Pest detection device and pest occurrence forecast system

Abstract

Provided is a pest detection device capable of detecting pests simply and with high accuracy, and a pest occurrence prediction system capable of predicting the occurrence of pests simply and with high accuracy. [Solution] This device does not have a mechanism for catching or collecting pests, and is composed of a pest attractant unit 2, an imaging unit 3, a temperature measuring unit 4a, a humidity measuring unit 4b, and a solar cell unit 6. The pest attractant unit 2 is composed of a pheromone agent 21, a protective member 22, and a background plate 23. The imaging unit 3 has an infrared sensor 31, and acquires image data of a pest 9 each time it is photographed. The image data includes image date and time data 5a, location information data 5b, and image data 5c. The temperature measuring unit 4a measures the temperature, and the humidity measuring unit 4b measures the humidity. The image data transmission unit 5 of the imaging unit 3 links the temperature data and humidity data to the image data and transmits them to a server 7 outside the device.

Description

[Technical field]

[0001] The present invention relates to a technique for grasping the occurrence status of pests and predicting future occurrence of pests. [Background technology]

[0002] The common cutworm, Spodoptera litura, is a representative cutworm pest and a serious pest of soybeans and vegetables. It mainly occurs after summer and is known to often cause great damage to autumn-grown vegetables. The basic countermeasure is to keep track of the occurrence of the cutworm. Pheromone traps are used to investigate the occurrence of Spodoptera litura and to determine the timing of control. Pheromone traps are a system in which females use an odor to lure males and capture them, but traditional surveys have been conducted entirely by hand, which makes them complicated, as there are problems with counting the captured cutworms, such as the risk of miscounting as more than 100 insects are caught in a single trap, and the need to visit the site regularly.

[0003] In response to this, a flying pest counting device is known that uses an infrared sensor to count the number of pests that have entered a trap (see Patent Document 1). However, the counting device of Patent Document 1 requires the installation of multiple infrared sensors, which results in a problem of high installation costs. Also, a pest monitoring device is known in which an attraction space for attracting and killing pests and an imaging space for imaging the pests are partitioned, and pests present in the imaging space are imaged by an imaging means (see Patent Document 2). In the pest monitoring device of Patent Document 2, pests present in the imaging space can be imaged by a single imaging means. However, because the pest monitoring device of Patent Document 2 is structured to kill pests attracted to the attraction space, it is necessary to periodically collect the captured and killed pests, which also poses the problem of being cumbersome. In addition, while the flying pest counting device of Patent Document 1 and the pest monitoring device of Patent Document 2 can count the number of flying pests attracted by pheromones, there is a problem in that they do not take into consideration how to use the collected data.

[0004] As a technology that notifies users of the effective timing to exterminate pests based on collected data, a prediction device is known that predicts the emergence date when a pest will reach a specified development stage based on information on the reference date when the pest hatched and the accumulated temperature, which is the temperature calculated by subtracting the zero point of development from the average temperature on a certain day and accumulating it for each date (see Patent Document 3). However, in order to use the prediction device of Patent Document 3, workers must regularly observe crops and check for pest hatching, and then operate a user terminal to notify the prediction device of information such as the name and growth stage of the pest, which makes it difficult to use. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2001-17053 A [Patent Document 2] JP 2022-127613 A [Patent Document 3] JP 2019-54771 A Summary of the Invention [Problem to be solved by the invention]

[0006] In view of the above circumstances, an object of the present invention is to provide a pest detection device capable of detecting pests simply and with high accuracy, and a pest infestation prediction system capable of predicting the infestation of pests simply and with high accuracy. [Means for solving the problem]

[0007] In order to solve the above problems, the pest detection device of the present invention is a device that does not have a mechanism for capturing or collecting pests, and is equipped with a pest attracting unit that includes a pheromone agent that attracts specific pests, a protective member that is breathable with a gap between the pheromone agent and the protective member, and a background plate on which the protective member is positioned in the center as a subject to be photographed, and an imaging unit that includes an infrared sensor that reacts to moving objects, and an imaging data transmission unit that photographs the pests attracted by the pheromone agent with the infrared sensor against the background plate and transmits the date and time of the photograph to the outside as photography data for each photograph. Since the pest attracting section is not provided with a pest trapping mechanism and the device is capable of detecting the occurrence of pests without killing or collecting them, unlike devices that capture and then count the number of pests, there is no need to process the captured pests. In addition, since the imaging section transmits the date and time of each capture as imaging data to the outside, the number of times the imaging data is transmitted to the outside can be used as useful data related to the number of detected pests. As the imaging unit, a known trail camera is preferably used. When the pest is a common cutworm, the pheromone agent is preferably a solid litre agent prepared by formulating a sex pheromone released by a female adult of the common cutworm.

[0008] In the pest detection device of the present invention, it is preferable that the shooting data further includes location information of the shooting location and captured image data. By including not only the number of times of shooting but also the location information of the shooting location in the shooting data, it is possible to predict the occurrence of pests in the vicinity of the shooting location, and the data can be transmitted to the outside as high-quality data having more detailed information. In addition, by including not only the number of times of shooting but also the captured image data in the shooting data, it is possible to determine whether a moving object is a pest or not by analyzing the captured image, and the data can be transmitted to the outside as high-quality data having more detailed information.

[0009] The pest detection device of the present invention may further include a solar cell unit having a solar panel and a storage battery, the imaging unit being powered by the solar cell unit, and the solar panel functioning as a shading plate that protects the imaging unit from sunlight. By providing the solar cell unit, the trouble of battery replacement is eliminated, and the frequency with which the manager of the device visits the site to perform maintenance can be reduced, making the device usable as a simple device. In order to prevent the imaging unit from becoming too hot, the solar panel is preferably provided in a position where the imaging unit is shaded. Furthermore, by using a large-sized solar panel, the imaging unit can be prevented from becoming too hot, and a shading plate is not required, thereby reducing costs.

[0010] The pest detection device of the present invention further includes a temperature measurement unit that measures temperature and transmits the measured temperature data to the imaging unit, and a hygrometer unit that measures humidity and transmits the measured humidity data to the imaging unit, and the imaging unit may link the temperature data and humidity data to the photographed data and transmit them to the outside. By linking the temperature data and humidity data to the photographed data, it is possible to grasp the correlation between the temperature and humidity and the timing of pest emergence, and to transmit the data to the outside as higher quality data.

[0011] The pest occurrence prediction system of the present invention is a system in which any of the above pest detection devices and a server transmit and receive data over a network, and the server includes a first communication unit capable of transmitting and receiving data, a storage unit for storing the photographed data received from the pest detection device via the first communication unit, and a time-series data generation unit for generating first time-series data for a predetermined period based on the number of times photographed data is received per unit time. This makes it possible to convert changes in pest occurrence conditions into data with high accuracy and in a visually easy-to-understand form using a simple method.

