Predicting maintenance requirements for an insect trap

Abstract

The systems, methods and computer programs disclosed herein relate to predicting maintenance requirements for an insect trap.

Description

[0001] Predicting maintenance needs for an insect trap

[0002] TECHNICAL FIELD

[0003] The systems, methods, and computer programs disclosed herein relate to predicting maintenance needs for an insect trap.

[0004] INTRODUCTION

[0005] WO2018054767A1 discloses an insect trap that a user visits to check whether any insects have entered the trap. Using a smartphone, the user captures an image of the insects in the trap. A computer program automatically detects, counts, and / or identifies the insects depicted in the image.

[0006] W02020058175A1 and W02020058170A1 disclose an insect trap equipped with a camera. The camera automatically captures images of a collection area of ​​the insect trap where insects accumulate. The images are transmitted via a transmitter unit to a separate computer system, where they can be reviewed by a user and / or automatically analyzed to detect, count, and / or identify the insects in the collection area.

[0007] The insect traps disclosed in W02020058175A1 and W02020058170A1 have the advantage over the insect trap disclosed in WO2018054767A1 that the user does not have to visit the insect traps to check whether insects have entered the insect traps.

[0008] The condition of an insect trap can change over time. If a liquid is used in the insect trap to immobilize insects, the liquid may evaporate and / or become contaminated over time. If an adhesive layer is used to immobilize insects, this adhesive layer may also become contaminated over time. Likewise, it is possible that more and more insects will accumulate in the trap over time, making (automated) detection, counting, and / or identification of insects no longer possible because the insects overlap and / or agglomerate in the collection area.

[0009] An insect trap must therefore be inspected and maintained from time to time to ensure its functionality. It would be desirable to know when maintenance is due (at the latest) to maintain the insect trap's functionality.

[0010] SUMMARY

[0011] This object is achieved by the subject matter of the independent claims of the present disclosure. Preferred embodiments can be found in the dependent claims, the description, and the drawings.

[0012] The present disclosure describes means for predicting the timing of maintenance.

[0013] A first aspect of the present disclosure is a computer-implemented method for predicting maintenance needs for a camera-monitored insect trap. The method comprises:

[0014] Receiving data, the data comprising a first image recording, the first image recording showing a collection area of ​​an insect trap at a first time, determining a first state of the insect trap at the first time based on the first image recording,

[0015] Determining a critical point in time at which the insect trap reaches a critical state, based on the first state and the first point in time, wherein the critical state is characterized by one or more functionalities of the insect trap being impaired,

[0016] Issuing a notification, the notification including information about the critical time and / or the critical condition.

[0017] Another subject of the present disclosure is a computer system comprising: an input unit, a control and computing unit, and an output unit, wherein the control and computing unit is configured

[0018] Receiving data, the data comprising a first image recording, the first image recording showing a collection area of ​​an insect trap at a first time,

[0019] Determining a first state of the insect trap at the first time based on the first image recording,

[0020] Determining a critical point in time at which the insect trap reaches a critical state, based on the first state and the first point in time, wherein the critical state is characterized by one or more functionalities of the insect trap being impaired,

[0021] Issuing a notification, the notification including information about the critical time and / or the critical condition.

[0022] Another subject of the present disclosure is a non-transitory computer-readable storage medium having stored thereon software instructions that, when executed by a processor of a computer system, cause the computer system to perform the following steps:

[0023] Receiving data, the data comprising a first image recording, the first image recording showing a collection area of ​​an insect trap at a first time,

[0024] Determining a first state of the insect trap at the first time based on the first image recording,

[0025] Determining a critical point in time at which the insect trap reaches a critical state, based on the first state and the first point in time, wherein the critical state is characterized by one or more functionalities of the insect trap being impaired,

[0026] Issuing a notification, the notification including information about the critical time and / or the critical condition.

[0027] Another subject of the present disclosure is a system comprising: an insect trap, a camera, a control unit, • an analysis unit and

[0028] • an output unit, wherein the control unit is configured to cause the camera to generate a first image recording, wherein the first image recording shows a collection area of ​​the insect trap at a first point in time, wherein the analysis unit is configured to determine a first state of the insect trap at the first point in time based on the first image recording, wherein the analysis unit is configured to determine a critical point in time based on the first state and the first point in time, wherein the critical state is characterized in that one or more functionalities of the insect trap is / are impaired, wherein the output unit is configured to output a message, wherein the message comprises information about the critical point in time and / or the critical state.

[0029] A further subject of the present disclosure is a kit comprising an insect trap and a computer program product, wherein the insect trap comprises a camera or means for receiving a camera, wherein the computer program product comprises program instructions, wherein the program instructions can be loaded into a working memory of a computer system and cause the computer system to perform the following steps:

[0030] Receiving data, the data comprising a first image recording, the first image recording showing a collection area of ​​an insect trap at a first time,

[0031] Determining a first state of the insect trap at the first time based on the first image recording,

[0032] Determining a critical point in time at which the insect trap reaches a critical state, based on the first state and the first point in time, wherein the critical state is characterized by one or more functionalities of the insect trap being impaired,

[0033] Issuing a notification, the notification including information about the critical time and / or the critical condition.

[0034] BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Fig. 1 (a), Fig. 1 (b) and Fig. 1 (c) show, by way of example and schematically, the determination of a critical point in time on the basis of one or more time-varying states.

[0036] Fig. 2 shows an exemplary and schematic embodiment of the method for determining the critical point in time in the form of a flow chart.

[0037] Fig. 3 shows an exemplary and schematic illustration of an embodiment of a computer system of the present disclosure.

[0038] Fig. 4 shows, by way of example and schematically, another embodiment of a computer system of the present disclosure. DETAILED DESCRIPTION

[0039] The invention is explained in more detail below, without distinguishing between the subject matters of the present disclosure (method, computer system, computer-readable storage medium, system, kit). Rather, the following statements apply mutatis mutandis to all subject matters of the invention, regardless of the context in which they are described (method, computer system, computer-readable storage medium, system, kit).

[0040] If steps are specified in a particular order in this description or in the claims, this does not necessarily mean that the invention is limited to the specified order. Rather, it is conceivable that the steps could also be performed in a different order or even in parallel, unless one step builds on another, which necessarily requires that the subsequent step be performed (although this will become clear in the individual case). The specified orders are therefore preferred embodiments of the present disclosure.

[0041] The invention is explained in more detail at some points with reference to drawings. The drawings depict specific embodiments with specific features and combinations of features, which primarily serve for illustrative purposes; the invention should not be understood as being limited to the features and combinations of features shown in the drawings. Furthermore, statements made in the description of the drawings regarding features and combinations of features are intended to apply generally, meaning they are also transferable to other embodiments and are not limited to the embodiments shown.

[0042] The present disclosure describes means by which the time for maintenance of an insect trap can be predicted. This time is also referred to in this description as the "critical time." In a preferred embodiment, the critical time is the time at which limitations of one or more functionalities of the insect trap are to be expected. Maintenance of the insect trap should therefore be performed up to this critical time in order to maintain the full functionality of the insect trap.

[0043] An “insect trap” is a device that is visited by insects either randomly or deliberately and that allows a user to detect whether insects are present in an area.

[0044] The “area” may, for example, be a field or a greenhouse for growing crops, a building (e.g. a warehouse for storing food and / or animal feed, a hospital, a retirement home, a school and / or the like), a room in a building (e.g. a living room, a bedroom, a children's room, a storage room, a canteen, a hospital ward and / or the like) or another area.

[0045] The term “insect” includes all stages from the larva (caterpillar, dew larva) to the adult stage.

[0046] The term "insect trap" should not be understood to imply that only insects can enter the trap. The term "insect trap" was chosen because such traps are primarily used to check whether insects are present in an area. However, the insect trap can also be used to detect the presence of other arthropods (Latin: Arthropoda), such as spiders. It is also conceivable that the insect trap is used to detect the presence of a specific species in an area and is accordingly designed to attract, immobilize, and / or detect this specific species.

[0047] Examples of such defined species are: codling moth, aphid, natterjack moth, fruit skin tortrix moth, Colorado potato beetle, cherry fruit fly, cockchafer, European corn borer, plum tortrix moth, rhododendron leafhopper, seed moth, scale insect, gypsy moth, spider mite, grape tortrix moth, walnut fruit fly, whitefly, large rapeseed stem weevil, spotted cabbage stem weevil, rapeseed pollinator, cabbage pod weevil, cabbage pod midge or rapeseed flea, or a forest pest such as aphid, blue pine jewel beetle, bark beetle, oak jewel beetle, oak processionary moth, oak tortrix moth, spruce web sawfly, common woodworm, large brown barkeater, pine bush sawfly, pine owl, pine moth, small spruce sawfly, nun moth, Horse chestnut leaf miner, gypsy moth, sapwood beetle, mosquitoes (e.g. Asian tiger mosquito).

[0048] The insect trap may comprise means for immobilizing insects. The insect trap may, for example, comprise a bowl filled with a liquid (e.g., water or an aqueous solution). The liquid may conceivably comprise a surfactant to reduce surface tension and / or an anti-algae agent and / or an attractant to attract insects. Insects that enter the liquid may, for example, drown in the liquid or be trapped by the liquid. The insect trap may also comprise a surface coated with glue or another adhesive to which insects adhere. However, an insect trap does not need to comprise means for immobilizing insects; for the intended use of the insect trap, it may be sufficient for insects to enter the collection area and remain there for a while.

