Ripening prediction method and ripening prediction program for strawberry

Abstract

To predict a yield of strawberry fruits in a prescribed range with high accuracy at an early stage after planting strawberries.SOLUTION: A strawberry ripening prediction method makes a computer execute processing for acquiring information on a flowering date of each small flower in each fruit cluster of each strawberry nursery plant planted in a prescribed range, predicting a ripening date of fruit of each small flower by using the information on the flowering date of each small flower and environment information after the flowering date of each small flower, and estimating the number of fruits ripening in each day in the prescribed range on the basis of the predicted ripening date of fruit of each small flower. The strawberry ripening prediction method acquires a flowering date of a first flower and predicts a flowering date of an m-th flower (m is a natural number of two or more) by using the acquired information on the flowering date of the first flower and the environment information after the flowering date of the first flower in the processing for acquiring the information on the flowering date of each small flower.SELECTED DRAWING: Figure 12

Description

[Technical Field]

[0001] The present invention relates to a method and a program for predicting strawberry maturity. [Background technology]

[0002] It is important for strawberry growers to be able to predict when and how many strawberries will ripen (be able to be harvested). For example, at tourist strawberry farms, visitors concentrate on weekends, so if they can predict the amount of fruit (number of fruits) that will ripen on weekends, they can set an appropriate number of reservations for visitors. Also, strawberry farms sometimes hire part-time employees for harvesting, preparation, and shipping work, and if they can predict the amount of fruit (number of fruits) that will ripen each day, they can appropriately determine the number of staff required each day in advance.

[0003] In the past, the amount of strawberries that could be harvested was often predicted by experienced growers based on their experience and intuition. However, in recent years, research has been progressing on techniques for predicting the yield and growth status of agricultural crops (see, for example, Patent Documents 1 to 4 and Non-Patent Documents 1 and 2). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2022-060782 [Patent Document 2] Patent Publication No. 2021-179983 [Patent Document 3] Patent Publication No. 2021-128770 [Patent Document 4] Japanese Patent Application Publication No. 2020-054289 [Non-patent literature]

[0005] [Non-Patent Document 1] Kyushu Agricultural Research, No. 56, p. 189: Predicting the flowering period of forced strawberries (1994) [Non-patent document 2] Kagoshima Prefectural Agricultural Experiment Station Research Report, No. 30, p.7-16: Modeling of flower induction in forced strawberries and harvest time prediction technology (2002) Summary of the Invention [Problem to be solved by the invention]

[0006] For example, Patent Document 4 discloses that when predicting the harvest date, etc., it is necessary to determine the flowering date of strawberries from images captured by a camera. Furthermore, Non-Patent Documents 1 and 2 disclose methods for predicting the harvest date of the first fruit of each strawberry cluster. However, even with the above-mentioned technology, it is difficult to accurately predict at an early stage (for example, before the flowering date of the strawberries) when and on which flower of which cluster the fruit will mature (be able to be harvested).

[0007] The present invention aims to provide a method and program for predicting strawberry maturity that can accurately predict the maturity of strawberry fruits at an early stage after strawberries are planted. [Means for solving the problem]

[0008] The strawberry maturity prediction method of the present invention is a maturity prediction method in which a computer executes the following processes: obtain information on the flowering date of each floret in each fruit cluster of each strawberry plant planted in a specified range; predict the maturity date of the fruit of each floret using the information on the flowering date of each floret and environmental information after the flowering date of each floret; estimate the number of fruits that will mature each day in the specified range based on the predicted maturity date of the fruit of each floret; and, in the process of obtaining information on the flowering date of each floret, obtain the flowering date of the first flower and predict the flowering date of the mth flower (m is a natural number greater than or equal to 2) using the obtained information on the flowering date of the first flower and environmental information after the flowering date of the first flower. [Effects of the Invention]

