measurement device 2 and the second measurement device 4 may be carried by an operator or may be mounted on a cart or the like. Also, only the first measurement device 2 may be mounted on the agricultural machine 6, and the second measurement device 4 may be arranged at a predetermined position. In this case, the observation by the first measurement device 2 is performed while traveling, and the observation by the second measurement device 4 is performed at a fixed point.

[0049] 〔Regarding the management server 8〕 FIG. 5 is a block diagram showing a configuration example of the management server 8. As shown in FIG. 5, the management server 8 (processing device) is a type of information processing device having a processing unit 32, a storage unit 34, and a communication device 36. The communication device 36 is a communication interface capable of communicating with an external device via the public network NW. The processing unit 32 is, for example, various processors suitable for computer control such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a DSP (Digital Signal Processor), an FPGA (Field Programmable Gate Array), etc.

[0050] The storage unit 34 is, for example, a flash memory, a hard disk, a ROM (Read Only Memory), a RAM (Random Access Memory), or the like. The storage unit 34 stores a computer program for causing the processing unit 32 to execute and necessary information. The processing unit 32 realizes various processing functions that the processing unit 32 has by executing a computer program stored in a computer-readable non-transitory recording medium such as the storage unit 34.

[0051] Further, the storage unit 34 stores a plurality of first calibration curve data C1, a plurality of second calibration curve data C2, a plurality of scaling data S, and a quality value database 40. The plurality of first calibration curve data C1 are data for obtaining a quality value (first quality value) based on the output of the first measuring device 2. The plurality of second calibration curve data C2 are data for obtaining a quality value (second quality value) based on the output of the second measuring device 4. The plurality of scaling data S are data indicating the correlation between the first quality value and the second quality value (reference quality value). The plurality of scaling data S are generated in the quality value acquisition process 32a executed by the processing unit 32. The quality value database 40 is a database for registering and accumulating the measured quality values obtained by the quality value acquisition process 32a executed by the processing unit 32.

[0052] The processing unit 32 has a function of executing a quality value acquisition process 32a and a prediction process 32b. The quality value acquisition process 32a (first process) is a process for obtaining the measured quality value of the target fruit KT based on the scaling data S, the first quality value of the target fruit KT, and the like. The target fruit KT is the fruit for which the measured quality value is to be obtained among the fruits K. Further, the measured quality value is the quality value obtained by the quality value acquisition process 32a, which corrects the first quality value of the target fruit KT obtained based on the output of the first measuring device 2 and has a higher accuracy than the first quality value. The processing unit 32 obtains a plurality of types of measurement quality values based on the outputs of the measuring devices 5 (the first measuring device 2 and the second measuring device 4). The plurality of types of quality values include sugar content, acidity, pH, polyphenol content, and the like.

[0053] Further, the prediction process 32b includes a process (second process) of acquiring a plurality of time-series data obtained by accumulating the plurality of measurement quality values obtained by the quality value acquisition process 32a in time series, and a process (third process) of obtaining a prediction period predicted to be the appropriate harvest time of the fruit based on the plurality of time-series data. These processes will be described in detail later.

[0054] 〔Regarding the quality measurement work of the fruit K in the field F〕 FIG. 6 is a flowchart showing an example of the quality measurement work of the fruit K in the field F. As shown in FIG. 6, in the quality measurement work of the fruit K, first, quality measurement is performed by the first measuring device 2 and the second measuring device 4 (step S1 in FIG. 6).

[0055] FIG. 7 is a plan view of the field F. In FIG. 7, two mutually perpendicular directions are defined as the X direction and the Y direction. As shown in FIG. 7, one direction in the X direction is the X1 direction, and the opposite direction of the X1 direction is the X2 direction. One direction in the Y direction is the Y1 direction, and the opposite direction of the Y1 direction is the Y2 direction. The quality measurement of the measuring devices 2 and 4 is performed by running the agricultural machine 6 in the field F. In the field F shown in FIG. 7, for example, a plurality of trees T (15 in the illustration) are cultivated. The trees T are arranged in 5 rows in the Y direction and 3 rows in the X direction. When the Y direction is the column direction, the trees T are arranged in 3 columns. One column is composed of 5 trees T. Each of the 15 trees T cultivated in the field F is given an ID as identification information. The integers from 1 to 15 are given as the ID to the 15 trees T. The quality measurement work of the fruit K in the field F is performed for all 15 trees T in the field F. Of the 15 trees T, the hatched trees T (trees T with IDs 2, 4, 8, 12, and 14) are the trees T for which the quality of the fruit K is measured by both the first measuring device 2 and the second measuring device 4. The other trees T are the trees T for which the quality of the fruit K is measured only by the first measuring device 2. That is, the first measuring device 2 measures the quality of the fruit K for all the trees T, and the second measuring device 4 measures the quality of the fruit K for some of the trees T in the field F.

[0056] The quality measurement by the first measuring device 2 and the second measuring device 4 in step S1 may be performed by the operation of an operator driving the agricultural machine 6, or may be performed by remote control based on an instruction from the operator 14. When the quality measurement is performed by the operator, the agricultural machine 6 travels by the manual driving of the operator, and further, the first measuring device 2 and the second measuring device 4 perform the quality measurement by the manual operation of the operator. When the quality measurement is performed by remote control based on an instruction from the operator 14, the agricultural machine 6 travels by automatic driving, and the first measuring device 2 and the second measuring device 4 perform the quality measurement by control based on an instruction from the operator 14. In this embodiment, the case where the operator driving the agricultural machine 6 performs the quality measurement will be described.

