JP7385931B2 - Information processing device, information processing method, and program - Google Patents

Description

The present invention relates to an information processing device, an information processing method, and a program.

Conventionally, an information detecting means for acquiring information on cultivated crops, a storage means for storing crop registration information for predicting the growth status of the crops, and a storage means for storing crop registration information based on the information on the crops, A field management system is known that includes a growth prediction means for predicting the growth situation of a field, and a display means for displaying the growth situation predicted by the growth prediction means (Patent Document 1).

Japanese Patent Application Publication No. 2016-49102

In conventional techniques, individual growth models are not created in consideration of influencing factors such as various conditions and disturbance elements, and as a result, it is sometimes not possible to accurately predict the condition of crops.

The present invention has been made in consideration of such circumstances, and one of its objects is to provide an information processing device, an information processing method, and a program that can accurately predict the condition of crops.

The information processing device according to the first aspect of the present invention includes an acquisition unit that acquires information on influencing factors including conditions given to crops and disturbance elements, and a step to the next growth stage based on the influencing factors and the number of growing days. A progress speed derivation unit that derives the progress speed toward the transition for each growth trait index of the crop at least, and a vector in which the integral values of the progress speed from the reference time to the predicted time are arranged, and a state value deriving unit that derives a predicted state vector including a state value for each growth trait index of the crop by multiplying by a connection matrix obtained by subtracting the input arc from the output arc in a transition event.

In the information processing device according to a second aspect of the present invention, in the first aspect, the progression rate derivation unit derives the progression rate regarding the same growth trait index with a different tendency for each growth stage, and defines the usage of the integral value regardless of the growth stage.

In the information processing device according to a third aspect of the present invention, in the first or second aspect, the acquisition unit performs a process of generating information on the influencing factor based on an environmental measurement value.

In the information processing device according to a fourth aspect of the present invention, in the first to third aspects, the acquisition unit changes the predicted state while changing a processing method for generating information on the influencing factor based on the environmental measurement value. The present invention further includes an evaluation unit that derives a vector and evaluates a processing method for generating information on the influencing factor based on the degree of applicability of the predicted state vector to the actual crop.

The information processing device according to a fifth aspect of the present invention further includes a display control unit that causes a display device to display an image that is a graph of the relationship among at least the influencing factor, the transition event, and the growth trait index. .

The information processing device according to the sixth aspect of the present invention further includes a display control unit that causes a display device to display an image in which changes in the growth trait index are graphed.

In the information processing method according to the seventh aspect of the present invention, a computer acquires information on influencing factors including conditions given to crops and disturbance elements, and proceeds to the next growth stage based on the influencing factors and the number of growing days. The rate of progress toward the transition of the crop is derived for at least each growth trait index of the crop, and the output arc at the transition event of the growth stage is created in a vector in which the integral values of the rate of progress from the reference time to the predicted time are arranged. By multiplying by a connection matrix obtained by subtracting the input arc from , a predicted state vector including state values for each growth trait index of the crop is derived.

A program according to an eighth aspect of the present invention causes a computer to acquire information on influencing factors including conditions given to crops and disturbance elements, and determines the transition to the next growth stage based on the influencing factors and the number of growing days. The rate of progress towards the crop is derived at least for each growth trait index of the crop, and inputted from the output arc at the transition event of the growth stage into a vector in which integral values of the rate of progress from the reference time to the predicted time are arranged. By multiplying the connection matrix by subtracting the arc, a predicted state vector including the state value for each growth trait index of the crop is derived.

According to each of the above aspects, the condition of crops can be predicted with high accuracy.

FIG. 1 is a diagram illustrating an example of a configuration of an information processing device 100 and processing targets according to an embodiment. FIG. 2 is a diagram for explaining the functions of an acquisition unit 110. FIG. It is a diagram showing the growth process of wheat. FIG. 3 is a diagram for explaining the functions of a traveling speed deriving section 120 and a state value deriving section 130. It is a figure which shows the result of calculating the state of t=0, ie, the growth start day, by a model. FIG. 7 is a diagram showing the results of calculating the state when t=5.5 using a model. FIG. 6 is a diagram showing the results of calculating the state when t=6 using a model. FIG. 7 is a diagram showing the result of calculating the state when t=30 using a model. FIG. 3 is a diagram showing the overall result of calculating the state when t=30 using a model. FIG. 7 is a diagram showing the overall results of calculation using a model of a state in which damage caused by birds and beasts occurs at t=33. It is a diagram showing in a graph the results of calculations performed until the maturity of crops (t=166), reflecting the occurrence of damage caused by birds and animals.

DESCRIPTION OF THE PREFERRED EMBODIMENTS Embodiments of an information processing apparatus, an information processing method, and a program according to the present invention will be described below with reference to the drawings.