[0009] The strawberry maturity prediction method and prediction program of the present invention have the effect of enabling accurate prediction of strawberry fruit maturity at an early stage after strawberries are planted. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a diagram illustrating a configuration of a maturity prediction system according to an embodiment. [Figure 2] FIG. 2(a) is a diagram showing the hardware configuration of a maturity prediction server, a bud detection server, and an environmental information management server, and FIG. 2(b) is a diagram showing the hardware configuration of a user terminal. [Figure 3] FIG. 2 is a functional block diagram of a maturity prediction server. [Figure 4] FIG. 10 is a diagram (part 1) showing an example of an input screen. [Figure 5] 10 is a table (part 1) for explaining the processing of the first prediction unit. [Figure 6] 10 is a table (part 2) for explaining the processing of the first prediction unit. [Figure 7] 10 is a third table for explaining the processing of the first prediction unit. [Figure 8] 10 is a fourth table illustrating the processing of the first prediction unit. [Figure 9] FIG. 2 is a diagram schematically illustrating a prediction process by a first prediction unit of a maturity prediction server. [Figure 10] FIG. 10 is a diagram (part 2) showing an example of the input screen. [Figure 11] FIG. 10 is a diagram schematically illustrating a prediction process by a second prediction unit of the maturity prediction server. [Figure 12] FIG. 10 is a diagram (part 3) showing an example of an input screen. [Figure 13] 10 is a table for explaining the processing of the third prediction unit. [Figure 14] FIG. 10 is a diagram schematically illustrating a prediction process by a third prediction unit of the maturity prediction server. [Figure 15] 10 is a flowchart showing the processing of the maturity prediction server. DETAILED DESCRIPTION OF THE INVENTION

[0011] An embodiment of a strawberry maturity prediction system will be described in detail below with reference to Figs. 1 to 15. Fig. 1 shows a schematic configuration of a maturity prediction system 100 according to one embodiment. The maturity prediction system 100 of this embodiment is a system used by strawberry producers and the like (hereinafter referred to as users), which makes predictions regarding strawberry maturity in response to input from the users and provides the users with the prediction results.

[0012] As shown in Figure 1, the maturity prediction system 100 comprises a maturity prediction server 10, a flower bud detection server 12, an environmental information management server 14, and a user terminal 70. The maturity prediction server 10, flower bud detection server 12, environmental information management server 14, and user terminal 70 are connected via a network 80 such as the Internet, allowing information to be exchanged between each device.

[0013] The maturity prediction server 10 makes various predictions regarding strawberry maturity in response to input from the user terminal 70, and outputs the prediction results to the user terminal 70. The maturity prediction server 10 cooperates with the bud detection server 12 and the environmental information management server 14 to acquire necessary data from each of the servers 12, 14, and makes various predictions using the acquired data.

[0014] FIG. 2(a) shows a schematic diagram of the hardware configuration of the maturity prediction server 10. As shown in FIG. 2(a), the maturity prediction server 10 includes a central processing unit (CPU) 90, a read-only memory (ROM) 92, a random access memory (RAM) 94, storage (e.g., a solid-state drive (SSD) or a hard disk drive (HDD)) 96, a network interface 97, and a portable storage medium drive 99. These components of the maturity prediction server 10 are connected to a bus 98. In the maturity prediction server 10, the CPU 90 executes a program (including a maturity prediction program) stored in the ROM 92 or the HDD 96, or a program read from the portable storage medium 91 by the portable storage medium drive 99, thereby realizing the functions of the components shown in FIG. 3. The functions of the components shown in FIG. 3 may be implemented by an integrated circuit, such as an application-specific integrated circuit (ASIC) or a field-programmable gate array (FPGA). Details of the functions of the components shown in FIG. 3 will be described later.

[0015] The bud emergence detection server 12 acquires images of strawberry plants in a farm field (e.g., in a greenhouse) taken at predetermined intervals, and acquires bud emergence information such as the bud emergence date and the number of bud emergent plants based on the acquired images. However, the bud emergence detection server 12 may also detect bud emergence using a method other than acquiring bud emergence information from images. The bud emergence detection server 12 has the same hardware configuration as the maturity prediction server 10 (see FIG. 2(a)).

[0016] The environmental information management server 14 accumulates and manages past environmental information (temperature, etc.) of the field. Specifically, the environmental information management server 14 acquires and manages, for example, environmental data observed by sensors in the field (inside the greenhouse), weather data obtained from the Japan Meteorological Agency's database, and mesh agricultural weather data from the National Agriculture and Food Research Organization. In addition, the environmental information management server 14 provides the maturity prediction server 10 with past environmental information of the field, predicted values ​​for future environmental information, and average values, in response to a request from the maturity prediction server 10. The environmental information management server 14 has the same hardware configuration as the maturity prediction server 10 and the flower bud detection server 12 (see FIG. 2(a)).

[0017] The user terminal 70 is a terminal such as a smartphone or PC (Personal Computer) used by strawberry producers (users). The user inputs information necessary for predicting strawberry maturity into the user terminal 70. The user terminal 70 transmits the input information to the maturity prediction server 10, causing it to make predictions regarding strawberry maturity. The user terminal 70 also obtains and displays the prediction results from the maturity prediction server 10.

