Silkworm disease prediction method and system based on silkworm breeding environment

Abstract

The invention discloses a silkworm disease prediction method and system based on a silkworm breeding environment, and relates to the technical field of prediction methods, the silkworm breeding environment of silkworms is determined based on environment detection of a silkworm environment area, an abnormal area of a silkworm breeding room is determined according to the silkworm breeding environment of the silkworms and a silkworm activity track, and an abnormal image of the silkworms is marked. Accurate detection of the abnormal area of the silkworm breeding room is ensured, and the accuracy of the abnormal image of the silkworm is ensured. Therefore, according to the abnormal images of the silkworms, the skin abnormal features and the posture abnormal features of the silkworms are determined, and the excrement forms of the silkworms are determined through detection along the movement tracks of the silkworms; the silkworm disease type of the silkworms is predicted based on the skin abnormal features and posture abnormal features of the silkworms and the excrement forms of the silkworms, the environment regulation and control logic of the silkworm breeding room is triggered according to the silkworm disease type of the silkworms and the silkworm breeding environment of the silkworms, accurate prediction of the silkworm disease type of the silkworms is achieved, and the silkworm breeding environment of the silkworms in the silkworm breeding room is optimized in time.

Description

Technical Field

[0001] The present invention relates to the technical field of prediction methods, and in particular to a method and system for predicting silkworm diseases based on the silkworm-raising environment. Background Art

[0002] With the development of technology, silkworms are a kind of animals and are cultivated in a silkworm-raising room. At this time, the silkworms move in the silkworm-raising room and are affected by the silkworm-raising environment in real time. In the prior art, the silkworm-raising environment and the morphology of silkworms are collected, and the types of silkworm diseases are predicted according to the silkworm-raising environment and the morphology of silkworms. However, the influence of the abnormal characteristics of silkworms is not taken into account, and the accurate prediction of the types of silkworm diseases cannot be achieved. Summary of the Invention

[0003] The purpose of the present invention is to overcome the deficiencies of the prior art, and the present invention provides a method and system for predicting silkworm diseases based on the silkworm-raising environment.

[0004] An embodiment of the present invention provides a method for predicting silkworm diseases based on the silkworm-raising environment, including: Real-time monitoring of the silkworm-raising room and collecting the silkworm-raising distribution map of the silkworm-raising room; Determining the silkworm movement trajectory and the silkworm environment area according to the recognition of the silkworm-raising distribution map; Determining the silkworm-raising environment of silkworms based on the environmental detection of the silkworm environment area, determining the abnormal area of the silkworm-raising room according to the silkworm-raising environment of silkworms and the silkworm movement trajectory, and marking the abnormal images of silkworms; Determining the skin abnormal characteristics and posture abnormal characteristics of silkworms according to the abnormal images of silkworms, and determining the excrement morphology of silkworms along the detection of the silkworm movement trajectory; Predicting the types of silkworm diseases based on the skin abnormal characteristics, posture abnormal characteristics of silkworms and the excrement morphology of silkworms, and triggering the environmental regulation logic of the silkworm-raising room according to the types of silkworm diseases and the silkworm-raising environment of silkworms.

[0005] An embodiment of the present invention provides a prediction system for silkworm diseases based on the silkworm-raising environment. The prediction system for silkworm diseases based on the silkworm-raising environment is applied to the above-mentioned method for predicting silkworm diseases based on the silkworm-raising environment. The prediction system for silkworm diseases based on the silkworm-raising environment includes: A silkworm-raising distribution map module for real-time monitoring of the silkworm-raising room and collecting the silkworm-raising distribution map of the silkworm-raising room; A silkworm recognition module for determining the silkworm movement trajectory and the silkworm environment area according to the recognition of the silkworm-raising distribution map; An abnormal detection module for determining the silkworm-raising environment of silkworms based on the environmental detection of the silkworm environment area, determining the abnormal area of the silkworm-raising room according to the silkworm-raising environment of silkworms and the silkworm movement trajectory, and marking the abnormal images of silkworms; The morphological detection module is used to determine the skin abnormality features and posture abnormality features of the silkworm based on the abnormal images of the silkworm, and determine the morphological form of the silkworm's excrement along the detection of the silkworm's activity trajectory; The prediction module is used to predict the types of silkworm diseases based on the skin abnormality features, posture abnormality features of the silkworm and the morphological form of the silkworm's excrement, and trigger the environmental control logic of the silkworm rearing room according to the types of silkworm diseases and the silkworm rearing environment of the silkworm.

[0006] Compared with the prior art, the beneficial effects of the present invention are: In the embodiment of the present invention, through the method in the embodiment of the present invention, the silkworm rearing environment of the silkworm is determined based on the environmental detection of the silkworm environmental area, the abnormal area of the silkworm rearing room is determined according to the silkworm rearing environment of the silkworm and the silkworm activity trajectory, and the abnormal images of the silkworm are marked, which takes into account the overall consideration of the silkworm rearing environment and the silkworm activity trajectory of the silkworm, ensures the accurate detection of the abnormal area of the silkworm rearing room, and ensures the accuracy of the abnormal images of the silkworm.