[0049] The insect trap may include means for attracting insects. Some insects (e.g., rapeseed pests such as the large rapeseed stem weevil) are attracted by a yellow color, for example. Some insects (e.g., male pantry moths) can be attracted by a pheromone. The use of food for the insects to attract them is also possible. Some insects are attracted by electromagnetic radiation within a defined wavelength range. The insect trap may be equipped with a source of electromagnetic radiation that emits electromagnetic radiation within such a defined wavelength range (or multiple wavelength ranges). However, the insect trap does not need to contain attractants; for the intended use of the insect trap, it may be sufficient for insects to accidentally stray into the trap or come into contact with it.

[0050] The insect trap includes a collection area. The collection area is an area that can be visited by insects (or other arthropods). This can be a flat surface, such as a board or map. It can also be the bottom of a container. The insect trap may include multiple collection areas. It is also conceivable for the insect trap to have different collection areas, for example, one collection area for (specific) pests and another collection area for (specific) beneficial organisms.

[0051] The collection area preferably comprises a flat, smooth or textured surface with a round, oval, elliptical, angular (triangular, quadrangular, pentagonal, hexagonal or generally n-sided, where n is an integer greater than or equal to three) cross-section. The cross-section is preferably round or rectangular (in particular square). Walls can extend upwards from the surface to form a container. The container can, for example, be cylindrical, conical or box-shaped. It preferably has a round or angular cross-section and the walls extend upwards from the base in a conical shape, with the base surface and wall surface preferably running at an angle of more than 90° and less than 120° to one another. In the case of a angular cross-section, the corners can be rounded.

[0052] The bottom of the container or the adhesive card or board may have markings and / or a structure that allows automated focusing of the camera and / or that provides a reference, for example to determine the size of an insect.

[0053] The bottom of the container can have recesses, as described, for example, in WO2022243150A1, to achieve the separation of insects in the collection area. Separation facilitates the automated detection, counting, and / or identification of insects in the collection area.

[0054] The collection area can be part of a pest trapping device, such as a yellow trap tray or an optionally glued color panel. The insect trap is preferably a trap as described in WO2020058175A1, W02020058170A1, WO2021213824A1, or WO2022243150A1.

[0055] The insect trap is a camera-monitored insect trap. This means that a camera is positioned and aligned to capture images of one or more of the trap's collection areas.

[0056] A "camera" is a device that can generate images in digital form and store them and / or make them available via an interface. A camera typically comprises an image sensor and optical elements. The image sensor is a device for electrically capturing two-dimensional images from light. These are typically semiconductor-based image sensors such as CCD (charge-coupled device) or CMOS (complementary metal-oxide-semiconductor) sensors. The optical elements (lenses, apertures, and the like) serve to create the sharpest possible image of the object, of which a digital image is to be generated, on the image sensor.

[0057] The camera can, for example, be a component of a smartphone or tablet computer.

[0058] The camera is used to generate digital images of the collection area or a portion thereof. The generated images can be used (i) to detect whether one or more insects are present in the collection area (insect detection), (ii) to count insects in the collection area, and / or (iii) to identify insects, i.e., to determine the type of insect (subclass, superorder, order, suborder, family, genus, species, stage, and / or sex).

[0059] The term "image capture" preferably refers to a two-dimensional representation of one or more objects. The term "digital" means that the image capture can be processed by a machine, usually a computer system. "Processing" refers to the well-known methods of electronic data processing (EDP).

[0060] Digital images can be processed, edited, and reproduced using computer systems and software, and converted into standardized data formats such as JPEG (Joint Photographie Experts Group graphics format), PNG (Portable Network Graphics), or SVG (Scalable Vector Graphics). Digital images can be visualized using suitable display devices, such as computer monitors, projectors, and / or printers.

[0061] In a digital image, image content is usually represented and stored as whole numbers. In most cases, these are two-dimensional images that can be binary encoded and, if necessary, compressed. Digital images are usually raster graphics in which the image information is stored in a uniform raster. Raster graphics consist of a grid-like arrangement of so-called image elements (pixels) in the case of two-dimensional representations, each of which is assigned a color or a gray value. The main characteristics of a 2D raster graphic are therefore the image size (width and height measured in pixels, colloquially also called image resolution) and the color depth. Each pixel in a digital image file is usually assigned a color. The color coding used for a pixel is defined, among other things, by the color space and the color depth.The simplest case is a binary image, in which each pixel stores a black-and-white value. In an image whose color is defined by the so-called RGB color space (RGB stands for the primary colors red, green, and blue), each pixel consists of three color values: one color value for the color red, one color value for the color green, and one color value for the color blue. The color of a pixel results from the superposition (additive mixing) of the three color values. The individual color value is discretized, for example, into 256 distinguishable levels called tonal values, which usually range from 0 to 255. The color nuance "0" of each color channel is the darkest. If all three channels have a tonal value of 0, the corresponding pixel appears black; if all three channels have a tonal value of 255, the corresponding pixel appears white. There are a multitude of possible digital image formats and color codings.For the sake of simplicity, this description assumes that the images in question are RGB raster graphics with a specific number of pixels. However, this assumption should not be interpreted as limiting in any way. Those skilled in image processing will know how to apply the principles of this description to images in other formats and / or where the color values ​​are coded differently.

[0062] To image the collection area on one or more image sensors, a light source is required to illuminate the collection area so that light (electromagnetic radiation in the infrared, visible, and / or ultraviolet ranges of the spectrum) is scattered / reflected from the illuminated collection area toward the camera. Daylight can be used for this purpose. However, it is also conceivable to use a lighting unit that provides defined illumination independent of daylight. This is preferably mounted to the side of the camera so that the camera does not cast a shadow on the collection area.

[0063] It is also conceivable to position a lighting source below the collection area and / or next to the collection area, which illuminates the collection area "from below" and / or "from the side", while a camera takes one or more images "from above".

[0064] It is conceivable that several lighting sources illuminate the collection area from different directions.

[0065] The terms "light" and "illumination" should not imply that the spectral range is limited to visible light (approximately 380 nm to approximately 780 nm). It is also conceivable that electromagnetic radiation with a wavelength below 380 nm (ultraviolet light: 100 nm to 380 nm) or above 780 nm (infrared light: 780 nm to 1000 pm) is used for illumination. The image sensor and optical elements are usually adapted to the electromagnetic radiation used.

[0066] The camera-monitored insect trap includes a control unit. The control unit can be a component of the camera or a separate device. The control unit is configured to cause the camera to generate one or more images of a collection area or a portion thereof. The control unit can be a computer system, as described later in the description. The camera can be a component of such a computer system.

[0067] The one or more image recordings may be individual image recordings or sequences of image recordings (e.g. video recordings).

[0068] The control unit can be configured to cause the camera to capture images at defined times (e.g., once a day at 12 noon) and / or recurringly at defined time intervals (e.g., every hour between 7 a.m. and 8 p.m.) and / or upon the occurrence of a defined event (e.g., after sunrise when a defined brightness is reached or as a result of the detection of an insect by a sensor) and / or as a result of a command from a user and / or randomly. The control unit can be part of the camera or a device independent of the camera that can communicate with the camera via a wired or wireless connection (e.g., Bluetooth).

[0069] The insect trap further comprises a transmitting unit. Images and / or information can be transmitted to a separate computer system via the transmitting unit. Transmission preferably occurs via a radio network, for example, a mobile network. The transmitting unit can be a component of the control unit or a unit independent of the control unit.

[0070] The insect trap may include a receiving unit for receiving commands from a separate computer system. The transmitting unit and / or the receiving unit may be components of a computer system, as described further below.

[0071] The images generated by the camera are typically analyzed automatically to detect, count, and / or identify the insects present in the collection area or part thereof. The term “automated” means without human intervention. This analysis can be performed by an analysis unit that may be part of the insect trap; however, it can also be performed by an analysis unit that may be part of a separate computer system to which the images are transmitted via the insect trap’s transmission unit. The analysis unit may be part of a computer system as described later in the description. The analysis unit may comprise a trained machine learning model that is configured and trained to detect, count, and / or identify insects depicted in images.Details on the automated detection, counting and / or identification of insects in images are described in publications on this topic (see e.g.: DCK Amarathunga et al. : Methods of Insect Image Capture and Classification: A Systematic Literature Review, Smart Agricultural Technology, Volume 1 , 2021 , 100023 ; C. Zhu et al. : Insect Identification and Counting in Stored Grain: Image Processing Approach and Application Embedded in Smartphones, Mob. Inf. Syst. 2018, 5491706:1-5, W02020058175A1, W02020058170A1).

[0072] The images generated by the camera can also be used to determine a time-varying state of the insect trap.

[0073] Such a time-varying state represents one or more properties of the insect trap at a defined point in time. The defined point in time is usually the point in time at which the image was created, i.e., the point in time at which the image shows the collection area (or part of it) of the insect trap. The state is referred to as time-varying because it usually changes over time. At a later point in time, a changed state may therefore exist, i.e., one or more properties of the insect trap may have changed and / or have been changed. The term "time-varying" can therefore also be described as "time-varying" or "changing over time."

