JP2020146030A - Agricultural system - Google Patents

Abstract

To provide an agricultural system aimed at improving yield or quality of field crop.SOLUTION: An agricultural system acquires in advance first association degrees w13 to w22, at three or more stages, between: a combination of reference image information P11 to P13 in which field crops being raised are previously imaged by an unmanned aircraft, and reference history information P22 to P25 including a history of farm works applied to the field crops by the unmanned aircraft; and a farm work to be applied next to the combination by the unmanned aircraft. Then, the system searches optimum farm works A to E on the basis of a difference between image information in which a farm field of field crop where a farm work will be newly performed by the unmanned aircraft is imaged and reference image information P11 to P13 of the first association degrees, and third association degrees acquired by second reference information P22 to P24 which is a history of farm works of the unmanned aircraft which has been caused to execute the farm works.SELECTED DRAWING: Figure 16

Description

The present invention relates to an agricultural system including an unmanned aerial vehicle that performs optimal agricultural work with a view to improving the yield and quality of agricultural products.

With the aging of the agricultural population, the number of veteran farmers who have farming skills is decreasing, and the shortage of young farmers who pass on their skills has become a problem these days. Under these circumstances, instead of passing on skills by veteran farmers, the idea that artificial intelligence limits the cultivation method has been proposed.

In order to assist the advice on cultivation methods for agricultural work with artificial intelligence, it is necessary to carry out more optimal cultivation at the present time after forecasting the future yield and quality of the crops being grown. However, in the past, there has been no particular proposal for artificial intelligence that gives optimal advice for improving the yield and quality of this agricultural product. In recent years, agricultural systems have been proposed that allow unmanned aerial vehicles such as drones to carry out agricultural work. By having unmanned aerial vehicles incorporating such artificial intelligence perform agricultural work, the yield and quality of agricultural products Can be realized while reducing the burden of labor. However, the current situation is that unmanned aerial vehicles incorporating such artificial intelligence have not yet been proposed.

Therefore, the present invention has been devised in view of the above-mentioned problems, and the purpose of the present invention is to improve the yield and quality of agricultural products, and to carry out the optimum agricultural work for aiming at this. The idea is to propose an agricultural system that includes unmanned aerial vehicles.

The agricultural system to which the present invention is applied is an agricultural system in which agricultural work is carried out by an unmanned aerial vehicle, in which the first reference image information obtained by preliminarily imaging a growing product by an unmanned aerial vehicle and the above-mentioned unmanned aerial vehicle are used. The first to obtain in advance the first degree of association of three or more stages between the combination having the first reference history information including the history of the farm work performed and the farm work to be performed next by the unmanned aerial vehicle for the combination. The means for acquiring the degree of association, the first image information obtained by capturing a field of agricultural products to be newly farmed by an unmanned aerial vehicle, and the first history information including the history of farm work performed by the unmanned aerial vehicle. The first image information and the first history acquired through the information acquisition means by referring to the first information acquisition means for acquiring the information and the first association degree acquired by the first association degree acquisition means. Based on the information, the first information acquisition means is provided with a search means for searching for agricultural work to be performed by the unmanned aerial vehicle and a work control means for causing the unmanned aerial vehicle to execute the agricultural work searched by the search means. Acquires the first image information in the division area unit set on the flight path by taking images in time series in the process of the unmanned aerial vehicle flying in the flight path on the field, and obtains the first image information in the division area unit, and obtains the first image information in the division area unit. Is characterized in that it searches for agricultural work to be performed in the divided area unit, and the work control means controls the agricultural work to be executed by the unmanned aerial vehicle in the divided area unit.

With a view to improving the yield and quality of this crop, it is possible to have an unmanned aerial vehicle perform farm work based on instructions from artificial intelligence that gives optimal advice to aim for this, and improve the yield and quality of the crop. Can be realized while reducing the burden of labor.

It is a block diagram which shows the whole structure of the system to which this invention is applied. It is a figure which shows the specific configuration example of a search device. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention.

Hereinafter, the agricultural system to which the present invention is applied will be described in detail with reference to the drawings.

The first embodiment FIG. 1 is a block diagram showing an overall configuration of an agricultural system 101 to which an agricultural product cultivation advice program to which the present invention is applied is implemented. The agricultural system 101 can communicate by wire or wirelessly between the information acquisition unit 9, the search device 102 connected to the information acquisition unit 9, the database 103 connected to the search device 102, and the search device 102. It is equipped with an unmanned aerial vehicle 1.

The information acquisition unit 9 is a device for a person using this system to input various commands and information, and specifically, is composed of a keyboard, buttons, a touch panel, a mouse, a switch, and the like. The information acquisition unit 9 is not limited to a device for inputting text information, and may be configured by a device such as a microphone that can detect voice and convert it into text information. Further, the information acquisition unit 9 may be configured as an image pickup device capable of capturing an image of a camera or the like. The information acquisition unit 9 may be configured by a scanner having a function of recognizing a character string from a paper-based document. Further, the information acquisition unit 9 may be integrated with the search device 102 described later. The information acquisition unit 9 outputs the detected information to the search device 102. 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 103 stores various information regarding the cultivation of past crops. For example, image data that captures the growth status of agricultural products, image data that shows the damage status due to pests of agricultural products and the damage status due to diseases of agricultural products, soil data that analyzes the soil in which agricultural products are planted, and the external environment detected during the growing process of the agricultural products. Data (for example, data on weather conditions such as solar radiation, temperature, humidity, wind direction, and rainfall, data on disaster conditions such as typhoons, floods, droughts, and sunshine), data on past farm work history, data on crop growing time, Data on the types of agricultural products are recorded.

The search device 102 is composed of, for example, an electronic device such as a personal computer (PC), but is realized by any other electronic device such as a mobile phone, a smartphone, a tablet terminal, a wearable terminal, etc., in addition to the PC. It may be converted. By obtaining the search solution by the search device 102, the user can obtain advice on the optimum cultivation method for the crop currently being cultivated. When actually giving advice, the search device 102 displays the advice content of a specific cultivation method on the screen, plays it by voice, or prints the advice content on a paper medium with a printer and displays it. It may be.

FIG. 2 shows a specific configuration example of the search device 102. The search device 102 communicates with a control unit 124 for controlling the entire search device 102, an operation unit 125 for inputting various control commands via operation buttons, a keyboard, and the like, and, for example, an unmanned aerial vehicle 1. Alternatively, the communication unit 126 for performing wireless communication, the judgment unit 127 for making various judgments, and the storage unit 128 for storing a program for performing a search to be executed represented by a hard disk or the like are connected to the internal bus 121. Each is connected. Further, a display unit 123 as a monitor that actually displays information is connected to the internal bus 121.

The control unit 124 is a so-called central control unit for controlling each component mounted in the search device 102 by transmitting a control signal via the internal bus 121. Further, the control unit 124 transmits various control commands via the internal bus 121 in response to the operation via the operation unit 125.

The operation unit 125 is embodied by a keyboard or a touch panel, and an execution command for executing a program is input from the user. When the execution command is input by the user, the operation unit 125 notifies the control unit 124 of the execution command. Upon receiving this notification, the control unit 124, including the determination unit 127, executes a desired processing operation in cooperation with each component. The operation unit 125 may be embodied as the information acquisition unit 9 described above.

Judgment unit 127 is responsible for determining what kind of advice should be given regarding the cultivation method of agricultural products. The determination unit 127 reads out various information stored in the storage unit 128 and various information stored in the database 103 as necessary information when executing the estimation operation. The determination unit 127 may be controlled by artificial intelligence. This artificial intelligence may be based on any well-known artificial intelligence technique.

The display unit 123 is composed of a graphic controller that creates a display image based on the control by the control unit 124. The display unit 123 is realized by, for example, a liquid crystal display (LCD) or the like.

When the storage unit 128 is composed of a hard disk, predetermined information is written to each address based on the control by the control unit 124, and this is read out as needed. Further, the storage unit 128 stores a program for executing the present invention. This program will be read and executed by the control unit 124.

The operation in the agricultural system 101 having the above-described configuration will be described.

In the agricultural system 101, 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 taken by a camera of a crop in the process of growing. The photographed images of the agricultural products may be sequentially photographed in chronological order from the stage of sowing and seedling to the harvesting. In addition, the captured image of the crop may be composed of an image of the shooting range that captures the entire field or paddy field, or includes an image of the leaves, stems, fruits, etc. of the crop in the field or paddy field taken at a close distance. .. Further, the captured image may be captured through an unmanned aerial vehicle such as a drone, or may be captured by a camera installed on the ground. With such a camera, it is possible to detect the growth state of the crop, the damage caused by the pests on the crop, the disease on the crop, and the like. By the way, as this reference image information, the raw image taken by the camera may be acquired as it is as image information, or only the characteristic part of the image is extracted by utilizing the well-known deep learning technology. This may be used as reference image information.