[0018] Here, the user terminal 70 has, as an example, a hardware configuration as shown in Fig. 2(b). As shown in Fig. 2(b), the user terminal 70 includes a CPU 190, a ROM 192, a RAM 194, a storage 196, a network interface 197, a display unit 193, an input unit 195, and a portable storage medium drive 199 capable of reading data stored in a portable storage medium 191. The display unit 193 includes a liquid crystal display or the like, and the input unit 195 includes a touch panel, a keyboard, a mouse, and the like. These components of the user terminal 70 are connected to a bus 198.

[0019] (For details on the maturity prediction server 10) Fig. 3 shows a functional block diagram of the maturity prediction server 10. In the maturity prediction server 10, the CPU 90 executes a program to realize the functions shown in Fig. 3. Specifically, the maturity prediction server 10 has an input receiving unit 30, a first prediction unit 101, a second prediction unit 102, a third prediction unit 103, and an output unit 40.

[0020] The input receiving unit 30 acquires information entered by the user on input screens such as those shown in FIGS. 4, 10, and 12 displayed on the display unit 193 of the user terminal 70, as well as information on buttons pressed by the user on the input screens. A predetermined area of ​​the input screen (area L in FIG. 4) is provided with a field for entering "variety" information, a field for entering "field" information, a field for entering when to start and stop heating, and a field for entering when to open and close the "side windows." The input screen also has tabs that allow the user to select one of three modes: "automatic prediction," "maturity date prediction," and "manual prediction." The user can change the prediction mode by selecting one of the tabs (see FIGS. 4, 10, and 12).

[0021] The first prediction unit 101 executes the prediction process when the "Automatic prediction" tab is selected on the input screen displayed on the display unit 193 of the user terminal 70 as shown in Fig. 4, a date is entered in the "Harvest date" field, and information on the number of fruits per inflorescence is entered in the "Number of fruits / fruit cluster" field, and then the "Harvest date fruit number prediction" button is pressed. Note that the user enters the date of the day for which they want to predict how many fruits can be harvested in the "Harvest date" field, and enters information on how many fruits will be borne per inflorescence after fruit thinning in the "Number of fruits / fruit cluster" field.

[0022] As shown in FIG. 3, the first prediction unit 101 includes a bud information acquisition unit 32, a flowering date prediction unit 34, a maturity date prediction unit 36, and a mature fruit number prediction unit 38.

[0023] The bud emergence information acquisition unit 32 acquires bud emergence information in the field (information indicating when, on which cluster, and on how many plants buds emerged) from the bud emergence detection server 12. FIG. 5 shows a table for explaining the prediction process by the first prediction unit 101. For example, as shown in FIG. 5, the bud emergence information acquisition unit 32 acquires information on how many plants budded from the terminal cluster and axillary cluster in the field on what date and month. In the example of FIG. 5, for example, information is acquired that the number of buds on the terminal cluster were 10, 30, 50, 30, and 10 from October 15th to October 19th.

[0024] The flowering date prediction unit 34 predicts the flowering date of the nth flower in the fruit cluster (n is a natural number greater than or equal to 1 and less than or equal to the number entered by the user in the "Number of fruits / fruit cluster" field on the input screen) based on the flowering information of each fruit cluster acquired by the flowering information acquisition unit 32.

[0025] Specifically, the flowering date predicting unit 34 predicts the flowering date Df1 of the first flower based on the following formula (1) (referred to as the first model). Df1=(a / Tb q )+Db …(1)

[0026] Here, a means the cumulative temperature from the bud to the first flower opening, and is a constant specific to the variety. q means the average temperature (°C) (predicted value or average value) for the period from the bud emergence date to q days later. Note that q is a value determined for each variety. That is, (a / Tb q ) means the period from budding until the accumulated temperature reaches the temperature at which the first flower blooms. Also, Db means the budding date. The flowering date prediction unit 34 acquires field temperature information (past data on average daily temperatures, forecast data, average year data, etc.) entered by the user from the environmental information management server 14 of Figure 1. The flowering date prediction unit 34 also corrects the temperature information acquired from the environmental information management server 14 based on information on heating and side windows entered by the user on the input screen, and uses the corrected information as Tbq.