[0012] In the pest occurrence forecasting system of the present invention, it is preferable that the server further comprises a pest occurrence peak analysis unit that analyzes a first occurrence peak of pests during a predetermined period from the first time series data, and a pest control data calculation unit that calculates first pest control data related to an optimal pest control time and a pest control area from the first occurrence peak. This makes it possible to easily know the optimal pest control time, such as the time to spray pesticides, and areas where pest control is necessary.

[0013] The pest occurrence prediction system of the present invention further comprises a client terminal capable of transmitting and receiving data to and from the server via a network, the server further comprises a pest occurrence prediction data display unit that visually displays pest occurrence prediction data consisting of at least one of the first time series data, the first occurrence peak, and the first control data, the client terminal comprises a second communication unit capable of transmitting and receiving data, and the pest occurrence prediction data display unit preferably displays the pest occurrence prediction data on the display of the client terminal in response to a request from the client terminal. With such a configuration, a user can easily check the pest occurrence status and the optimal control timing even from a remote location.

[0014] The pest occurrence prediction system of the present invention further comprises a pest collection device including a pest collection unit that kills or collects pests, a pest counting unit that counts the number of pests killed or collected, and a counting data transmission unit that transmits the counted data to the outside, and the pest collection device and the server transmit and receive data via a network, and the memory unit stores the counting data received from the pest collection device via the first communication unit, and the time series data generation unit may generate second time series data for a predetermined period based on the number of pests killed or collected per unit time. By acquiring information from different devices in the server, a variety of time series data can be generated. In this specification, the term "capture" is sometimes used not only in the narrow sense of "capture" but also in the sense of "capture and kill."

[0015] In the pest occurrence prediction system of the present invention, the server may further include a pest occurrence peak analysis unit that analyzes a first pest occurrence peak during a predetermined period from the first time series data and analyzes a second pest occurrence peak during a predetermined period from the second time series data, and a pest control data calculation unit that calculates first pest control data related to an optimal pest control time and a pest control area from the first pest occurrence peak and calculates second pest control data related to an optimal pest control time and a pest control area from the second pest occurrence peak. By calculating different pest control data for each device, it is possible to present a variety of information to the user.

[0016] In the pest occurrence prediction system of the present invention, the control data calculation unit may further calculate third control data related to the optimal control time and control area based on the first occurrence peak and the second occurrence peak, the number of pest detection devices corresponding to the first occurrence peak and the number of pest collection devices corresponding to the second occurrence peak, and the weighted coefficients for the pest detection devices and the pest collection devices. By calculating one control data from data obtained from different devices, it is possible to present appropriate information to the user. The weighted coefficient for the device is a coefficient given based on the performance of the device. In addition, the number of devices is used in the calculation of the third control data because the devices with a larger number of devices among those used in the calculation are more affected. Therefore, when one pest detection device and one pest collection device having the same performance are used, the first occurrence peak and the second occurrence peak are treated equally, and the average value of both peaks is calculated.

[0017] The pest occurrence prediction system of the present invention further comprises a client terminal capable of transmitting and receiving data to and from the server via a network, the server further comprises a pest occurrence prediction data display unit that visually displays pest occurrence prediction data consisting of at least one of the first or second time series data, the first or second occurrence peak, and the first to third control data, the client terminal comprises a second communication unit capable of transmitting and receiving data, and the pest occurrence prediction data display unit preferably displays the pest occurrence prediction data on the display of the client terminal in response to a request from the client terminal. This makes it possible to present diverse and appropriate information to users who use the client terminal.

[0018] It is preferable that the client terminal includes an evaluation data input unit that receives input of evaluation data related to the pest occurrence forecast data, the evaluation data is transmitted to the server through the second communication unit, and the control data calculation unit calculates a coefficient based on the evaluation data, thereby improving the accuracy of the control data.

[0019] In the pest occurrence prediction system of the present invention, the client terminal preferably further comprises a user information registration unit that transmits user information, including location information for which pest occurrence prediction is desired, to the server and registers the same, and the server preferably transmits pest occurrence prediction data or an alert to the client terminal in response to a request from the client terminal or automatically for a period and area where notification is required, based on the user information and pest occurrence prediction data received from the client terminal. This makes it possible to reliably present appropriate information, such as the pest occurrence status and the optimal timing for control, to the user at the appropriate time. Effect of the Invention

[0020] The pest detection device of the present invention has an advantage that pests can be detected simply and with high accuracy, and the pest occurrence prediction system of the present invention has an advantage that pest occurrence can be predicted simply and with high accuracy. [Brief description of the drawings]

[0021] [Figure 1] Functional block diagram of a pest detection device according to a first embodiment [Diagram 2] FIG. 1 is a perspective view of a pest detection device according to a first embodiment; [Diagram 3] FIG. 1 is a right side view of a pest detection device according to a first embodiment. [Figure 4] Flow diagram of use of the pest detection device of Example 1 [Diagram 5] Functional block diagram of a pest occurrence prediction system according to a second embodiment [Figure 6] Configuration image of the pest occurrence prediction system of the second embodiment [Figure 7] Time series data generation image [Figure 8] Image of pest occurrence forecast data display in Example 2 [Figure 9] FIG. 13 is a perspective view of a pest detection device according to a fourth embodiment. [Figure 10] Image of time series data generation in other embodiments [Figure 11] Functional block diagram of a pest occurrence prediction system according to a third embodiment [Figure 12] Configuration image of the pest occurrence prediction system of the third embodiment [Figure 13] Example 3 Pest Infestation Forecast Data Display Image 1 [Figure 14] Example 3 Pest Infestation Forecast Data Display Image 2 [Figure 15] Display image of pest occurrence forecast data in other examples DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0022] Hereinafter, an example of an embodiment of the present invention will be described in detail with reference to the drawings. Note that the scope of the present invention is not limited to the following examples and illustrated examples, and many modifications and variations are possible. EXAMPLES

[0023] Fig. 1 shows a functional block diagram of a pest detection device of Example 1. As shown in Fig. 1, the pest detection device 1 of this embodiment is composed of a pest attracting unit 2, an imaging unit 3, a temperature measuring unit 4a, a humidity measuring unit 4b, and a solar cell unit 6, and does not have a mechanism for catching or collecting pests. The pest attracting unit 2 is composed of a pheromone agent 21 that attracts a specific pest, a protective member 22 that has a gap between it and the pheromone agent 21 and has breathability, and a background plate 23 that has the protective member positioned in the center as a subject to be photographed. The imaging unit 3 is equipped with an infrared sensor 31 that reacts to moving objects such as animals and insects, and acquires photographic data of a pest 9 attracted by the pheromone agent 21 photographed by the infrared sensor 31 with the background plate 23 as the background for each photograph. The photographic data transmitting unit 5 transmits the acquired photographic data (photographing date and time data 5a, position information data 5b of the photographing location, and photographed image data 5c) to the outside. The temperature measuring unit 4a measures the surrounding temperature and transmits the measured temperature data to the imaging unit 3. The humidity measuring unit 4b measures the surrounding humidity and transmits the measured humidity data to the imaging unit 3. The photographic data transmitting unit 5 of the imaging unit 3 links the temperature data and humidity data to the photographic data and transmits them to the outside, such as a server 7. The solar cell unit 6 has a solar panel 61 and a storage battery 62, and supplies power generated by sunlight to the imaging unit 3. In this embodiment, the pest 9 refers to an adult male of the common cutworm.

