JP6704148B1 - Crop yield forecast program and crop quality forecast program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a crop yield forecasting program and a crop quality forecasting program capable of accurately forecasting the yield and quality of a crop currently being cultivated. SOLUTION: In a crop yield prediction program for predicting crop yield, a combination of reference image information of an image of a growing crop and reference soil information on the soil on which the crop is planted, A relevance acquisition step for acquiring in advance three or more levels of relevance with the harvest amount when the above-mentioned growing crop is harvested for a combination, and a new growing crop when predicting a new crop yield While acquiring the image information by shooting the image of, the information acquisition step of acquiring the soil information regarding the soil on which the agricultural product is cultivated, and the degree of association acquired in the degree of association acquisition step is referred to, and the information acquisition is performed. It is characterized in that the computer is caused to execute a prediction step of predicting a harvest amount of a newly grown agricultural product based on the image information and the soil information acquired through the step. [Selection diagram] Fig. 3

Description

The present invention relates to a crop yield prediction program and a crop quality prediction program for automatically predicting a crop yield predicting a crop yield.

With the aging of the agricultural population, the decrease in the number of veteran farmers with agricultural work skills, and the shortage of young farmers who pass on the skills, has become a problem in recent years. Under such circumstances, the idea of assisting the work plan of agricultural work with artificial intelligence has been proposed instead of handing down skills to veteran farmers.

In order to assist the work plan of agricultural work with artificial intelligence, it is necessary to predict the future yield and quality of the agricultural products under cultivation. If this yield and quality can be predicted, it can be fed back to the work plan for further improvement. However, until now, there has been no particular proposal for a technique for predicting the yield and quality of this agricultural product with high accuracy.

Therefore, the present invention has been devised in view of the above-described problems, and an object thereof is to harvest crops capable of highly accurately predicting the yield and quality of the crops currently being cultivated. To provide a quantity forecasting program and a crop quality forecasting program.

The crop yield prediction program according to the present invention is a crop yield prediction program that predicts the crop yield of a crop, from an image obtained by capturing an image of a crop being grown, the growth status of the crop, the damage caused by pests on the crop, and the crop. Reference image information for extracting any of the diseases that occurred in the reference information, and the reference information acquisition step of acquiring the reference soil information reflecting the survey results of the components of the soil on which the crop is planted, and the above-mentioned reference The degree of association between the combination of the reference image information and the reference soil information acquired in the operation information acquisition step and the harvest amount when the above-mentioned growing crop is harvested for the combination is acquired. By taking an image of the crop that is being newly cultivated in the step of obtaining the degree of association and newly predicting the yield of the crop, the growth status of the above crop, the damage caused by the pests on the crop, and the disease caused in the crop While acquiring the image information extracted any one of, the information acquisition step of acquiring the soil information regarding the soil where the agricultural product is cultivated, and the association degree acquired in the association degree acquisition step is referred to, and the information acquisition step It is characterized in that the computer is caused to execute a prediction step of predicting the yield of the agricultural product that is being newly cultivated, based on the image information and the soil information acquired through.

The crop yield prediction program according to the present invention is a crop yield prediction program that predicts the crop yield of a crop, from an image obtained by capturing an image of a crop being grown, the growth status of the crop, the damage caused by pests on the crop, and the crop. Reference information acquisition step for acquiring reference image information for extracting any of the diseases that have occurred in the above, and reference external environment information for detecting a disaster situation including floods and droughts in the growing process of the crop, and the above-mentioned reference The degree of association between the combination of the reference image information and the reference soil information acquired in the operation information acquisition step and the harvest amount when the above-mentioned growing crop is harvested for the combination is acquired. By taking an image of the crop that is being newly cultivated in the step of obtaining the degree of association and newly predicting the yield of the crop, the growth status of the above crop, the damage caused by the pests on the crop, and the disease caused in the crop Refer to the degree of association obtained in the step of obtaining image information that extracts any one of the above, and the external environment information regarding the disaster situation including flood and drought in the cultivation process of the crop, and the degree of association acquired in the step of obtaining the degree of association described above. Then, the computer is caused to execute a predicting step of predicting the yield of the agricultural product that is being newly grown, based on the image information and the external environment information acquired through the information acquiring step.

The crop yield prediction program according to the present invention is a crop yield prediction program that predicts the crop yield of a crop, from an image obtained by capturing an image of a crop being grown, the growth status of the crop, the damage caused by pests on the crop, and the crop. Image information for reference that has extracted any of the diseases that have occurred in the reference information, and a reference information acquisition step of acquiring reference history information regarding the history of the agricultural work actually performed on the agricultural product, and the reference information acquisition step. The association degree acquisition step of obtaining a degree of association of three or more levels between the combination of the reference image information and the reference history information acquired in And, when newly predicting the yield of crops, by taking an image of the crops that are being newly cultivated, any of the growth status of the crops, damage caused by pests on the crops, and diseases caused on the crops can be determined. In addition to acquiring the extracted image information, refer to the information acquisition step that acquires history information regarding the history of farm work actually performed on the farm product in the growing process of the farm product, and the degree of association acquired in the association degree acquisition step. Then, the computer is caused to execute a predicting step of predicting the yield of the agricultural product that is being newly grown based on the image information and the history information acquired through the information acquiring step.