[0027] The flowering date predicting unit 34 also predicts the flowering date Df of the mth flower (m is a natural number that is 2 or more and is equal to or less than the number input by the user in the "Number of fruits / fruit clusters" field on the input screen) based on the following formula (2) (referred to as the second model): m Predict. Df m =(c / Tf k )+Df1…(2)

[0028] Here, c means the cumulative temperature from the first flower blooming to the mth flower blooming, and is a constant specific to the variety and floret order. k means the average temperature (°C) (predicted value or average value) for the period from the first flower blooming to k days later. Note that k is a value determined for each variety and floret order. That is, (c / Tf k ) means the period from when the first flower blooms until the accumulated temperature reaches the temperature at which the mth flower blooms. The flowering date prediction unit 34 acquires information on the temperature after the first flower blooms (forecast data and average data) from the environmental information management server 14 in FIG. 1, corrects the acquired information based on information on heating and side windows, and calculates Tf k Use as.

[0029] For example, the flowering date prediction unit 34 predicts the flowering date of the first flower for the terminal fruit cluster (10 plants) that budded on "October 15th" in FIG. 5 using the first model (Equation (1)). FIG. 6 shows the result of the prediction, indicated by symbol A, that the first flower is predicted to flower on "October 22nd." The flowering date prediction unit 34 also predicts the flowering date of the second flower using the second model (Equation (2)). FIG. 6 shows the result of this prediction, indicated by symbol B, that the second flower is predicted to flower on "October 25th." Similarly, the flowering date prediction unit 34 also predicts the flowering dates of the third flower, fourth flower, etc. using the second model. FIG. 6 shows the result of the prediction, indicated by symbols C and D in FIG. 6, that the third flower, fourth flower, etc. are predicted to flower on October 28th, October 31st, etc. (see symbols C and D in FIG. 6). The flowering date predicting unit 34 also predicts the flowering date of the nth flower for the terminal fruit cluster that buds on a day other than October 15th (October 16th to October 19th) in the same manner.

[0030] Returning to Figure 3, the maturity date prediction unit 36 ​​predicts the date on which the fruit of each flower will ripen (maturity date) based on the flowering date of the nth flower predicted by the flowering date prediction unit 34 and the environmental information obtainable from the environmental information management server 14.

[0031] Specifically, the maturity date predicting unit 36 ​​predicts the maturity date Dn of the fruit of the n-th flower based on the following equation (3) (referred to as the third model). Dn = [Number of days when Σθi>θmin] + Df n …(3)

[0032] Here, i means the number of days from the flowering date of the nth flower, and θi means the effective temperature equivalent on the ith day, which is the value expressed by the following formula (4). θi = αi × Ti … (4)

[0033] Here, αi means the effective temperature coefficient at the average temperature on day i, and is expressed by the following equation (5). αi=θmin / (Ti·Di) …(5)

[0034] Here, θmin is a constant specific to the variety, and Ti means the average temperature on day i. Also, Di means the number of days to maturity at the average temperature on day i, and is expressed by the following formula (6). Here, a and b are constants specific to the variety. Di = exp(Ti / (g Ti+h)) …(6)

[0035] Details of this third model are disclosed in "Morishita Shozo and Honda Fujio, 1985: Research on the maturation of forced strawberries. Vegetable Experiment Station Report 8, 59-69." (Internet: https: / / agriknowledge.affrc.go.jp / RN / 2010320379).

[0036] For example, the maturation date prediction unit 36 ​​uses the third model to predict the maturation date (maturity date of the first fruit of the terminal cluster) of the first flower (10 flowers) of the terminal cluster that bloomed on "October 22" in FIG. 6. FIG. 7 shows the prediction result, indicated by symbol E, that the fruit of the first flower is predicted to mature on "November 22." The maturation date prediction unit 36 ​​also uses the third model to predict the maturation date of the fruit (first fruit of the terminal cluster) of the first flower (30, 50, 30, 10 flowers) of the terminal cluster that bloomed from October 23 to 26 in FIG. 6. FIG. 7 shows the prediction result, indicated by symbol F, that the fruit of the first flower is predicted to mature from November 23 to 26. The maturation date prediction unit 36 ​​also uses the third model to predict the maturation dates (maturity dates of the second fruits of the terminal cluster) of the second flowers (10, 30, 50, 30, 10) of the terminal cluster that bloomed from October 26th to 29th in Figure 6. Figure 7 shows the prediction results, which indicate that the second fruits of the terminal cluster are predicted to mature from November 25th to 27th, 29th, and 30th. In this way, the maturation date prediction unit 36 ​​uses the third model to predict the dates on which the fruits of each floret whose flowering date was predicted by the flowering date prediction unit 34 will mature.