[0057] The operator boards the agricultural machine 6 and travels along the dashed line in FIG. 7 along the side of a row of a plurality of trees T in the field F. Thus, the agricultural machine 6 approaches each tree T in order from the tree T with ID = 1. When the operator reaches the side of each tree T, the operator stops the agricultural machine 6 and performs the quality measurement by the first measuring device 2 and the second measuring device 4. For example, when the operator parks the agricultural machine 6 on the side (the X1 direction side) of the tree T with ID = 1 as shown in FIG. 7, the operator operates the first measuring device 2 and images a plurality of fruits K of the tree T with ID = 1 included in the imaging area. As a result, the first measuring device 2 outputs a spectral image of the plurality of fruits K of the tree T with ID = 1 and provides it to the management server 8. At this time, the first measuring device 2 adds the ID of the tree T to the output spectral image and transmits it. The first measuring device 2 adds the ID of the tree T to the spectral image according to the operator's operation input. When the output (spectral image) of the first measuring device 2 is provided to the management server 8, the quality measurement of the fruit K on the tree T with ID = 1 is completed.

[0058] After finishing the quality measurement of the fruit K on the tree T with ID = 1, the operator moves the agricultural machine 6 in the Y2 direction and parks the agricultural machine 6 on the side (the X1 direction side) of the tree T with ID = 2. Here, the tree T with ID = 2 is the tree T for which the quality measurement of the fruit K is performed by both the first measuring device 2 and the second measuring device 4. Therefore, the operator operates the first measuring device 2 and images a plurality of fruits K on the tree T with ID = 2 included in the imaging area. As a result, the first measuring device 2 outputs a spectral image of the plurality of fruits K of the tree T with ID = 2 and provides the spectral image with the ID of the tree T added to the management server 8.

[0059] Furthermore, the operator operates the second measuring device 4 to perform a quality measurement. The operator uses the manipulator 12 to bring the second measuring head 26 of the second measuring device 4 close to the tree T. The operator brings the second measuring head 26 close to one fruit K imaged by the first measuring device 2 among the plurality of fruits K of the tree T. The operator operates the second measuring device 4 to cause the second measuring device 4 to receive transmitted light from the fruit K. As a result, the second measuring device 4 outputs spectral information of the fruit K of the tree T with ID = 2 and provides it to the management server 8. In the following description, the fruit K measured by the second measuring device 4 is also referred to as a reference fruit KR. The second measurement device 4 also adds the ID of the tree T to the output spectral image and transmits it. The second measurement device 4 adds the ID of the tree T to the spectral information according to the operator's operation input. Furthermore, the second measurement device 4 may also add position information indicating the position of the reference fruit KR to the spectral information according to the operator's operation input. When the outputs of the first measurement device 2 and the second measurement device 4 are provided to the management server 8, the quality measurement of the tree T with ID = 2 is completed.

[0060] As described above, the operator performs quality measurements of the fruits K on a plurality of trees T in the order of the IDs. The outputs of the first measurement device 2 and the second measurement device 4 (spectral image and spectral information) are stored in the storage unit 34 of the management server 8. Therefore, the storage unit 34 stores spectral images with IDs = 1 to 15 added, and spectral information with IDs = 2, 4, 8, 12, and 14 added.

[0061] As shown in FIG. 6, after the quality measurement by the first measurement device 2 and the second measurement device 4 is completed, next, the quality value acquisition process by the management server 8 is performed (step S2 in FIG. 6).

[0062] 〔Regarding the quality value acquisition process〕 FIG. 8 is a flowchart showing an example of the quality value acquisition process. In the quality value acquisition process, the measured quality values of the fruits K of each of the 15 trees T are obtained.

[0063] As shown in FIG. 8, first, the processing unit 32 of the management server 8 obtains the first quality value and the second quality value (step S21 in FIG. 8). The processing unit 32 obtains the first quality value based on the output (spectral image) of the first measurement device 2. Also, the processing unit 32 obtains the second quality value based on the output (spectral information) of the second measurement device 4.

[0064] The processing unit 32 obtains the first quality value and the second quality value by a spectroscopic analysis method using near-infrared light. Quantitative analysis by spectroscopic analysis using near-infrared light is an analytical method that utilizes the fact that the degree of light absorption in a wavelength band where a specific component significantly absorbs light changes according to the content of the specific component. The processing unit 32 obtains the sugar content, acidity, pH, and polyphenol content as the first quality value and the second quality value. The wavelength bands in the near-infrared region used for analyzing each of the sugar content, acidity, pH, and polyphenol content are preset.

[0065] First, the process of obtaining the first quality value will be described. The processing unit 32 obtains a spectroscopic image of a wavelength band corresponding to each quality value from the spectral image that is the output of the first measuring device 2. In the present embodiment, the processing unit 32 obtains a spectroscopic image of a wavelength band corresponding to the sugar content, a spectroscopic image of a wavelength band corresponding to the acidity, a spectroscopic image of a wavelength band corresponding to the pH, and a spectroscopic image of a wavelength band corresponding to the polyphenol. Note that a spectroscopic image is an image in which the luminance of pixels constituting the image represents the light intensity of a predetermined wavelength band.

[0066] Hereinafter, the process when the processing unit 32 obtains the sugar content as the first quality value from the spectroscopic image of the wavelength band corresponding to the sugar content will be described. The processing unit 32 specifies the image regions of portions of a plurality of fruits K in the spectroscopic image of the wavelength band corresponding to the sugar content. The luminance of the pixels included in these plurality of image regions indicates the light intensity of the wavelength band corresponding to the sugar content. In other words, the luminance of the pixels indicates the amount of light absorption.

[0067] The processing unit 32 obtains a representative value of the luminance obtained from one spectroscopic image based on the luminance of the pixels included in the image regions of the plurality of fruits K. For example, the processing unit 32 may use the average value of the luminance of the pixels included in the image regions of the plurality of fruits K as the representative value. Also, in order to specify the image regions of portions of a plurality of fruits K in the spectroscopic image, a threshold value can be set for the luminance. In this case, the processing unit 32 can specify the region with a luminance equal to or higher than the threshold value as the image region of the fruit K.