[0074] The time-varying state is associated with one or more functionalities of the insect trap. The one or more properties of the insect trap that characterize the state of the insect trap can provide information about whether one or more functionalities of the insect trap are present (given) or whether one or more functionalities are impaired. This means that one or more functionalities of the insect trap can change, and such a change is reflected by the time-varying state.

[0075] Before reaching a critical point, the insect trap typically exhibits full functionality, i.e., no functionality of the insect trap is impaired. All functions that the insect trap is intended to perform are fulfilled. Functions that the insect trap typically has to perform are attracting insects and / or immobilizing insects and / or isolating insects in the collection area and / or illuminating the collection area with one or more light sources and / or generating images of the collection area and / or sending images and / or other / further information to a separate computer system and / or other / further functions.

[0076] At the critical point in time, the time-varying state of the insect trap reaches a critical state in which one or more functions are impaired, ie are no longer fully present: there is a functional impairment.

[0077] This will be explained in more detail below using examples, without wishing to reduce the invention to the examples mentioned. The examples therefore merely represent preferred embodiments. A time-varying state can, for example, indicate the liquid level in a collection area of ​​an insect trap designed as a container. In other words: the time-varying state indicates the extent to which the container is filled with liquid and / or how much liquid is present in the container and / or the height of the liquid level in the container. There can be a state in which the container is completely filled with liquid; there can be a state in which the container contains no liquid, and there can be a multitude of states in which the liquid level in the container lies between the extreme states of completely full and completely empty.

[0078] The amount of liquid is time-variable, as it can increase and / or decrease over time. It can decrease, for example, as a result of evaporation; it can also increase as a result of precipitation (e.g., rainwater).

[0079] The amount of liquid used is related to the functionality of the insect trap. The liquid is typically used to immobilize insects in the collection area. If the amount of liquid decreases, it may no longer be sufficient to immobilize insects. If the amount of liquid increases, it is possible that the liquid will overflow one edge of the container and carry insects out of the container.

[0080] It is also possible that insects are only partially covered by the liquid when the liquid level in the collection area drops, making automated detection, counting, and / or identification more difficult. For example, the contours of insects may not be clearly visible in an image due to the partial coverage, and / or unwanted reflections may occur at the transition points between the liquid and the insect.

[0081] A critical condition may be reached when the amount of liquid in the collection area has reached a minimum or maximum amount and / or the liquid level has reached a minimum or maximum height. If the amount of liquid falls below the minimum amount and / or the liquid level falls below the minimum height, immobilization of insects may be impaired and / or the automated detection, counting, and / or identification of insects in the collection area based on an image of the collection area may be impaired.If the amount of liquid exceeds a maximum value and / or the liquid level exceeds a maximum height, the immobilization of insects in the collection area and / or the automated detection, counting and / or identification of insects in the collection area based on an image of the collection area may be impaired because insects are washed out of the collection area.

[0082] The amount of liquid in the collection area and / or the height of the liquid level is a time-varying property of the insect trap. The amount of liquid in the collection area and / or the height of the liquid level can be determined from an image of the collection area. Typically, the transition from liquid to water can be seen on the walls of the container and defines the height of the liquid level. Markings on the walls can help quantify the height of the liquid level. In other words, an image of the collection area can be taken and analyzed to determine the height of the liquid level in the container and / or to determine the amount of water in the container. Such analysis can be automated using image processing and image recognition methods.

[0083] It is also possible that, based on an image recording, not (only) the amount of liquid and / or the height of the liquid level in the collection area is determined, but (also) the amount of liquid in a storage container and / or the liquid level in a storage container that is connected to the collection area and from which liquid flows into the collection area when the amount of liquid in the collection area falls below a threshold value and / or the liquid level in the collection area falls below a threshold value, as described, for example, in WO2021213824A1. In the case of such a storage container, a critical state is reached, for example, when no more liquid can flow from the storage container into the collection area and / or when air bubbles are introduced into the collection area during the flow, which can lead to further functional impairments (e.g. foam).

[0084] Another time-varying condition can be the degree of contamination in the collection area. It is possible that contaminants may accumulate in the collection area over time, making automated detection, counting, and / or identification of insects difficult. Contaminants may completely or partially obscure insects or clump with them (form agglomerates). Contaminants may include leaves and / or other plant parts, dust, excretions from insects and / or other animals, and / or similar items.

[0085] A critical condition may be reached when the degree of contamination has become so great that insects are no longer recognizable as individual units in the collection area of ​​the insect trap and / or insects cannot be distinguished from contamination and / or contamination clouds a liquid in the collection area that is used to immobilize insects, so that insects that sink to the bottom in the liquid are no longer (clearly) recognizable and / or dirt particles cover parts of insects and / or dirt particles clump together with insects to form agglomerates.

[0086] The degree of contamination and / or the amount of contamination can be determined from an image of the collection area, for example, based on the area covered by dirt particles and / or the number of dirt particles and / or the degree of turbidity of a liquid in the collection area. Dirt particles can be distinguished from insects, for example, based on their morphology and / or size and / or color and / or other characteristics. The detection and / or quantification of dirt particles and / or other contaminants can be automated using image processing and image recognition methods. It is possible to train a machine learning model to distinguish dirt particles from insects.

[0087] Contamination can also be caused, for example, by algae, which can form and multiply over time in a liquid used to immobilize insects in the collection area. Algae can cause a green and / or brown color and / or cloudiness of the liquid and / or completely or partially obscure insects, which can complicate the automated detection, counting, and / or identification of insects in the collection area. Algae in the collection area can complicate or even prevent immobilization because insects can escape from the collection area along the algae.

[0088] The amount of algae in the collection area can be determined automatically from an image of the collection area using image recognition methods, e.g. based on a green or brown color and / or turbidity of the liquid in the collection area.

[0089] A critical condition may be reached when the collection area is exhausted. It is possible that a large number of insects have already accumulated in the collection area, which are partially or completely overlapping and / or aggregating into clusters. This can impair the automated detection, counting, and / or identification of the insects.

[0090] The quantity of insects in the collection area (e.g., the number or the area covered by insects) can be automatically determined from an image of the collection area using image recognition methods. For this purpose, the techniques described above for automated insect detection and counting can be used, for example. A critical condition can be reached when foam forms in a liquid used to immobilize insects in the collection area. This foam can completely or partially obscure the view of insects in the collection area. Furthermore, it is possible that insects are no longer immobilized by the liquid.

[0091] Forming foam can be automatically detected in an image, for example, by an increasing number and / or size of bubbles on the surface of the liquid and / or in the interface between the liquid, the foam, and the container walls. The air pockets, which are usually round in plan view, can be detected and quantified using pattern recognition methods (image recognition) and / or a trained machine learning model.

[0092] A critical condition may occur when the camera's field of view is so severely restricted by cobwebs, plant parts growing into the insect trap (e.g., branches, leaves, roots), and / or other animal or plant organisms and / or structures in the insect trap that insects in the collection area are obscured, thus making automated detection, counting, and / or identification of the obscured insects difficult or impossible. Furthermore, animal structures and / or plant parts in the insect trap can make it difficult and / or impossible to immobilize insects if the insects can escape from the collection area via the structures and / or plant parts.

[0093] Such structures and / or plant parts can be automatically detected and quantified in images of the collection area, for example, using an increasingly reduced field of view of the camera and / or by means of pattern recognition methods and / or by means of a trained machine learning model.

[0094] Contamination can affect not only the collection area, but also the camera and / or its components, such as a lens. It is possible that a buildup of debris could restrict the camera's field of view, resulting in the camera no longer capturing the entire original collection area. It is conceivable that debris could result in blurred or partially blurred images. It is possible that water (e.g., rainwater) and / or another liquid (e.g., a liquid from the collection area) could get onto a lens, restricting the field of view and / or causing blurred images.

[0095] Restrictions in the field of view and / or increasing blur can be automatically detected and quantified in images of the collection area, for example using pattern recognition methods and / or a trained machine learning model.

[0096] A critical condition can occur when a lighting source no longer emits sufficient light into the collection area, for example, due to increasing contamination. The decreasing illumination can lead to a loss of contrast and / or increased noise in the images, which in turn can complicate the automated detection, counting, and / or identification of insects.

[0097] Decreasing illumination can be automatically detected in an image of the collection area, for example, based on decreasing brightness (e.g. based on a tonal value averaged over all or some pixels of the image).

[0098] A critical situation can occur when unwanted reflections appear in the images and overlay part of the imaged collection area. It is possible that reflections can be observed in the images at certain times, for example from sunlight entering the collection area at a defined angle. It is possible that sunlight enters the collection area at certain times of day and / or year and causes unwanted reflections there. It is possible that such unwanted reflections from sunlight were not observed when the insect trap was set up and / or only appeared later. Due to the seasonal changes in the position of the sun, such reflections may only appear at a later time (after the insect trap has been set up) and increase over time.Such reflections can complicate the automated detection, counting, and / or identification of insects in the collection area. Reflections in images can be automatically detected and quantified based on time-varying characteristic brightness values ​​of image elements.

[0099] If an insect trap is set up in an area, a camera captures images of the trap's collection area at regular or irregular intervals. For each image, a time-varying state is automatically determined. It is possible for multiple time-varying states to be detected.