FIG. 1 is a diagram illustrating an example of the configuration and processing targets of an information processing apparatus 100 according to an embodiment. The information processing device 100 is, for example, a device that derives state values for each crop growth trait index for each individual plant in a target field on cultivated land in a natural environment. The information processing device 100 includes, for example, an acquisition section 110, a progress speed derivation section 120, a state value derivation section 130, an evaluation section 140, and a display control section 150. These components are realized by, for example, a hardware processor such as a CPU (Central Processing Unit) executing a program (software). Some or all of these components are hardware (circuit parts) such as LSI (Large Scale Integration), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), and GPU (Graphics Processing Unit). (including circuitry), or may be realized by collaboration between software and hardware. The program may be stored in advance in a storage device (a storage device with a non-transitory storage medium) such as an HDD (Hard Disk Drive) or flash memory, or may be stored in a removable storage device such as a DVD or CD-ROM. It may be stored in a medium (non-transitory storage medium), and installed in the storage device by loading the storage medium into a drive device.

The functions of each part of the information processing device 100 will be explained below. FIG. 2 is a diagram for explaining the functions of the acquisition unit 110.

The acquisition unit 110 acquires information on influencing factors given to crops. The influencing factor is input information given to the process of calculating the traveling speed, which will be described later. The influencing factors include those generated by the acquisition unit 110 based on environmental measurement values and those that indicate the occurrence of an event. Regarding the former, the acquisition unit 110 generates information on environmental factors from the environmental measurement values. Environmental measurements include, for example, the cumulative temperature obtained from time-series temperature data, the amount of sunlight obtained from time-series sunlight data, the amount of water obtained from time-series water supply data, and the amount of oxygen supply obtained from time-series data. This is the amount of oxygen required and the cumulative temperature amount determined from time-series fertilization data.

The acquisition unit 110 generates a temperature condition, which is one of the influencing factors, based on the cumulative temperature amount. The acquisition unit 110 generates a sunshine condition, which is one of the influencing factors, based on the amount of sunlight. The acquisition unit 110 generates water conditions, which are one of the influencing factors, based on the amount of water. The acquisition unit 110 generates an oxygen condition, which is one of the influencing factors, based on the amount of oxygen. The acquisition unit 110 generates fertilizer conditions, which are one of the influencing factors, based on the amount of fertilizer. Each of the temperature conditions, sunlight conditions, water conditions, oxygen conditions, and fertilizer conditions is any form of information that can be provided to the progress rate calculation process. The acquisition unit 110 can change the generation method of these influencing factors by, for example, changing parameters.

Further, influencing factors indicating the occurrence status of an event include the occurrence status of pests and diseases, the status of damage caused by birds and animals, human involvement (control) conditions, the status of weed occurrence, and others. These influencing factors are information represented by, for example, 1 indicating occurrence, zero indicating non-occurrence, etc.

The environmental factors obtained in this way are used for processing by the progress speed deriving unit 120. In the figure, circles represent conditions or states caused by the crop's own growth conditions or external factors, and black dots within the circles represent one condition or state. Environmental factors are those that influence transition events. Transition events include, for example, germination, tillering, heading, and ripening. The states between transition events are referred to as growth stages. In FIG. 2, post-germination and post-tillering (before heading) are shown as examples of growth stages. When a transition event arrives, a growth stage transitions to the next growth stage.

Below, wheat will be explained as an example of a crop. FIG. 3 is a diagram showing the growth process of wheat. Wheat reaches maturity through the growth stages of germination, tillering, heading, and ripening. At each growth stage, conditions such as peak tillering, ear opening, flowering, and yellow fever occur. From FIG. 4 onwards, the functions of each part will be explained on the premise that the model is applied to wheat. Note that the present invention is applicable not only to wheat but also to any crops or plants.

FIG. 4 is a diagram for explaining the functions of the advancing speed deriving section 120 and the state value deriving section 130. The progress rate deriving unit 120 derives, based on the influencing factors and the number of growing days, the rate of progress toward transition to the next growth stage for at least each growth trait index of the crop. Growth trait indicators include, for example, plant height, number of leaves, number of stems, and number of panicles. Growth trait indicators are represented by double circles in FIG. Some growth trait indicators, such as the number of panicles, appear after reaching a specific growth stage.

The state value derivation unit 130 multiplies a vector in which the integral values of the progress speed from the reference time point (for example, the time of sowing seeds) to the predicted time point are arranged by a connection matrix A obtained by subtracting the input arc from the output arc in the transition event of the growth stage. By doing so, a predicted state vector including state values for each growth trait index of the crop is derived.