The reference soil information also includes all information about the soil in which the crop is planted. Examples of this reference soil information include soil components, pH, water content, temperature and the like. The result of actually collecting the components of the soil and analyzing it based on the chemical analysis method may be used, or the data detected by a well-known soil sensor may be used. Further, an image obtained by capturing the soil with a camera, and an image obtained by extracting only a characteristic part of the image by utilizing a well-known deep learning technique may be used.

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. The intermediate node shown in FIG. 3 is a combination of reference soil information and reference image information as such input data. Each intermediate node is further linked to the output. In this output, the method of cultivating crops as an output solution is displayed.

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 cultivation method of the crop as this output solution. The reference image information and the reference soil information are arranged on the left side through this degree of association, and the cultivation method of each crop is arranged on the right side through this degree of association. The degree of association indicates the degree of relevance to which crop cultivation method is highly related to the reference image information and the reference soil information arranged on the left side. In other words, this degree of association is an index indicating what kind of crop cultivation method is likely to be associated with each reference image information and reference soil information, and the reference image information and reference soil information. It shows the accuracy in selecting the most probable and most suitable cultivation method for crops. In the example of FIG. 3, w13 to w22 are shown as the degree of association. These w13 to w22 are shown in 10 stages as shown in Table 1 below, and the closer to 10 points, the higher the degree of relevance of each combination as an intermediate node to the cultivation method of the crop as an output. On the contrary, the closer to one point, the lower the degree of relevance of each combination as an intermediate node to the cultivation method of the crop as an output.

The search device 102 acquires in advance the degree of association w13 to w22 of three or more stages shown in FIG. That is, the search device 102 accumulates past data on the reference image information, the reference soil information, and the appropriate cultivation method of the agricultural product in that case in determining the actual search solution. By analyzing and analyzing these, the degree of association shown in FIG. 3 is created.

For example, it is assumed that the reference image information P11 reflects the state of the crop damaged by outsourcing. At this time, when the components of the soil in which the crop was actually cultivated were investigated and the value was "pH ●●, component ○ ×" corresponding to the reference soil information P14, the actual crop was cultivated in the previous data. Investigate the methods to find out which cultivation method is best for improving yields or improving crop quality. Under the circumstances of the reference image information P11 and the reference soil information P14, the crops have been cultivated in the past, and as a result, the yield and quality of the crops have been investigated. Form a degree of association. Under the conditions of the reference image information P11 and the reference soil information P14, for example, as a result of performing the cultivation method "spraying fertilizer 〇〇 twice a week and spraying pesticide △△ once a month", the yield and quality are improved. If it improves, the degree of association of the cultivation method will be strengthened. On the other hand, as a result of performing the cultivation method "spraying water twice a day and weeding once a week" under the conditions of the reference image information P11 and the reference soil information P14, the yield and quality are not good. If so, the degree of association is lowered.

The degree of association is formed based on the past cultivation methods applied to the reference image information and the reference soil information and the results (harvest amount, etc.).

If there is electronic data that actually describes the relationship between the past cultivation method applied to the reference image information and reference soil information and the result (yield, etc.), analyze and analyze this. Then, the degree of association may be created. This analysis and 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 and the cultivation method actually applied are shown in the past. Analyze from the data. Cultivation method "Spraying fertilizer 〇〇 twice a week, spraying pesticide △△ once a month", if the yield is higher than before, this cultivation method "spraying fertilizer 〇〇" Set a higher degree of association that leads to "spraying pesticides △△ twice a week once a month". Cultivation method "Water spraying twice a day, weeding once a week" is applied, and if the yield is higher than before, this cultivation method "Water spraying twice a day, weeding" Set a higher degree of association that leads to "once a week".

Further, the degree of association shown in FIG. 3 may be composed of the nodes of the 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, the network is not limited to a neural network, and may be composed of all decision-making factors constituting artificial intelligence.

In the example of the degree of association shown in FIG. 3, the node 61b is a node in which the reference soil information P14 is combined with the reference image information P11, and the cultivation method “fertilizer □□ is mixed with fertilizer XX for a week. The degree of association of "once spraying" is w15, and the degree of association of the cultivation method "spraying pesticide △ ○ once every two weeks, weeding twice a week" is w16. The node 61c is a node in which the reference soil information P15 and P17 are combined with the reference image information P12, and the degree of association of the cultivation method “water spraying twice a day, weeding once a week” is w17. , The degree of association of the cultivation method "put up an insect repellent net 3 months after sowing" is w18.

Such a degree of association is what is called learned data in artificial intelligence. After creating such learned data, when actually giving new advice on the cultivation method of agricultural products, the above-mentioned learned data will be used to search for the cultivation method of agricultural products. In such a case, image information is newly acquired and soil information is acquired.

The newly acquired image information is captured by the camera by the information acquisition unit 9 described above. This shooting targets the crops that are about to be cultivated.

The acquisition of soil information is the soil in which the crop to be newly cultivated is actually planted, and the acquisition method is the same as when acquiring the reference soil information described above.

Based on the newly acquired image information and soil information in this way, the cultivation method of the crop for which the newly acquired image information and soil information are actually acquired is searched for. In such a 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 via the degree of association, and this node In 61d, "mixing fertilizer □□ with fertilizer XX and spraying once a week" is associated with w19, and "putting an insect repellent net 3 months after sowing" is associated with a degree of association w20. In such a case, "mix fertilizer □□ with fertilizer XX and spray once a week", which has a higher degree of association, is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and the one with the lowest degree of association but the association itself is recognized. Select "Insect repellent net is put up 3 months after sowing" as the optimum solution. You may do so. In addition to this, it goes without saying that an output solution to which the arrows are not connected may be selected, and as long as it is based on the degree of association, it may be selected in any other priority.

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

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

FIG. 4 shows an example in which the combination of the above-mentioned reference image information and the reference external environment information and the degree of association between the combination and the cultivation method of the agricultural product are set to three or more levels.

As the input data, such reference image information and reference external environment information are arranged side by side. The intermediate node shown in FIG. 4 is a combination of reference image information and reference external environment information as such input data.

The reference external environment information is external environment data detected in the process of growing the agricultural product, for example, data on weather conditions such as solar radiation, temperature, humidity, wind direction, and rain, typhoons, floods, droughts, sunshine, and the like. Data related to the disaster situation. Actually, it is desirable, but not limited to, the reference external environment information to acquire the external environment at the time of acquisition of the reference image information. These reference external environment information may be composed of sensing means for acquiring real-time data such as a temperature sensor, a humidity sensor, a light amount sensor, an anemometer, and a rain gauge, but may include the damage status of a typhoon or a flood. It may be an ex post facto analysis of the situation such as typhoon and sunshine.

The search device 102 acquires in advance the degree of association w13 to w22 of three or more stages shown in FIG. That is, the search device 102 accumulates reference image information, reference external environment information, and data on which is the optimum cultivation method for the crop in that case, in order to newly advise the actual cultivation method of the crop. By analyzing and analyzing these, the degree of association shown in FIG. 5 is created.

In the example of the degree of association shown in FIG. 4, the node 61b is a node of a combination of the reference external environment information P18 “rainfall ●●, temperature ○ ×” with respect to the reference image information P11, and is a node of “fertilizer □□”. The degree of association of "mixing fertilizer XX and spraying once a week" is w15, and the degree of association of "spraying pesticide Δ〇 once every two weeks and weeding twice a week" 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 external environment information for reference described above.

In giving new advice on the cultivation method of agricultural products, the degree of association shown in FIG. 4 obtained 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. Node 61c is associated with "spraying water twice a day, weeding once a week" with a degree of association w17, and "putting an insect repellent net 3 months after sowing" with a degree of association w18. As a result of such a degree of association, based on w17 and w18, the cultivation method of the agricultural product at the time when the new image information and the external environment information are actually acquired will be searched.

FIG. 5 shows an example in which the combination of the above-mentioned reference image information and the reference history information and the degree of association between the combination and the cultivation method of the agricultural product are set to three or more levels.

As the input data, such reference image information and reference history information are arranged side by side. The intermediate node 61 shown in FIG. 5 is a combination of reference image information and reference history information as such input data.

The reference history information is the history of the agricultural work actually performed in the process of growing the crop. It summarizes what kind of farming work has been done from sowing to planting seedlings to harvesting. For example, when, how much, and how the agricultural work such as sprinkling water, fertilizing, spraying pesticides, and exterminating weeds was performed is reflected in this reference history information. .. Actually, this reference history information may be composed of an electronic data of the farm work diary kept by the farmer, or it may be obtained through a PC, a smartphone, etc. in which the record of the actual farm work is recorded. You may.