[0100] Examples of time-varying states (and parameters that characterize or represent the time-varying state) are:

[0101] Number of insects in the collection area of ​​the insect trap Area of ​​the collection area covered with insects

[0102] Height of a liquid level in the collection area

[0103] Height of a liquid level in a storage container

[0104] Amount of liquid in the collection area

[0105] Amount of liquid in a storage container

[0106] Turbidity of a liquid in the collection container

[0107] Turbidity of a liquid in a storage container

[0108] Degree of coloration (e.g. green or brown coloration) of a liquid in the collection container Degree of coloration (e.g. green or brown coloration) of a liquid in a storage container

[0109] Number of dirt particles in the collection area of ​​the insect trap Area of ​​the collection area covered with dirt particles

[0110] Degree of brightness in the collection area

[0111] Size and / or number of areas in the collection area where reflections occur

[0112] Size and / or number of areas in the collection area where bubbles and / or foam occur Area of ​​the collection area covered with foam and / or bubbles

[0113] Size and / or number of air bubbles in the collection area

[0114] Based on the determined time-varying state, a critical point in time is determined at which the insect trap reaches a critical state. The term "based on" shall mean "at least partially based on," unless explicitly stated otherwise. The term "based on" can mean "with the aid of," "using," or "by means of."

[0115] Examples of critical states (and critical values ​​for parameters that characterize or represent the critical state) are:

[0116] Number of insects in the collection area of ​​the insect trap reaches a predefined threshold area of ​​the collection area covered with insects reaches a predefined threshold height of a liquid level in the collection area reaches a predefined lower or upper predefined threshold

[0117] Height of a liquid level in a storage tank reaches a predefined lower or upper predefined threshold

[0118] Amount of liquid in the collection area reaches a predefined lower or upper predefined threshold Amount of liquid in a storage container reaches a predefined lower or upper predefined threshold

[0119] Turbidity of a liquid in the collection tank reaches a predefined threshold Turbidity of a liquid in a storage tank reaches a predefined threshold

[0120] Degree of coloration (e.g. green or brown coloration) of a liquid in the collection container reaches a predefined threshold

[0121] Degree of coloration (e.g. green or brown coloration) of a liquid in a storage container reaches a predefined threshold

[0122] Number of dirt particles in the collection area of ​​the insect trap reaches a predefined threshold area of ​​the collection area covered with dirt particles reaches a predefined threshold

[0123] Degree of brightness in the collection area reaches a predefined threshold

[0124] Size and / or number of areas in the collection area where reflections occur reaches a predefined threshold

[0125] Size and / or number of areas in the collection area where air bubbles and / or foam occur reaches a predefined threshold Area of ​​the collection area covered with foam and / or air bubbles reaches a predefined threshold

[0126] Size and / or number of air bubbles in the collection area reaches a predefined threshold

[0127] In general, a critical condition can be reached when one or more parameters that characterize and / or represent the condition reach a predefined threshold. If a parameter exceeds or falls below a predefined threshold, a functional impairment of the insect trap is to be expected or a functional impairment of the insect trap has occurred.

[0128] A predefined threshold can be set by an expert and / or determined based on empirical studies.

[0129] It is also possible for the computer system / computer program according to the invention to be configured to receive an input from a user that includes the predefined threshold. In other words, the user can set the predefined threshold themselves.

[0130] The critical point in time at which the critical state is reached can be determined in several ways.

[0131] In one embodiment, the critical point in time can be determined by extrapolation. "Extrapolation" preferably refers to the continuation of a time series beyond the last observed value. In other words, the extrapolation is preferably an estimate or prediction based on an observed development trend.

[0132] Such an extrapolation can be performed based on two parameters that characterize or represent two states of the insect trap at two points in time. According to the invention, at least one parameter is derived from an image of the insect trap's collection area, which shows the collection area at a defined point in time. Another parameter can be derived from another image of the insect trap's collection area, which shows the collection area at another defined point in time.

[0133] For example, it is possible to receive a first image recording that shows the collection area at a first time ti in a first state Zi, and to receive a second image recording that shows the collection area at a second time in a second state Z2. The second time can be at a time interval from the first time ti, e.g., at a time interval of one hour or several hours, or of one day or several days, or of one week or several weeks, or of one month or several months.

[0134] The term "receiving" as used in this disclosure encompasses both retrieving image recordings (and / or other / further information and / or data) and receiving image recordings (and / or other / further information and / or data) that are transmitted, for example, to the computer system of the present disclosure. The image recordings can be received, for example, by a camera of an insect trap, which transmits the image recordings to the computer system. The image recordings (and / or other / further information and / or data) can be read from one or more data storage devices and / or transmitted from a separate computer system.

[0135] It is possible that a first value of a parameter that characterizes or represents the first state is determined on the basis of the first image recording, and that a second value of the parameter that characterizes or represents the second state is determined on the basis of the second image recording.

[0136] Based on the first and second values, a critical value of the parameter can be extrapolated. The critical value of the parameter characterizes or represents the critical state of the insect trap. The critical value can be an upper or lower predefined threshold.

[0137] The extrapolation can continue the temporal development from the first state to the second state. The extrapolation can be based on a linear temporal development of the state. In other words, a straight line equation can be determined for the temporal development from the first state to the second state; the straight line can be extended in time beyond the second value until the critical value is reached; the time corresponding to the critical value is then the critical time.

[0138] It is also possible to use a non-linear function for the temporal development. For example, it is possible for the temporal development to be described by a quadratic or generally polynomial function, an exponential function, a logarithmic function, or another function.

[0139] A function describing the temporal development of a condition can be defined in advance by an expert. Such a function can be determined empirically and applied to all insect traps or insect traps of a certain type installed in a country or region. Such a function can also be determined empirically for the type of area in which the presence of insects is to be assessed.

[0140] The extrapolation can also be based on more than two states. It is possible that a third and a fourth and possibly further images are generated. The third image shows the collection area of ​​the insect trap at a third time ts (which is usually at a temporal distance from the second time) in a third state Z3. The fourth image shows the collection area of ​​the insect trap at a fourth time k (which is usually at a temporal distance from the third time ts) in a fourth state Z4. In general, each received image shows the collection area of ​​the insect trap at a time t q in a q-th state Z q, where q is an integer indicating the number of time points for which images are available. The interval between two immediately consecutive time points t and ti+i (where i is an integer such that 0 < i < q) can be the same or different for all immediately consecutive time points.

[0141] A state can be determined from each received image. Each state can be described by one or more parameters. Each parameter can represent a property of the insect trap. For each parameter, a value can be determined that characterizes the respective state. The temporal development of the values ​​can be described (e.g., approximated) using one function or several functions (e.g., spline functions). In other words, a regression analysis can be performed on the determined values ​​as a function of time in order to determine a function (or several functions) or to determine the parameters for a function specified (e.g., by an expert).

[0142] Once the function and its parameters have been determined, an extrapolation to the critical state can be made and the critical point in time at which the critical state is reached can be determined.

[0143] It is possible that an initial value is used for extrapolation. The initial value can characterize and / or represent the initial state of the insect trap at the time of its setup and / or installation or after maintenance (e.g., after cleaning and / or after refilling a liquid used in the insect trap to immobilize insects).

[0144] For example, at the initial state, the number of insects in the collection area of ​​the insect trap may be zero, the contamination level may be zero, the turbidity level of a liquid used to immobilize insects may be zero or the value of the pure liquid, and / or the coloration level may be zero or the value of the pure liquid.

[0145] Especially when using an initial value for extrapolation, in principle only a single image acquisition is necessary to determine the temporal development of one or more states of the insect trap. The initial value represents the initial state, and the single image acquisition represents a further state at a point in time that is usually some distance from the initial point in time. From the change from the initial state to the further state, a temporal development can be derived, which can then be extrapolated to the critical state.

[0146] As described below, in the case of a single image acquisition, the determination of the critical time or state can be carried out, in particular, with the help of a trained machine learning model.

[0147] It is possible to incorporate additional values ​​from other parameters into the determination of the critical point in time. These additional parameters can be parameters that can influence the condition and / or the temporal development of the condition of the insect trap.

[0148] An example of a further parameter is the temperature in the insect trap (especially in the collection area) and / or in the surrounding area of ​​the insect trap (e.g., within a radius of a few centimeters and / or meters and / or kilometers). The temperature can be an average (e.g., arithmetically averaged) temperature, averaged over a period of one or more days, for example. The temperature can be a minimum and / or maximum temperature that occurs within a defined period of time, e.g., one or more days.

[0149] It is possible that algae preferentially grow within a defined temperature range and / or that certain temperature ranges promote algae growth. Typically, algae grow faster up to a maximum temperature with increasing temperature. If temperature is taken into account, the temporal development of the condition of the insect trap in relation to any impairment of function by algae in the collection area can be better described and / or predicted. In addition to the presence of algae in the collection area, temperature can also influence the number of insects in the collection area and / or the degree of contamination in the collection area. Many insects are only active within a specific temperature range; for example, if the temperature is too low, they remain in their hiding place. Thus, the probability of insects reaching the collection area of ​​the insect trap is low below a temperature that is specific for each insect species.Temperature can influence how quickly liquid evaporates in the collection area. The temperature can be measured continuously or at defined intervals over a period of several days, weeks, or months. The time-varying temperature values ​​can be used to determine the critical point.