The crop quality prediction program according to the present invention is a crop quality prediction program for predicting the quality of crops, from an image of a crop being grown, from the image of the crop being grown, the growth status of the crop, the damage caused by pests on the crop, and the crop. Reference information acquisition step for acquiring reference image information that extracts any of the diseases and reference soil information that reflects the survey results of the components of the soil in which the crop is planted, and the reference information acquisition The association degree obtaining step of obtaining a degree of association of three or more between the combination of the reference image information and the reference soil information obtained in step and the quality of the harvested agricultural crop for the combination. And when newly predicting the quality of crops, by picking up an image of the crops that are being newly cultivated, it is possible to extract any of the growth status of the above crops, damage of pests that have occurred on the crops, and diseases that have occurred on the crops. While acquiring the image information, the information acquisition step of acquiring the soil information regarding the soil on which the agricultural product is cultivated, and the association degree acquired in the association degree acquisition step are referred to and acquired through the information acquisition step. It is characterized in that the computer is caused to execute a prediction step of predicting the quality of the agricultural product which is being newly grown, based on the image information and the soil information.

The crop quality prediction program according to the present invention is a crop quality prediction program for predicting the quality of crops, from an image of a crop being grown, from the image of the crop being grown, the growth status of the crop, the damage caused by pests on the crop, and the crop. Reference information acquisition step of acquiring reference image information for extracting any of the diseases and reference external environment information for detecting a disaster situation including flood and drought in the growing process of the crop, and acquisition of the reference information The association degree obtaining step of obtaining a degree of association of three or more between the combination of the reference image information and the reference soil information obtained in step and the quality of the harvested agricultural crop for the combination. And when newly predicting the quality of crops, by picking up an image of the crops that are being newly cultivated, it is possible to extract any of the growth status of the above crops, damage of pests that have occurred on the crops, and diseases that have occurred on the crops. The information acquisition step that acquires the external image information related to the disaster situation including the flood and drought in the growing process of the agricultural products and the association degree acquired in the association degree acquisition step, and obtains the information described above. It is characterized in that the computer is caused to execute a prediction step of predicting the quality of the agricultural product which is being newly grown, based on the image information obtained through the step and the external environment information.

The crop quality prediction program according to the present invention is a crop quality prediction program for predicting the quality of crops, from an image of a crop being grown, from the image of the crop being grown, the growth status of the crop, the damage caused by pests on the crop, and the crop. The reference image information for extracting any of the diseases and the reference information acquisition step for acquiring the reference history information regarding the history of the farm work actually performed on the crop, and the reference information acquisition step. The association degree acquisition step of obtaining a degree of association of three or more levels between the combination of the reference image information and the reference history information and the quality at the time of harvesting the agricultural product under cultivation for the combination, When newly predicting the quality, by taking an image of the crop that is being newly cultivated, it is possible to obtain image information by extracting any of the growth status of the crop, the damage caused by pests on the crop, and the disease that has occurred on the crop. While acquiring the information, refer to the information acquisition step for acquiring history information regarding the history of farm work actually performed on the agricultural product in the process of growing the agricultural product, and the degree of association acquired in the association degree acquisition step, to acquire the information described above. It is characterized in that the computer is caused to execute a prediction step of predicting the quality of a crop that is being newly grown, based on the image information and the history information acquired through the step.

It is possible to predict with high accuracy the yield and quality of agricultural products that are currently being raised.

It is a block diagram showing the whole composition of the system to which the present invention is applied. It is a figure which shows the specific structural example of a prediction apparatus. It is a figure for demonstrating operation|movement of this invention. It is a figure for demonstrating operation|movement of this invention. It is a figure for demonstrating operation|movement of this invention. It is a figure for demonstrating operation|movement of this invention. It is a figure for demonstrating operation|movement of this invention. It is a figure for demonstrating operation|movement of this invention. It is a figure for demonstrating operation|movement of this invention. It is a figure for demonstrating operation|movement of this invention.

Hereinafter, a crop yield prediction program to which the present invention is applied will be described in detail with reference to the drawings.

FIG. 1 is a block diagram showing the overall configuration of a crop yield prediction system 1 in which a crop crop forecast program according to the present invention is implemented. The yield prediction system 1 includes an information acquisition unit 9, a prediction device 2 connected to the information acquisition unit 9, and a database 3 connected to the prediction device 2.

The information acquisition unit 9 is a device for a person who utilizes the system to input various commands and information, and is specifically configured by a keyboard, buttons, touch panel, mouse, switch and the like. The information acquisition unit 9 is not limited to a device for inputting text information, but may be configured by a device such as a microphone capable of detecting voice and converting the voice into text information. In addition, the information acquisition unit 9 may be configured as an imaging device that can capture an image of a camera or the like. The information acquisition unit 9 may be composed of a scanner having a function of recognizing a character string from a paper medium document. The information acquisition unit 9 may be integrated with the prediction device 2 described later. The information acquisition unit 9 outputs the detected information to the prediction device 2. Further, it may be composed of various sensors for measuring the external environment, such as a temperature sensor, a humidity sensor, and a rainfall sensor.

The database 3 stores various kinds of information about past farming cultivation. For example, image data that captures the growth status of crops, image data that indicates the damage status of pests on crops and the damage status of crop diseases, soil data that analyzes the soil on which the crops are cultivated, and the external environment detected during the growing process of the crops. Data (for example, data on weather conditions such as the amount of solar radiation, temperature, humidity, wind direction, and rainfall, data on disaster conditions such as typhoons, floods, droughts, and sunshine), data on past agricultural work history, data on the growing season of crops, Data on the types of crops are recorded.

The prediction device 2 is composed of, for example, an electronic device such as a personal computer (PC) or the like, but is also embodied in any other electronic device such as a mobile phone, a smart phone, a tablet terminal, a wearable terminal, etc. in addition to the PC. It may be converted into one. By obtaining the search solution by the prediction device 2, the user can highly accurately predict the harvest amount and quality of the agricultural product currently being cultivated.

FIG. 2 shows a specific configuration example of the prediction device 2. The prediction device 2 performs wired communication or wireless communication with a control unit 24 for controlling the entire prediction device 2 and an operation unit 25 for inputting various control commands via operation buttons, a keyboard or the like. A communication unit 26, a determination unit 27 that makes various determinations, and a storage unit 28, which is represented by a hard disk or the like and stores a program for performing a search to be executed, are connected to the internal bus 21. .. Further, the internal bus 21 is connected to a display unit 23 as a monitor that actually displays information.