[0024] Fig. 2 shows a schematic diagram of the pest detection device of Example 1. Fig. 3 shows a schematic diagram of the pest detection device of Example 1 as viewed from the right side. As shown in Fig. 2, the pest detection device 1 includes a housing 11 made of a metal pipe member, a light shielding plate 12, a background plate 23, a trail camera 32, a thermometer 41, a hygrometer 42, a solar panel 61, and a storage battery 62 installed therein. The housing 11 is composed only of pipe members, and has a structure that allows pests to freely enter and exit from above, front, back, left and right, except for the area where the background board 23 is installed. The skeletal shape of each pipe member constituting the housing 11, such as thickness, length, position, etc., is merely an example, and it is sufficient that each member can be placed in an appropriate position.

[0025] As shown in FIG. 3, a pheromone agent 21 is provided on the surface of a background plate 23, and a protective member 22 is attached so as to cover the pheromone agent 21. The pheromone agent 21 is a solid litre agent formulated with the sex pheromone released by adult female cutworms, and is attached to a background board 23. The protective member 22 is made of a breathable stainless steel mesh member so as not to impede the effect of the pheromone agent 21, and is installed with a gap between it and the pheromone agent 21 so that the attracted pests (9a-9c) do not come into direct contact with the pheromone agent 21. Trail camera 32 functions as imaging unit 3, and a wide variety of known trail cameras can be used. A macro lens is used as the camera lens. As shown in FIG. 2 or FIG. 3, trail camera 32 sets a predetermined range as imaging area 13 centered on the position where pheromone agent 21 is provided on background board 23, and performs continuous sensing using infrared sensor 31 possessed by trail camera 32. The distance between trail camera 32 and pheromone agent 21 is approximately 40 cm. Thermometer 41 functions as temperature measurement unit 4a in Fig. 1, and hygrometer 42 functions as humidity measurement unit 4b in Fig. 1. Thermometer 41 or hygrometer 42 is connected to trail camera 32 and is structured so that temperature data or humidity data can be sent to an external server via trail camera 32. Note that if trail camera 32 has a built-in thermometer, the built-in thermometer may be used as temperature measurement unit 4a.

[0026] The solar panel 61 and the storage battery 62 make up the solar cell unit 6, and the solar panel 61 and the storage battery 62 are connected by a power cable 63a. The storage battery 62 and the trail camera 32 are also connected by a power cable 63b, and power generated by the solar cell unit 6 is supplied to the trail camera 32. Although not shown, the solar panel 61 has a mechanism that allows the mounting position, direction, and angle to be adjusted, and is structured to generate power efficiently. The shade 12 blocks sunlight, rain, and the like, and is installed with a gap between it and the top of the trail camera 32, thermometer 41, and hygrometer 42. The trail camera 32 is sturdy, weather-resistant, and waterproof so it can be used in all weather conditions, but by providing the shade 12, the trail camera 32, thermometer 41, or hygrometer 42 can be more effectively prevented from becoming too hot, allowing for stable and accurate measurements.

[0027] Next, a method of using the pest detection device 1 will be described. Fig. 4 shows a flow diagram of how to use the pest detection device. As shown in Fig. 4, sensing is performed continuously by the infrared sensor 31 of the trail camera 32 (step S01). Specifically, as shown in Figs. 2 and 3, sensing is performed continuously in the imaging area 13. Since the pheromone agent 21 is provided on the background board 23, as shown in FIG. 3, the pests (9a to 9c) attracted by the pheromone agent 21 approach the pheromone agent 21. Here, the pests (9b, 9c) are not in the imaging area 13, but the pest 9a is in the imaging area 13. Therefore, when the pest 9a enters the imaging area 13, the infrared sensor 31 detects the pest 9a as a moving object (step S02), and the trail camera 32 automatically photographs the pest 9a (step S03). The photographed data is transmitted to the server for each photograph (step S04). Thereafter, the infrared sensor 31 of the trail camera 32 again performs continuous sensing (step S01). Therefore, when the pest 9b subsequently enters the imaging area 13, the infrared sensor 31 detects the pest 9b as a moving object (step S02), and the trail camera 32 automatically captures the pest 9b (step S03). The captured data is transmitted to the server (step S04).

[0028] In addition, if a pest 9 approaches the pheromone agent 21 once, leaves the pheromone agent 21, and then approaches the pheromone agent 21 again, one pest 9 will be counted twice, but it is generally known that adult male cutworms are attracted by a pheromone agent, but when they realize that the pheromone is not that of an adult female cutworm, they leave the area and tend not to approach again. Therefore, if pest 9a shown in Figure 3 approaches pheromone agent 21 once and then leaves pheromone agent 21, it will not approach the pheromone agent 21 thereafter. When pest 9b and pest 9c enter the imaging area 13 at approximately the same time, the infrared sensor 31 detects the pests (9b, 9c) as moving objects (step S02), and the pests are automatically photographed by the trail camera 32 (step S03), and the photographed data is sent to the server (step S04). In the pest detection device of this embodiment, the number of pests is counted as one for each photograph, so that the number of pests may be counted incorrectly, but this phenomenon is rare and does not result in a large error.

[0029] In this embodiment, the photographing data transmission unit 5 is configured to transmit photographing date and time data 5a, location information data 5b, and image data 5c to the outside, but if only counting the detection of pests is required, it is sufficient to only record and transmit photographing date and time data 5a. In such a case, the amount of data required for communication can be reduced, and the device can be used as a simple device.

[0030] The pest detection device 1 of this embodiment is a device that can detect the occurrence of pests without capturing them, and therefore does not require the disposal of captured pests, unlike devices that capture and then count the number of pests. In addition, the pest detection device 1 has the advantage of being equipped with a solar cell unit 6, which eliminates the need to replace batteries. Therefore, by using the pest detection device 1, it is not necessary for the manager of the device to visit the site to perform maintenance, making it a highly convenient device. EXAMPLES

[0031] Fig. 5 shows a functional block diagram of a pest occurrence prediction system of Example 2. As shown in Fig. 5, the pest occurrence prediction system 100 of Example 2 is a system in which a pest detection device 1, a server 7, and a client terminal 8 transmit and receive data through a network. The pest detection device 1 has the same configuration as the pest detection device 1 of Example 1. The server 7 includes a first communication unit 71, a memory unit 72, a time-series data generation unit 73, a pest occurrence peak analysis unit 74, a control data calculation unit 75, and a pest occurrence prediction data display unit 76. In addition, the client terminal 8 includes a second communication unit 81 and a user information registration unit 82.