The search device 102 acquires in advance the degree of association w13 to w22 of three or more stages shown in FIG. That is, the search device 102 accumulates reference image information, reference history information, and data on which is the most suitable cultivation method for the crop in that case when newly searching for the actual cultivation method of the crop. By analyzing and 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 node in which the reference image information P11 and the reference external environment information P22 are combined, and “a fertilizer □□ mixed with fertilizer XX is mixed once a week. The degree of association of "repeating spray" is w15, and the degree of association of "spraying pesticide △ ○ once every two weeks and weeding twice a week" 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 method of acquiring the history information is the same as the method of acquiring the reference history information described above.

In searching for a cultivation method of agricultural products, 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 history information corresponds to the reference history information P23, the combination is associated with the node 61c, and the node 61c is associated with the combination. Is associated with "spraying water twice a day, weeding once a week" with a degree of association w17, and "putting up an insect repellent net 3 months after sowing" with a degree of association w18. As a result of such a degree of association, based on w17 and w18, the image information and the history information are actually newly acquired, and the cultivation method of the agricultural product is sought.

In FIG. 6, in addition to the above-mentioned reference image information and reference soil information, a combination of reference timing information and a crop cultivation method for the combination are set to have three or more levels of association. An example is shown.

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

In such a case, the degree of association is expressed as a set of combinations of reference image information, reference soil information, and reference timing information as nodes 61a to 61e of intermediate nodes as described above.

For example, in FIG. 6, in the node 61c, the reference image information P12 is associated with the association degree w3, the reference soil information P15 is associated with the association degree w7, and the reference time information P27 is associated with 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 cultivation method of the crop is searched based on the newly acquired image information, the soil information, and the timing information at the time of acquisition of the image information.

In searching for the cultivation method of this crop, the degree of association shown in FIG. 6 acquired in advance 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 A node 61c is associated with this node 61c, which has a degree of association w17 of "spraying water twice a day and weeding once a week" and "putting up an insect repellent net 3 months after sowing". It is associated with the degree of association w18. As a result of such a degree of association, a search solution is actually obtained based on w17 and w18.

When further combining such reference timing 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, and the reference image information It can also be applied in combination with history information for reference.

In FIG. 7, in addition to the above-mentioned reference image information and reference soil information, a combination of reference type information and a crop cultivation method for the combination have three or more levels of association with each other. An example is shown.

The reference type information is information on the type and variety of agricultural products. The type of crop is obtained by listening to the farmer who grows the crop or by discriminating it from the image.

In such a case, as shown in FIG. 7, the degree of association is expressed as a set of combinations of reference image information, reference soil information, and reference type information as nodes 61a to 61e of intermediate nodes as described above. Will be done.

For example, in FIG. 7, in the node 61c, the reference image information P12 is associated with the association degree w3, the reference soil information P15 is associated with the association degree w7, and the reference type information P29 is associated with 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 cultivation method of the crop is searched based on the newly acquired image information, the soil information, and the type of the crop that can be said to be the acquisition target of the image information. ..

In searching for the cultivation method of this crop, the degree of association shown in FIG. 7 acquired in advance 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 type information corresponds to the reference type information P29, the combination is A node 61c is associated with this node 61c, which has a degree of association w17 of "spraying water twice a day and weeding once a week" and "putting up an insect repellent net 3 months after sowing". It is associated with the degree of association w18. As a result of such a degree of association, a search solution is actually obtained based on w17 and w18.

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

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

According to the present invention having the above-described configuration, it is possible to easily perform from the search for the cultivation method of the agricultural product to the advice based on the search result without requiring special skill and with a small amount of labor. Further, according to the present invention, it is possible to determine the search solution with higher accuracy than that performed by a human being. 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, according to the present invention, there is a feature in that a search for a cultivation method of an agricultural product is performed through a degree of association set to three or more stages. The degree of association can be described by, for example, a numerical value from 0 to 100% in addition to the above-mentioned five stages, but is not limited to this, and any stage can be described as long as it can be described by a numerical value of three or more stages. It may be configured.

By searching for the most probable crop cultivation method based on the degree of association expressed by the numerical values of three or more stages, the degree of association is high under the situation where there are multiple possible candidates for the search solution. It is also possible to search and display in order. If the user can be displayed in descending order of the degree of association in this way, it is possible to preferentially display more probable search solutions.

In addition to this, according to the present invention, it is possible to judge without overlooking the discrimination result of the output having an extremely low degree of association such as 1%. Remind the user that even a judgment result with an extremely low degree of association is connected as a slight sign, and may be useful as the judgment result 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 lowered, 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 detected favorably, and a lot of noise may be picked up. is there. On the other hand, if the threshold value is raised, there is a high possibility that the optimum search solution can be detected with high probability, but the degree of association is usually low and it is passed through, but it is suitable to appear once in tens or hundreds of times. Sometimes the solution is overlooked. It is possible to decide which one to prioritize based on the ideas of the user side and the system side, but it is possible to increase the degree of freedom in selecting the points 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, images of agricultural products are taken, and in addition to this, soil information, external environment information, history information, time information, type information, and knowledge, information, and data on the yield and quality of these are acquired, and the yield and quality are obtained. When information on cultivation methods of crops suitable for improvement is obtained, the degree of association is increased or decreased accordingly.

In other words, this update corresponds to learning in the sense of artificial intelligence. It can be said that it is a learning act because it acquires new data and reflects it in the learned data.

In addition, this update of the degree of association is done by the system side or the user side based on the contents of research data, papers, conference presentations, newspaper articles, books, etc. by experts, except when it is based on information that can be obtained from the public communication network. It may be updated artificially or automatically. Artificial intelligence may be utilized in these update processes.

Further, the process of first creating the trained model and the above-mentioned update may use not only supervised learning but also unsupervised learning, deep learning, reinforcement learning, and the like. In the case of unsupervised learning, instead of reading and learning the data set of input data and output data, information corresponding to the input data is read and trained, and the degree of association related to the output data is self-formed from there. You may let it.

Second Embodiment Hereinafter, the second embodiment using an unmanned aerial vehicle for the agricultural system 1 to which the present invention is applied will be described in detail with reference to the drawings.

FIG. 8 shows the appearance configuration of the unmanned aerial vehicle 1 to which the present invention is applied and the operation terminal 2 for maneuvering the unmanned aerial vehicle 1.

The unmanned aerial vehicle 1 is a so-called small drone (multicopter) or unmanned helicopter capable of unmanned flight, and has a rotor 11, a rotor motor 12 for driving the rotor 11, and a rotor motor 12 attached to the tip. The motor stay 13, the installation device 20 attached to the base of the motor stay 13, the first central plate 16 and the second central plate 17 that sandwich the installation device 20 from above and below, and the second central plate 17 are provided. The control unit 15 is provided with a third central plate 18 provided parallel to the second central plate 17 so as to be separated from the upper side, and a battery 14 provided on the third central plate 18.

Further, the unmanned aerial vehicle 1 includes a plurality of legs 26 extending downward from the first central plate 16, two skids 28 provided at the lower ends of the legs 26, and the two skids. A mounting arm 27 erected on the 28, a chemical tank 24 mounted on the mounting arm, a pair of left and right right booms 21 and a left boom 22 extending outward from the legs 26. The nozzles 23a to 23c provided on the right boom 21 and the nozzles 23d to 23f provided on the left boom 22 are provided.

The rotor 11 rotates based on the rotation of the rotor motor 12, and can give buoyancy to the unmanned aerial vehicle 1. In the present embodiment, a quadcopter having four rotors 11 will be described as an example, but the description is not limited to this, and the required flight performance, reliability against failures, allowable cost, etc. It is embodied as a helicopter composed of one rotor 11, a tricopter composed of three rotors 11, a hexacopter composed of six rotors 11, and an octocopter composed of eight rotors 11 according to the above. It may be a thing.

The rotor motor 12 is provided for each of the rotors 11 and is capable of rotating based on the electric power supplied from the battery 14 via the motor stay 13. The rotor motor 12 is not limited as long as it has the above functions, and any commercially available motor 12 can be applied. The rotor 11 can be rotated by rotating the rotor motor 12, and the unmanned aerial vehicle 1 can be immediately raised or lowered in the vertical direction, or can be stopped in place. Further, when the unmanned aerial vehicle 1 is moved back and forth and left and right, the rotation speed of the rotor motor 12 in the traveling direction is decreased, and the rotation speed of the rotor motor 12 on the opposite side of the traveling direction is increased. As a result, the unmanned aerial vehicle 1 is in a leaning posture with respect to the traveling direction, and can move in the traveling direction. Further, by adjusting the output according to the rotation direction of the rotor motor 12, it is possible to rotate the unmanned aerial vehicle 1 itself. The rotation speed of the rotor motor 12 is controlled via the control unit 15.