[0068] Also, when the reference fruit KR can be identified from the spectral images of the trees T with IDs = 2, 4, 8, 12, and 14 based on the position information indicating the position of the reference fruit KR, the processing unit 32 may obtain a representative value of the luminance based on the pixels included in the image region of only the portion of the reference fruit KR. In this case, the luminance of the reference fruit KR can be obtained.

[0069] Next, the processing unit 32 refers to the first calibration curve data C1 and obtains the sugar content based on the luminance (representative value). FIG. 9 is a diagram showing an example of a plurality of first calibration curve data C1. FIG. 9 schematically shows the first calibration curve data C1. As shown in FIG. 9, among the plurality of first calibration curve data C11 to C14, the first calibration curve data C11 shows the correlation between the luminance of the pixels of the spectral image in the wavelength band corresponding to the sugar content and the sugar content. Although omitted in FIG. 9, the first calibration curve data C12 shows the correlation between the luminance of the pixels of the spectral image in the wavelength band corresponding to the acidity and the acidity. The first calibration curve data C13 shows the correlation between the luminance of the pixels of the spectral image in the wavelength band corresponding to the pH and the pH. The first calibration curve data C14 shows the correlation between the luminance of the pixels of the spectral image in the wavelength band corresponding to the polyphenol and the polyphenol content.

[0070] The plurality of first calibration curve data C1 may be data that can obtain the first quality value from the luminance of the pixels of the spectral image, and may be a table obtained by experiments, simulations, etc., or may be a linear or non-linear mathematical formula.

[0071] When obtaining the sugar content as the first quality value, the processing unit 32 refers to the first calibration curve data C11 of the sugar content and obtains the sugar content corresponding to the luminance obtained above. This sugar content is the first quality value.

[0072] The processing unit 32 also obtains the acidity, pH, and polyphenol content other than the sugar content by the same method as the method for the sugar content. The processing unit 32 obtains the first quality values (sugar content, acidity, pH, and polyphenol content) for each of the trees T with IDs = 1 to 15 based on the output of the first measuring device 2 as described above.

[0073] Next, the process of obtaining the second quality value will be described. The processing unit 32 obtains the absorbance in the wavelength band corresponding to each quality value from the spectral information that is the output of the second measuring device 4. Note that the absorbance is a value indicating the degree of light absorption in a predetermined wavelength band with respect to the light of the light source 27 as a reference.

[0074] Hereinafter, the process when the processing unit 32 obtains the sugar content as the first quality value will be described. The processing unit 32 refers to the second calibration curve data C2 and obtains the sugar content based on the absorbance (representative value).

[0075] FIG. 10 is a diagram showing an example of a plurality of second calibration curve data C2. FIG. 10 schematically shows the second calibration curve data C2. As shown in FIG. 10, among the plurality of second calibration curve data C21 to C24, the second calibration curve data C21 shows the correlation between the absorbance in the wavelength band corresponding to the sugar content and the sugar content. Although omitted in FIG. 10, the second calibration curve data C22 shows the correlation between the absorbance in the wavelength band corresponding to the acidity and the acidity. The second calibration curve data C23 shows the correlation between the absorbance in the wavelength band corresponding to the pH and the pH. The second calibration curve data C24 shows the correlation between the absorbance in the wavelength band corresponding to the polyphenol and the polyphenol content.

[0076] The plurality of second calibration curve data C2 may be data that can obtain the second quality value from the absorbance, and may be a table obtained by experiments, simulations, etc., or may be a linear or non-linear mathematical formula.

[0077] When obtaining the sugar content as the second quality value, the processing unit 32 refers to the second calibration curve data C21 of the sugar content and obtains the sugar content corresponding to the absorbance obtained above. This sugar content is the second quality value.

[0078] The processing unit 32 also obtains the acidity, pH, and polyphenol content other than the sugar content by the same method as the sugar content method. The processing unit 32 obtains the second quality values (sugar content, acidity, pH, and polyphenol content) in each of the trees T with ID = 2, 4, 8, 12, and 14 based on the output of the second measuring device 4 as described above.

[0079] As described above, the processing unit 32 obtains the first quality value in each of the trees T with ID = 1 to 15 and the second quality value in each of the trees T with ID = 2, 4, 8, 12, and 14 (in FIG. 8, step S21). Next, the processing unit 32 generates the scaling data S as shown in FIG. 8 (in FIG. 8, step S22).

[0080] The scaling data S is obtained based on the first quality value and the second quality value obtained when the reference fruit KR is measured by both the first measuring device 2 and the second measuring device 4. That is, the scaling data S is obtained based on the first quality value in each of the trees T with ID = 2, 4, 8, 12, and 14 and the second quality value in each of the trees T with ID = 2, 4, 8, 12, and 14. Hereinafter, the first quality value with ID = 2, 4, 8, 12, and 14 is also referred to as the reference first quality value, and the second quality value with ID = 2, 4, 8, 12, and 14 is also referred to as the reference second quality value.

[0081] Note that the first quality value in each of the trees T with ID = 2, 4, 8, 12, and 14 may be the average of the quality values of a plurality of fruits K including the reference fruit KR. Also, the first quality value in each of the trees T with ID = 2, 4, 8, 12, and 14 may include only the quality value of the reference fruit KR.

[0082] FIG. 11 is a diagram showing an example of scaling data S. As shown in FIG. 11, among a plurality of scaling data S1 to S4, the scaling data S1 shows the correlation between the sugar content measured by the first measuring device 2 and the sugar content measured by the second measuring device 4. Although omitted in FIG. 11, the scaling data S2 shows the correlation between the acidity measured by the first measuring device 2 and the acidity measured by the second measuring device 4. The scaling data S3 shows the correlation between the pH measured by the first measuring device 2 and the pH measured by the second measuring device 4. The scaling data S4 shows the correlation between the polyphenol content rate measured by the first measuring device 2 and the polyphenol content rate measured by the second measuring device 4.