[0032] Fig. 6 shows a configuration image diagram of a pest occurrence prediction system of Example 2. As shown in Fig. 6, a pest detection device 1, a server 7, and client terminals (8a, 8b) transmit and receive data using the Internet 14. The client terminal 8a is a PC, and the client terminal 8b is a smartphone. As the client terminal 8, not only the PC and smartphone shown in Fig. 6 but also, for example, a tablet terminal can be used. Although the present embodiment is described as a client-server system, it is also possible to implement it as a cloud computing system, which allows users (not shown) to access virtual computing resources in the cloud, regardless of the underlying physical systems used to provide the computing resources and the location of those systems.

[0033] 5, a first communication unit 71 transmits and receives data. A storage unit 72 stores the image capture data received from the pest detection device 1 via the first communication unit 71, as well as the temperature data and humidity data associated with the image capture data. As in the first embodiment, the image capture data includes image capture date and time data 5a, position information data 5b of the image capture location, and captured image data 5c.

[0034] (Time series data generation) The time series data generating unit 73 generates time series data for a predetermined period based on the number of times photographic data is received per unit time. The unit time here can be set appropriately, for example, every week or every day (24 hours). The predetermined period can also be set appropriately, for example, from January to December, or it can be limited to a period when the possibility of pest infestation is high. Note that "time series data" in this embodiment means "first time series data." Since the photographed data is transmitted from the photographed data transmission unit 5 to the server 7 every time photographing is performed by the trail camera 32, the number of photographs taken and the number of receptions are the same. Note that, if the photographed data is not transmitted in real time but is instead stored in a memory provided in the imaging unit 5 and then transmitted to the server 7 at predetermined intervals, such as once a day, time-series data for a predetermined period can be generated based on the number of photographs taken rather than the number of receptions.

[0035] Fig. 7 is an image diagram of time-series data generation, which is a graph of the number of times received from April to November of a certain year. All of the images were taken at the same location. That is, the time-series data in Fig. 7 is generated mainly using the image capture date and time data 5a from the image capture data received from the pest detection device 1. The average value for the past 10 years is also shown. FIG. 7 only shows time series data at a specific shooting location, but for example, multiple pest detection devices 1 may be installed in various locations, the shooting data obtained at each shooting location may be received by the server 7, and time series data may be created for each location information data 5b.

[0036] The pest infestation peak analysis unit 74 analyzes the pest infestation peak during a predetermined period from the generated time-series data. Note that the "infestation peak" in this embodiment means the "first infestation peak." The peak of pest occurrence is analyzed from the change in the number of receptions during a specified period based on time series data. For example, if the number of receptions increases rapidly during a specified period and then decreases rapidly, the maximum value of the number of receptions at the timing when the number of receptions switches from the rapid increase to the rapid decrease can be set as the peak. The rapid increase in the number of receptions is determined based on whether or not the correlation between the lower limit and the upper limit when the number of receptions continues to increase during the period and the period from the lower limit to the upper limit exceeds a predetermined threshold. The rapid decrease in the number of receptions is determined based on whether or not the correlation between the upper limit and the lower limit when the number of receptions continues to decrease during the period and the period from the upper limit to the lower limit exceeds a predetermined threshold. In the example shown in FIG. 7, a peak P1 is detected in late July, a peak P2 in mid-August, and a peak P3 in early September from the time series data of the embodiment.

[0037] The control data calculation unit 75 calculates control data relating to the optimal control timing and control area from the peak of pest occurrence during a specified period. Specifically, in this embodiment, pest control data is calculated as pest control data relating to the appropriate pesticide spraying timing and spraying area. Note that "control data" in this embodiment means "first pest control data." In the example shown in FIG. 7, control data relating to the appropriate time to spray pesticides (optimum control time) is calculated using three pest occurrence peaks, peaks P1 to P3, as references. The optimum control time is generally set to be approximately 7 to 10 days after the peak of pest occurrence, but the optimum control time is calculated using not only the peak of pest occurrence during a specified period and the above period, but also meteorological conditions (effective accumulated temperature). Temperature data linked to the photographing data is used to calculate the effective accumulated temperature. In addition to this, humidity data may also be used to calculate the control data. In addition, the scattering area is calculated based on the position information data 5b included in the photographing data. In the example shown in FIG. 7, since the photographing data constituting the time series data all have the same position information data 5b, the area indicated by the position information data 5b is indicated. In contrast, when the pest control data is calculated based on the position information data 5b included in the photographing data photographed at a plurality of different locations, the pest control data is calculated for each photographing location. In addition, the pest control data at an arbitrary position on the map may be calculated based on the proximity of the position information using the time series data created for each different position information data 5b. The proximity of the position information is determined based on a predetermined distance, for example, within a radius of 30 to 50 km from an arbitrary position on the map.

[0038] The client terminal 8 includes a second communication unit 81 capable of transmitting and receiving data. The client terminal 8 also includes a user information registration unit 82 that transmits user information to the server 7 and registers it. The user information to be registered can include personal information such as name, sex, date of birth, address, and email address, and information on the agricultural crops such as the type of agricultural crops produced, variety, production area, farmland size, and years of production experience. The production area registered here is automatically treated as location information for which prediction of pest infestation is desired, but location information can also be registered as a region or place other than the production area for which prediction of pest infestation is desired. In this embodiment, it is assumed that area A is registered as the production area.

[0039] The pest occurrence forecast data display unit 76 visually displays pest occurrence forecast data consisting of time series data, occurrence peaks, and control data on the display of the client terminal 8. As a specific method of use, a user uses the client terminal 8 to transmit and receive data to and from the server 7, thereby displaying the pest occurrence forecast data on the display of the client terminal 8. FIG. 8 is a display image diagram of pest occurrence forecast data, where (1) shows a pest occurrence distribution image, and (2) shows a display image of time series data and control data. As shown in FIG. 8(1), the current or recent pest occurrence situation nationwide can be visually displayed for each detection level on the display 84 of the client terminal 8. In the example shown in FIG. 8(1), the pest occurrence situation is visually displayed divided into five detection levels. "Not detected" means that no photographed data has been received within a predetermined period from the pest detection device 1 installed in the area. Level 1 means that the number of times photographed data has been received is small, and level 4 means that the number of times photographed data has been received is the largest. In this way, by visually displaying the pest infestation status, the user can intuitively recognize the current pest infestation status.

[0040] Also, information such as "Pests were detected in XX region on XX month" is displayed below the display 84. Registered user information and necessary information are displayed here according to the occurrence status of pests. For example, it may show characteristic changes in the detection status in a specific region, such as "detection levels in XX region have risen sharply in the past week," or it may display information on a more relevant region based on location information such as production areas registered by the client terminal 8 used by the user.

[0041] As for the display of time series data and control data, in the example shown in FIG. 8(2), the display 84 of the client terminal 8 displays the time series data and control data in which the pest occurrence status in the area A is graphed, and advice on control. As shown in FIG. 8(2), the display 84 displays the pest occurrence status for the area A, which is the registered location information, in a graph, and the peak of pest occurrence is shown. The graph also shows the appropriate pesticide spraying time (optimum control time) calculated based on the peak of occurrence. In addition, the average value for the past 10 years is also shown, so that the user can easily grasp the change in the pest occurrence status in the area A this year, the peak of occurrence, the appropriate pesticide spraying time, and past trends just by looking at the graph. Furthermore, specific advice such as "In the area A, start spraying pesticides from around XX month XX day" is also displayed as information indicating the pesticide spraying time, making the display easier to understand.