The motor stay 13 extends from the first central plate 16 and the second central plate 17 in different directions. In particular, when it is composed of a quadcopter having four rotors 11, the motor stays 13 supporting each of them are extended so as to be spaced about 90 ° from each other in a plan view. The motor stay 13 may be made of a tube made of, for example, metal or resin, carbon, or other material. In such a case, a cable for supplying electric power from the battery 14 can be inserted into the tube of the motor stay 13.

The first central plate 16 and the second central plate 17 are each made of a plate-like body made of metal, resin, or the like. The first central plate 16 and the second central plate 17 are provided so as to be substantially parallel to each other via an installation device 20 to be sandwiched. The first central plate 16 is provided with screw holes and the like (not shown) necessary for attaching the legs 26 in advance. Similarly, the second central plate 17 is provided with screw holes necessary for attaching the control unit 15 in advance.

The control unit 15 is composed of a housing for accommodating integrated circuits and devices required for various controls. The control unit 15 is fixed to a screw hole provided on the second central plate 17 via a screw. Details of the block configuration of the control unit 15 will be described later.

The third central plate 18 is made of a plate-like body made of metal, resin, or the like. The third central plate 18 is provided so as to be parallel to the second central plate 17 while being separated from the second central plate 17 by being fixed via a long screw 18a erected on the surface of the second central plate 17. ..

The battery 14 is a battery for supplying electric power necessary for driving the control unit 15 and the rotor motor 12. The battery 14 also supplies the power required to control the nozzle 23. The battery 14 may be detachably configured and rechargeable.

The skid 28 provided at the lower end of the leg portion 26 is provided for grounding the unmanned aerial vehicle 1 when it lands on the ground. Similarly, the mounting arm 27 provided between the skids 28 also plays a role of grounding the unmanned aerial vehicle 1 when it lands on the ground, but also plays a role of supporting the chemical liquid tank 24 from below.

The right side boom 21 and the left side boom 22 may be provided with respect to the leg portion 26 via a rotating device 29a and a rotating device 29b. As a result, the right side boom 21 and the left side boom 22 are configured to be rotatable in the direction A in the drawing by the rotating device 29a and the rotating device 29b. For example, when the unmanned aerial vehicle 1 is stored in a warehouse or the like, not only can it be removed, but also the right boom 21 and the left boom 22 can be rotated upward and folded via the rotating devices 29a and 29b. .. Further, by freely rotating the right side boom 21 and the left side boom 22 in the A direction via the rotating devices 29a and 29b, it is possible to adjust the spraying direction of the spray liquid from the nozzle 23. Since the right side boom 21 and the left side boom 22 are provided slightly above the lower end of the leg portion 26, the nozzle 23 is on the ground when the unmanned aerial vehicle 1 is grounded via the skid 28 at the time of landing. Can be prevented from coming into contact with. The right side boom 21 and the left side boom 22 may be manually rotated via the rotating devices 29a and 29b, or the rotating devices 29a and 29b themselves may be rotated via an electric signal from the control unit 14. It may be automatically rotated.

At the time of landing, the aircraft of the unmanned aerial vehicle 1 lands horizontally, but if there is an operation error or a crosswind at the time of landing, the aircraft may tilt. In preparation for such a case, the right boom 21 and the left boom 22 may be folded upward to prevent the boom from coming into contact with the ground at the time of landing.

The chemical liquid tank 24 is a tank for storing the spray liquid, and the material thereof is made of a material such as resin or metal. The chemical liquid tank 24 has a lid 24a provided so as to be openable and closable. When the spray liquid is injected, the lid 24a is opened, and when the spray liquid is actually sprayed, the lid 24a is opened so as not to leak. The lid will be closed tightly. The chemical tank 24 may be removed from the unmanned aerial vehicle 1 by a simple operation. In such a case, by preparing a plurality of chemical liquid tanks 24 in advance and filling them with the spraying liquid, it is possible to efficiently perform the spraying a plurality of times.

The spray liquid stored in the chemical liquid tank 24 is supposed to be a pesticide for spraying on agricultural land, but is not limited to this, and includes, for example, liquid fertilizer, paint, water, and any other liquid. .. A hose 32 extends from the inside of the chemical tank 24, and each hose 32 is continuous with the nozzles 23a to 23c provided on the right boom 21 and the nozzles 23d to 23f provided on the left boom 22. The chemical liquid tank 24 is not limited to the case where it is mounted on the mounting arm 27, and may be suspended from a structure composed of the first central plate 16 and the installation device 20. Alternatively, it may be suspended from a plurality of legs 26 or the like.

FIG. 9 shows the flow path configuration from the chemical liquid tank 24 to the nozzle 23. The spray liquid discharged from the chemical liquid tank 24 branches into two spray liquid pipes 36a and 36b and flows. Then, the spray liquid pipe 36a reaches the chemical liquid pump 35a, and the spray liquid pipe 36b reaches the chemical liquid pump 35b. The hose 32 is continuously connected to the nozzles 23a to 23c from the chemical pump 35a. Further, the hose 32 is continuously connected to the nozzles 23d to 23f from the chemical liquid pump 35b.

Here, the chemical liquid pumps 35a and 35b have a structure in which the spray liquid is sucked from the spray liquid pipes 36a and 36b by the piston reciprocating with the motor as a power source and discharged to the hoses 32 and the nozzles 23a to 23c and 23d to 23f. It is a thing. By the way, the chemical liquid pumps 35a and 35b can be independently controlled via the control unit 15. For example, when the operation command is transmitted from the control unit 15 for the chemical solution pump 35a and the operation command is not transmitted from the control unit 15 for the chemical solution pump 35b, the spray liquid is discharged only from the nozzles 23a to 23c connected to the chemical solution pump 35a. While being injected, it can be controlled to stop the injection of the spray liquid from the nozzles 23d to 23f connected to the chemical liquid pump 35b. In the above-mentioned example, the case where the chemical solution pumps 35a and 35b are configured has been described as an example, but the present invention is not limited to this, and the chemical solution pump 35 is used especially in the case of spraying a relatively small volume. It may be composed of only one. Further, when spraying a large volume of spraying liquid, the chemical liquid pump 35 may be composed of three or more.

Further, by controlling the discharge force of the chemical liquid pump 35, it is possible to control the amount of the sprayed liquid sprayed from the nozzle 23. That is, the amount of the spray liquid sprayed from the nozzle 23 can be reduced by weakening the discharge force of the spray liquid from the chemical liquid pump 35, and the nozzle 23 can be strengthened by increasing the discharge force of the spray liquid from the chemical liquid pump 35. The amount of sprayed liquid from the water can be increased. Moreover, since the discharge force can be controlled separately between the chemical liquid pumps 35a and 35b, it is possible to control the spraying amount of the nozzles 23a to 23c and the nozzles 23d to 23f independently of each other. When two chemical liquid pumps 35a and 35b are used, the flow rate control device for each nozzle 23 may be omitted. In such a case, the discharge amount for each of the right boom 21 and the left boom 22 is simply changed. This configuration only controls the discharge amount for each of the left and right sides of the machine body, but the structure of each nozzle 23 can be simplified and the cost can be reduced.

The nozzle 23 is supported by the right boom 21 or the left boom 22 described above, and the spray liquid is sent via the connected hose 32. In the present embodiment, the case where the nozzles 23 are arranged in the six nozzles 23a to 23f will be described as an example, but the present invention is not limited to this, and any number of nozzles 23 may be arranged.

The nozzle 23 sprays the sent spray liquid at a predetermined diffusion angle. The diffusion angle of the spray liquid and any one or more of the spray directions may be controllable. When changing the diffusion angle of the spray liquid, for example, a commercially available spray nozzle having a variable diffusion angle may be used. Further, when the spraying direction is changed, a commercially available spray direction free nozzle may be used. The diffusion angle or spraying direction of these spray liquids may be changed manually, or may be changed based on an electrical signal under the control of the control unit 15. In such a case, by combining the nozzle 23 with a servomotor, it is possible to automatically adjust the diffusion angle and the spraying direction of the nozzle 23 based on an electric signal.

Next, the detailed configuration of the control unit 15 will be described. As shown in FIG. 10, the control unit 15 is centered on a flight controller 50, and includes a wireless communication unit 51, an electric gimbal 52, a camera 53, and an ESC (Electronic Speed Controller) 54 connected to the flight controller 50. There is. The configuration of the electric gimbal 52 and the camera 53 is not essential and may be omitted.