The control unit 24 is a so-called central control unit for controlling each component installed in the prediction device 2 by transmitting a control signal via the internal bus 21. The control unit 24 also transmits various control commands via the internal bus 21 in response to an operation via the operation unit 25.

The operation unit 25 is embodied by a keyboard or a touch panel, and an execution command for executing a program is input by the user. When the user inputs the execution command, the operation unit 25 notifies the control unit 24 of the input. The control unit 24 that has received this notification will start the determination unit 27 and will execute the desired processing operation in cooperation with each component. The operation unit 25 may be embodied as the information acquisition unit 9 described above.

The determination unit 27 is responsible for determining the yield of agricultural products and the quality of agricultural products. The determination unit 27 reads various information stored in the storage unit 28 and various information stored in the database 3 as necessary information when executing the estimation operation. The determination unit 27 may be controlled by artificial intelligence. This artificial intelligence may be based on any known artificial intelligence technology.

The display unit 23 is configured by a graphic controller that creates a display image under the control of the control unit 24. The display unit 23 is realized by, for example, a liquid crystal display (LCD) or the like.

When the storage unit 28 is configured by a hard disk, under the control of the control unit 24, predetermined information is written to each address, and this information is read as necessary. The storage unit 28 also stores a program for executing the present invention. This program is read and executed by the control unit 24.

The operation of the crop yield prediction system 1 having the above-described configuration will be described.

In the harvest prediction system 1, for example, as shown in FIG. 3, it is premised that a combination of reference image information and reference soil information is formed. The reference image information is an image of a farm product in the growing process taken by a camera. The photographed image of the agricultural product may be one that is sequentially photographed in time series from the stage of sowing and seedling production to the harvest. In addition, the photographed image of the crop may be composed of an image of the photographing range that comprehensively captures the field or paddy field, and also includes an image of the leaves, stems, fruits, etc. of the crop in the field or paddy field at a close range. .. Further, the captured image may be one captured through an unmanned aerial vehicle such as a drone, or may be one captured by a camera installed on the ground. With such a camera, it is possible to detect the growth status of crops, damage of pests caused by crops, diseases caused by crops, and the like. By the way, as for this reference image information, a raw image taken by a camera may be directly acquired as image information, or a well-known deep learning technique may be used to extract only a characteristic part of the image. This may be used as reference image information.

In addition, the reference soil information includes all information regarding the soil on which the crop is planted. Examples of this reference soil information include soil components, pH, water content, temperature, and the like. The result obtained by actually collecting the soil component and analyzing it based on a chemical analysis method may be used, or the data detected by a well-known soil sensor may be used. Alternatively, an image obtained by capturing the soil with a camera, or a well-known deep learning technique may be used to extract only the characteristic portion of the image.

In the example of FIG. 3, it is assumed that the input data is, for example, reference image information P11 to P13 and reference soil information P14 to 17. A combination of the reference image information as such input data and the reference soil information is the intermediate node shown in FIG. Each intermediate node is further connected to an output. In this output, the harvest amount is displayed as an output solution.

Each combination (intermediate node) of the reference image information and the reference soil information is associated with each other through three or more levels of association with the crop yield of the agricultural product as the output solution. The reference image information and the reference soil information are arranged on the left side through this degree of association, and the yields of each crop are arranged on the right side through the degree of association. The degree of association indicates a degree of which crop yield is highly relevant to the reference image information and the reference soil information arranged on the left side. In other words, the degree of association is an index indicating which crops of each reference image information and reference soil information are likely to be associated with the crop yield, and the reference image information and the reference soil information. It shows the accuracy in selecting the most probable crop yield from. In the example of FIG. 3, w13 to w22 are shown as the degree of association. These w13 to w22 are shown in 10 levels as shown in Table 1 below, and the closer to 10 points, the higher the degree of relation between each combination as an intermediate node and the crop yield of output as an output. On the contrary, the closer to one point, the lower the degree of association between each combination as an intermediate node and the crop yield of output as an output.

The prediction device 2 acquires in advance the association degrees w13 to w22 of three or more stages shown in FIG. In other words, the prediction device 2 accumulates past data, which is the reference image information, the reference soil information, and the crop yield of the crop in that case, in determining the actual search solution. By analyzing these, the association degree shown in FIG. 3 is created.

For example, it is assumed that the reference image information P11 reflects the state of crops damaged by outsourcing. At this time, when the component of the soil in which the agricultural product was actually planted was investigated, and when it was “pH●●, component ○×” corresponding to the reference soil information P14, the actual agricultural product was harvested in the previous data. As a result of the follow-up survey up to, the amount of harvest was extracted. Although the harvest amount may be configured in any unit, for example, the harvest amount of the agricultural product per unit area may be indicated by weight (ton).

This analysis may be performed by artificial intelligence. In such a case, for example, when the reference image information P11 and the reference soil information P16 "pH ▲ ▲ component □○", the actual yield of the crop is analyzed from past data. If there are many cases where the harvest amount is 9 tons, the degree of association that leads to this harvest amount of 9 tons is set higher, and there are many cases where the harvest amount is 3 tons and there are few cases where the harvest amount is 9 tons. For this, the degree of association leading to a harvest of 3 tons is set high, and the degree of association leading to a harvest of 9 tons is set low. For example, in the example of the intermediate node 61a, the outputs of the harvest amount of 9 tons and the harvest amount of 3 tons are linked. The degree of association of w14 leading to is set to two points.