[0042] Furthermore, the server 7 transmits pest occurrence prediction data or an alert to the client terminal 8 in response to a request from the client terminal 8 or automatically for a time and area where notification is required, based on the user information and pest occurrence prediction data received from the client terminal 8. A request from the client terminal 8 here means, for example, setting permission to receive data from the server 7. Automatic transmission means, for example, that even if permission to receive data from the server 7 has not been set in advance by the client terminal 8, pest occurrence prediction data or an alert is temporarily transmitted to the client terminal 8 whose location information for the relevant area is registered, for data determined to be of particularly high urgency or importance. Specifically, it is preferable that the data to be transmitted include a graph as shown in FIG. 8 and data containing detailed information about the warning.

[0043] The pest infestation forecasting system 100 of this embodiment uses a pest detection device 1, which is a device that can detect the infestation status without capturing pests, and therefore does not require the processing of captured pests, unlike devices that capture and then count the number of pests. In addition, the pest detection device 1 is equipped with a solar cell unit 6, which has the advantage that pests can be observed at all times and the trouble of changing batteries can be eliminated. Therefore, by using the pest detection device 1, it is not necessary for the manager of the device to visit the site to perform maintenance, making it a highly convenient device. The pest occurrence prediction system 100 of this embodiment is capable of grasping the arrival status of pests and issuing control information in real time using the server 7 and the client terminal 8. This system allows the user to easily check the pest occurrence status and the optimal control timing in a visually easy-to-understand manner even from a remote location, and furthermore, to receive notifications regarding highly urgent information. Note that while it is preferable to implement the pest occurrence prediction system 100 as a Web application, it may also be possible to use the system by installing the application in the client terminal 8.

[0044] Since it is possible to install many pest detection devices 1 over a wide area, photographic data detected in various locations can be centrally managed and visualized in the server 7 and quickly shared with users. As the number of survey points increases across the country, the number of survey points and the survey density in specific areas will increase, improving the accuracy of pest occurrence prediction. Note that, although this embodiment is described using the common cutworm as an example, it is also possible to apply this to other pests for which pheromone traps can be used. In this way, the pest occurrence prediction system 100 of this embodiment allows the system operator to realize smarter pest (spodoptera) prediction work and reduce the operating costs related to occurrence prediction. It also allows for smarter information provision to farmers. For farmers, by taking appropriate control measures and implementing control at the appropriate time, not only labor costs but also pesticide costs can be reduced. EXAMPLES

[0045] In the second embodiment, a pest occurrence prediction system using only the pest detection device of the first embodiment has been described, but there are also devices of the type that capture and kill pests, as in Patent Document 2. In pest occurrence prediction, it is beneficial to collect as much collection data and detection data as possible and use them as prediction data. However, in the past, pest occurrence prediction was often performed individually, such as by local governments or farms, and the measurement methods and types of data collected were different, making data collection complicated, and the reality is that data useful for prediction has not been fully integrated. Therefore, in this embodiment, a system that can present highly accurate pest occurrence prediction data in a wider area by using different types of devices in combination will be described.

[0046] Fig. 11 shows a functional block diagram of a pest infestation prediction system of Example 3. As shown in Fig. 11, a pest infestation prediction system 100a of Example 3 is a system in which a pest detection device 1, a pest collection device 10, a server 70, and a client terminal 80 transmit and receive data through a network. The pest detection device 1 has the same configuration as the pest detection device 1 of Example 1. The pest collection device 10 includes a pest collection unit 20 that kills or collects pests, a pest counting unit 30 that counts the number of pests killed or collected, and a count data transmission unit 50 that transmits the counted data to the outside. The server 70 includes a first communication unit 71, a storage unit 72a, a time-series data generation unit 73a, a pest occurrence peak analysis unit 74a, a control data calculation unit 75a, and a pest occurrence forecast data display unit 76a. The client terminal 80 includes a second communication unit 81 capable of transmitting and receiving data, a user information registration unit 82, and an evaluation data input unit 83.

[0047] Fig. 12 shows a configuration image diagram of a pest occurrence prediction system of Example 3. As shown in Fig. 12, a pest detection device 1, a pest collection device 10, a server 70, and client terminals (8a, 8b) transmit and receive data using the Internet 14. The client terminal 8a is a PC, and the client terminal 8b is a smartphone. As the client terminal 80, not only the PC and smartphone shown in Fig. 12 but also, for example, a tablet terminal can be used. In this embodiment, a client-server system is described, but it is also possible to implement it as a cloud computing system.

[0048] In the server 70 shown in FIG. 11, the first communication unit 71 transmits and receives data. The storage unit 72a stores the photographing data received from the pest detection device 1 via the first communication unit 71, and the temperature data and humidity data linked to the photographing data. As in the first embodiment, the photographing data includes photographing date and time data 5a, location information data 5b of the photographing location, and photographed image data 5c. The storage unit 72a also stores the counting data received from the pest collection device 10 via the first communication unit 71. Although not shown in detail in FIG. 12, the pest collection device 10 uses a pheromone trap to collect pests and photographs the collected pests with a camera. Then, the image analysis device analyzes the captured image to count the number of pests in the image, and transmits the obtained data, photographing date and time, and location information to the server 70 after linking them. That is, the camera and image analysis device here function as the pest counting unit 30 shown in FIG. 11. It should be noted that the pest trapping device 10 may be provided with a thermometer and a hygrometer, and temperature data and humidity data may be received from the pest trapping device 10 via the first communication unit 71 and stored in the memory unit 72a.

[0049] The client terminal 80 includes a second communication unit 81 capable of transmitting and receiving data. The client terminal 80 also includes a user information registration unit 82 that transmits user information to the server 70 and registers it. The user information to be registered can include personal information such as name, sex, date of birth, address, and email address, and information about the agricultural crops such as the type of agricultural crop to be produced, variety, production area, farmland size, and years of production experience. The production area registered here is automatically treated as location information for which prediction of pest occurrence is desired, but location information can also be registered as a region or place other than the production area as a region or place for which prediction of pest occurrence is desired. In this embodiment, it is assumed that area A is registered as the production area.

[0050] (Time series data generation) The time series data generating unit 73a generates first time series data for a predetermined period based on the number of times photographed data is received per unit time, similarly to the second embodiment. Also, unlike the second embodiment, the time series data generating unit 73a generates second time series data for a predetermined period based on the number of pests killed or collected per unit time. The unit time here can be appropriately set, for example, every week or every day (24 hours). The predetermined period can also be appropriately set, and may be, for example, from January to December, or may be limited to a period when pest infestation is likely to occur.