The wireless communication unit 51 also includes an antenna that converts an electric signal into a radio wave or converts a radio wave into an electric signal by performing frequency conversion and other various conversion processes necessary for performing wireless communication with the operation terminal 2. Is done. The wireless communication unit 51 converts the maneuvering information superimposed on the radio waves transmitted from the operation terminal 2 into an electric signal, and then outputs the flight controller 50. As a result, control of the flight controller 50 based on the flight control information from the operation terminal 2 is realized. Further, the wireless communication unit 51 converts the data sent from the flight controller 50 into radio waves and transmits the data to the operation terminal 2. If possible, these data may be transmitted to a public communication network such as an Internet network. The wireless communication unit 51 may acquire various information from the public communication network through wireless communication and transmit the information to the flight controller 50.

The flight controller 50 includes a control unit 57, a flight control sensor group 55 connected to the control unit 57, and a GNSS (Global Navigation Satelite System) receiving unit 56.

The control unit 57 has a CPU (Central Processing Unit) 111, a memory 112 connected to the CPU 111, and a PWM controller 113, respectively. The control unit 57 is connected to the chemical pump 35 and the nozzle 23.

The memory 112 is a storage means embodied as a ROM (Read Only Memory) or a RAM (Random Access Memory). The ROM stores a program for controlling the hardware resources of the entire control unit 15. The RAM is also used as a work area used for data storage and expansion, and temporarily stores various instructions for controlling the hardware resources of the entire control unit 15.

The CPU 111 is a so-called central arithmetic unit for controlling all the components. The CPU 111 reads a program stored in the memory 112 and notifies each component of an instruction for performing various operations. For example, if the program stored in the memory 112 relates to a method of determining the flight path of the unmanned aerial vehicle 1 or a flight method, various commands for flying based on the method are stationary and transmitted to each component. If the program stored in the memory 112 relates to a method for spraying the spray liquid by the unmanned aerial vehicle 1, various commands for spraying the spray liquid are generated based on the program and transmitted to each component.

Further, the CPU 111 generates various commands based on the maneuvering information and other information sent from the wireless communication unit 51 and transmits them to each component. Further, the CPU 111 controls each component based on the data sent from the flight control sensor group 55 and the current position information of the unmanned aerial vehicle 1 sent from the GNSS receiving unit 56. Further, the CPU 111 generates and transmits an electrical signal for controlling the connected chemical liquid pump 35 and nozzle 23. The CPU 111 controls the electric gimbal 52 and the camera 53, respectively, and also transmits necessary commands to the PWM controller 113.

The PWM controller 113 controls the rotation speed, rotation speed, etc. of the rotor motor 12 via the ESC 54 under the control of the CPU 111.

The flight control sensor group 55 includes at least an acceleration sensor, an angular velocity sensor, a pressure sensor (altitude sensor), a geomagnetic sensor (orientation sensor), an altitude meter for detecting flight altitude, and an anemometer for detecting wind speed and direction. It is composed of various sensors such as an acceleration sensor and a gyro sensor for detecting the tilt angle and tilt direction of the aircraft. By the way, the flight control sensor group 55 is not limited to the case where all of these sensors are mounted. For example, the flight speed of the unmanned aerial vehicle 1 can be detected from an acceleration sensor and an angular velocity sensor. Further, the tilt direction and tilt angle of the unmanned aerial vehicle 1 can be detected from the gyro sensor, the acceleration sensor, and the angular velocity sensor. Further, the wind direction and anemometer can detect the wind direction and speed of the wind blowing on the spot during the flight of the unmanned aerial vehicle 1 in real time. It is possible to detect the flight altitude of the unmanned aerial vehicle 1 in real time from the altimeter. The flight control sensor group 55 transmits each detected data to the control unit 57.

The GNSS receiving unit 56 acquires the current position information of the unmanned aerial vehicle 1 at the time of flight in real time based on the satellite positioning signal sent from the artificial satellite. The GNSS receiving unit 56 transmits the acquired position information to the control unit 57.

The electric gimbal 52 is a turntable on which the camera 53 is mounted. The electric gimbal 52 is rotatably configured under the control of the CPU 111 in the control unit 57. By rotating the electric gimbal 52, the shooting direction of the camera 53 can be changed. The electric gimbal 52 may be provided with a vibration absorbing mechanism for preventing the vibration from the unmanned aerial vehicle 1 from being transmitted to the camera 53.

The camera 53 captures a subject in a shooting direction determined based on the rotation of the electric gimbal 52. The imaging timing of the camera 53 will be controlled by the CPU 111. The camera 53 transmits the captured image to the control unit 57. The image transmitted to the control unit 57 is stored in the memory 112 under the control of the CPU 111, and may be sent to the public communication network via the wireless communication unit 51 as needed.

Among the above-mentioned components, the flight controller 50, the electric gimbal 52, the camera 53, and the ESC 54 are all connected to the battery 14 to supply electric power.

The operation terminal 2 is composed of terminal devices capable of wireless communication such as a PC (personal computer), a mobile terminal, a smartphone, a tablet terminal, and a wearable terminal, but the operation terminal 2 is not limited to this, and is not limited to this. It may be embodied by. The operation terminal 2 includes a user I / F 6 for the user to actually perform a desired operation, and a wireless communication unit 7 connected to the user I / F 6.

The user I / F6 is composed of a touch panel, buttons, levers, and the like for inputting maneuvering information for maneuvering the unmanned aerial vehicle 1. The user I / F6 also includes a liquid crystal panel or the like for displaying various information to the user. The user I / F 6 transmits the input maneuvering information to the wireless communication unit 7. Further, when various information received by the wireless communication unit 7 is transmitted, the user I / F 6 displays it to the user via a liquid crystal panel or the like as necessary.

The wireless communication unit 7 also includes an antenna that converts an electric signal into a radio wave or converts a radio wave into an electric signal by performing frequency conversion and other various conversion processes necessary for performing wireless communication with the unmanned aerial vehicle 1. Is done. The wireless communication unit 7 outputs the information transmitted from the unmanned aerial vehicle 1 and the information transmitted from the public communication network to the user I / F6. Further, the wireless communication unit 7 converts the maneuvering information sent from the user I / F 6 into radio waves and transmits it to the unmanned aerial vehicle 1.

Next, the operation of the unmanned aerial vehicle 1 having the above-described configuration will be described.

First, the unmanned aerial vehicle 1 performs agricultural work. Agricultural work by this unmanned aerial vehicle 1 is spraying, sowing, pollination, etc. of a spray liquid consisting of water, fertilizer (liquid), pesticides, and the like. For sowing and pollination, powders and solids are sprayed, but by accommodating these in the above-mentioned chemical liquid tank 24, it is possible to spray them in the same manner.
When the user himself / herself inputs the agricultural work area, the input operation is performed via the user I / F6 on the control terminal 2. The input agricultural work target area is transmitted to the wireless communication unit 51 of the unmanned aerial vehicle 1 via the wireless communication unit 7. The control unit 57 in the flight controller 50 acquires the farm work target area and stores it in the memory 112 as needed.

Next, the CPU 111 actually formulates a flight plan for the map information based on this agricultural work target area. For the formulation of this flight plan, the flight plan formulation program stored in the memory 112 is read and executed. The formulation of the flight plan is not limited to the case of reading from the memory 112, and may be based on the input information from the user I / F6. In such a case, each time the input information regarding the flight plan is received from the user I / F6, it may be transmitted to the control unit 57 of the unmanned aerial vehicle 1.

FIG. 11 shows an example of formulating a flight plan. The CPU 111 formulates a flight plan so that the acquired agricultural work target area 71 can be almost filled with, for example, the actual agricultural work range indicated by diagonal lines. For example, since the width w of the spraying area to which the spray liquid is sprayed from the nozzle 23 in the unmanned aerial vehicle 1 is known, various flight path candidates that can fill the agricultural work target area 71 within the spraying range of this width w are listed. be able to. Among these, for example, by advancing in a zigzag shape as shown by the dotted line in FIG. 11, the agricultural work target area 71 can be covered by the spraying range of the width w around this. In this flight plan, as shown in FIG. 11, a route may be set so as to overrun the upper end or the lower end of the agricultural work target area 71, make a U-turn, and return to the agricultural work target area 71 again. As a result, the inside of the agricultural work target area 71 can be filled with the spraying range without any gap. By the way, during the flight outside the overrun agricultural work target area 71, the spraying of the spray liquid may be temporarily stopped.

In addition to this, when the area 71 reaches substantially the upper end or the lower end, the flight path may be made to make a U-turn by flying along the boundary between the upper end and the lower end without overrunning.

After setting such a flight path, the CPU 111 controls the PWM controller 113 to fly the unmanned aerial vehicle 1 based on the flight path. The PWM controller 113 flies on the flight path shown in FIG. 11 by controlling the rotation speed, rotation speed, rotation direction, etc. of the rotor motor 12 via the ESC 54 under the control of the CPU 111.