Hereinafter, the functions of the advancing speed deriving section 120 and the state value deriving section 130 will be explained while showing a simpler example and calculation results. In the following description, e represents an influencing factor, t represents the number of growing days, j represents a growth stage, and k represents an identifier of a growth trait index. 5 to 8 are diagrams illustrating the processing of the advancing speed deriving section 120 and the state value deriving section 130. In the example of these figures, there are two transition events, T1 and T2. Furthermore, in order to simplify the explanation, the growth stage will be explained up to after tillering (before heading), and the growth trait index will be focused on plant height, but the same can be applied to other parts. FIG. 5 is a diagram showing the results of calculation using a model for the state of t=0, that is, the growth start date.

The switching days of the transition event are predetermined, and it is defined that T1 will occur after 6 days and T2 will occur after 120 days. The number of switching days may be variable or may be an appropriate value determined from experience for the crop in question. In this case, the traveling speed derived by the traveling speed deriving unit 120 is expressed by the following formula. In the formula, E (e, t, j, k) is a function or algorithm that derives the progress rate based on the influencing factor e, the number of growing days t, the growing stage j, and the growth trait index k. E(e,t,j,k) is, for example, determined from experience regarding the crop in question.

A connection matrix (connection matrix) A used by the state value deriving unit 130 regarding the models shown in FIGS. 5 to 8 is expressed by the following equation. The connectivity matrix A is the output arc O minus the input arc I at the growth stage transition event. The input arc is a matrix in which vectors are arranged for each transition event, with vectors defined as 1 for states that are prior to a transition event and that affect the transition event, and zero for states that do not. An output arc is a matrix in which vectors are arranged for each transition event, with vectors defined as 1 for states that act immediately after the transition event and zero for other states.

If the processing performed by the advancing speed deriving unit 120 and the state value deriving unit 130 is expressed in a general formula, it will be as shown in the following formula. where S ₀ is the predicted state vector at the initial state, S _t is the predicted state vector at growing days t, and u is the time increment. The elements of S ₀ and S _t include at least a growth trait index, for example, {P ₁ (t), P ₂ (t), P ₃ (t), P _e (t), P _2-1 (t ),P _3-1 (t)} Represented by ^T. In this way, the progress rate derivation unit 120 derives the progress rate regarding the same growth trait index with different tendencies for each growth stage, and the connection matrix A is configured to calculate the usage of integral values (selecting and adding This defines whether the effect is to be applied in a positive or negative manner.

FIG. 6 is a diagram showing the results of calculating the state when t=5.5 using a model. When t=5.5, 1.0 is calculated as _P2-1 , that is, the growth trait index "plant height" of the crop whose growth stage is "post-germination." The calculation formula in this case is expressed by the following formula.

FIG. 7 is a diagram showing the result of calculating the state when t=6 using a model. When t=6, _P2-1 , that is, 1.2 is calculated as the growth trait index "plant height" of the crop whose growth stage is "post-germination." The calculation formula in this case is expressed by the following formula.

FIG. 8 is a diagram showing the result of calculating the state when t=30 using a model. When t=30, 11.5 is calculated as the growth trait index "plant height" of _P3-1 , that is, the crop whose growth stage is "post-tillering (before heading)". The calculation formula in this case is expressed by the following formula. Since the transition event (tillering) occurred when the transition conditions were satisfied at t=6, the growth trait index for t=6 and thereafter is determined based on v ₂ (p _3-1 ).

By performing calculations as described above, each growth trait index can be determined for any number of growth days.

The entire growth stage will be explained again. FIG. 9 is a diagram showing the overall result of calculating the state when t=30 using a model. As shown in the figure, not only the plant height but also the number of leaves and stems are calculated using the same method.

Here, we will explain a method that reflects influencing factors such as the occurrence of pests and diseases, damage caused by birds and animals, human involvement (control) conditions, and weed occurrence. For example, assuming that damage caused by birds and animals occurs at time t=33, the acquisition unit 110 acquires, for example, actual measured values, predetermined post-damage growth trait values, or damage levels with respect to a predetermined growth trait index. Influence factors are defined by calculating them from FIG. 10 is a diagram generally showing the results of calculation using a model of the state in which damage caused by birds and beasts occurs at t=33. As shown in the figure, it can be seen that the values of plant height and number of leaves have decreased from the state when t=30.

FIG. 11 is a graph showing the results of calculations performed until crop maturity (t=166), reflecting the occurrence of damage caused by birds and animals. As shown in the figure, it can be seen that the plant height and number of leaves that were reduced due to damage at t=33 have since recovered, and the crop is growing.