[0037] The mature fruit number prediction unit 38 predicts the number of mature fruits for each day using the predicted maturation date of each floret (each fruit) in each fruit cluster, as shown in Fig. 7. Specifically, the mature fruit number prediction unit 38 vertically adds up the number of mature fruits for each day (first fruit in the terminal cluster, second fruit in the terminal cluster, ...) in Fig. 7 to determine the number of mature fruits for each day. In the example of Fig. 7, the number of mature fruits on November 22nd is 10, the number of mature fruits on November 23rd is 30, the number of mature fruits on November 24th is 50, the number of mature fruits on November 25th is 40, the number of mature fruits on November 26th is 40, ...

[0038] The output unit 40 outputs information on the number of mature fruits on the date (harvest date) entered by the user in the "harvest date" field as the prediction result of the mature fruit number prediction unit 38. In addition, when the user presses the "download detailed data" button on the input screen of Figure 4, the output unit 40 uploads (transmits) the tables of Figures 6 and 7 to the user terminal 70.

[0039] The bud emergence information acquisition unit 32 may also acquire the number of buds emerging from the primary axillary fruit clusters, the number of buds emerging from the secondary axillary fruit clusters, etc. as bud emergence information within the field from the bud emergence detection server 12. In this case, as shown by symbol G in Figure 8, the number of buds emerging from the primary axillary fruit clusters and the number of buds emerging from the secondary axillary fruit clusters are managed in a table, and as shown by symbol H, the first model and the second model are used to predict the flowering date of the nth flower of each axillary fruit cluster. In addition, the third model is used to predict the maturity date of the fruit (nth fruit) of the nth flower of each axillary fruit cluster.

[0040] Here, Fig. 9 schematically shows the prediction process by the first prediction unit 101. As shown in Fig. 9, when the first prediction unit 101 acquires the bud emergence date of each fruit cluster, it predicts the flowering date of the first flower of each fruit cluster from a first model using the bud emergence date and environmental information after the bud emergence date (step S101). Furthermore, the first prediction unit 101 predicts the flowering dates of the second flower, third flower, ..., nth flower of each fruit cluster from a second model using the flowering date of the first flower of each fruit cluster and environmental information after the flowering date of the first flower (step S102). Then, the first prediction unit 101 predicts the fruit maturity date of each floret from a third model using the flowering date of each floret and environmental information after the flowering date (step S103). In this way, the first prediction unit 101 predicts the flowering date of each nth flower from the budding date of each fruit cluster, and predicts the maturity date of the nth fruit from the flowering date of each nth flower. This makes it possible to accurately predict the maturity date of each fruit in each fruit cluster.

[0041] Returning to Fig. 3, the second prediction unit 102 executes the prediction process when the "Maturity Date Prediction" tab is selected on the input screen displayed on the display unit 193 of the user terminal 70 as shown in Fig. 10, a date is entered in the "First Flower Opening Date" field, and the "Maturity Date Prediction" button is pressed. Note that the user enters information about the blooming date of the first flower for which they wish to predict the maturity date in the "First Flower Opening Date" field.

[0042] As shown in FIG. 3, the second prediction unit 102 includes a first flowering date acquisition unit 50 and a first flower maturation date prediction unit 52.

[0043] The first flowering date acquisition unit 50 acquires the information entered by the user in each field in range L of FIG. 10, and the date information entered in the "first flowering date" field.

[0044] The first flower maturation date prediction unit 52 predicts the maturation date of the fruit (first fruit) of the first flower from the third model (the above formula (3)) using the date information acquired by the first flower opening date acquisition unit 50 and environmental information on and after that date. The processing details of the first flower maturation date prediction unit 52 are the same as those of the maturation date prediction unit 36. The first flower maturation date prediction unit 52 notifies the output unit 40 of the prediction result. In this case, the output unit 40 outputs (transmits) the maturation date information, "The maturation date is ____ month ____ day," to the user terminal 70 as the prediction result of the first flower maturation date prediction unit 52, and therefore, "The maturation date is ____ month ____ day" is displayed on the input screen of the user terminal 70 (see FIG. 10).

[0045] Fig. 11 schematically shows the prediction process by the second prediction unit 102. As shown by the solid line in Fig. 11, the second prediction unit 102 predicts the maturity date of the fruit of the first flower from the third model using the flowering date of the first flower and environmental information after the flowering date (S103).