[0051] FIG. 13 is a display image diagram of pest occurrence forecast data in the third embodiment, showing a display image of pest control data for each device. The solid line graph shown in Fig. 13 is a graph of the number of times (numbers on the left axis) received from the pest detection device 1 from July to mid-September of a certain year. The shooting locations for each time series of data shown in the solid line graph are all the same. In other words, of the shooting data received from the pest detection device 1, the first time series data is generated mainly using shooting date and time data 5a. 13 is a graph of the number of pests (numbers on the right axis) captured by the pest trapping device 10 from July to mid-September of a certain year. The locations of the images for each time series of data shown in the dashed line graph are all the same. That is, the second time series data is generated using the count data received from the pest trapping device 10.

[0052] The location where the pest detection device 1 is photographed and the location where the pest collection device 10 is photographed do not need to be exactly the same, and the server 70 links the pest detection device 1 and the pest collection device 10 that are determined to be substantially in the same area, and uses them as related data for visual display of data and calculation of control data. Here, the device that is determined to be substantially in the same area refers to a device that is located within a predetermined distance from a specific point where the occurrence of pests is desired to be predicted, and in this embodiment, the server 70 detects the pest collection device 10 that exists within a radius of about 50 km from the location where the pest detection device 1 is photographed as the specific point, and uses it as a comparison target. The specific point may be automatically set based on information such as the production area registered by the user information registration unit 82 provided in the client terminal 80, or may be selected from a list of locations where the pest detection device 1 and the pest collection device 10 are located by accepting a manual operation by the client terminal 80, or may be selected arbitrarily regardless of the installation location of the device, i.e., the photographing location. In this embodiment, the pest detection device 1 and the pest collection device 10 are extracted in the server 70 based on the region A registered as a production area.

[0053] In addition, in this embodiment, an example using one pest detection device 1 and one pest collection device 10 is described, but a configuration using multiple pest detection devices or multiple pest collection devices may be used. For example, multiple pest detection devices 1 may be installed at various locations, the server 70 may receive the shooting data obtained at each shooting location, and the first time series data may be created for each position information data 5b, or multiple pest collection devices 10 may be installed at various locations, the server 70 may receive the counting data obtained at each shooting location, and the second time series data may be created for each position information data. In addition to the number of devices, the type of device may also be configured to use multiple types of pest detection devices or multiple types of pest collection devices.

[0054] (Analysis of pest outbreak peaks) In the server 70, a pest infestation peak analysis unit 74a analyzes a first pest infestation peak during a predetermined period from the first time-series data, and analyzes a second pest infestation peak during a predetermined period from the second time-series data. The first pest occurrence peak is analyzed from the change in the number of receptions during a predetermined period based on the first time series data. For example, if the number of receptions increases rapidly during a predetermined period and then decreases rapidly, the maximum value of the number of receptions at the timing when the number of receptions switches from the rapid increase to the rapid decrease can be set as the peak. The rapid increase in the number of receptions is determined based on whether or not the correlation between the lower limit and the upper limit when the number of receptions continues to increase during the period and the period from the lower limit to the upper limit exceeds a predetermined threshold. The rapid decrease in the number of receptions is determined based on whether or not the correlation between the upper limit and the lower limit when the number of receptions continues to decrease during the period and the period from the upper limit to the lower limit exceeds a predetermined threshold. In the example shown in FIG. 13, a peak P4 is detected in early September from the first time series data related to the pest detection device 1.

[0055] The second pest occurrence peak is analyzed from the change in the number of captured pests during a predetermined period based on the second time series data. For example, if the number of captured pests increases rapidly during a predetermined period and then decreases rapidly, the maximum number of captured pests at the timing when the number of captured pests switches from the rapid increase to the rapid decrease can be set as the peak. The rapid increase in the number of captured pests is determined based on whether or not the correlation between the lower limit and the upper limit when the number of captured pests continues to increase during the period exceeds a predetermined threshold. The rapid decrease in the number of captured pests is determined based on whether or not the correlation between the upper limit and the lower limit when the number of captured pests continues to decrease during the period exceeds a predetermined threshold. In the example shown in FIG. 13, a peak P5 is detected in early September from the second time series data related to the pest collection device 10.

[0056] (Regarding pest control data calculation) The control data calculation unit 75a calculates first control data regarding the optimum control time and control area from the first occurrence peak, and calculates second control data regarding the optimum control time and control area from the second occurrence peak. In the example shown in FIG. 13, the first control data regarding the appropriate time to spray the pesticide (optimum control time) is calculated based on the peak P4, which is the first occurrence peak. The optimum control time T1 shown in FIG. 13 indicates the first control data. The optimum control time is generally set to be about 7 to 10 days from the peak of pest occurrence, but in calculation, the optimum control time is calculated using not only the peak of pest occurrence during a specified period and the above period, but also meteorological conditions (effective accumulated temperature). Temperature data linked to the photographing data is used to calculate the effective accumulated temperature. In addition to this, humidity data may be used to calculate the first control data. In addition, the scattering area is calculated based on the position information data 5b included in the photographing data. In the example shown in Fig. 13, since all the photographing data constituting the first time series data have the same position information data 5b, the area indicated by the position information data 5b is indicated. In contrast, when the first control data is calculated based on the position information data 5b included in the photographing data photographed at a plurality of different locations, the first control data is calculated for each photographing location.

[0057] In addition, for the second occurrence peak, the second control data related to the appropriate time to spray the pesticide (optimum control time) is calculated based on the peak P5 shown in FIG. 13. The optimum control time T2 shown in FIG. 13 indicates the second control data. In the calculation, the optimum control time is calculated using not only the occurrence peak of the pests during the specified period and the standard period of 7 to 10 days, but also meteorological conditions (effective accumulated temperature). The calculation of the effective accumulated temperature uses data obtained from the Japan Meteorological Agency, etc., but if the pest collecting device 10 is equipped with a thermometer, temperature data linked to the counting data is used. In addition to this, humidity data may be used to calculate the second control data. In addition, the scattering area is calculated based on the location information data linked to the count data. In the example shown in Fig. 13, the count data constituting the second time series data all have the same location information data, so the area indicated by the location information data is indicated. In contrast, when the second control data is calculated based on the location information data included in the count data photographed and analyzed at multiple different locations, the second control data is calculated for each photograph location.

[0058] The control data calculation unit 75a further calculates third control data regarding the optimal control period and control area based on the first occurrence peak and the second occurrence peak, the number of pest detection devices 1 corresponding to the first occurrence peak and the number of pest collection devices 10 corresponding to the second occurrence peak, and coefficients weighted to the pest detection devices 1 and the pest collection devices 10. 14 is a display image diagram of the pest occurrence forecast data of Example 3, showing a display image of the third control data. The meaning of the vertical axis and horizontal axis is the same as in FIG. The third control data is calculated based on the first occurrence peak P4, the second occurrence peak P5, the number of pest detection devices 1 corresponding to peak P4, the number of pest collection devices 10 corresponding to peak P5, and the weighting coefficients assigned to the pest detection devices 1 and the pest collection devices 10. In this embodiment, since there is only one pest detection device 1 and one pest collection device 10, the weighting by the number of devices is equal. In addition, the weighting assigned to the device itself is illustrated as being equal in FIG. 14, but as described later, evaluation data related to the pest occurrence forecast data is input to the server 70, and the weighting is recalculated based on the input data, so that the weighting assigned to the device itself changes. It is preferable that the weighting assigned to the device itself be assigned to each device having the same function; however, depending on environmental conditions such as the location where the device is installed, devices having the same function may have different pest detection accuracy, etc., and in such cases, different weightings may be assigned to devices of the same type. In this embodiment, the optimum control period T3 is shown as the third control data as shown in FIG. 14, but in addition to this display, a specific date such as "around XX month XX day" may be displayed.