Returning to FIG. 1, the acquisition unit 110 derives a predicted state vector while changing the processing method for generating information on influencing factors based on environmental measurement values. The evaluation unit 140 evaluates the processing method for generating influencing factor information based on the degree of applicability of the predicted state vector to the actual crop. Then, the evaluation unit 140 extracts a predetermined number of models (methods of influencing factors) that are well-applicable (highly similar) to the target field and predicts the future state of the community. The predetermined number of models with good fit are those within a certain decision frame range from the maximum evaluation value (for example, within the range of 90% to 100% of the maximum evaluation value). The evaluation unit 140 may perform the evaluation using, for example, a genetic algorithm, a heuristic method such as an annealing method, a Monte Carlo method, or the like. Furthermore, the evaluation unit 140 may determine the amount of fertilizer applied to increase the crop yield based on the crop growth amount or activation index based on the derivation result of the state value derivation unit 130, or may determine the amount of fertilizer applied to increase the crop yield based on the crop growth amount or activation index, or prevent pest damage. It can be used for forecasting, determining the optimal number of plants to be planted at each sowing period, and determining fertilization management to prioritize the quality and grade of the harvest.

For example, as shown in FIGS. 4 to 10, the display control unit 150 causes the display device 200 to display an image in which the relationships among at least influencing factors, transition events, and growth trait indicators are graphed. Further, as shown in FIG. 11, the display control unit 150 may cause the display device 200 to display an image that is a graph of changes in the growth trait index, which is generated by the functions of each unit described above. The display device 200 may be attached to the information processing device 100, or may be a device that provides images from the information processing device 100 via a network such as the Internet or a LAN (Local Area Network) (for example, a personal computer). (computers, tablet terminals, smartphones, etc.).

According to the embodiment described above, the acquisition unit 110 acquires information on influencing factors including conditions given to crops and disturbance elements, and the acquisition unit 110 acquires information on influencing factors including conditions given to crops and disturbance elements, and information on transition to the next growth stage based on the influencing factors and the number of growing days. A progress speed derivation unit 120 derives the progress speed for each growth trait index of the crop at least, and a vector in which integral values of the progress speed from the reference time point to the predicted time point are arranged from the output arc at the transition event of the growth stage. A state value deriving unit 130 that derives a predicted state vector including a state value for each growth trait index of the crop by multiplying by a connection matrix obtained by subtracting the input arc, thereby accurately predicting the state of the crop. be able to.

Although the mode for implementing the present invention has been described above using embodiments, the present invention is not limited to these embodiments in any way, and various modifications and substitutions can be made without departing from the gist of the present invention. can be added.

100 Information processing device 110 Acquisition unit 120 Progressing speed derivation unit 130 State value derivation unit 140 Evaluation unit 150 Display control unit 200 Display device

Claims (8)

an acquisition unit that acquires information on influencing factors including conditions and disturbance factors given to crops;
a progress rate derivation unit that derives a progress rate toward transition to the next growth stage for at least each growth trait index of the crop, based on the influencing factors and the number of growing days;
The state of each growth trait index of the crop can be determined by multiplying a vector listing the integral values of the progress speed from the reference time to the predicted time by a connection matrix obtained by subtracting the input arc from the output arc at the transition event of the growth stage. a state value derivation unit that derives a predicted state vector including the value;
An information processing device comprising: The progression rate derivation unit derives the progression rate regarding the same growth trait index with different trends for each growth stage,
The connection matrix defines the usage of the integral value regardless of the growth stage,
The information processing device according to claim 1. The acquisition unit performs a process of generating information on the influencing factor based on environmental measurement values.
The information processing device according to claim 1 or 2. The acquisition unit derives a predicted state vector while changing a processing method for generating information on the influencing factor based on the environmental measurement value,
further comprising an evaluation unit that evaluates a processing method for generating information on the influencing factors based on the degree of applicability of the predicted state vector to the actual crop;
An information processing device according to any one of claims 1 to 3. further comprising a display control unit that causes a display device to display an image that is a graph of the relationship between at least the influencing factor, the transition event, and the growth trait index;
An information processing device according to any one of claims 1 to 4. further comprising a display control unit that causes the display device to display an image in which changes in the growth trait index are graphed;
An information processing device according to any one of claims 1 to 5. The computer is
Obtain information on influencing factors including conditions and disturbance factors given to crops,
Based on the influencing factors and the number of growing days, the rate of progress toward transition to the next growth stage is derived for at least each growth trait index of the crop,
The state of each growth trait index of the crop can be determined by multiplying a vector listing the integral values of the progress speed from the reference time to the predicted time by a connection matrix obtained by subtracting the input arc from the output arc at the transition event of the growth stage. Derive a predicted state vector containing the values,
Information processing method. to the computer,
Obtain information on influencing factors including conditions and disturbance factors given to crops,
Based on the influencing factors and the number of growing days, the rate of progress toward transition to the next growth stage is derived for at least each growth trait index of the crop;
The state of each growth trait index of the crop can be determined by multiplying a vector listing the integral values of the progress speed from the reference time to the predicted time by a connection matrix obtained by subtracting the input arc from the output arc at the transition event of the growth stage. Derive a predicted state vector containing the values,
program.

Images