Further, the degree of association shown in FIG. 3 may be composed of nodes of a neural network in artificial intelligence. That is, the weighting coefficient for the output of the node of this neural network corresponds to the above-mentioned degree of association. Further, it is not limited to the neural network, and may be composed of any decision-making factor that constitutes artificial intelligence.

In the example of the degree of association shown in FIG. 3, the node 61b is a node of a combination of the reference image information P11 and the reference soil information P14, and the degree of association of the harvest amount of 6 tons is w15 and the harvest amount of 1 ton. The degree of association is w16. The node 61c is a node that is a combination of the reference soil information P15 and P17 with respect to the reference image information P12, and the degree of association of the harvest amount of 3 tons is w17 and the degree of association of the harvest amount of 6 tons is w18. ..

Such a degree of association is the learned data, which is the artificial intelligence. After such learned data is created, when actually determining a new crop yield from now on, the crop yield is determined using the learned data described above. In such a case, the image information is newly acquired and the soil information is acquired.

For the image information to be newly acquired, an image is captured by the camera by the information acquisition unit 9 described above. This shooting is aimed at agricultural products that are about to be newly raised.

The acquisition of the soil information is the soil on which the crop to be newly grown is actually cultivated, and the acquisition method is the same as the acquisition of the reference soil information described above.

Based on the image information newly acquired in this way and the soil information, the harvest amount of the agricultural product that actually acquired the new image information and soil information is predicted. In this case, the degree of association shown in FIG. 3 (Table 1) acquired in advance is referred to. For example, when the newly acquired image information is the same as or similar to P12 and the soil information is P17, the node 61d is associated through the association degree, and this node is 61d is associated with "harvest amount 6 tons" w19 and "harvest amount 7 tons" with association degree w20. In such a case, "harvest amount 6 tons" having a higher degree of association is selected as the optimum solution. However, it is not essential to select the one having the highest degree of association as the optimal solution, and the "harvest amount 7 tons" which has the degree of association but the degree of association itself may be selected as the optimal solution. In addition to this, it goes without saying that an output solution to which no arrow is connected may be selected, and any other priority may be selected as long as it is based on the degree of association.

Table 2 below shows examples of the association degrees w1 to w12 extending from the input.

The intermediate node 61 may be selected based on the association degrees w1 to w12 extending from this input. That is, the greater the association degrees w1 to w12, the heavier the weighting in selecting the intermediate node 61 may be. However, all the degrees of association w1 to w12 may have the same value, and the weighting in the selection of the intermediate node 61 may be the same.

FIG. 4 shows the quality of an agricultural product, not the yield, in the same manner. In such a case as well, similarly, the quality of the agricultural products for the reference image information and the reference soil information is previously investigated from the past data, and the degree of association is similarly set to construct the learned model. Then, the image information and the soil method are similarly acquired from the growing crop, and the quality of the crop is predicted by referring to the learned model (the degree of association) from these. This makes it possible to predict the quality of crops as well as the yield.

FIG. 5 illustrates an example in which a combination of the above-described reference image information and reference external environment information and the degree of association of three or more levels with the crop yield of the combination are set.

As input data, such reference image information and reference external environment information are arranged. A combination of the reference image information as the input data and the reference external environment information is the intermediate node shown in FIG.

The external environment information for reference is external environment data detected in the process of growing the crop, for example, data on weather conditions such as the amount of solar radiation, temperature, humidity, wind direction, and rainfall, typhoons, floods, droughts, sunshine, etc. It is data on the disaster situation. Actually, it is desirable to acquire the external environment at the time of acquisition of the reference image information, but the external environment for reference is not limited to this. The external environment information for reference may be composed of a temperature sensor, a humidity sensor, a light amount sensor, an anemoscope, a rain gauge, or other sensing means for acquiring real-time data. It may be a post-mortem analysis of a situation such as drought or sunshine.

The prediction device 2 acquires in advance the association degrees w13 to w22 of three or more levels shown in FIG. That is, the prediction device 2 accumulates reference image information, reference external environment information, and data of how much the harvest amount was in that case in predicting the actual harvest amount of the agricultural product. By analyzing these, the degree of association shown in FIG. 5 is created.

In the example of the degree of association shown in FIG. 5, the node 61b is a combination of the reference image information P11 and the reference external environment information P18 “rainfall ●●, temperature ◯×”, and the yield of 6 tons. The degree of association is w15, and the degree of association of 1 ton of harvest is w16.

Similarly, when such a degree of association is set, image information is newly acquired and external environment information is acquired. The image information corresponds to the reference image information, and the external environment information corresponds to the reference external environment information.

The method of acquiring the external environment information is the same as the method of acquiring the reference external environment information described above.

In obtaining the yield, the degree of association shown in FIG. 5 acquired in advance is referred to. For example, when the acquired image is the same as or similar to the reference image information P12 and the acquired external environment information corresponds to the reference external environment information P19, the combination is associated with the node 61c. In the node 61c, the harvest amount of 3 tons is associated with the association degree w17, and the harvest amount of 7 tons is associated with the association degree w18. As a result of such a degree of association, based on w17 and w18, the crop yield of the agricultural product at the time when the new image information and the external environment information are actually acquired will be obtained.

FIG. 6 shows the output of the quality of agricultural products, not the yield, in the same manner. In such a case as well, similarly, the quality of the agricultural products with respect to the reference image information and the reference external environment information is previously investigated from the past data, and the degree of association is similarly set to construct the learned model. Then, the image information and the soil method are similarly acquired from the growing crop, and the quality of the crop is predicted by referring to the learned model (the degree of association) from these. This makes it possible to predict the quality of crops as well as the yield.

FIG. 7 shows an example in which a combination of the above-described reference image information and reference history information and the degree of association of three or more levels with the crop yield of the combination are set.

As the input data, such reference image information and reference history information are arranged. A combination of the reference image information as such input data and the reference history information is the intermediate node 61 shown in FIG. 7.