[0046] Returning to Figure 3, the third prediction unit 103 executes the prediction process when the "Manual Prediction" tab is selected on the input screen displayed on the display unit 193 of the user terminal 70 as shown in Figure 12, various information is entered on the input screen, and the "Predict number of mature fruits on harvest date" button is pressed.

[0047] Here, within range J on the screen of FIG. 12, the user can input when, on how many plants, and on which trusses the first flowers bloomed. Specifically, range J has columns for "Truss," "Number of Fruits / Truss," "First Flower Bloom Date," and "Number of Plants." The "Truss" column is used to input information about trusses, such as "terminal truss" and "primary axillary truss." The "Number of Fruits / Truss" column is used to input information about how many fruits should be grown on each truss after thinning. The "First Flower Bloom Date" column is used to input information about when the first flowers bloomed. The "Number of Plants" column is used to input information about how many plants in the field bloomed their first flowers on the date input in the "First Flower Bloom Date" column. If the user wants to input information about multiple first flowers blooming, he or she can press the "Enter Next Information" button in FIG. 12. By pressing this button, the information entered within range J is sent to the maturity prediction server 10, and each field within range J is cleared. This allows the user to enter new information into each field within range J. Note that when the user sequentially enters information into range J in FIG. 12, this means manually entering values ​​into the columns of "First flower of terminal fruit cluster," "First flower of primary axillary fruit cluster," etc. in FIG. 6 and FIG. 7.

[0048] After entering all the information the user wishes to input in range J on the screen of Figure 12, the user enters the date for which they wish to predict how many fruits will be harvested in the "Harvest Date" field provided in range K. Then, the user presses the "Harvest Date Mature Fruit Count Prediction" button.

[0049] As shown in FIG. 3, the third prediction unit 103 includes a farm field information acquisition unit 60 and a harvest date mature fruit number prediction unit 62.

[0050] The in-field information acquisition unit 60 acquires the information entered by the user in each field within range L and range J in FIG.

[0051] The harvest date mature fruit number prediction unit 62 predicts the flowering date of the mth flower (m is a natural number greater than or equal to 2 and less than or equal to the number entered in the "Number of fruits / fruit bunch" field) of the same fruit bunch as the first flower from a second model (formula (2)) using the first flower flowering date acquired by the in-field information acquisition unit 60 and environmental information from the first flower flowering date onwards (see Figure 13). Furthermore, the harvest date mature fruit number prediction unit 62 predicts the maturity date of the florets that flowered on each day from a third model (formula (3)) using the flowering date of the nth flower (n is a natural number greater than or equal to 1 and less than or equal to the number entered in the "Number of fruits / fruit bunch" field) and environmental information from the first flower flowering date onwards (see Figure 13). Then, the harvest date mature fruit number prediction unit 62 obtains the number of mature fruits on the date entered in the "harvest date" column from the table in Fig. 13 and notifies the output unit 40 of information on the number of mature fruits on the harvest date, such as "Harvest date: The number of mature fruits on XX month XX day is XX." In this case, the output unit 40 outputs the prediction result notified by the harvest date mature fruit number prediction unit 62 to the user terminal 70. For example, if "November 25th" is entered in the "harvest date" column, the output unit 40 outputs information to the user terminal 70 that "The number of mature fruits on harvest date: November 25th is 40."

[0052] FIG. 14 schematically illustrates the prediction process performed by the third prediction unit 103. As indicated by the solid line in FIG. 14, the third prediction unit 103 predicts the flowering date of the m-th flower (m is 2 or more) from the second model using the flowering date of the first flower and environmental information from the flowering date onward (step S102). Then, the third prediction unit 103 predicts the ripening date of the fruit of each floret from the third model using the flowering date of each floret and environmental information from the flowering date onward (step S103). In this way, the third prediction unit 103 predicts the flowering date of each of the second and subsequent florets from the flowering date of the first flower, and predicts the ripening date of the n-th fruit from the flowering date of each n-th flower. This allows for accurate prediction of the ripening date of each fruit in each fruit cluster.

[0053] (Regarding the processing of the maturity prediction server 10) FIG. 15 is a flowchart showing the processing of the maturity prediction server 10.