[0083] The scaling data S1 includes a diagram L showing the correlation between the sugar content measured by the first measuring device 2 and the sugar content measured by the second measuring device 4. The horizontal axis in the scaling data S1 is the sugar content (first quality value) measured by the first measuring device 2, and the vertical axis is the sugar content (second measured value) measured by the second measuring device 4. The diagram L is a straight line passing through the point VU and the point VL. The five points in FIG. 11 are points obtained by plotting the reference fruit KR having the reference first quality value and the reference second quality value. Among the five points, the point VU is the point of the reference fruit KR having the maximum value of the sugar content (a plurality of reference first quality values) measured by the plurality of first measuring devices 2 and the maximum value of the sugar content (a plurality of reference second quality values) measured by the plurality of second measuring devices 4. The point VL is the point of the reference fruit KR having the minimum value of the sugar content (a plurality of reference first quality values) measured by the plurality of first measuring devices 2 and the minimum value of the sugar content (a plurality of reference second quality values) measured by the plurality of second measuring devices 4.

[0084] Thus, in the present embodiment, the scaling data S1 is obtained based on a plurality of reference first quality values and a plurality of reference second quality values obtained when a plurality of reference fruits KR are measured by both the first measuring device 2 and the second measuring device 4. In this case, the first quality value and the second quality value are associated with each other by the plurality of reference fruits KR. Therefore, the accuracy of the scaling data S can be further improved.

[0085] Further, the scaling data S1 is obtained based on the maximum value and the minimum value among a plurality of reference first quality values (outputs of the first measuring device 2), and the maximum value and the minimum value among a plurality of reference second quality values. In this case, the reference first quality value and the reference second quality value are associated with each other based on at least their respective maximum values and minimum values. Therefore, the scaling data S1 can be easily obtained without degrading the accuracy.

[0086] Other scaling data S2 to S4 are also obtained in the same manner as the scaling data S1. The scaling data S may be data indicating the correlation between the first quality value (output of the first measuring device 2) and the second quality value, and may be a table or a mathematical formula.

[0087] As described above, the processing unit 32 generates the scaling data S (step S22 in FIG. 8). Next, as shown in FIG. 8, the processing unit 32 calculates the measured quality value (step S23 in FIG. 8).

[0088] The processing unit 32 selects the target fruit KT from among the fruits K on the trees T with IDs = 1 to 15, and obtains the measured quality value of the target fruit KT based on the scaling data S and the first quality value of the target fruit KT. The processing unit 32 sequentially selects the target fruit KT from among the fruits K on the trees T with IDs = 1 to 15, and repeatedly obtains the measured quality value. Thereby, the processing unit 32 obtains the measured quality value of each of the fruits K on the trees T with IDs = 1 to 15. The processing unit 32 refers to the scaling data S and obtains the second quality value corresponding to the first quality value of the target fruit KT. The processing unit 32 obtains the second quality value corresponding to this first quality value as the measured quality value of the target fruit KT.

[0089] For example, the case of obtaining the sugar content as the measured quality value of the fruit K on the tree T with ID = 1 will be described. FIG. 12 is a diagram showing an aspect when the processing unit 32 obtains the measurement quality value of the fruit K on the tree T with ID = 1. The processing unit 32 selects the fruit K on the tree T with ID = 1 as the target fruit KT. Next, the processing unit 32 refers to the scaling data S1, and in the diagram L, obtains the sugar content (vertical axis in FIG. 12) by the second measuring device 4 corresponding to the sugar content (horizontal axis in FIG. 12), which is the first quality value of the fruit K (target fruit KT) with ID = 1. The processing unit 32 sets the sugar content by the second measuring device 4 corresponding to the first quality value as the measurement quality value. Thus, the vertical axis of the scaling data S1 indicates the sugar content by the second measuring device 4 and also indicates the measurement quality value obtained from the first quality value.

[0090] For the acidity, pH, and polyphenol content rate other than the sugar content among the measurement quality values, the processing unit 32 obtains them by the same method as the method for the sugar content. The processing unit 32 repeats the same processing for the fruit K on the trees T with ID = 1 to 15, and similarly obtains the measurement quality values of the fruit K on each of the trees T with ID = 1 to 15. Regarding the fruit K on the trees T with ID = 2, 4, 8, 12, 14 including the reference fruit KR, the second quality value measured by the second measuring device 4 may be directly used as the measurement quality value.

[0091] According to this quality value acquisition process, based on the scaling data S, the second quality value corresponding to the first quality value (output of the first measuring device) of the target fruit KT can be obtained, and the obtained second quality value can be set as the measurement quality value of the target fruit KT. As a result, the first quality value of the target fruit KT can be corrected to be equivalent to the quality value of the second measuring device 4 having higher measurement accuracy than the first measuring device 2, and the quality measurement accuracy can be easily improved.

[0092] In addition, since the first measurement head 22 includes a hyperspectral camera (spectral camera), the first measurement device 2 is more convenient and can measure a wider range at one time than the second measurement device 4 including a light source 27 and a spectroscope 28 that splits transmitted light. Therefore, the convenience can be improved by using the first measurement device 2 while improving the quality measurement accuracy.

[0093] As described above, the processing unit 32 calculates the measured quality value (step S23 in FIG. 8). Next, the processing unit 32 proceeds to step S3 in FIG. 6 and executes prediction processing (step S3 in FIG. 6).