Further, in the process of flying on this flight path, the control unit 57 transmits an operation command to the chemical liquid pump 35 to discharge the spray liquid by the pump. As a result, the spray liquid stored in the chemical liquid tank 24 is sent to the nozzles 23a to 23f by the chemical liquid pump 35. The spray liquid sent to the nozzles 23a to 23f will be sprayed within the spray range.

In the process of spraying the spray liquid, the unmanned aerial vehicle 1 will continuously fly on the flight path. As a result, as shown in FIG. 11, the spray liquid can be sprayed over the spray range along the flight path. Then, by flying to the end point of the flight path, it becomes possible to spray the spray liquid over most of the spray target area 71.

In the present invention, the flight speed of the unmanned aerial vehicle 1 may be detected via an acceleration sensor, an angular velocity sensor, or the like in the flight control sensor group 55 in the process of flying in this flight path. The detected flight speed is sent to the control unit 57, and the control unit 57 controls the amount of sprayed liquid sprayed from the nozzle 23 by controlling the discharge force of the chemical liquid pump based on this flight speed.

Here, it is assumed that the flight speed of the unmanned aerial vehicle 1 is 20 km / hour and the spray amount is 1 l / sec, so that the spray amount per unit area in the spray target area 71 becomes appropriate. At the start of the flight, the flight speed and the amount of spray were set to be such, and when the flight speed was detected via the flight control sensor group 55 at point P, for example, the flight speed was 20 km as in the beginning. If it is / hour, no control is performed to change the spray amount. Next, when the flight speed measured at point Q is 25 km / hour, the amount of spraying per unit area is reduced by that amount because the flight speed is increased. Therefore, the control unit 57 that detects the flight speed controls the chemical solution pump 35 so that the amount of spraying is more than 1 l / sec. Next, when the flight speed measured at the R point is 15 km / hour, the flight speed is slowed down, so that the amount of spraying per unit area increases accordingly. Therefore, the control unit 57 that detects the flight speed controls the chemical solution pump 35 so that the spraying amount is lower than 1 l / sec.

In this way, in the present invention, the amount of the spray liquid stored in the chemical liquid tank 14 is controlled based on the detected flight speed. Thereby, the spraying amount of the spraying liquid per unit area in the agricultural land in the spraying target area 71 can be uniformly adjusted. As a result, it is possible to prevent uneven spraying amount of the spray liquid, and prevent pesticide burning due to the spray liquid spray amount being too large and disease and pest damage to crops due to the spray liquid spray amount being too small. It becomes possible.

In particular, even if the flight speed of the unmanned aerial vehicle 1 is set to be constant, the flight speed is not always constant due to sudden winds, changes in the surrounding environment, or each component of the unmanned aerial vehicle 1. It may blur in a small range. Even in such a case, by detecting the change in flight speed in real time and adjusting the spraying amount based on the change, it is possible to prevent the spraying liquid from being uneven as a result.

In the above-described embodiment, the case where the flight speed is detected at three points from the P point to the R point has been described as an example, but the description is not limited to this, and the flight speed is increased at a shorter pitch. It may be detected. In such a case, for example, the flight speed may be detected over a second, and the amount of spray may be controlled accordingly.

When spraying the spray liquid on the end portion 72 of the spray target area 71 as shown in FIG. 12, it may be effective to intentionally slow down the flight speed. In this way, the flight speed may be increased or decreased depending on the position in the spraying target area 71. In such a case, the current position information in the spray target area 71 is received in real time via the GNSS receiving unit 56, and the control unit 57 flies based on the relationship of the received position information with the spray target area 71. The speed may be controlled. Since the spray target area 71 is acquired in advance as map information, by superimposing the received position information on the map information, which position on the spray target area 71 the unmanned aerial vehicle 1 is currently flying is determined. Can be detected in real time. The control unit 57 will control the flight speed based on the information.

Further, the spray amount may be directly controlled or the spray range may be controlled by using the result of detecting in real time which position on the spray target area 71 the unmanned aerial vehicle 1 is currently flying. It may be. The method of controlling the spray amount is as described above, but when controlling the spray range, for example, as shown in FIG. 13, the spray liquid is sprayed only from the nozzles 23d to 23f, and the spray liquid is sprayed from the nozzles 23a to 23c. Control to stop the injection. These controls are realized by transmitting an operation command from the control unit 15 to the chemical liquid pumps 35a and 35b as described above. Since the control unit 15 detects in real time which position on the spray target area 71 it is flying, when it is determined that it is just flying at the end of the spray target area 71, it is a spray target. By injecting the spray liquid only from the nozzles 23d to 23f located on the region 71, the spray liquid can be sprayed on the crops. Further, by stopping the injection of the spray liquid from the nozzles 23a to 23c that are outside the spray target area 71, it is possible to prevent damage caused by spraying the spray liquid outside the spray target area 71.

Further, according to the present invention, the spraying amount of the spray liquid may be controlled based on the detected flight altitude. In such a case, the flight altitude of the unmanned aerial vehicle 1 may be detected via an altimeter or the like in the flight control sensor group 55. The detected flight altitude is sent to the control unit 57, and the control unit 57 controls the amount of the spray liquid sprayed from the nozzle 23 in real time by controlling the discharge force of the chemical liquid pump based on the flight altitude.

Further, according to the present invention, the camera 53 may be used to image a field of agricultural products in the process of the unmanned aerial vehicle 1 flying in the flight path. The image information captured by the camera 53 is sent to the search device 102 and is stored in the database 103. By taking images in time series in the process of the unmanned aerial vehicle 1 flying in the flight path on the field, it is possible to acquire image information in units of division areas (not shown) set on the flight path. The division region may be composed of, for example, a circle or a rectangle centered on the diameter W of P, Q, and R shown in FIG. Each position information of this division area is acquired via the GPS receiving unit 56. The position information of this division area is acquired and stored in association with the image information acquired for the division area.

In the present invention, we search for agricultural work to be performed on such an unmanned aerial vehicle 1. The search method is based on FIG. 5 in the first embodiment.

A method of searching for agricultural work will be described with reference to FIG. FIG. 14 shows an example in which a combination of reference image information and reference history information and three or more levels of association with the agricultural work to be performed by the unmanned aerial vehicle 1 are set for the combination. Of course, each node constituting this degree of association may be composed of each node of artificial intelligence and neural network.

As the input data, such reference image information and reference history information are arranged side by side. The intermediate node 61 is a combination of reference image information and reference history information as such input data.

The reference history information is the history of the agricultural work actually performed by the unmanned aerial vehicle 1 in the process of growing the crops. It summarizes what kind of farming work has been done from sowing to planting seedlings to harvesting. For example, it refers to any agricultural work through unmanned aerial vehicle 1, such as watering, fertilizing, spraying pesticides, sowing seeds, pollinating pollen.

If the agricultural work corresponding to the output is, for example, spraying a pesticide, the agricultural work A has a flight speed of 20 km / hour in the division area P, a spray amount of 1 l / sec, and a flight speed of 15 km / hour in the division area Q. , The spray amount is set to 1.5 l / sec, etc., and the agricultural work B has a flight speed of 10 km / hour in the division area P, a spray amount of 2 l / sec, and a flight speed of 12 km / second in the division area Q. At times, the spray rate is set to 1.3 l / sec or the like. The reference history information is also organized in the same way for the agricultural work that has been done so far.

The reference image information is an image of a field taken aerial from the above-mentioned unmanned aerial vehicle 1, and may be composed of not only a visible image but also an infrared image and a spectrum image.

The search device 102 acquires in advance the degree of association w13 to w22 of three or more stages shown in FIG. That is, the search device 102 accumulates reference image information, reference history information, and data on which farm work is optimal in that case when newly searching for farm work by the actual unmanned aerial vehicle 1. By analyzing and analyzing these, the degree of association shown in FIG. 14 is created.

This degree of association becomes the learned data, which may be configured based on the reference image information acquired for fields other than the work target field, the reference history information, and the farm work in that case, or the work target. It may be obtained from the same field in the field. An image of an image of a field (reference image information) obtained by actually flying an unmanned aerial vehicle 1 and a reference history information consisting of agricultural work performed by the unmanned aerial vehicle 1 for the field) are acquired and performed for the field. Learn which farming work is right for you. Its suitability may be determined based on how much the yield was as a result of the actual farming work.

In the example of the degree of association shown in FIG. 5, the node 61b is a node in which the reference image information P11 is combined with the reference external environment information P22, the degree of association of the agricultural work C is w15, and the degree of association of the agricultural work E is. It is w16.

On the premise that such a degree of association is set, image information is newly acquired by imaging the crops in the field where the unmanned aerial vehicle 1 is actually subjected to agricultural work. In addition, the history information of the farm work up to now in the field where the farm work is actually performed on the unmanned aerial vehicle 1 is acquired. The image information corresponds to the reference image information, and the history information corresponds to the reference history information.