The reference history information is the history of the agricultural work actually performed in the growing process of the crop. It outlines what kind of agricultural work has been done from seed planting to planting and harvesting. For example, when, how much, and how the agricultural work such as sprinkling water, applying fertilizers, spraying pesticides, and exterminating weeds is reflected in this reference history information. .. Actually, this reference history information may be composed of electronic data of the farm work diary attached by the farmer, or it may be obtained through a PC or smartphone in which records of actual farm work are recorded. May be.

The prediction device 2 acquires in advance the association degrees w13 to w22 of three or more levels shown in FIG. In other words, the prediction device 2 accumulates reference image information, reference history information, and data about the amount of harvest in that case when predicting the actual yield of crops. By analyzing and analyzing, the association degree shown in FIG. 7 is created.

In the example of the degree of association shown in FIG. 7, the node 61b is a node of a combination of the reference image information P11 and the reference external environment information P22, and the degree of association of the harvest amount of 6 tons is w15 and the harvest amount of 1 ton. The degree of association is w16.

Similarly, when such a degree of association is set, image information is newly acquired and history information is acquired. The image information corresponds to the reference image information, and the history information corresponds to the reference history information.

The history information acquisition method is the same as the reference history information acquisition method described above.

In obtaining the harvest amount, the previously acquired association degree shown in FIG. 7 is referred to. For example, when the acquired image is the same as or similar to the reference image information P12 and the acquired history information corresponds to the reference history information P23, the combination is associated with the node 61c. , The harvest amount of 3 tons is associated with the association degree w17, and the harvest amount of 7 tons is associated with the association degree w18. Based on the result of the degree of association, w17 and w18, the image information and the history information are actually newly acquired, and the crop yield of the agricultural product is obtained.

FIG. 8 shows the quality of an agricultural product, not the yield, in the same manner. In such a case as well, similarly, the quality of the agricultural products with respect to the reference image information and the reference history information is previously investigated from the past data, and the degree of association is similarly set to construct the learned model. Then, the image information and the soil method are similarly acquired from the growing crop, and the quality of the crop is predicted by referring to the learned model (the degree of association) from these. This makes it possible to predict the quality of crops as well as the yield.

FIG. 9 shows an example in which, in addition to the reference image information and the reference soil information described above, a combination of reference time information and a degree of association of three or more levels with the harvest amount for the combination are set. Shows.

The reference time information is information indicating when the reference image information is actually acquired.

In such a case, as shown in FIG. 9, the degree of association is expressed as a set of combinations of the reference image information, the reference soil information, and the reference time information as the nodes 61a to 61e of the intermediate nodes as described above. Will be done.

For example, in FIG. 9, in the node 61c, the reference image information P12 has the association degree w3, the reference soil information P15 has the association degree w7, and the reference time information P27 has the association degree w11. Similarly, in the node 61e, the reference image information P13 is associated with the association degree w5, the reference soil information P15 is associated with the association degree w8, and the reference time information P26 is associated with the association degree w10.

Similarly, when such a degree of association is set, the yield is predicted based on newly acquired image information, soil information, and time information at the time of acquisition of the image information.

The degree of association shown in FIG. 9 that is acquired in advance in obtaining the harvest amount is referred to. For example, when the acquired image is the same as or similar to the reference image information P12, the acquired soil information corresponds to the reference soil information P15, and the acquired time information corresponds to the reference time information P27, the combination is The node 61c is associated with the node 61c. The harvest amount of 3 tons is associated with the association degree w17 and the harvest amount of 7 tons is associated with the association degree w18. As a result of such a degree of association, the search solution is actually obtained based on w17 and w18.

When further combining such reference time information, in addition to the combination of the reference image information and the reference soil information described above, the combination of the reference image information and the reference external environment information, the reference image information It is also applicable to a combination of and reference history information.

Further, when the quality of the agricultural product is output as the output solution by further combining the reference time information, it is similarly applicable.

FIG. 10 shows an example in which, in addition to the above-described reference image information and reference soil information, a combination of reference type information and a yield of three or more levels with respect to the combination are set. Shows.

The reference type information is information on the type and variety of agricultural products. The type of agricultural product is acquired by listening to the farmer who grows the agricultural product or by distinguishing it from the image.

In such a case, as shown in FIG. 10, the degree of association is expressed as a set of combinations of the reference image information, the reference soil information, and the reference type information as the nodes 61a to 61e of the intermediate nodes as described above. Will be done.

For example, in FIG. 10, in the node 61c, the reference image information P12 has the association degree w3, the reference soil information P15 has the association degree w7, and the reference type information P29 has the association degree w11. Similarly, in the node 61e, the reference image information P13 is associated with the association degree w5, the reference soil information P15 is associated with the association degree w8, and the reference type information P28 is associated with the association degree w10.

Similarly, when such a degree of association is set, the yield is predicted based on the newly acquired image information and the soil information, as well as the type of agricultural crop that can be said to be the target for the image information acquisition.

To obtain this yield, reference is made to the degree of association acquired in advance and shown in FIG. For example, when the acquired image is the same as or similar to the reference image information P12, the acquired soil information corresponds to the reference soil information P15, and the acquired type information corresponds to the reference type information P29, the combination is The node 61c is associated with the node 61c. The harvest amount of 3 tons is associated with the association degree w17 and the harvest amount of 7 tons is associated with the association degree w18. As a result of such a degree of association, the search solution is actually obtained based on w17 and w18.

When such reference type information is further combined, in addition to the combination of the reference image information and the reference soil information described above, the combination of the reference image information and the reference external environment information, the reference image information It is also applicable to a combination of the reference history information and the reference time information.

Further, by additionally combining the reference type information, the same can be applied when the quality of the agricultural product is output as the output solution.