[0150] Instead of a temperature, or in addition to a temperature, a heat sum can also be used to determine the critical point. A "heat sum" is the sum of certain temperature values ​​within a defined period of time, e.g., the hourly measured temperature values ​​inside or outside the insect trap over a period of, say, 24 hours. The temperature can also be measured continuously, and the temperature values ​​can be integrated over a defined period of time (e.g., 24 hours).

[0151] Another parameter that can be used to determine the critical time is the duration of sunshine. Sunshine duration is the actual duration of direct sunlight at a specific location within a defined period of time (e.g. day, week, month, season, or year). The electromagnetic radiation emitted by the sun is essential for plant growth and influences the temperature in the insect trap and its surroundings. It can influence algae growth in a liquid used to immobilize insects in the collection area of ​​the insect trap. It can influence how many insects are in the area around the insect trap and enter the insect trap. It can influence how quickly a liquid in the collection area evaporates.It can influence how quickly the liquid becomes contaminated, cloudy and / or takes on an increasing color.

[0152] Sunshine duration can be measured continuously over a period of several days, weeks, or months. Instead of, or in addition to, sunshine duration, the solar radiation intensity at the location of the insect trap and / or its surroundings can be measured and used to determine the critical time.

[0153] Another parameter that can be used to determine the critical time is the duration and / or amount of rain. Rain can influence how many insects are in the vicinity of the insect trap and thus enter the trap. Rain can influence whether and / or how much dirt and / or water enters the collection area. The amount and / or duration of rain can be measured continuously over a period of days, weeks, or months.

[0154] Other parameters that influence the functional impairment of the insect trap and can be used to determine the critical point in time are the air humidity, the wind speed and / or the wind direction, the air pressure at the location of the insect trap and / or in its surroundings, the type and / or quantity of plants growing in the area surrounding the insect trap and / or their distance from the insect trap, the duration and / or intensity of pollen flight at the location of the insect trap and / or in its surroundings, the type and quantity of bodies of water in the area surrounding the insect trap and / or their distance from the insect trap, the location of the insect trap (e.g. in the form of longitude and latitude information) and / or the like.

[0155] Also, the direction of insect migration and / or the species and / or quantities of insects detected and / or counted and / or identified in other insect traps (e.g., neighboring insect traps and / or insect traps within a radius of several meters or kilometers), or seasonal insect movements may be taken into account in determining the critical time.

[0156] Parameters such as temperature, sunshine duration, radiation intensity, wind speed, wind direction, humidity, rainfall amount, rainfall duration, pollen count, and insects in the surrounding area can be measured with sensors that can be part of the insect trap and / or located at the location of the insect trap and / or in its surroundings. The parameters can be measured at defined intervals and / or continuously. The parameters can be transmitted to a separate computer system via a transmitter unit in the insect trap and / or a separate transmitter unit.

[0157] It is also possible for the parameters mentioned to be obtained from one or more databases, e.g., from databases of weather services and / or meteorological stations, and / or agronomic databases. Furthermore, past experience with the insect trap and / or with insect traps of the same type and / or with insect traps in the surrounding area, such as past maintenance intervals, can be incorporated into the determination of the critical point in time.

[0158] Information about the location of the insect trap (e.g. in the form of GPS coordinates) and / or the altitude of the insect trap location above sea level can also be used to determine the critical time.

[0159] The determination of the critical point in time can be based on regression analysis, as described above. Regression analysis is a statistical method for modeling the relationships between one or more (dependent) parameters that characterize and / or represent the condition of the insect trap and one or more (independent) parameters that influence the condition of the insect trap.

[0160] For the regression analysis, a mathematical function with function parameters can be specified (e.g. by an expert), and in the regression analysis, the measured values ​​of various (measurement) parameters can be used to modify the function parameters so that the final function best describes and / or approximates the temporal course of one or more states (represented by one or more (measurement) values).

[0161] It is also possible to use a mathematical function whose result directly provides the critical point in time.

[0162] It is also possible to train a machine learning model to predict the temporal progression of one or more states of the insect trap and / or to predict the critical time.

[0163] Such a "machine learning model" can be understood as a computer-implemented data processing architecture. The model can receive input data and produce output data based on this input data and model parameters. Through training, the model can learn a relationship between the input data and the output data. During training, model parameters can be adjusted to produce a desired output for a given input.

[0164] When training such a model, the model is presented with training data from which it can learn. The trained machine learning model is the result of the training process. The training data includes input data and the correct output data (target data) that the model is supposed to generate based on the input data. During training, patterns are recognized that map the input data to the target data.

[0165] During the training process, the input data of the training data is fed into the model, and the model generates output data. The output data is compared with the target data. Model parameters are modified so that the deviations between the output data and the target data are reduced to a (defined) minimum. An optimization method such as a gradient descent method can be used to modify the model parameters to reduce the deviations.

[0166] The deviations can be quantified using a loss function. Such an error function can be used to calculate an error (loss) for a given pair of output and target data. The goal of the training process can be to modify (adjust) the parameters of the machine learning model so that the error is reduced to a (defined) minimum for all pairs in the training dataset.

[0167] For example, if the output and target data are numbers, the error function can be the absolute difference between these numbers. In this case, a high absolute error may indicate that one or more model parameters need to be significantly changed.

[0168] For example, for output data in the form of vectors, difference metrics between vectors such as the mean square error, a cosine distance, a norm of the difference vector such as a Euclidean distance, a Chebyshev distance, an Lp norm of a difference vector, a weighted norm, or another type of difference metric between two vectors can be chosen as the error function.

[0169] For higher-dimensional outputs, such as two-dimensional, three-dimensional, or higher-dimensional outputs, an element-wise difference metric can be used. Alternatively or additionally, the output data can be transformed, e.g., into a one-dimensional vector, before calculating an error value.

[0170] In this case, the machine learning model can be trained to predict a critical point in time based on input data representing one or more time-varying states of an insect trap at one or more points in time. This critical point in time is when the insect trap reaches a critical state that impairs its functionality. Additional input data can be used to predict the critical point in time, such as the parameters described in this description that influence the functionality of the insect trap and thus the critical point in time.

[0171] Such training can be based on training data that, for each of a plurality of insect traps, includes i) data on the temporal progression of one or more states of the insect trap as input data and ii) data on the critical point in time at which the functionality of the insect trap is impaired as target data. Further input data can be one or more of the parameters described in this description that influence the functionality of the insect trap and thus the critical point in time.

[0172] For each insect trap, the input data may include one or more values ​​for parameters that represent and / or characterize one or more states of the insect trap at different points in time. For example, the input data for one or more points in time may include one or more of the following:

[0173] Number of insects in the collection area of ​​the insect trap Area of ​​the collection area covered with insects

[0174] Height of a liquid level in the collection area

[0175] Height of a liquid level in a storage container

[0176] Amount of liquid in the collection area

[0177] Amount of liquid in a storage container

[0178] Turbidity of a liquid in the collection container

[0179] Turbidity of a liquid in a storage container

[0180] Degree of coloration (e.g. green or brown coloration) of a liquid in the collection container Degree of coloration (e.g. green or brown coloration) of a liquid in a storage container

[0181] Number of dirt particles in the collection area of ​​the insect trap Area of ​​the collection area covered with dirt particles

[0182] Degree of brightness in the collection area

[0183] Size and / or number of areas in the collection area where reflections occur. Size and / or number of areas in the collection area where air bubbles and / or foam occur. Area of ​​the collection area covered with foam and / or air bubbles.

[0184] Size and / or number of air bubbles in the collection area

[0185] Preferably, the input data also includes information about the one or more points in time. Points in time can be specified as absolute data (e.g., in the form of a date and time) and / or as a time difference from the time of a defined event. The time of the defined event can, for example, be the time of installation and / or commissioning of the insect trap and / or the time of the last maintenance.

[0186] The input data may include additional data such as:

[0187] Location of the insect trap

[0188] Height of the insect trap above sea level

[0189] Distance of the insect trap to the nearest body of water

[0190] Type of nearest body of water

[0191] Type and / or quantity of plants growing in the vicinity of the insect trap and / or their distance from the insect trap

[0192] Number and / or species of insects detected in one or more insect traps in the area during a defined period of time

[0193] Migration direction of insects at the location of the insect trap and / or in the surrounding area; minimum, maximum and / or average temperature in the insect trap and / or in the surrounding area of ​​the insect trap at one or more points in time; minimum, maximum and / or average temperature in the insect trap and / or in the surrounding area of ​​the insect trap over one or more defined periods of time (e.g. 24 hours)

[0194] Heat sum over one or more time periods in the insect trap and / or in the environment of the insect trap

[0195] Rainfall at the location of the insect trap over one or more defined periods of time (e.g. 24 hours) Minimum, maximum and / or average air pressure in the insect trap and / or in the area surrounding the insect trap over one or more defined periods of time (e.g. 24 hours) Minimum, maximum and / or average air humidity in the insect trap and / or in the area surrounding the insect trap over one or more defined periods of time (e.g. 24 hours) Minimum, maximum and / or average wind speed in the insect trap and / or in the area surrounding the insect trap over one or more defined periods of time (e.g. 24 hours) Duration of sunshine over one or more defined periods of time (e.g. 24 hours) Solar radiation intensity at the location of the insect trap over one or more defined periods of time (e.g. 24 hours)

[0196] Duration and / or intensity of pollen at the location of the insect trap for one or more periods

[0197] Type of insect trap

[0198] Size of the collection area

[0199] Type of attachment of the insect trap.