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

In searching for a cultivation method of agricultural products, the degree of association shown in FIG. 14 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 history information corresponds to the reference history information P23, the combination is associated with the node 61c, and the node 61c is associated with the combination. Agricultural work B is associated with a degree of association w17, and agricultural work D is associated with a degree of association w18. As a result of such a degree of association, based on w17 and w18, the new image information and history information are actually acquired, and the agricultural products to be carried out for the unmanned aerial vehicle 1 are searched for and obtained. ..

As a result of the search, the pesticide is sprayed in the division area P at a flight speed of 10 km / hour and a spray amount of 2 l / sec, and in the division area Q at a flight speed of 12 km / hour and a spray amount of 1.3 l / sec. When it is searched for, the search device 102 creates a work instruction and a work command for the unmanned aerial vehicle 1 to perform such farm work, and transmits this to the unmanned aerial vehicle 1. The unmanned aerial vehicle 1 that has received the work instruction and the work order flies over the field under the control of the CPU 111, and executes the operation according to the work instruction and the work order. That is, the work control of the unmanned aerial vehicle 1 is performed on the search device 102 side.

Incidentally, when the agricultural work to be performed by the unmanned aerial vehicle 1 sprays a spray liquid of any of pesticides, water, and fertilizers, the farm work as an output may be configured by the spray amount and the flight speed of the spray liquid. As a result, the agricultural work to be searched can be acquired through the amount of spray and the flight speed. In such a case, the yield as a result of the agricultural work and the degree of association formed based on the price information of the spray liquid may be acquired. In other words, when constructing each weighting of the degree of association, the price of the spray liquid is taken into consideration in addition to the yield amount, and these data are acquired and then linked. If the yield increases as the amount of spray liquid increases, the weighting of the output solution with a large amount of spray liquid is increased, but if the total amount of spray liquid in the entire field is large, the cost of the spray liquid increases. That is, the optimum amount of application and flight speed for each division area are determined by the balance between the total amount of application and the amount of harvest in the entire field. Therefore, these data may be reflected in the degree of association.

By taking images in time series in the process of the unmanned aerial vehicle 1 flying in the flight path on the field, the image information is acquired in units of the division areas set on the flight path. Further, the search for agricultural work according to FIG. 14 searches for agricultural work to be performed in units of divided areas such as division areas P, Q, .... Further, in the process of controlling the work by the search device 102, the agricultural work to be executed by the unmanned aerial vehicle 1 is controlled for each division area.

As a result, it is possible to have an unmanned aerial vehicle perform farming work based on the instructions given by artificial intelligence, which gives the best advice for improving the yield and quality of crops, and the yield and quality of crops. Can be realized while reducing the burden of labor.

In the above-mentioned example, a case where the search device 102 performs a search by artificial intelligence and controls the farm work by the unmanned aerial vehicle 1 based on the search device 102 is described, but the search device 102 is not limited to this. All the search functions executed on the side may be implemented on the unmanned aerial vehicle 1 side. If necessary, the degree of association and the trained model stored in the database 103 may be stored in the unmanned aerial vehicle 1.

As a result, it is possible to search and control agricultural work from beginning to end through the unmanned aerial vehicle 1 in which all of these functions are implemented, without going through the search device 102.

In the process of controlling the agricultural work of the unmanned aerial vehicle 1, the agricultural work may be executed by searching for the flight path of the unmanned aerial vehicle 1 and controlling the flight of the searched flight path.

FIG. 15 shows an example in which three or more levels of association with the flight path of the unmanned aerial vehicle 1 are set for reference agricultural work information. Of course, each node constituting this degree of association may be composed of each node of artificial intelligence and neural network.

As input data, such reference farm work information is lined up. The reference agricultural work information is obtained by converting the agricultural work searched by the degree of association shown in FIG. 14 into reference information, and the type of information is the same as that of the agricultural work as the output data shown in FIG.

The flight path corresponding to the output is a flight path for carrying out agricultural work of the unmanned aerial vehicle 1, for example, a route traveling on the field as shown in FIG. 11, or a route traveling on P, Q, R at the shortest distance. It is information for identifying whether to proceed or what other flight route to take.

The search device 102 acquires in advance the degree of association w13 to w22 of three or more stages shown in FIG. That is, the search device 102 accumulates reference farm work information and data on which flight route is optimal in the case of newly searching the farm work by the actual unmanned aerial vehicle 1, and analyzes these. , The degree of association shown in FIG. 15 is created by analysis.

This degree of association becomes the learned data, but this may be configured based on the reference agricultural work information acquired for other than the field to be worked on, and the flight path in that case, or the same in the field to be worked. It may be obtained from the field. In order to fly the unmanned aerial vehicle 1 that actually performs the farm work and perform each farm work, which route uses the least amount of electricity, which route has the highest degree of reduction of the spray liquid, which route If so, the weighting of the degree of association may be determined based on whether the yield is large or not.

On the premise that such a degree of association is set, the agricultural work actually searched by the method shown in FIG. 14 is newly acquired. Then, the optimum flight path is searched for by referring to the degree of association shown in FIG. 15 acquired in advance. Then, the unmanned aerial vehicle 1 is flown based on the searched flight path to control the agricultural work.

For example, a large amount of spray liquid is sprayed on the Q region and the R region, and when it is found that the spray liquid does not need to be sprayed on the P region, the spray liquid is directly flown to the Q region and sprayed without going through the P region. It is more efficient to move to the R region and then spray. In this way, in the agricultural work to be actually carried out, the optimum flight route will be searched through the degree of linkage shown in FIG.

In the present invention, for example, as shown in FIG. 16, the state of the crops in the field may be acquired by tracking in time series, and the optimum farming work may be executed on the unmanned aerial vehicle 1 each time.

The first degree of association shown in FIG. 16 is the same as that in FIG. The unmanned aerial vehicle 1 is made to perform the agricultural work searched through this first degree of association. Then, the image of the agricultural product after the execution is taken by the unmanned aerial vehicle 1. Next, the difference between the image information captured first and the image information captured later in referring to the first degree of association is obtained. The method of obtaining this difference may be obtained through the difference value between the brightness of the image captured first and the brightness of the image of the crop after executing the searched agricultural work. The difference between the image information obtained first and the image information after the searched farm work is executed is defined as a difference image. Through this difference image, the third degree of association is used to search for the agricultural work to be performed on the unmanned aerial vehicle 1. Before executing these, the third degree of association is configured in advance.

The third degree of association is the reference difference image obtained by detecting the difference between the image information obtained by capturing the image of the agricultural product after the agricultural work is executed and the reference image information, and the unmanned aerial vehicle 1 for the agricultural product. It is composed of a combination having a second reference history information including a history of farm work performed by the unmanned aerial vehicle 1 and a farm work to be performed next by the unmanned aerial vehicle 1 for the combination.

The reference difference image is the same as the method for constructing the difference image described above. Further, the second reference history information is information on the farm work history of the actually unmanned aerial vehicle 1 that has carried out the farm work searched through the first linkage degree. Since this second reference history information is the same as the agricultural work searched through the first linkage degree, the agricultural work searched through the first linkage degree may be applied as it is, or the work history may be applied again. It may be generated by importing. The work history may be obtained, for example, by recording the actual flight path by the unmanned aerial vehicle 1 and the amount of sprayed liquid sprayed by the search device 102.

Through such a reference difference image and the second reference history information, the relationship between the agricultural work actually performed on the unmanned aerial vehicle 1 and the image information (reference difference image) as a result of this is optimal. You can explore various farming operations. If it is found through the difference image that the pests have almost died due to the pesticide spraying as a result of carrying out the agricultural work searched through the first linkage degree, the amount of pesticide sprayed is based on the difference image and the history information applied so far. Reduce the cost of the spray liquid by reducing the amount of water. Set a high degree of association for agricultural work. Similarly, if it is found through the difference image that pests are hardly killed by spraying pesticides as a result of carrying out the agricultural work searched through the first degree of association, the difference image and the history information applied so far are used. , Set a high degree of association for agricultural work such as increasing the amount of pesticide sprayed and changing the type of pesticide.

Such a degree of association is created in advance in the relationship between the reference difference image and the agricultural work with respect to the second reference history information. This method of making may be the same as the example of FIG. 14 described above. Then, when searching for the farm work of the unmanned aerial vehicle 1 that actually carries out the farm work, the history information (second history information) of the farm work carried out on the unmanned aerial vehicle 1 through the first linkage degree and the unmanned vehicle 1 The difference image captured by the aircraft 1 is acquired. Then, the second history information is compared with the second reference history information, and the difference image is compared with the reference difference image to search for the agricultural work to be performed next. The method for causing the unmanned aerial vehicle 1 to carry out the searched agricultural work is the same as described above.