In the above-mentioned degree of association, the degree of association is expressed by a 10-level evaluation, but the present invention is not limited to this, and it is sufficient if the degree of association is expressed by 3 or more levels, and conversely 3 or more levels. For example, it may be 100 steps or 1000 steps. On the other hand, this degree of association does not include two levels, that is, whether or not they are associated with each other and expressed by either 1 or 0.

According to the present invention configured as described above, it is possible to easily predict the harvest amount and the quality with a small amount of labor without requiring special skill. Further, according to the present invention, it is possible to make the determination of the search solution with higher accuracy than that made by a human. Further, by configuring the above-mentioned degree of association with artificial intelligence (neural network or the like), it is possible to further improve the discrimination accuracy by learning this.

Further, the present invention is characterized in that the optimum physical properties and the generation mechanism are searched for through the association degrees set in three or more steps. The degree of association can be described by a numerical value of 0 to 100%, for example, in addition to the above-mentioned five levels, but is not limited to this, and at any step as long as it can be described by a numerical value of three or more levels. It may be configured.

By searching for the most probable yield and quality based on the degree of association represented by three or more numerical values, the degree of association is high in situations where multiple candidates for the search solution are considered. It is also possible to search and display in order. If it is possible to display to the user in the descending order of the degree of association, it is possible to preferentially display a more probable search solution.

In addition to this, according to the present invention, it is possible to make a determination without missing a determination result of an output having an extremely low degree of association such as 1%. Remind users that even discrimination results with a very low degree of association are connected as slight signs, and may be useful as discrimination results once every tens or hundreds of times. be able to.

Further, according to the present invention, there is an advantage that the search policy can be determined by the method of setting the threshold value by performing the search based on the degree of association of three or more stages. If the threshold value is set low, even if the above-mentioned degree of association is 1%, it can be picked up without omission, but it is unlikely that a more appropriate discrimination result can be suitably detected, and a lot of noise may be picked up. is there. On the other hand, if the threshold value is set high, it is highly possible that the optimal search solution can be detected with high probability, but normally, the degree of association is low, and although it is passed through, it appears once in tens or hundreds of times. Sometimes you overlook a solution. It is possible to decide which is to be emphasized based on the idea of the user side and the system side, but it is possible to increase the degree of freedom in selecting such a point to be emphasized.

Further, in the present invention, the above-mentioned degree of association may be updated. This update may reflect information provided via a public communication network such as the Internet. In addition, when images of crops are captured and other than this, soil information, external environment information, history information, time information, type information, and knowledge, information, and data related to the harvest amount and quality for these are acquired, the correlation is performed according to these. Increase or decrease the degree.

In other words, this update is equivalent to learning in artificial intelligence. It is a learning act because new data is acquired and reflected in the learned data.

In addition to updating the association degree, the system side or the user side may update the information based on the contents of research data and papers by experts, conference presentations, newspaper articles, books, etc. It may be updated artificially or automatically. You may make it utilize artificial intelligence in these update processes.

Further, not only supervised learning but also unsupervised learning, deep learning, reinforcement learning, and the like may be used for the process of first creating a learned model and the above-described update. In the case of unsupervised learning, instead of reading the data set of the input data and the output data and learning, the information corresponding to the input data is read and learned, and the degree of association related to the output data is self-formed from there. It may be allowed to.

1 Yield Prediction System 2 Prediction Device 21 Internal Bus 23 Display 24 Control Unit 25 Operating Unit 26 Communication Unit 27 Estimating Unit 28 Storage Unit 61 Node

Claims (16)