[0200] During training, the input data is fed into the machine learning model. The machine learning model generates an output based on the input data and model parameters. This output can be a predicted critical time. The predicted critical time can be compared with the respective critical time of the training data (target data). Using an error function, the deviation between the output and the target data can be quantified. In an optimization process (e.g. a gradient method), the deviations can be reduced by modifying the model parameters. If the deviations reach a defined minimum and / or the errors calculated using the error function reach a plateau, i.e. the errors can no longer be reduced by further modification of the model parameters, training can be terminated.

[0201] The trained machine learning model can be used for prediction. To do this, the trained machine learning model can be presented with new input data. The term "new" means that this data was not already used to train the machine learning model. The new input data includes values ​​of parameters that represent one or more time-varying states of the insect trap at one or more points in time. The input data can include values ​​of other parameters that may influence the functionality of the insect trap.

[0202] The new input data can be fed into the trained machine learning model and the machine learning model can output a predicted critical time.

[0203] The machine learning model can be or include one or more of the following models: artificial neural network, random forest, support vector machine, gradient boosted trees.

[0204] In a preferred embodiment, the machine learning model is or comprises an artificial neural network.

[0205] An “artificial neural network” comprises at least three layers of processing elements: a first layer with input neurons (nodes), an Nth layer with at least one output neuron (node), and N-2 inner layers, where N is a natural number and greater than 2.

[0206] The input neurons are used to receive the input data. Typically, there is one input neuron for each value of the input data.

[0207] The output neurons can be used to output a critical time (output data).

[0208] The processing elements of the layers between the input neurons and the output neurons are connected in a predetermined pattern with predetermined connection weights.

[0209] The neural network can be trained, for example, using a backpropagation method. The goal is to achieve the most reliable mapping of the input data to the output data. The quality of the prediction is described by an error function. The goal is to minimize the error function. In the backpropagation method, an artificial neural network is trained by changing the connection weights.

[0210] In the trained state, the connection weights between the processing elements contain information regarding the relationship between one or more time-varying states of insect traps at one or more time points and the critical times at which a critical state is reached, which can be used.

[0211] In a preferred embodiment, the artificial neural network is or comprises a recurrent neural network (RNN).

[0212] Recurrent neural networks (“RNNs”) are a family of artificial neural networks that contain feedback connections between layers. RNNs enable the modeling of sequential data by sharing parameter data across different parts of the neural network. The architecture for an RNN contains cycles. The cycles represent the influence of a current value of a variable on its own value at a future time, since at least part of the output data from the RNN is used as feedback to process subsequent inputs in a sequence. An example of an RNN is the so-called Long Short-Term Memory (LSTM) network (see, e.g., B. Lindemann et al., “A Survey on Long Short-Term Memory Networks for Time Series Prediction,” 2020, 10.13140 / RG.2.2.36761.65129 / 1).

[0213] It is also possible to train an artificial neural network directly on the basis of the images, i.e. it is not necessary to obtain one or more values ​​of parameters that represent or characterize the time-varying state of the insect trap from the images in a first step, e.g. using image recognition methods. It is possible to enter one or more images directly as input data into the artificial neural network. Preferably, with each image recording, a time specification is also entered into the artificial neural network, which indicates at which point in time (absolute or in relation to other points in time at which further images were generated) the respective image recording was generated. Information that indicates when a critical point in time was reached for an insect trap whose collection area is shown in the at least one image recording.Target data can also include information about which critical state was reached at the critical point in time, i.e. which functionality(s) was / were impaired.

[0214] The artificial neural network can therefore be trained to predict a critical point in time for reaching a critical state and optionally the respective critical state based on images taken at different times and showing the collection areas of insect traps where there is (not yet) any functional impairment or where there is one or more functional impairments.

[0215] As described, the critical time point obtained by extrapolation and / or regression and / or predicted by a trained machine learning model can be output, i.e. displayed on a screen, printed on a printer, stored in a data storage device and / or transmitted to a separate computer system via a network.

[0216] It is also possible for information about the critical condition to be output. For example, it can output which critical condition will be reached at the critical time. Information can be output about one or more measures that a user should take to prevent a functional impairment. It is possible for an earlier time to be output instead of or in addition to the critical time. The earlier time can give the user a time period within which the user can carry out maintenance on the insect trap before the critical condition is reached. It is possible for the user to specify this time period themselves. For example, it is possible for the user to configure the computer system / computer program to output a time period that is one day, several days, one week, or another time period before the critical time is reached.

[0217] It is also possible for a warning message to be sent to the user a defined time before the critical point is reached. The warning message can inform the user that the insect trap will reach a critical state after the defined time period has elapsed and that maintenance should be performed within the critical time period to prevent functional impairment.

[0218] It is also possible, in addition to or instead of a critical point in time, to determine a probability (e.g., predict it using a machine learning model) that a functional impairment will occur within a defined period of time (e.g., within the next few days or weeks), and, if applicable, which functional impairment will occur. The probability can be output. The probability can be compared with a predefined threshold. If the probability reaches or exceeds the predefined threshold, a message can be output stating that a functional impairment is to be expected within the period of time for which the probability was determined. The functional impairment to be expected can also be output. The determination of the critical point in time can be continuously updated.It is possible that whenever a new image is taken of a collection area of ​​an insect trap, an automated determination of a critical time point can take place. The determination of the critical time point can be based on all time-varying states that were determined from an initial state. It is possible that determined time-varying states at later times are given a higher weighting, i.e. taken into account to a greater extent than states at earlier times. It is also possible that only time-varying states from a number of previous times are taken into account, e.g. the last two or the last three or the last four or the last five or the last six or another number.

[0219] The invention is explained in more detail below with reference to drawings, without wishing to limit the invention to the features and combinations of features shown in the drawings.

[0220] Fig. 1 (a), Fig. 1 (b) and Fig. 1 (c) show, by way of example and schematically, the determination of a critical point in time on the basis of one or more time-varying states.

[0221] Fig. 1 (a), Fig. 1 (b), and Fig. 1 (c) show the temporal evolution of a parameter P in the form of a two-dimensional Cartesian coordinate system. The ordinate represents the parameter P, and the abscissa represents time t. The parameter P is a time-varying parameter because it changes with time t. The parameter P represents and / or characterizes a time-varying state of an insect trap.

[0222] The parameter P can, for example, be one of the following values:

[0223] Number of insects in the collection area of ​​the insect trap Area of ​​the collection area covered with insects

[0224] Height of a liquid level in the collection area

[0225] Height of a liquid level in a storage container

[0226] Amount of liquid in the collection area

[0227] Amount of liquid in a storage container

[0228] Turbidity of a liquid in the collection container

[0229] Turbidity of a liquid in a storage container

[0230] Degree of coloration (e.g. green or brown coloration) of a liquid in the collection container Degree of coloration (e.g. green or brown coloration) of a liquid in a storage container

[0231] Number of dirt particles in the collection area of ​​the insect trap Area of ​​the collection area covered with dirt particles

[0232] Degree of brightness in the collection area

[0233] Size and / or number of areas in the collection area where reflections occur

[0234] Size and / or number of areas in the collection area where bubbles and / or foam occur Area of ​​the collection area covered with foam and / or bubbles

[0235] Size and / or number of air bubbles in the collection area

[0236] At an initial time to, the parameter P has the value Po- The initial time to can, for example, be the time at which the insect trap was set up and / or put into operation for the first time and / or subjected to maintenance and / or cleaning.

[0237] At a first time ti, the parameter P reaches the value P\. The parameter P\ is determined based on a first image h, which shows a collection area of ​​the insect trap at the first time ti in a first state Zi.

[0238] Based on the points (to, Po) and (i, Pi), a straight line equation is set up that describes / approximates the temporal evolution of the parameter P. For the straight line G, P, — P o ti ■ P o — t0■ P, P(t) = — - - ■ t + - - - - - - - - to - to

[0239] The temporal development of the parameter P can continue beyond time t1. Fig. 1 (b) shows the continuation of the straight line G in dashed form. The time at which the parameter P reaches a critical value k is the critical time tk. At this critical time tk, the insect trap reaches a critical state Zk (represented and / or characterized by the value k of the parameter P). From this point on, a functional impairment of the insect trap can be expected. The critical time tk can be calculated using the following equation:

[0240] Fig. 1 (c) shows that, in addition to the first image h, there are also a second image P and a third image h. The second image P shows the collection area of ​​the insect trap at a second time p in a second state Z2 (represented and / or characterized by the value 2). The third image p shows the collection area of ​​the insect trap at a third time ts in a third state Z3 (represented and / or characterized by the value P3).

[0241] The temporal course of the parameter P can be approximated by the straight line G'. The straight line G' can be obtained by means of linear regression on the basis of the points (to, Po), (ti, Pi), fe 2) and (s, P3). The straight line G' can be extended beyond the point (s, P3) in order to continue the temporal development trend of the parameter P described by the straight line G'. When the straight line G' reaches the value k, the critical time tk, from which a functional impairment of the insect trap can be expected (critical state Zk), is reached.

[0242] Linear regression does not have to include all points; it is conceivable that linear regression is performed based on only a subset of the points; for example, based on the points from the last two or three previous points in time.