[0059] In response to a request from the client terminal 80, the pest infestation forecast data display unit 76a visually displays data consisting of at least any of the first or second time series data, the first or second infestation peak, and the first to third pest control data on the display of the client terminal 80. As a specific method of use, a user uses a client terminal 80 to transmit and receive data to and from the server 70, as in the second embodiment, and pest occurrence forecast data is displayed on the display of the client terminal 80. The display image is as shown in Fig. 13 or 14. Also, as in Fig. 8 described in the second embodiment, it is possible to visually display the current or most recent pest occurrence status nationwide for each detection level, or to display graphed time-series data and control data of the pest occurrence status in region A, as well as advice on pesticide spraying.

[0060] The evaluation data input unit 83 accepts input of evaluation data related to pest occurrence prediction data. The input evaluation data is transmitted to the server 70 through the second communication unit 81, and the control data calculation unit 75a calculates a coefficient based on the evaluation data. As an example of input of evaluation data, the date and time of pest control performed with respect to previously acquired pest occurrence prediction data and an evaluation of the effectiveness of pest control when pest control is performed according to the control data are input. The evaluation of the effectiveness of pest control is input using a five-level evaluation such as "very effective", "slightly effective", "neither effective nor negative", "not very effective", and "not effective at all". In addition, input of comments in free text may be accepted. The input evaluation data is transmitted to the server 70 through the second communication unit 81 and stored in the storage unit 72a. The control data calculation unit 75a recalculates the coefficients based on the transmitted evaluation data. Specifically, for example, on the premise that a predetermined number or more of evaluation data are obtained, the average value of the above-mentioned five-level evaluation is calculated, and if an evaluation exceeding a predetermined threshold is obtained, the numerical value indicating the performance of the device is increased, and conversely, if an evaluation below the predetermined threshold is obtained, the numerical value indicating the performance of the device is decreased. The calculated coefficients are stored in the storage unit 72a. Note that instead of using a predetermined algorithm, the server 70 may learn the evaluation data and change the coefficients weighted for each device using a learning model.

[0061] The server 70 transmits pest occurrence forecast data or an alert to the client terminal 80 based on the user information and pest occurrence forecast data received from the client terminal 80, in response to a request from the client terminal 80, or automatically for a time and area where notification is required. A request from the client terminal 80 here means, for example, setting permission to receive data from the server 70. In addition, automatically transmitting means, for example, sending pest occurrence forecast data or an alert temporarily to the client terminal 80 whose location information for the relevant area is registered for data determined to be of particularly high urgency or importance, even if permission to receive data from the server 70 has not been set in advance by the client terminal 80. Specifically, the data to be transmitted preferably includes a graph showing the pest control data and detailed information about the warning.

[0062] The pest occurrence prediction system 100a of this embodiment has the advantage that information from different devices, the pest detection device 1 and the pest collection device 10, can be acquired by the server 70 and the information can be presented in a variety of appropriate forms to a user operating a client terminal 80. Some users may desire comprehensive prediction data that consolidates data obtained from multiple devices, as shown in Fig. 14, while other users may desire data obtained from multiple devices to be displayed individually, as shown in Fig. 13, so that the characteristics and differences of each device can be visually and intuitively grasped. By making the system capable of using various data in this way, it is possible to increase the amount of information that can be collected by the server 70, and improve the prediction accuracy. In addition, by storing evaluation data from users in the storage unit 72a, it can be said that the system not only improves the prediction accuracy, but also contributes to the evaluation and improvement of each device. EXAMPLES

[0063] FIG. 9 shows a schematic diagram of a pest detection device of Example 4. As shown in FIG. 9, the pest detection device 1a of Example 4 is configured without a light shielding plate 12, unlike the pest detection device 1 of Example 1. In addition, a solar panel 61a larger in size than the solar panel 61 of Example 1 is provided, which prevents the trail camera 32, thermometer 41, and hygrometer 42 from becoming too hot. With this configuration, power can be supplied more stably, and the device can be manufactured at low cost because the light shielding plate 12 is not required.

[0064] (Other Examples) 1) FIG. 10 shows an image diagram of time-series data generation in another embodiment. The time-series data shown in FIG. 10 shows data on regions A, B, and C in a superimposed manner. Here, only three regions are shown, but data on two regions may be displayed in a superimposed manner, or data on four or more regions may be displayed in a superimposed manner. For example, the multiple regions to be displayed may be based on location information registered by the client terminal (8, 80), and regional information on the pest detection device 1 or pest collection device 10 close to the location may be preferentially displayed, or representative locations may be set in advance for each prefecture and selected from these, or the user may be able to select any region using the client terminal (8, 80). In this way, by graphing the data for each survey point and displaying them in an overlapping manner, it is possible to easily grasp the differences, similarities, and trends between regions. Therefore, the time-series data shown in Fig. 10 may be used to display pest occurrence forecast data by the pest occurrence forecast data display unit (76, 76a).

[0065] 2) Unlike the pest occurrence prediction system 10 of the second embodiment, the server 7 may further include an image analysis unit that analyzes the image data 5c received from the imaging unit 3, and if multiple pests are captured in the image data 5c, it may recognize and treat it as multiple receptions, and if only a moving object other than the detection target is captured, it may exclude it from the number of receptions. This makes it possible to increase the accuracy of the pest count and further increase the accuracy of pest occurrence prediction.

[0066] 3) In the pest occurrence forecasting system 100a of the third embodiment, a device that does not have a mechanism for catching or collecting pests other than the pest detection device 1 may be used instead of the pest detection device 1, or may be used in combination with the pest detection device 1. As a device that does not have a mechanism for catching or collecting pests, a wide variety of known methods for attracting insects can be used. For example, a light trap using an ultraviolet light or a fluorescent light, a food attractant using a specific food or scent, a color trap that utilizes the fact that insects are attracted to specific colors such as yellow or blue, a sound wave trap that uses sound waves of a specific frequency, a chemical attractant using a specific chemical substance, a plant attractant using the scent of a specific plant or flower, a water trap that uses water, a temperature trap that attracts insects that are attracted to a specific temperature, and a wind trap that uses wind to guide insects to a specific location can be used. In addition, as a method for detecting a moving object, not only an infrared sensor but also a wide variety of known methods that can identify a moving object can be used. For example, ultrasonic sensors, LiDAR, pressure sensors, magnetic sensors, sonic microphones, thermal imaging sensors, optical sensors, electromagnetic wave sensors, and video motion detection that analyzes camera footage to detect moving objects can be used.