FIG. 17 shows a case where a combination of three or more stages with the reference market condition information is further set for the degree of association shown in FIG. FIG. 17 shows an example in which, in addition to the above-mentioned reference image information and reference history information, a combination of reference market condition information and three or more levels of association with agricultural work for the combination are set. ing.

The reference market information shows all the information related to the market conditions of agricultural products, and the market price, price movement, market fluctuation tendency, etc. are converted into data for each type of agricultural product. The method of performing a solution search using the degree of association in which output solutions are set for such three or more reference information will be omitted below by quoting the explanation of FIG.

By actually searching for the optimum farming work including market information, it is possible to control whether to have a good harvest, a slightly good harvest, or a bad harvest. When the production is adjusted according to the market conditions, the unmanned aerial vehicle 1 is made to perform the agricultural work according to the production amount to be adjusted. In this production adjustment, for example, the production amount may be slightly reduced while suppressing the cost by intentionally reducing the amount of pesticides and fertilizers.

In the past, under what market conditions and how much production adjustment was desired from the viewpoint of cost effectiveness, we verified from market condition data, cost data, actual sales data, etc., and set the degree of association based on this. deep. Then, in the case of actually searching for the agricultural work to be executed by the unmanned aerial vehicle 1, the current market condition information (market condition information) up to the present is taken in, and the judgment is made by comparing this with the reference market condition information.

FIG. 18 shows a case where the degree of association shown in FIG. 14 is further combined with the reference climate information in three or more stages. FIG. 18 shows an example in which, in addition to the above-mentioned reference image information and reference history information, a combination of reference climate information and three or more levels of association with agricultural work for the combination are set. ing.

The reference climate information shows all the information about the climate, and consists of data such as temperature, humidity, wind direction, typhoon, rainfall, daily illuminance, and weather (sunny, cloudy, rain). The method of performing a solution search using the degree of association in which output solutions are set for such three or more reference information will be omitted below by quoting the explanation of FIG.

By actually searching for the optimum farm work including climate information, the optimum farm work may change depending on what the climate was like in the search for the actual farm work.

In the past, what kind of climate and how much farming work was desired from the viewpoint of yield is verified from the above-mentioned climate data and yield data, and the degree of association is set based on this. Then, in the case of actually searching for the agricultural work to be executed by the unmanned aerial vehicle 1, the current climate information (climate information) up to the present is taken in, and the judgment is made by comparing this with the reference climate information.

It should be noted that the present invention is not limited to the above-described embodiment, and it is needless to say that the present invention may be embodied as an unmanned aerial vehicle 1 equipped with the above-mentioned linkage degree search function.

1 Agricultural system 2 Search device 121 Internal bus 123 Display unit 124 Control unit 125 Operation unit 126 Communication unit 127 Estimating unit 128 Storage unit 61 node

The agricultural system according to the present invention is an agricultural system in which agricultural work is carried out by an unmanned aerial vehicle. The first association that obtains in advance the first degree of association of three or more stages between the combination having the first reference history information including the history of the farm work performed and the farm work to be performed by the unmanned aerial vehicle next to the combination. Degree acquisition means, first image information obtained by capturing a field of agricultural products to be newly farmed by an unmanned aerial vehicle, and first history information including a history of farm work performed on the field by the unmanned aerial vehicle. The first image information and the first history acquired through the information acquisition means by referring to the first information acquisition means for acquiring the information and the first association degree acquired by the first association degree acquisition means. Based on the information, the first information acquisition means is provided with a search means for searching for agricultural work to be performed by the unmanned aerial vehicle and a work control means for causing the unmanned aerial vehicle to execute the agricultural work searched by the search means. Acquires the first image information in the division area unit set on the flight path by taking images in time series in the process of the unmanned aerial vehicle flying in the flight path on the field, and obtains the first image information in the division area unit, and obtains the first image information in the division area unit. Is characterized in that it searches for agricultural work to be performed in the divided area unit, and the work control means controls the agricultural work to be executed by the unmanned aerial vehicle in the divided area unit.

Claims (7)

In an agricultural system where unmanned aerial vehicles are used for agricultural work
A combination having a first reference image information in which a crop in the growing process is imaged in advance by an unmanned aerial vehicle and a first reference history information including a history of agricultural work performed on the crop by the unmanned aerial vehicle. The first association degree acquisition means for acquiring in advance the first association degree of three or more stages with the agricultural work to be performed by the unmanned aerial vehicle next to the combination, and
The first image information obtained by capturing a field of a crop to be newly farmed by an unmanned aerial vehicle and the first history information including the history of the farming work performed by the unmanned aerial vehicle. Information acquisition means and
With reference to the first degree of association acquired by the first degree of association acquisition means, based on the first image information and the first history information acquired through the above information acquisition means, then by the above-mentioned unmanned aerial vehicle. Search means for exploring the agricultural work to be done,
It is provided with a work control means for causing the unmanned aerial vehicle to execute the agricultural work searched by the search means.
The first information acquisition means obtains images in time series in the process of an unmanned aerial vehicle flying in a flight path on the field, thereby performing first image information in units of division areas set on the flight path. To get and
The search means searches for agricultural work to be performed in each of the divided areas, and
The work control means is an agricultural system characterized in that the agricultural work to be executed by the unmanned aerial vehicle is controlled in units of the divided areas. It is provided with a second degree of association acquisition means for acquiring in advance a second degree of association of three or more stages between the reference agricultural work information consisting of the agricultural work searched by the search means in the division area unit and the flight path of the unmanned aerial vehicle. ,
When a new agricultural work is searched by the search means, the work control means refers to the second linkage degree acquired by the second linkage degree acquisition means, and is used for reference according to the searched agricultural work. The agricultural system according to claim 1, wherein the flight path is searched based on the second degree of association between the agricultural work information and the flight path in three or more stages, and the above-mentioned agricultural work is executed based on the searched flight path. When the agricultural work to be performed by the unmanned aerial vehicle sprays a spray liquid of pesticide, water, or fertilizer, the first degree of association acquisition means constitutes the farm work by the spray amount and flight speed of the spray liquid. ,
The search means refers to the first degree of association acquired by the first degree of association acquisition means, and based on the first image information and the first history information acquired through the information acquisition means, the following The agriculture according to claim 1, wherein the farming work to be performed by the unmanned aerial vehicle is searched for, and the farming work is executed based on the searched spraying amount and flight speed. system. The second association degree acquisition means is characterized in that the first association degree is acquired based on the yield amount as a result of the agricultural work and the total amount of the sprayed liquid sprayed amount. Agricultural system. The reference difference image obtained by detecting the difference between the image information obtained by capturing the image of the agricultural product after the agricultural work is executed and the first reference image information, and the agricultural product are subjected to the unmanned aerial vehicle. A third association that obtains in advance a third degree of association of three or more stages between a combination having a second reference history information including a history of farm work performed and the next farm work to be performed by the unmanned aerial vehicle for the combination. Degree acquisition means and
The difference image obtained by detecting the difference between the second image information obtained by capturing the image of the agricultural product after the agricultural work is executed by the work control means and the first image information, and the work control means execute the operation. It is provided with a second information acquisition means for acquiring a second history information including the history of the farm work that has been performed.
The search means refers to the third degree of association acquired by the third degree of association acquisition means, and based on the difference image acquired through the second information acquisition means and the second history information, the following The agricultural system according to any one of claims 1 to 4, wherein the agricultural work to be performed by the above-mentioned unmanned aerial vehicle is searched for. The first degree of association acquisition means acquires in advance three or more stages of the first degree of association with the above combination with the reference climate information regarding the climate condition in the growing process of the crop and the next agricultural work to be performed by the above unmanned aerial vehicle. ,
The first information acquisition means is to acquire climatic information on the climatic conditions in the process of growing crops for new agricultural work.
The search means refers to the first degree of association acquired by the first means for acquiring the degree of association, and further, based on the climate information acquired through the means for acquiring information, the agricultural work to be performed next by the unmanned aerial vehicle is performed. The agricultural system according to any one of claims 1 to 5, characterized in that it is searched. The first association degree acquisition means acquires in advance three or more stages of the first association degree with the agricultural work to be performed by the unmanned aerial vehicle next to the combination with the reference market condition information regarding the market condition of the crop.
The first information acquisition means described above acquires market information regarding the market conditions of agricultural products for which new agricultural work is to be performed.
The search means refers to the first degree of association acquired by the first means for acquiring the degree of association, and further, based on the market condition information acquired through the means for acquiring information, the agricultural work to be performed next by the unmanned aerial vehicle is performed. The agricultural system according to any one of claims 1 to 6, characterized in that it is searched.

Images