[0054] When the processing of FIG. 15 starts, first, in step S10, the input receiving unit 30 determines whether or not the user has pressed the "Predict number of mature fruits on harvest date" button on the input screen (FIG. 4). If the determination in step S10 is affirmative, the processing proceeds to step S12, where the first prediction unit 101 predicts the number of mature fruits on each day using the first to third models based on the bud information acquired from the bud detection server 12. In addition, the output unit 40 outputs information on the number of mature fruits on the harvest date input by the user from the prediction results of the first prediction unit 101 to the user terminal 70. Thereafter, the processing proceeds to step S14.

[0055] When the process proceeds to step S14, the input receiving unit 30 waits until the "download detailed data" button is pressed. If the determination in step S14 is affirmative, the process proceeds to step S16, where the output unit 40 uploads a file of the prediction result to the user terminal 70. Specifically, the output unit 40 transmits the prediction result (detailed data) as shown in FIGS. 6 and 7 to the user terminal 70.

[0056] After step S16, the process proceeds to step S 18. If the determination in step S10 is negative, the process proceeds to step S18 without going through steps S12 to S16.

[0057] In step S18, the input receiving unit 30 determines whether the user has pressed the "Maturity Date Prediction" button on the input screen in Figure 10. If the determination in step S18 is affirmative, the process proceeds to step S20, where the second prediction unit 102 predicts the maturity date of the fruit of the first flower using the third model. The output unit 40 then outputs the prediction result of the second prediction unit 102 to the user terminal 70.

[0058] After the process of step S20 is performed, the process proceeds to step S22. If the determination in step S18 is negative, the process proceeds to step S22 without passing through step S20.

[0059] In step S22, the input receiving unit 30 determines whether the user has pressed the "Predict number of mature fruits on harvest date" button on the input screen of Fig. 12. If the determination in step S22 is affirmative, the process proceeds to step S24, where the third prediction unit 103 predicts the number of mature fruits on the harvest date using the second and third models based on the information entered on the input screen of Fig. 12 (ranges L, J, K). The output unit 40 then outputs the prediction result of the third prediction unit 103 to the user terminal 70.

[0060] After step S24, the process returns to step S 10. If the determination in step S22 is negative, the process returns to step S10 without going through step S24.

[0061] The process of FIG. 15 ends when the user operates the user terminal 70 to close the input screen, for example.

[0062] As described above in detail, in this embodiment, the bud emergence information acquisition unit 32 acquires information on the bud emergence date for a specific cluster of strawberry plants, and the flowering date prediction unit 34 predicts the flowering date of the nth flower (n is a natural number greater than or equal to 1) for the specific cluster of strawberry plants using the acquired bud emergence date information and environmental information from the bud emergence date onward, based on the second model (S101, S102). The maturity date prediction unit 36 ​​then predicts the fruit maturity date for the nth flower using the information on the flowering date for the nth flower and environmental information from the flowering date for the nth flower onward, based on the third model (S103). This allows the strawberry fruit maturity date to be predicted early after planting (for example, before the first flower blooms). Furthermore, by predicting the flowering date of the nth flower based on the information on the bud emergence date and environmental information, and then predicting the maturation date of the nth flower's fruit based on the predicted flowering date of the nth flower and environmental information, the maturation date of each fruit can be predicted specifically in stages, thereby making it possible to accurately predict the maturation date of each fruit.

[0063] Furthermore, in this embodiment, in the process of predicting the flowering date of the nth flower, the flowering date of the first flower is first predicted, and then the flowering date of the mth flower (m is a natural number greater than or equal to 2) is predicted using information on the predicted flowering date of the first flower and environmental information from the flowering date of the first flower onwards. This makes it possible to predict the flowering date of each floret more accurately than when predicting the flowering dates of all florets on the same fruit cluster from the bud emergence date of that fruit cluster.

[0064] In this embodiment, the maturity prediction server 10 predicts the number of fruits that will ripen in the field each day. This allows for early and highly accurate prediction of the harvest volume in the field each day, allowing a tourist strawberry farm to set the number of reservations for visitors to an appropriate value at an early stage. Also, a typical strawberry grower can appropriately adjust the employment of part-time employees.

[0065] The formulas of the first to third models described in the above embodiment are merely examples. The first model may be any other formula as long as it can predict the flowering date of the first flower using information on the flowering date of the first flower and environmental information on the period after the flowering date. The second model may be any other formula as long as it can predict the flowering date of the mth flower (m is a natural number equal to or greater than 2) using information on the flowering date of the first flower and environmental information on the period after the flowering date of the first flower. The third model may be any other formula as long as it can predict the fruit maturation date of the nth flower using information on the flowering date of the nth flower and environmental information on the period after the flowering date of the nth flower. The above embodiment describes a case where temperature is used as environmental information and the flowering date and maturation date are predicted from the first to third models, but this is not limiting. Other environmental information (e.g., solar radiation, CO2 concentration, etc.) may be used as environmental information in addition to or instead of temperature. The first to third models may also be modified according to the type of environmental information used.