[0067] 4) As a method for visually displaying pest occurrence forecast data, it is also possible to display data on precipitation and temperature. For precipitation, data obtained from the Japan Meteorological Agency and the like can be used. For temperature, not only data obtained from a thermometer but also data obtained from the Japan Meteorological Agency and the like can be used. FIG. 15 is a display image diagram of pest occurrence forecast data in another embodiment, in which (1) shows the amount of precipitation and (2) the number of insects attracted. Specifically, the bar graph in FIG. 15(2) shows the trend in the number of insects attracted (heads) (numbers on the left axis), the line graph shows the actual temperature values ​​(numbers on the right axis), and the future temperature forecast is displayed for the period from October 29 onwards in the graph. By easily comparing such different graphs by switching the screen display or displaying them side by side on one screen, the actual precipitation values ​​and the trend in the number of insects can be easily compared and examined. [Industrial Applicability]

[0068] The present invention is useful as a technique for grasping the occurrence status of pest insects and predicting future occurrence of pest insects. [Explanation of symbols]

[0069] 1,1a Pest detection device 2. Pest attractant 3. Imaging unit 4a Temperature measurement section 4b Humidity measurement section 5. Shooting data transmission unit 5a Shooting date and time data 5b Location data 5c Image data 6 Solar cell unit 7,70 Server 8,8a,8b,80 Client terminal 9,9a~9c Pests 10 Pest trap 11. Cabinet 12 Shading plate 13 Imaging area 14. Internet 20 Pest Collection Department 21 Pheromone 22 Protective materials 23 Background board 30 Pest Counting Division 31 Infrared Sensor 32 Trail Camera 41 Thermometer 42 Hygrometer 50 Counting data transmission unit 61,61a Solar Panel 62 Storage battery 63a, 63b Power cable 71 First Communications Department 72,72a Storage section 73,73a Time series data generation section 74,74a Pest occurrence peak analysis section 75,75a Pest control data calculation section 76,76a Pest occurrence forecast data display section 81 Second Communication Department 82 User Information Registration Department 83 Evaluation Data Input Section 84 Display 100,100a Pest outbreak prediction system P1~P5 peaks T1~T3 optimal control period

Claims

1. A device that does not have a mechanism for catching or collecting pests, a pest attracting unit including a pheromone agent that attracts a specific pest, a protective member having a gap between the pheromone agent and the protective member and having air permeability, and a background plate on which the protective member is positioned in the center as a subject to be photographed; A pest detection device comprising an imaging unit including an infrared sensor that reacts to moving objects, and an imaging data transmission unit that photographs pests attracted by the pheromone agent with the infrared sensor against the background of the background board and transmits the date and time of each photograph to the outside as photographing data.

2. The pest detection device according to claim 1 , wherein the photographing data further includes location information of a photographing location and image data of the photographed image.

3. The solar cell unit further includes a solar panel and a storage battery. the imaging unit is powered by the solar cell unit, 3. The pest detection device according to claim 2, wherein the solar panel functions as a shading plate that protects the imaging unit from sunlight.

4. The pest detection device described in claim 3, further comprising a temperature measuring unit that measures temperature and transmits the measured temperature data to the imaging unit, and a hygrometer side unit that measures humidity and transmits the measured humidity data to the imaging unit, wherein the imaging unit links the temperature data and the humidity data to the shooting data and transmits them to the outside.

5. A system in which the pest detection device according to any one of claims 1 to 4 and a server transmit and receive data via a network, The server, A first communication unit capable of transmitting and receiving data; A storage unit that stores the photographing data received from the pest detection device via a first communication unit; a time series data generating unit that generates first time series data for a predetermined period based on the number of times the photographic data is received per unit time; A pest occurrence prediction system comprising:

6. The server, a pest infestation peak analysis unit that analyzes a first pest infestation peak during a predetermined period from the first time series data; A control data calculation unit that calculates first control data regarding an optimal control time and a control area from the first occurrence peak; The pest occurrence prediction system according to claim 5, further comprising:

7. The apparatus further includes a client terminal capable of transmitting and receiving data to and from the server via the network; The server, Further comprising a pest occurrence forecast data display unit that visually displays pest occurrence forecast data composed of at least any of the first time series data, the first occurrence peak, and the first control data; the client terminal includes a second communication unit capable of transmitting and receiving data; 7. The pest occurrence prediction system according to claim 6, wherein the pest occurrence prediction data display unit displays the pest occurrence prediction data on a display of the client terminal in response to a request from the client terminal.

8. A system further comprising a pest trapping device including a pest trapping unit that kills or collects pests, a pest counting unit that counts the number of the pests that have been killed or collected, and a count data transmission unit that transmits the counted data to an outside, wherein the pest trapping device and a server transmit and receive data via a network, The storage unit stores the count data received from the pest trapping device via the first communication unit, The pest occurrence prediction system according to claim 5, characterized in that the time series data generation unit generates second time series data for a specified period based on the number of pests killed or collected per unit time.

9. The server, a pest infestation peak analysis unit that analyzes a first pest infestation peak during a predetermined period from the first time series data and analyzes a second pest infestation peak during a predetermined period from the second time series data; A control data calculation unit that calculates first control data regarding an optimal control time and a control area from the first occurrence peak, and calculates second control data regarding an optimal control time and a control area from the second occurrence peak; The pest occurrence prediction system according to claim 8, further comprising:

10. The pest infestation prediction system of claim 9, characterized in that the control data calculation unit further calculates third control data regarding the optimal control time and control area based on a first occurrence peak and a second occurrence peak, the number of pest detection devices corresponding to the first occurrence peak and the number of pest collection devices corresponding to the second occurrence peak, and coefficients weighted to the pest detection devices and the pest collection devices.

11. The apparatus further includes a client terminal capable of transmitting and receiving data to and from the server via the network; The server further includes a pest occurrence forecast data display unit that visually displays pest occurrence forecast data consisting of at least one of the first or second time series data, the first or second occurrence peak, and the first to third control data; the client terminal includes a second communication unit capable of transmitting and receiving data; 11. The pest occurrence prediction system according to claim 10, wherein the pest occurrence prediction data display unit displays the pest occurrence prediction data on a display of the client terminal in response to a request from the client terminal.

12. The client terminal includes an evaluation data input unit that receives an input of evaluation data related to the pest occurrence prediction data, The evaluation data is transmitted to the server through a second communication unit, The pest occurrence prediction system according to claim 11, characterized in that the control data calculation unit calculates the coefficients based on the evaluation data.

13. The client terminal further includes a user information registration unit that transmits user information including location information for which the user desires to predict pest infestation to the server and registers the user information, The server, The pest infestation forecasting system described in claim 12, characterized in that, based on the user information received from the client terminal and the pest infestation forecasting data, the pest infestation forecasting data or an alert is sent to the client terminal in response to a request from the client terminal or automatically for a time and area where notification is required.

Images