[0094] 〔Regarding prediction processing〕 FIG. 13 is a flowchart showing an example of prediction processing. In the prediction processing, the processing unit 32 of the management server 8 obtains a prediction period predicted to be the appropriate harvest time of the fruit, as described above. In the present embodiment, the prediction period is obtained as a period with one day as the minimum unit. As shown in FIG. 13, first, the processing unit 32 registers a plurality of types of measured quality values (brix, acidity, pH, and polyphenol content) obtained by the quality value acquisition process 32a in the quality value database 40 (step S31 in FIG. 13). FIG. 14 is a diagram showing an example of the quality value database 40. The quality value database 40 includes a brix database 40a, an acidity database 40b, a pH database 40c, and a polyphenol database 40d. In FIG. 14, in the brix database 40a, the ID of the tree T and the brix are registered in association with each other. Also, regarding the brix, it is registered in time series for each measurement date when the brix was measured. That is, time series data in which the brix of each tree T is accumulated in time series is registered in the brix database 40a.

[0095] The acidity database 40b, the pH database 40c, and the polyphenol database 40d are the same as the sugar content database 40a. Therefore, time-series data (multiple time-series data) of the acidity, pH, and polyphenol content of each tree T are registered in the acidity database 40b, the pH database 40c, and the polyphenol database 40d.

[0096] The processing unit 32 registers four measurement quality values of the sugar content, acidity, pH, and polyphenol content in the quality value database 40. That is, the processing unit 32 acquires four time-series data in which the four measurement quality values are accumulated in time series respectively (second process).

[0097] Next, the processing unit 32 obtains a prediction period based on the plurality of time-series data (third process). More specifically, as shown in FIG. 13, the processing unit 32 obtains a predicted quality value (step S32 in FIG. 13). FIG. 15 is a graph showing an example of the predicted quality value. FIG. 15 shows the time-series data and predicted sugar content of the sugar content, and the time-series data and predicted acidity of the acidity. In FIG. 15, the horizontal axis represents the date, and the vertical axis represents the sugar content and acidity. Also, in FIG. 15, the circles represent the measured values (measurement quality values) of the sugar content, and the squares represent the measured values (measurement quality values) of the acidity. In the following description, the prediction process in the case of using two measurement quality values (two time-series data) of the sugar content and acidity will be described.

[0098] In the present embodiment, the processing unit 32 obtains the average value of the measurement quality values of the entire field F on each measurement date, and uses the average value as the quality value. For example, the value of the sugar content at the date d0 is the average value of the sugar content of the trees T with IDs 1 to 15 measured on the date d0. Similarly, the value of the acidity at the date d0 is the average value of the acidity of the trees T with IDs 1 to 15 measured on the date d0.

[0099] The processing unit 32 obtains a prediction curve L10 based on the value of the sugar content (time-series data of the sugar content). For example, the processing unit 32 obtains an approximation curve L11 based on the time-series data of the sugar content before the date d0, and extends the approximation curve L11 in the direction of the future from the date d0 to obtain the prediction curve L10 of the sugar content. This prediction curve L10 indicates the predicted value of the future sugar content after the date d0. That is, the prediction curve L10 is the predicted sugar content (predicted quality value).

[0100] In addition, the processing unit 32 obtains a prediction curve L20 based on the quality value of the acidity (time-series data of the acidity). For example, the processing unit 32 obtains an approximation curve L21 based on the time-series data of the sugar content before the date d0, and extends the approximation curve L21 in the direction of the future from the date d0 to obtain the prediction curve L20 of the acidity. This prediction curve L20 indicates the predicted value of the future acidity after the date d0. That is, the prediction curve L20 is the predicted acidity (predicted quality value). As a method for obtaining the approximation curve, a known method such as regression analysis using the least squares method is adopted.

[0101] As described above, the processing unit 32 obtains the prediction curve L10 as the predicted sugar content and obtains the prediction curve L20 as the predicted acidity.

[0102] Next, as shown in FIG. 13, the processing unit 32 acquires environmental prediction information (step S33 in FIG. 13). The processing unit 32 accesses the weather information server 7 to acquire environmental prediction information. The environmental prediction information of the present embodiment includes weather information for a period from the present to 9 days ahead. In the present embodiment, the weather information includes sunny / rainy prediction and predicted precipitation for a period from the present to 9 days ahead. The predicted precipitation is a predicted value indicating the predicted environmental state.

[0103] After acquiring the environmental prediction information, the processing unit 32 proceeds to step S34 and obtains a first period and a second period (step S34 in FIG. 13).

[0104] The first period is a period during which the predicted sugar content and the predicted acidity (multiple types of predicted quality values) satisfy predetermined conditions. The predetermined conditions are the quality conditions that the fruit should satisfy at the time of harvest. The predetermined conditions include a condition for the predicted sugar content and a condition for the predicted acidity. The condition for the predicted sugar content is the condition that it is equal to or higher than the first threshold Th1 (see Fig. 15). Also, the condition for the predicted acidity is the condition that it is equal to or higher than the second threshold Th2 (see Fig. 15). The first threshold Th1 and the second threshold Th2 are set to values necessary for grapes as raw materials for wine.

[0105] During the first period, both the predicted sugar content and the predicted acidity satisfy the predetermined conditions. Therefore, in Fig. 15, the first period is a period in which the period equal to or higher than the first threshold Th1 in the predicted sugar content curve L10 and the period equal to or higher than the second threshold Th2 in the predicted acidity curve L20 overlap.

[0106] As shown by the approximate curve L11 and the predicted curve L10 in Fig. 15, the sugar content tends to gradually increase as the number of days elapses. Therefore, the period equal to or higher than the first threshold Th1 in the predicted sugar content curve L10 is the period after the point P1 on the predicted curve L10. The point P1 is the point where the predicted curve L10 becomes the first threshold Th1. Also, as shown by the approximate curve L21 and the predicted curve L20 in Fig. 15, the acidity tends to gradually decrease as the number of days elapses. Therefore, the period equal to or higher than the second threshold Th2 in the predicted acidity curve L20 is the period before the point P2 on the predicted curve L20. The point P2 is the point where the predicted curve L20 becomes the second threshold Th2. In this way, the sugar content and the acidity have different increasing and decreasing tendencies with respect to the passage of days. For this reason, the first period during which both the sugar content and the acidity satisfy the predetermined conditions is the period from the date d1 to the date d2. The date d1 is the date corresponding to the point P1. Also, the date d2 is the date corresponding to the point P2.