[0066] In the above embodiment, the bud emergence information acquired by the bud emergence information acquisition unit 32 of the first prediction unit 101 is based on an image, but the present invention is not limited to this. For example, the bud emergence information acquisition unit 32 may predict the bud emergence date for each plant from biological information about the plant.

[0067] Biological information of the plant includes, for example, the number of endogenous leaves or the number of leaves between fruit clusters (Lb), the number of leaves that appeared after planting or after budding (Lp), the leaf emergence rate (emergence frequency) (Vl), and the date on which the Lpth leaf appeared (Dp).

[0068] In this case, the bud emergence information acquisition unit 32 may acquire biological information of each plant from an image of the plant or information input by the user, and predict the bud emergence date Db of each plant from the following equation (7). Db = (Lb - Lp) / Vl + Dp ... (7)

[0069] The bud emergence information acquisition unit 32 may predict the bud emergence date based on biological information other than the above.

[0070] In the above embodiment, the number of buds (whether to manage one bud or two buds for each cluster) may be input on the input screen. In this case, the prediction process for each cluster described in the above embodiment may be performed for each bud.

[0071] The above processing functions can be realized by a computer. In this case, a program is provided that describes the processing contents of the functions that the processing device should have. By executing the program on a computer, the above processing functions are realized on the computer. The program that describes the processing contents can be recorded on a computer-readable storage medium (excluding carrier waves).

[0072] When distributing a program, it is sold in the form of a portable storage medium on which the program is recorded, such as a DVD (Digital Versatile Disc) or a CD-ROM (Compact Disc Read Only Memory).The program can also be stored in the storage device of a server computer and transferred from the server computer to other computers via a network.

[0073] A computer that executes a program stores, for example, a program recorded on a portable storage medium or a program transferred from a server computer in its own storage device. The computer then reads the program from its own storage device and executes processing in accordance with the program. Note that the computer can also read the program directly from a portable storage medium and execute processing in accordance with that program. The computer can also execute processing in accordance with the program received each time a program is transferred from the server computer.

[0074] The above-described embodiment is a preferred example of the present invention, but the present invention is not limited to this and can be modified in various ways without departing from the spirit of the present invention. [Explanation of symbols]

[0075] 10 Maturity Prediction Server 12 Bud detection server 14 Environmental information management server 32 Bud information acquisition department 34 Flowering Date Prediction Section 36 Maturity Date Prediction Section 38. Mature Fruit Number Prediction Unit 50 First flower flowering date acquisition part 52 First Flower Maturity Date Prediction Section 60 Field information acquisition unit 62 Harvest date mature fruit number prediction section 70 User terminal 101 First Prediction Section 102 Second Prediction Section 103 Third Prediction Section 100 Maturity Prediction System

Claims

1. Acquire information on the flowering date of each floret in each fruit cluster of each strawberry plant planted in a predetermined area; predicting a maturity date of a fruit of each of the florets using information on the flowering date of each of the florets and environmental information after the flowering date of each of the florets; estimating the number of fruits that will mature on each day within the predetermined range based on the predicted fruit maturation date for each floret; The computer executes the processing, In the process of acquiring information on the flowering date of each floret, Obtaining the flowering date of the first flower; A method for predicting strawberry maturity, characterized by predicting the flowering date of the mth flower (m is a natural number greater than or equal to 2) using information on the flowering date of the first flower acquired and environmental information after the flowering date of the first flower.

2. The method for predicting strawberry maturity according to claim 1 , wherein the environmental information includes temperature information.

3. Acquire information on the flowering date of each floret in each fruit cluster of each strawberry plant planted in a predetermined area; predicting a maturity date of a fruit of each of the florets using information on the flowering date of each of the florets and environmental information after the flowering date of each of the florets; estimating the number of fruits that will mature on each day within the predetermined range based on the predicted fruit maturation date for each floret; Have the computer execute the process, In the process of acquiring information on the flowering date of each floret, Obtaining the flowering date of the first flower; A strawberry maturity prediction program characterized by predicting the flowering date of the mth flower (m is a natural number greater than or equal to 2) using information on the flowering date of the first flower acquired and environmental information after the flowering date of the first flower.

Images