In a crop yield forecasting program that predicts crop yields,
From the image of the crop being cultivated, the growth status of the crop, the damage caused by the pests on the crop, the reference image information that extracts any of the diseases that occurred on the crop, and the components of the soil on which the crop is planted A reference information acquisition step of acquiring reference soil information in which the survey result is reflected,
A combination of the combination of the reference image information and the reference soil information acquired in the reference information acquisition step, and the degree of association of three or more levels with the harvest amount when the agricultural product under cultivation for the combination is harvested. The association degree acquisition step to be acquired,
When newly predicting the amount of crops to be harvested, by taking an image of the crops that are being newly cultivated, any of the growth status of the above crops, damage of pests occurring in the crops, and diseases occurring in the crops were extracted. An information acquisition step of acquiring image information and also acquiring soil information regarding the soil on which the agricultural product is cultivated,
Referring to the degree of association acquired in the degree of association acquisition step, based on the image information and soil information acquired through the information acquisition step, a prediction step for predicting the yield of the crop that is being newly grown is stored in the computer. A crop yield forecasting program characterized by being executed. In a crop yield forecasting program that predicts crop yields,
Includes reference image information that extracts any of the growth status of crops, damage caused by pests on crops, and diseases that occurred on crops from the image of crops being grown, and floods and droughts in the process of growing the crops A reference information acquisition step of acquiring reference external environment information that has detected the disaster situation,
A combination of the combination of the reference image information and the reference soil information acquired in the reference information acquisition step, and the degree of association of three or more levels with the harvest amount when the agricultural product under cultivation for the combination is harvested. The association degree acquisition step to be acquired,
When newly predicting the amount of crops to be harvested, by taking an image of the crops that are being newly cultivated, any of the growth status of the above crops, damage of pests occurring in the crops, and diseases occurring in the crops were extracted. An information acquisition step of acquiring image information and external environmental information related to a disaster situation including floods and droughts in the process of growing the crops,
With reference to the degree of association obtained in the degree of association obtaining step, based on the image information and the external environment information obtained through the information obtaining step, a prediction step for predicting the yield of the crop that is being newly grown is computer. A crop yield prediction program characterized by being executed by In a crop yield forecasting program that predicts crop yields,
From the image of the crop being cultivated, the reference image information that extracts any of the growth status of the crop, the damage caused by pests on the crop, and the disease that occurred on the crop, and the actual agricultural work performed on the crop. A reference information acquisition step of acquiring reference history information regarding history,
A combination of the combination of the reference image information and the reference history information acquired in the reference information acquisition step, and a degree of association of three or more levels with the harvest amount when the agricultural product under cultivation is harvested for the combination. The association degree acquisition step to be acquired,
When newly predicting the amount of crops to be harvested, by taking an image of the crops that are being newly cultivated, any of the growth status of the above crops, damage of pests occurring in the crops, and diseases occurring in the crops were extracted. An information acquisition step of acquiring image information and acquiring history information regarding a history of farm work actually performed on the farm product in the process of growing the farm product,
Referring to the degree of association obtained in the degree of association obtaining step, based on the image information and history information obtained through the information obtaining step, a predicting step for predicting the yield of the crop being newly grown is provided to the computer. A crop yield forecasting program characterized by being executed. In the association degree obtaining step, further obtains a degree of association of three or more levels between the combination with the reference time information regarding the cultivation time of the agricultural product and the harvest amount when the agricultural product under cultivation for the combination is harvested,
In the information acquisition step, further acquire timing information regarding the cultivation time of the newly growing agricultural products,
In the said prediction step, based on the time information acquired through the said information acquisition step, the said crop amount is predicted, The crop amount prediction program of any one of Claims 1-3 characterized by the above-mentioned. .. In the association degree acquisition step, further obtains a degree of association of three or more levels between the combination with the reference type information regarding the type of the agricultural product, and the harvest amount when the agricultural product under cultivation for the combination is harvested,
In the information acquisition step, further acquire type information regarding the type of agricultural product that is being newly grown,
The predicting step further predicts the harvest amount based on the type information acquired through the information acquiring step. The harvest amount predicting program for crops according to claim 1, wherein .. The harvesting of crops according to any one of claims 1 to 5, wherein, in the association degree obtaining step, the association degree corresponding to the weighting coefficient of each output of the node of the neural network in the artificial intelligence is obtained. Quantity forecast program. In a crop quality prediction program that predicts the quality of crops,
From the image of the crop being cultivated, the growth status of the crop, the damage caused by the pests on the crop, the reference image information that extracts any of the diseases that occurred on the crop, and the components of the soil on which the crop is planted A reference information acquisition step of acquiring reference soil information in which the survey result is reflected,
Obtaining a degree of association of three or more levels between the combination of the reference image information and the reference soil information acquired in the reference information acquisition step and the quality of the harvested agricultural crop for the combination. The step of obtaining the degree of association,
When newly predicting the quality of crops, by taking an image of the crops that are being newly grown, the growth status of the crops, the damage caused by the pests on the crops, and the extracted disease on the crops are extracted. An information acquisition step of acquiring information and acquiring soil information on the soil on which the crop is planted,
Referring to the degree of association acquired in the degree of association acquisition step, based on the image information and the soil information acquired through the information acquisition step, a prediction step of predicting the quality of the newly grown agricultural product is executed on the computer. A program for predicting the quality of agricultural products characterized by In a crop quality prediction program that predicts the quality of crops,
Includes reference image information that extracts any of the growth status of crops, damage caused by pests on crops, and diseases that occurred on crops from the image of crops being grown, and floods and droughts in the process of growing the crops A reference information acquisition step of acquiring reference external environment information that has detected the disaster situation,
Obtaining a degree of association of three or more levels between the combination of the reference image information and the reference soil information acquired in the reference information acquisition step and the quality of the harvested agricultural crop for the combination. The step of obtaining the degree of association,
When newly predicting the quality of crops, by taking an image of the crops that are being newly grown, the growth status of the crops, the damage caused by the pests on the crops, and the extracted disease on the crops are extracted. An information acquisition step of acquiring information and external environmental information regarding a disaster situation including floods and droughts in the process of growing the agricultural products,
With reference to the degree of association obtained in the degree of association obtaining step, based on the image information and the external environment information obtained through the information obtaining step, a predicting step for predicting the quality of the crop that is being newly cultivated is stored in the computer. A program for predicting the quality of agricultural products characterized by being executed. In a crop quality prediction program that predicts the quality of crops,
From the image of the crop being cultivated, the reference image information that extracts any of the growth status of the crop, the damage caused by pests on the crop, and the disease that occurred on the crop, and the actual agricultural work performed on the crop. A reference information acquisition step of acquiring reference history information regarding history,
Acquiring a degree of association of three or more levels between the combination of the reference image information and the reference history information acquired in the reference information acquisition step and the quality of the harvested agricultural crop for the combination. The step of obtaining the degree of association,