[0107] That is, in the present embodiment, the first period is the period from date d1 to date d2. In the above manner, the processing unit 32 obtains the first period based on the predicted sugar content curve L10 and the predicted acidity curve L20.

[0108] When the first period does not exist, the processing unit 32 outputs the predicted curves L10 and L20 to the operator 14 through the management terminal 10. When the first period does not exist, the prediction period cannot be obtained. However, by outputting the predicted curves L10 and L20, information necessary for the operator 14 to determine the prediction period can be provided to the operator 14.

[0109] Also, the second period is a period determined to be a harvestable weather based on the predicted precipitation. More specifically, the second period is a period determined based on the comparison result between the predicted precipitation and a predetermined threshold. In the present embodiment, the predetermined threshold is set such that the predicted precipitation per day is 20 mm. The processing unit 32 determines that a day with a predicted precipitation of 20 mm or less per day is a harvestable weather.

[0110] FIG. 16 is a diagram showing a first example of the sunny / rainy prediction and the predicted precipitation included in the environmental prediction information. FIG. 16 shows the sunny / rainy prediction and the predicted precipitation for the period up to 9 days ahead from September 21st to September 29th. The sunny / rainy prediction and the predicted precipitation shown in FIG. 16 are as follows. September 21st - September 24th: Sunny / rainy prediction is "sunny", predicted precipitation is 0 mm September 25th: Sunny / rainy prediction is "partly cloudy with occasional sunshine", predicted precipitation is 20 mm September 26th - September 29th: Sunny / rainy prediction is "sunny", predicted precipitation is 0 mm

[0111] In this case, the predicted precipitation for the 9 days from September 21st to September 29th is 20 mm or less. Therefore, the processing unit 32 determines the 9 days from September 21st to September 29th as the second period. As described above, the processing unit 32 obtains the first period and the second period (step S34 in FIG. 13). Next, the processing unit 32 obtains a prediction period based on the first period and the second period (step S35 in FIG. 13).

[0112] In principle, the processing unit 32 sets the overlapping period in which the first period and the second period overlap as the prediction period. In FIG. 16, for example, assume that the first period is from September 26th to September 29th. In this case, all of the first period overlaps with the second period. Therefore, the entire first period becomes the overlapping period. Thus, the processing unit 32 sets the period from September 26th to September 29th as the prediction period.

[0113] FIG. 17 is a diagram showing a second example of the sunny / rainy prediction and the predicted precipitation included in the environmental prediction information. The sunny / rainy prediction and the predicted precipitation shown in FIG. 17 are as follows. September 21st - September 24th: Sunny / rainy prediction is "sunny", predicted precipitation is 0 mm September 25th: Sunny / rainy prediction is "partly cloudy with sunny intervals", predicted precipitation is 20 mm September 26th: Sunny / rainy prediction is "partly cloudy with rain", predicted precipitation is 30 mm September 27th - September 28th: Sunny / rainy prediction is "rain", predicted precipitation is 80 mm September 29th: Sunny / rainy prediction is "partly cloudy with rain", predicted precipitation is 40 mm

[0114] In this case, the processing unit 32 determines that the five-day period from September 21st to September 25th is the second period. Also, in FIG. 17, assume that the first period is from September 26th to September 29th. In this case, there is no overlapping period between the first period and the second period. When there is no overlapping period between the first period and the second period and the second period exists before the first period, the processing unit 32 sets the day closest to the first period within the second period as the prediction period. Therefore, in the case of FIG. 17, the processing unit 32 sets September 25th as the prediction period.

[0115] In the present embodiment, when there is no overlapping period and the second period exists before the first period, among the second periods, the day closest to the first period is set as the prediction period. Therefore, the prediction period can be set at a timing as close as possible to the necessary quality conditions among the harvestable weather.

[0116] FIG. 18 is a diagram showing a third example of the sunny / rainy prediction and predicted precipitation included in the environmental prediction information. The sunny / rainy prediction and predicted precipitation shown in FIG. 18 are as follows. September 21st - September 23rd: Sunny / rainy prediction is "sunny", predicted precipitation is 0 mm September 24th: Sunny / rainy prediction is "cloudy with occasional rain", predicted precipitation is 40 mm September 25th: Sunny / rainy prediction is "rain", predicted precipitation is 80 mm September 26th - September 28th: Sunny / rainy prediction is "sunny", predicted precipitation is 0 mm September 29th: Sunny / rainy prediction is "cloudy with occasional rain", predicted precipitation is 40 mm

[0117] In this case, the processing unit 32 determines that the three days from September 21st to September 23rd and the three days from September 26th to September 28th are the second periods. Also, in FIG. 17, assume that the first period is from September 26th to September 29th. In this case, the three days from September 26th to September 28th become the overlapping period.

[0118] Here, when there is a period that is not the second period immediately before the overlapping period, the processing unit 32 performs a process of providing at least a one-day interval between the period that is not the second period and the prediction period. In FIG. 18, September 24th and September 25th, which are immediately before the overlapping period, are periods that are not the second period. Therefore, the processing unit 32 sets September 27th and September 28th as the prediction period among the three days from September 24th to September 28th, which is the overlapping period. As a result, September 26th becomes the interval period.

[0119] Immediately after a period that is not the second period, the state of field F may not be good due to rainfall. In this regard, in the present embodiment, as described above, since at least a one-day interval period is provided between the period that is not the second period and the prediction period, the prediction period can be set while avoiding the timing when the state of field F is not good.