[0243] It should be noted that the temporal course of the parameter P does not necessarily have to be described / approximated by a straight line equation; it is conceivable that another mathematical function is used, the parameters of which can be obtained in a non-linear regression analysis.

[0244] In the example shown in Fig. 1 (a), Fig. 1 (b), and Fig. 1 (c), it is assumed that the parameter P depends only on time. It is possible that the temporal development of the parameter P depends on one or more other independent variables. In such a case, the temporal course of the parameter P can be described / approximated by a multivariable regression. Such a multivariable regression can be performed, for example, using an artificial neural network.

[0245] Fig. 2 shows an exemplary and schematic embodiment of the method for determining the critical point in time in the form of a flow chart. The method (100) comprises the following steps:

[0246] (110) receiving data, the data comprising a first image recording, the first image recording showing a collection area of ​​an insect trap at a first time,

[0247] (120) Determining a first state of the insect trap at the first time based on the first image recording,

[0248] (130) Determining a critical time at which the insect trap reaches a critical state based on the first state and the first time, wherein the critical state is characterized in that one or more functionalities of the insect trap is / are impaired, (140) Outputting a notification, wherein the notification comprises information about the critical time and / or the critical state.

[0249] The steps, methods and / or functions described in this disclosure may be performed in whole or in part by a computer system.

[0250] A "computer system" is an electronic data processing system that processes data using programmable computing instructions. Such a system typically includes a "computer," the unit containing a processor for performing logical operations, and peripherals.

[0251] In computer technology, "peripherals" refers to all devices connected to a computer that serve to control the computer and / or act as input and output devices. Examples include monitors, printers, scanners, mice, keyboards, drives, cameras, microphones, speakers, etc. Internal connectors and expansion cards are also considered peripherals in computer technology.

[0252] Today's computer systems are often divided into desktop PCs, portable PCs, laptops, notebooks, netbooks, and tablet PCs, as well as so-called handheld devices (e.g., smartphones); all of these systems can be used to implement the invention.

[0253] The term "computer" should be broadly interpreted to include any type of electronic device with data processing capabilities, including, as non-limiting examples, personal computers, servers, embedded cores, communications devices, processors (e.g., digital signal processors (DSPs), microcontrollers, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), etc.) and other electronic computing devices.

[0254] The term "process," as used above, is intended to encompass any type of calculation, manipulation, or transformation of data that is represented as physical, e.g., electronic, phenomena and that may occur or be stored, e.g., in registers and / or memory of at least one computer or processor. The term "processor" includes a single processing unit or a plurality of distributed or remote processing units.

[0255] Fig. 3 shows an exemplary and schematic representation of an embodiment of a computer system of the present disclosure. The computer system (1) comprises an input unit (10), a control and computing unit (20), and an output unit (30).

[0256] The control and computing unit (20) is configured to cause the input unit (10) to receive data, wherein the data characterize an insect trap at one or more points in time, wherein the data comprises a first image recording, wherein the first image recording shows a collection area of ​​an insect trap at a first point in time, to determine a first state of the insect trap at the first point in time based on the first image recording, to determine a critical point in time at which the insect trap reaches a critical state based on the first state and the first point in time, wherein the critical state is characterized in that one or more functionalities of the insect trap is / are impaired, to cause the output unit (30) to output a message, wherein the message comprises information about the critical point in time and / or the critical state.

[0257] Fig. 4 shows an exemplary and schematic illustration of another embodiment of a computer system of the present disclosure.

[0258] The computer system (1) comprises a processing unit (20) connected to a memory (50).

[0259] The processing unit (20) may comprise one or more processors alone or in combination with one or more memories. The processing unit (20) may be conventional computer hardware capable of processing information such as digital images, computer programs, and / or other digital information. The processing unit (20) typically consists of an arrangement of electronic circuits, some of which may be embodied as an integrated circuit or as multiple interconnected integrated circuits (an integrated circuit is sometimes referred to as a "chip"). The processing unit (20) may be configured to execute computer programs that may be stored in a main memory of the processing unit (20) or in the memory (50) of the same or another computer system.

[0260] The memory (50) may be ordinary computer hardware capable of storing information such as digital images (e.g., representations of the examination area), data, computer programs, and / or other digital information either temporarily and / or permanently. The memory (50) may comprise volatile and / or non-volatile memory and may be permanently installed or removable. Examples of suitable memories include RAM (Random Access Memory), ROM (Read-Only Memory), a hard disk, flash memory, a removable computer diskette, an optical disc, magnetic tape, or a combination of the above. Optical discs may include read-only compact discs (CD-ROM), read / write compact discs (CD-R / W), DVDs, Blu-ray discs, and the like.

[0261] In addition to the memory (50), the processing unit (20) can also be connected to one or more interfaces (11, 12, 30, 41, 42) for displaying, transmitting, and / or receiving information. The interfaces can include one or more communication interfaces (41, 42) and / or one or more user interfaces (11, 12, 30). The one or more communication interfaces (41, 42) can be configured to send and / or receive information, e.g., to and / or from an MRI scanner, a CT scanner, an ultrasound camera, other computer systems, networks, data storage devices, or the like. The one or more communication interfaces (41, 42) can be configured to transmit and / or receive information via physical (wired) and / or wireless communication connections.The one or more communication interfaces (41, 42) may include one or more interfaces for connecting to a network, e.g., using technologies such as cellular, Wi-Fi, satellite, cable, DSL, fiber optic, and / or the like. In some examples, the one or more communication interfaces (41, 42) may include one or more short-range communication interfaces configured to connect devices using short-range communication technologies such as NFC, RFID, Bluetooth, Bluetooth LE, ZigBee, infrared (e.g., IrDA), or the like.

[0262] The user interfaces (11, 12, 30) may comprise a display (30). A display (30) may be configured to display information to a user. Suitable examples include a liquid crystal display (LCD), a light-emitting diode display (LED), a plasma display (PDP), or the like. The user input interface(s) (11, 12) may be wired or wireless and may be configured to receive information from a user into the computer system (1), e.g., for processing, storage, and / or display. Suitable examples of user input interfaces (11, 12) include a microphone, an image or video capture device (e.g., a camera), a keyboard or keypad, a joystick, a touch-sensitive surface (separate from or integrated with a touchscreen), or the like.In some examples, the user interfaces may include automatic identification and data capture (AIDC) technology for machine-readable information. This may include barcodes, radio frequency identification (RFID), magnetic stripes, optical character recognition (OCR), integrated circuit cards (ICC), and the like. The user interfaces may further include one or more interfaces for communicating with peripheral devices such as printers and the like. One or more computer programs (60) may be stored in the memory (50) and executed by the processing unit (20), which is thereby programmed to perform the functions described in this description. The retrieval, loading, and execution of instructions of the computer program (60) may occur sequentially, such that one instruction is retrieved, loaded, and executed at a time. However, the retrieval, loading, and / or execution may also occur in parallel.

Claims

- TI - Patent claims 1. Computer-implemented method comprising: Receiving data, the data comprising a first image recording I\, the first image recording I\ showing a collection area of ​​a camera-monitored insect trap at a first time i, Determining a first state Zi of the insect trap at the first time i based on the first image recording I\, Determining a critical time tk at which the insect trap reaches a critical state Zk, based on the first state Zi and the first time ti, wherein the critical state Zk is characterized by one or more functionalities of the insect trap being impaired, Issuing a message, wherein the message comprises information about the critical time tk and / or the critical state Zk.

2. The method according to claim 1, wherein the data comprises information about an initial state Zo of the insect trap at an initial time to, wherein the initial time to is prior to the first time i, wherein determining the critical time tk comprises: Determining a temporal development of the insect trap from the initial state Zo to the first state Zi, Extrapolating the temporal development to the critical state Zk, Determine the critical time tk corresponding to the critical state Zk.

3. Method according to one of claims 1 or 2, wherein the data comprises a number q of image recordings / i to / qwherein each image recording I shows the collection area of ​​the insect trap at a time t, where i is an index that ranges through the integers from 1 to q, the method comprising: for each image recording I. determining a state Zi of the insect trap at time ti based on the image recording I, wherein the states Zi to Z q where determining the critical time tk includes: Approximating a temporal progression of at least some of the states Zo to Z q by at least one mathematical function, Extrapolating at least one mathematical function to the critical state Zk, Determining the critical time tk corresponding to the critical state Zk on the basis of at least one mathematical function.

4. Method according to one of claims 1 to 3, wherein the data comprises one or more further information about the insect trap, wherein the further information about the insect trap comprises one or more of the following information: Location of the insect trap Height of the insect trap above sea level Distance of the insect trap to the nearest body of water Type of nearest body of water Type and / or quantity of plants growing in the vicinity of the insect trap and / or their distance from the insect trap Number and / or species of insects detected in one or more insect traps in the area during a defined period of time Migration direction of insects at the location of the insect trap and / or in the surrounding area; minimum, maximum and / or average temperature in the insect trap and / or in the surrounding area of ​​the insect trap at one or more points in time; minimum, maximum and / or average temperature in the insect trap and / or in the surrounding area of ​​the insect trap over one or more defined periods of time Heat sum over one or more time periods in the insect trap and / or in the environment of the insect trap Rainfall at the location of the insect trap over one or more defined periods of time; minimum, maximum and / or average air pressure in the insect trap and / or in the area surrounding the insect trap over one or more defined periods of time; minimum, maximum and / or average air humidity in the insect trap and / or in the area surrounding the insect trap over one or more defined periods of time; minimum, maximum and / or average wind speed in the insect trap and / or in the area surrounding the insect trap over one or more defined periods of time Duration of sunshine over one or more defined periods Solar radiation intensity at the location of the insect trap over one or more defined periods of time Duration and / or intensity of pollen at the location of the insect trap for one or more periods Type of insect trap Size of the collection area Type of attachment of the insect trap, where the determination of the critical time tk includes: Determine a temporal development of the condition of the insect trap based on the additional information, Extrapolating the temporal development to the critical state Zk, Determining the critical time tk corresponding to the critical state Zk on the basis of at least one mathematical function.