When newly predicting the quality of crops, by taking an image of the crops that are being newly grown, the growth status of the crops, the damage caused by the pests on the crops, and the extracted disease on the crops are extracted. An information acquisition step of acquiring information and acquiring history information about a history of farm work actually performed on the farm product in the process of growing the farm product,
Referring to the degree of association acquired in the degree-of-association acquisition step, based on the image information and history information acquired through the information acquisition step, a prediction step of predicting the quality of the crop that is being newly grown is executed by the computer. A program for predicting the quality of agricultural products characterized by The quality of crops according to any one of claims 1 to 9, wherein the association degree acquisition step acquires the association degree corresponding to a weighting coefficient of each output of a node of a neural network in artificial intelligence. Prediction program. In a crop yield prediction system that predicts crop yields,
From the image of the crop being cultivated, the growth status of the crop, the damage caused by the pests on the crop, the reference image information that extracts any of the diseases that occurred on the crop, and the components of the soil on which the crop is planted Reference information acquisition means for acquiring the reference soil information reflecting the survey results,
A combination of the combination of the reference image information and the reference soil information acquired by the reference information acquisition means, and the degree of association of three or more levels with the harvest amount when the agricultural product under cultivation is harvested for the combination. An association degree acquisition means to be acquired,
When newly predicting the amount of crops to be harvested, by taking an image of the crops that are being newly cultivated, any of the growth status of the above crops, damage of pests occurring in the crops, and diseases occurring in the crops were extracted. An information acquisition unit that acquires image information and also acquires soil information regarding the soil on which the crop is planted,
With reference to the degree of association obtained by the degree of association obtaining means, based on the image information and the soil information obtained through the information obtaining means, a prediction means for predicting the yield of the crops newly grown is provided. A crop yield prediction system characterized by the following. In a crop yield prediction system that predicts crop yields,
Includes reference image information that extracts any of the growth status of crops, damage caused by pests on crops, and diseases that occurred on crops from the image of crops being grown, and floods and droughts in the process of growing the crops Reference information acquisition means for acquiring the reference external environment information that has detected the disaster situation,
A combination of the combination of the reference image information and the reference soil information acquired by the reference information acquisition means, and the degree of association of three or more levels with the harvest amount when the agricultural product under cultivation is harvested for the combination. An association degree acquisition means to be acquired,
When newly predicting the amount of crops to be harvested, by taking an image of the crops that are being newly cultivated, any of the growth status of the above crops, damage of pests occurring in the crops, and diseases occurring in the crops were extracted. Information acquisition means for acquiring image information and external environmental information on disaster situations including floods and droughts in the process of growing the crops,
Referring to the degree of association obtained by the degree of association obtaining means, based on the image information and the external environment information obtained via the information obtaining means, a predicting means for predicting the yield of the crops newly grown. A crop yield prediction system characterized by being equipped. In a crop yield prediction system that predicts crop yields,
From the image of the crop being cultivated, the reference image information that extracts any of the growth status of the crop, the damage caused by pests on the crop, and the disease that occurred on the crop, and the actual agricultural work performed on the crop. A reference information acquisition unit for acquiring reference history information regarding history,
A combination of the combination of the reference image information and the reference history information acquired by the reference information acquisition means, and the degree of association of three or more levels with the harvest amount when harvesting the agricultural product under cultivation for the combination. An association degree acquisition means to be acquired,
When newly predicting the amount of crops to be harvested, by taking an image of the crops that are being newly cultivated, any of the growth status of the above crops, damage of pests occurring in the crops, and diseases occurring in the crops were extracted. An information acquisition unit that acquires image information and also acquires history information regarding the history of farm work actually performed on the farm product in the process of growing the farm product,
With reference to the degree of association obtained by the degree of association obtaining means, based on the image information and history information obtained via the information obtaining means, a prediction means for predicting the yield of the crops being newly grown is provided. A crop yield prediction system characterized by the following. In a crop quality prediction system that predicts the quality of crops,
From the image of the crop being cultivated, the growth status of the crop, the damage caused by the pests on the crop, the reference image information that extracts any of the diseases that occurred on the crop, and the components of the soil on which the crop is planted Reference information acquisition means for acquiring the reference soil information reflecting the survey results,
Obtaining a degree of association of three or more levels between the combination of the reference image information and the reference soil information acquired by the reference information acquiring unit and the quality of the harvested agricultural crop for the combination. Means for obtaining the degree of association,
When newly predicting the quality of crops, by taking an image of the crops that are being newly grown, the growth status of the crops, the damage caused by the pests on the crops, and the extracted disease on the crops are extracted. An information acquisition means for acquiring information and also acquiring soil information regarding the soil on which the crop is planted,
Referring to the degree of association acquired by the degree of association acquiring means, based on the image information and the soil information acquired via the information acquiring means, a prediction means for predicting the quality of the crops newly grown is provided. A system for predicting the quality of agricultural products. In a crop quality prediction system that predicts the quality of crops,
Includes reference image information that extracts any of the growth status of crops, damage caused by pests on crops, and diseases that occurred on crops from the image of crops being grown, and floods and droughts in the process of growing the crops Reference information acquisition means for acquiring the reference external environment information that has detected the disaster situation,
Obtaining a degree of association of three or more levels between the combination of the reference image information and the reference soil information acquired by the reference information acquiring unit and the quality of the harvested agricultural crop for the combination. Means for obtaining the degree of association,
When newly predicting the quality of crops, by taking an image of the crops that are being newly grown, the growth status of the crops, the damage caused by the pests on the crops, and the extracted disease on the crops are extracted. An information acquisition means for acquiring information and external environmental information related to disaster situations including floods and droughts in the process of growing the crops,
With reference to the degree of association obtained by the degree of association obtaining means, based on the image information and the external environment information obtained via the information obtaining means, a prediction means for predicting the quality of the newly grown agricultural product is provided. A system for predicting the quality of agricultural products characterized by In a crop quality prediction system that predicts the quality of crops,
From the image of the crop being cultivated, the reference image information that extracts any of the growth status of the crop, the damage caused by pests on the crop, and the disease that occurred on the crop, and the actual agricultural work performed on the crop. A reference information acquisition unit for acquiring reference history information regarding history,
The degree of association of three or more levels between the combination of the reference image information and the reference history information acquired by the reference information acquisition means and the quality of the harvested agricultural crop for the combination is acquired. Means for obtaining the degree of association,
When newly predicting the quality of crops, by taking an image of the crops that are being newly grown, the growth status of the crops, the damage caused by the pests on the crops, and the extracted disease on the crops are extracted. An information acquisition unit that acquires information and history information related to the history of farm work actually performed on the crop in the process of growing the crop,
With reference to the degree of association obtained by the means for obtaining degree of association, based on the image information and history information obtained via the information obtaining means, a predicting means for predicting the quality of the crops newly grown A system for predicting the quality of agricultural products.

Images