[0120] The processing unit 32 that has obtained the prediction period gives information indicating the prediction period to the management terminal 10 as necessary, and outputs the prediction period as the appropriate harvesting time of the fruit to the operator 14 through the management terminal 10 (in FIG. 13, step S36). The processing unit 32 that has output the prediction period returns to the flowchart shown in FIG. 6 and repeats the same processing again. Each time quality measurement is performed on field F, the processing unit 32 performs quality value acquisition processing and prediction processing.

[0121] As described above, the process (third process) of obtaining the prediction period based on two time-series data (time-series data of sugar content and time-series data of acidity) includes a process of obtaining predicted sugar content and predicted acidity (multiple types of predicted quality values), a process of obtaining environmental prediction information, and a process of obtaining the prediction period based on the environmental prediction information and multiple types of predicted quality values.

[0122] According to the above configuration, future quality values can be predicted using the time-series data of sugar content and the time-series data of acidity (multiple time-series data), and the prediction period predicted to be the appropriate harvesting time can be obtained based on the predicted quality values. As a result, the prediction period can be output as the prediction result of the appropriate harvesting time of the fruit.

[0123] In addition, the prediction process of this embodiment includes a process of obtaining a predicted sugar content curve L10 and a predicted acidity curve L20 (predicted sugar content and predicted acidity) based on time-series data of sugar content and time-series data of acidity (step S32 in FIG. 13), a process of obtaining environmental prediction information indicating environmental prediction in the field F (step S33 in FIG. 13), and a process of obtaining a predicted period based on the environmental prediction information, the predicted sugar content, and the predicted acidity. In this case, in addition to the predicted quality value of the fruit, the predicted period can be obtained by taking into account the environmental prediction information of the field F.

[0124] In addition, the process of obtaining the predicted period based on the environmental prediction information, the predicted sugar content, and the predicted acidity includes a process of obtaining a first period in which the predicted sugar content and the predicted acidity satisfy predetermined conditions, and a process of obtaining a second period determined to be a harvestable weather based on the comparison result between the predicted precipitation and a predetermined threshold value (step S34 in FIG. 13), and a process of obtaining the predicted period based on the first period and the second period (step S35 in FIG. 13). Thereby, the predicted period can be appropriately obtained according to the relationship between the appropriate period in the quality value and the appropriate period in the weather.

[0125] 〔Others〕 It should be considered that the embodiments disclosed this time are illustrative in all respects and not restrictive. For example, in the above embodiment, the case where the environmental prediction information includes sunny / rainy prediction and predicted precipitation is illustrated. However, disease risk information regarding fruit diseases can also be used as the environmental prediction information. When disease risk information is used as the environmental prediction information, a disease prediction model that outputs the disease risk information is stored in the storage unit 34 of the management server 8. As this disease prediction model, for example, the Goidanich model for downy mildew is adopted. The Goidanich model is a model for predicting the growth of downy mildew bacteria and may be used for disease prediction. The disease prediction model is configured to output, as a percentage, the risk of disease caused by the Phytophthora fungus (disease risk information) when given temperature, humidity, and precipitation. The risk value represented by this percentage is used as a predicted value indicating the predicted environmental conditions.

[0126] The processing unit 32 may obtain the prediction period using the disease risk information instead of the sunny / rainy prediction and the predicted precipitation. In this case, when the processing unit 32 of the management server 8 acquires the environmental prediction information (step S33 in FIG. 13), it accesses the meteorological information server 7 to acquire the meteorological prediction information. As described above, the meteorological prediction information includes the sunny / rainy prediction, the predicted precipitation, the predicted temperature, and the predicted humidity for a period of about one week to ten days. The processing unit 32 provides the predicted precipitation, the predicted temperature, and the predicted humidity included in the meteorological prediction information to the disease prediction model, and causes the disease prediction model to output the disease risk information.

[0127] FIG. 19 is a diagram showing an example of the disease risk included in the environmental prediction information. FIG. 19 shows the disease risk information for the period up to 9 days ahead from September 21st to September 29th.

[0128] Here, the processing unit 32 determines that the days when the disease risk information is less than 20% are the periods without problems regarding the disease (the third period), and determines that the days when the disease risk information is 20% or more are the periods with problems regarding the disease.

[0129] In the case of FIG. 19, the disease risk information for the five days from September 21st to September 25th is 10% or less. Therefore, the processing unit 32 determines that the five days from September 21st to September 25th are the third period. Also, the processing unit 32 determines that the four days from September 26th to September 29th are the periods with problems regarding the disease.

[0130] The processing unit 32 performs the same processing as the determination using the first period and the second period in the above embodiment. That is, in principle, the processing unit 32 sets the overlapping period in which the first period and the third period overlap as the prediction period. Further, when there is no overlapping period between the first period and the third period and the third period exists before the first period, the processing unit 32 sets the day closest to the first period in the third period as the prediction period.

[0131] In FIG. 19, assuming that the first period is from September 26th to September 29th, the processing unit 32 sets September 25th as the prediction period. In this way, it is also possible to obtain prediction information by using disease risk information regarding fruit diseases as environmental prediction information.

[0132] In the above embodiment, the case where the prediction process is performed based on two types of measured quality values (sugar content and acidity) obtained by the quality value acquisition process is exemplified. However, the prediction process may be performed using at least two measured quality values. In addition to sugar content and acidity, pH and polyphenol content can also be used in the prediction process. As shown in the present embodiment, it is particularly preferable to use sugar content and acidity as the measured quality values used in the prediction process.

[0133] In the quality value acquisition process in the above embodiment, the case where the measured quality value is obtained based on the first quality value (output of the first measuring device) of the first measuring device 2 and the second quality value based on the output of the second measuring device 4 is exemplified. However, the second quality value obtained by the second measuring device 4 may be used as the measured quality value. In other words, the prediction process may be performed using the second quality value obtained by the second measuring device 4. In this case, it is not necessary to perform the quality measurement operation by the first measuring device 2. The second measuring device 4 can perform quality measurement of the fruits K for some or all of the plurality of trees T, and the obtained second quality value can be used for the prediction process.