5. The method according to any one of claims 1 to 4, wherein the data comprises one or more further information about the insect trap, wherein the further information about the insect trap comprises one or more of the following information: Location of the insect trap Height of the insect trap above sea level Distance of the insect trap to the nearest body of water Type of nearest body of water Type and / or quantity of plants growing in the vicinity of the insect trap and / or their distance from the insect trap Number and / or species of insects detected in one or more insect traps in the area during a defined period of time Migration direction of insects at the location of the insect trap and / or in the surrounding area; minimum, maximum and / or average temperature in the insect trap and / or in the surrounding area of ​​the insect trap at one or more points in time; minimum, maximum and / or average temperature in the insect trap and / or in the surrounding area of ​​the insect trap over one or more defined periods of time Heat sum over one or more time periods in the insect trap and / or in the environment of the insect trap Rainfall at the location of the insect trap over one or more defined periods of time; minimum, maximum and / or average air pressure in the insect trap and / or in the area surrounding the insect trap over one or more defined periods of time; minimum, maximum and / or average air humidity in the insect trap and / or in the area surrounding the insect trap over one or more defined periods of time; minimum, maximum and / or average wind speed in the insect trap and / or in the area surrounding the insect trap over one or more defined periods of time Duration of sunshine over one or more defined periods Solar radiation intensity at the location of the insect trap over one or more defined periods of time Duration and / or intensity of pollen at the location of the insect trap for one or more periods Type of insect trap Size of the collection area Type of attachment of the insect trap, where the determination of the critical time tk includes: Inputting the determined conditions and optionally the further information about the insect trap into a trained machine learning model, wherein the machine learning model has been trained on the basis of training data to predict a critical point in time based on input data, wherein the training data for each insect trap of a plurality of insect traps comprises (i) one or more image recordings of a collection area of ​​the insect trap as input data and (ii) a critical point in time as target data, wherein training the machine learning model comprises: o Inputting the input data into the machine learning model o Receiving output data from the machine learning model o Quantifying deviations between the output data and the target data o Minimizing the deviations by modifying parameters of the machine learning model Receiving the critical time tk and / or a probability of reaching the critical state Zk within a predefined time period from the trained machine learning model.

6. The method according to any one of claims 1 to 5, wherein determining the critical time tk comprises: Inputting the first image capture into a trained machine learning model, wherein the machine learning model has been trained based on training data to predict a critical time point based on image captures, wherein the training data for each insect trap of a plurality of insect traps comprises (i) one or more image captures of a collection area of ​​the insect trap as input data and (ii) a critical time point as target data, wherein training the machine learning model comprises: o Inputting the one or more image captures into the machine learning model o Receiving output data from the machine learning model o Quantifying deviations between the output data and the target data o Minimizing the deviations by modifying parameters of the machine learning model Receiving the critical time tk and / or a probability of reaching the critical state Zk within a predefined time period from the trained machine learning model.

7. Method according to one of claims 1 to 6, wherein each determined state is represented and / or characterized by one or more of the following parameters: Number of insects in the collection area of ​​the insect trap Area of ​​the collection area covered with insects Height of a liquid level in the collection area Height of a liquid level in a storage container Amount of liquid in the collection area Amount of liquid in a storage container Turbidity of a liquid in the collection container Turbidity of a liquid in a storage container Degree of coloration of a liquid in the collection container Degree of coloration of a liquid in a storage container Number of dirt particles in the collection area of ​​the insect trap Area of ​​the collection area covered with dirt particles Degree of brightness in the collection area Size and / or number of areas in the collection area where reflections occur Size and / or number of areas in the collection area where air bubbles and / or foam occur Area of ​​the collection area covered with foam and / or air bubbles Size and / or number of air bubbles in the collection area 8. Method according to one of claims 1 to 7, wherein the critical state is characterized and / or represented by one or more of the following states: Number of insects in the collection area of ​​the insect trap reaches a predefined threshold insect-covered area of ​​the collection area reaches a predefined threshold. Height of a liquid level in the collection area reaches a predefined lower or upper predefined threshold. Height of a liquid level in a storage tank reaches a predefined lower or upper predefined threshold Amount of liquid in the collection area reaches a predefined lower or upper predefined threshold Amount of liquid in a storage container reaches a predefined lower or upper predefined threshold Turbidity of a liquid in the collection tank reaches a predefined threshold Turbidity of a liquid in a storage tank reaches a predefined threshold Degree of coloration (e.g. green or brown coloration) of a liquid in the collection container reaches a predefined threshold Degree of coloration (e.g. green or brown coloration) of a liquid in a storage container reaches a predefined threshold Number of dirt particles in the collection area of ​​the insect trap reaches a predefined threshold area of ​​the collection area covered with dirt particles reaches a predefined threshold Degree of brightness in the collection area reaches a predefined threshold Size and / or number of areas in the collection area where reflections occur reaches a predefined threshold Size and / or number of areas in the collection area where air bubbles and / or foam occur reaches a predefined threshold Area of ​​the collection area covered with foam and / or air bubbles reaches a predefined threshold Size and / or number of air bubbles in the collection area reaches a predefined threshold.

9. The method according to any one of claims 1 to 8, wherein issuing the message comprises: Outputting information about which critical state Zk is reached at the critical time tk, and / or Output of information on which measure or measures are to be taken to remedy and / or prevent the critical condition Zk, and / or Outputting a probability that the critical state Zk will be reached within a predefined period of time, and / or in the event that the probability of reaching the critical state Zk within the predefined period of time reaches a predefined threshold: Outputting a message that one or more functional impairments are to be expected within the predefined period of time.

10. The method according to any one of claims 1 to 9, wherein issuing the message comprises: Outputting information at a time before reaching the critical time tk, wherein the message requests the user to take an action to maintain the functionality of the insect trap within the time period.

11. The method according to any one of claims 1 to 10, wherein the method further comprises: Issuing a warning message at a time before reaching the critical time tk about the approach of the critical time tk and / or about the need to carry out a measure to maintain the functionality of the insect trap.

12. A computer system (1) comprising: an input unit (10), a control and computing unit (20), and an output unit (30), wherein the control and computing unit (20) is configured to cause the input unit (10) to receive data, the data comprising a first image recording h, wherein the first image recording h shows a collection area of ​​an insect trap at a first time i, to determine a first state Zi of the insect trap at the first time i based on the first image recording h, to determine a critical time tk at which the insect trap reaches a critical state Zk based on the first state Zi and the first time i, wherein the critical state Zk is characterized in that one or more functionalities of the insect trap is / are impaired, to cause the output unit (30) to output a message,wherein the message comprises information on the critical time tk and / or the critical state Zk., 13. A non-transitory computer-readable storage medium storing software instructions which, when executed by a processor of a computer system (1), cause the computer system (1) to perform the following steps: Receiving data, the data comprising a first image recording h, the first image recording h showing a collection area of ​​a camera-monitored insect trap at a first time i, Determining a first state Zi of the insect trap at the first time i based on the first image recording h, Determining a critical time tk at which the insect trap reaches a critical state Zk, based on the first state Zi and the first time i, wherein the critical state Zk is characterized in that one or more functionalities of the insect trap is / are impaired, Issuing a message, wherein the message comprises information about the critical time tk and / or the critical state Zk.

14. System comprising: an insect trap, a camera, • a control unit, • an analysis unit and • an output unit, wherein the control unit is configured to cause the camera to generate at least a first image recording h, wherein the first image recording I shows a collection area of ​​the insect trap at a first time i, wherein the analysis unit is configured to determine a first state Zi based on the first image recording h, wherein the analysis unit is configured to determine a critical time tk based on the first state Zi and the first time i, wherein the insect trap reaches a critical state Zk at the critical time tk, wherein the critical state Zk is characterized in that one or more functionalities of the insect trap is / are impaired, wherein the output unit is configured to output a message, wherein the message comprises information about the critical time tk and / or the critical state Zk.

15. Kit comprising an insect trap and a computer program product, wherein the insect trap comprises a camera or means for receiving a camera, wherein the computer program product comprises program instructions, wherein the program instructions can be loaded into a working memory of a computer system (1) and cause the computer system (1) to carry out the following steps: Receiving data, the data comprising a first image recording h, the first image recording h showing a collection area of ​​a camera-monitored insect trap at a first time i, Determining a first state Zi of the insect trap at the first time i based on the first image recording h, Determining a critical time tk at which the insect trap reaches a critical state Zk, based on the first state Zi and the first time i, wherein the critical state Zk is characterized in that one or more functionalities of the insect trap is / are impaired, Issuing a message, wherein the message comprises information about the critical time tk and / or the critical state Zk.

Images