[0134] Furthermore, when performing the prediction process using the second quality value obtained by the second measuring device 4, the second calibration curve data C2 may be adjusted according to the time and location, and then the second quality value may be obtained. In this case, the accuracy in quality measurement can be further improved.

[0135] In addition, as a method for obtaining the quality value of the fruit, in this embodiment, the case where spectroscopic analysis using near-infrared light is used is exemplified. However, as long as the same quality value can be obtained, the quality value of the fruit may be obtained by other methods.

[0136] The scope of the present invention is not as described above, but is indicated by the scope of the claims, and it is intended that all meanings equivalent to the scope of the claims and all changes within the scope are included.

Explanation of Signs

[0137] 1 Harvest support system 2 First measurement device (first measurement unit) 4 Second measurement device (second measurement unit) 5 Measurement device 6 Agricultural machine 6a In-vehicle network 7 Weather information server 8 Management server (processing device) 10 Management terminal 12 Manipulator 14 Operator 18 Control device 19 Input / output device 20 Communication device 22 First measurement head 24 First control unit 26 Second measurement head 26a Light projecting unit 26b Light receiving unit 26c Head body 26c1 Annular tip surface 26c2 Hole portion 27 Light source 28 Spectrometer 30 Second control unit 32 Processing unit 32a Quality value acquisition process 32b Prediction process 34 Storage unit 36 Communication device 40 Quality Value Database 40a Brix Database 40b Acidity Database 40c pH Database 40d Polyphenol Database A Imaging Region BS Wireless Base Station C1, C11, C12, C13, C14 First Calibration Curve Data C2, C21, C22, C23, C24 Second Calibration Curve Data D1 First Interval D2 Second Interval F Field K Fruit KT Target Fruit KR Reference Fruit L Diagram L10 Prediction Curve L11 Approximation Curve L20 Prediction Curve L21 Approximation Curve NW Public Network S, S1, S2, S3, S4 Scaling Data T Tree d0, d1, d2 Date k1 Fruit Grain

Claims

1. A measurement device for measuring the quality of fruits cultivated in a field, and a processing device, and the processing device performs a first process of obtaining a plurality of types of quality values based on the output of the measurement device, a second process of obtaining a plurality of time-series data in which each of the plurality of types of quality values is accumulated in time series, and a third process of obtaining a prediction period predicted to be the appropriate harvesting time of the fruits based on the plurality of time-series data, and includes a processing unit that executes the processes. A harvest support system.

2. The third process includes a process of obtaining predicted quality values for each of the plurality of types of quality values based on the plurality of time-series data, a process of obtaining environmental prediction information indicating environmental prediction in the field, and a process of obtaining the prediction period based on the environmental prediction information and the plurality of predicted quality values. The harvest support system according to claim 1.

3. The environmental prediction information includes predicted values indicating predicted environmental states, and the process of obtaining the prediction period includes a process of obtaining a first period in which the plurality of predicted quality values satisfy a predetermined condition, and a process of obtaining a second period determined to be a harvestable environmental state based on a comparison result between the predicted value and a predetermined threshold value, and a process of obtaining the prediction period based on the first period and the second period. The harvest support system according to claim 2.

4. The process of obtaining the prediction period based on the first period and the second period includes a process of setting the overlapping period in which the first period and the second period overlap as the prediction period. The harvest support system according to claim 3.

5. The process of obtaining the prediction period based on the first period and the second period further includes a process of providing at least a one-day interval between the period that is not the second period and the prediction period when there is a period that is not the second period immediately before the overlapping period. The harvest support system according to claim 4.

6. The environmental prediction information includes at least one of weather information and disease risk information regarding diseases of the fruits. The harvest support system according to claim 2.

7. The process of obtaining the prediction period based on the first period and the second period includes a process of setting, as the prediction period, the day closest to the first period among the second periods when there is no overlapping period in which the first period and the second period overlap. The harvest support system according to claim 3.

8. The process of obtaining the prediction period When the first period does not exist, the method further includes a process of outputting the plurality of predicted quality values to the outside. The harvesting support system according to claim 3.

9. The measuring device includes a first measuring unit that measures the quality of the fruit, and a second measuring unit that measures the quality of the fruit with a configuration different from that of the first measuring unit. The first process includes a process of obtaining the plurality of types of quality values when the quality of the fruit is measured by the first measuring unit based on scaling data indicating a correlation between the output of the first measuring unit and a plurality of reference quality values based on the output of the second measuring unit. The harvesting support system according to claim 1.

10. The fruit includes grapes. The harvesting support system according to any one of claims 1 to 9.

11. The plurality of types of quality values include at least any two of a sugar content, an acidity, a pH, and a polyphenol content rate. The harvesting support system according to any one of claims 1 to 9.

12. a process of obtaining a plurality of types of quality values based on an output of a measuring device that measures the quality of fruit cultivated in a field; a process of obtaining a plurality of time-series data in which each of the plurality of types of quality values is accumulated in time series; and a processing unit that executes a process of obtaining a predicted period predicted to be an appropriate harvesting period of the fruit based on the plurality of time-series data. Processing device.

13. A computer program for causing a computer to execute a process of supporting the harvesting of fruit cultivated in a field, the computer program causing the computer to execute a step of obtaining a plurality of types of quality values based on an output of a measuring device that measures the quality of the fruit; execute a step of obtaining a plurality of time-series data in which each of the plurality of types of quality values is accumulated in time series; and execute a step of obtaining a predicted period predicted to be an appropriate harvesting period of the fruit based on the plurality of time-series data. Computer program.

Images