[0007] Therefore, the skin abnormality features and posture abnormality features of the silkworm are determined based on the abnormal images of the silkworm, and the morphological form of the silkworm's excrement is determined along the detection of the silkworm activity trajectory; the types of silkworm diseases are predicted based on the skin abnormality features, posture abnormality features of the silkworm and the morphological form of the silkworm's excrement, and the environmental control logic of the silkworm rearing room is triggered according to the types of silkworm diseases and the silkworm rearing environment of the silkworm, which takes into account the overall consideration of the skin abnormality features, posture abnormality features and the morphological form of the silkworm's excrement of the silkworm, realizes the accurate prediction of the types of silkworm diseases, triggers the environmental control logic of the silkworm rearing room, and timely optimizes the silkworm rearing environment of the silkworms in the silkworm rearing room. Description of the Drawings

[0008] Figure 1 is a schematic flowchart of the method for predicting silkworm diseases based on the silkworm rearing environment in the embodiment of the present invention; Figure 2 is a schematic flowchart of step S11 in the method for predicting silkworm diseases based on the silkworm rearing environment in the embodiment of the present invention; Figure 3 is a schematic flowchart of step S12 in the method for predicting silkworm diseases based on the silkworm rearing environment in the embodiment of the present invention; Figure 4 is a schematic flowchart of step S13 in the method for predicting silkworm diseases based on the silkworm rearing environment in the embodiment of the present invention; Figure 5 is a schematic flowchart of step S14 in the method for predicting silkworm diseases based on the silkworm rearing environment in the embodiment of the present invention; Figure 6 is a schematic flowchart of step S15 in the method for predicting silkworm diseases based on the silkworm rearing environment in the embodiment of the present invention; Figure 7It is a schematic structural composition diagram of a silkworm disease prediction system based on the silkworm raising environment in an embodiment of the present invention. Detailed implementation manners

[0009] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention.

[0010] Please refer to Figures 1 to 7 , a silkworm disease prediction method based on the silkworm raising environment, which is applied to a silkworm disease prediction scenario based on the silkworm raising environment; the silkworm disease prediction method based on the silkworm raising environment includes: Step S11: Monitor the silkworm raising room in real time and collect the silkworm raising distribution map of the silkworm raising room. Step S12: Determine the silkworm activity trajectory and the silkworm environment area according to the recognition of the silkworm raising distribution map. Step S13: Determine the silkworm raising environment of the silkworms based on the environmental detection of the silkworm environment area, determine the abnormal area of the silkworm raising room according to the silkworm raising environment of the silkworms and the silkworm activity trajectory, and mark the abnormal images of the silkworms. Step S14: Determine the skin abnormality characteristics and posture abnormality characteristics of the silkworms according to the abnormal images of the silkworms, and determine the excrement form of the silkworms along the detection of the silkworm activity trajectory. Step S15: Predict the types of silkworm diseases based on the skin abnormality characteristics, posture abnormality characteristics of the silkworms and the excrement form of the silkworms, and trigger the environmental regulation logic of the silkworm raising room according to the types of silkworm diseases of the silkworms and the silkworm raising environment of the silkworms. Refer to Figure 2 , in step S11, monitor the silkworm raising room in real time and collect the silkworm raising distribution map of the silkworm raising room. In the specific implementation process of the present invention, the specific steps are as follows: S111: Collect the position of the silkworm raising room, trigger the response of the corresponding visual detection component according to the position of the silkworm raising room. At this time, the visual detection component is converted from the standby state to the visual detection state during the response process, and collect the spatial positions of each visual detection component relative to the silkworm raising room. S112: Determine the real-time monitoring area of the silkworm raising room according to the spatial positions of each visual detection component relative to the silkworm raising room and the visual detection range of the visual detection component. At this time, the real-time monitoring area of the silkworm raising room covers the silkworm activity trajectory and the surrounding environment of the silkworms. S113: Each visual detection component moves circularly along the internal space of the silkworm raising room to collect multiple internal images of the silkworm raising room. At the same time, determine the internal distribution map of the silkworm raising room based on the position of the silkworm raising room and the database of the silkworm raising room, and determine the silkworm raising distribution map of the silkworm raising room based on the synthesis of the internal distribution map of the silkworm raising room and the multiple internal images.

[0011] In an embodiment of the present application, the location of the silkworm rearing room is collected, and the response of the corresponding visual detection component is triggered according to the location of the silkworm rearing room. At this time, the visual detection component is transformed from the standby state to the visual detection state during the response process, and the spatial positions of the respective visual detection components relative to the silkworm rearing room are collected. At this time, the precise location of the silkworm rearing room in the physical space is determined, which is usually accomplished through GPS positioning (if the silkworm rearing room is outdoors or within a large facility and GPS signals are reachable), indoor positioning technologies (such as Wi-Fi positioning, Bluetooth beacons, ultrasonic positioning, etc.), or manual input of coordinates.

[0012] Once the location of the silkworm rearing room is determined, the system triggers the response of the associated visual detection components (such as cameras) according to preset rules or algorithms. These visual detection components are transformed from the standby state to the visual detection state and are ready to start collecting image data; at this time, high-definition cameras are installed at each corner of the silkworm rearing room, and these cameras are all connected to a central control system; when the system determines the location of the silkworm rearing room through indoor positioning technology, it sends instructions to the nearest camera (or a group of cameras) to switch them from the standby state to the active state and start capturing images inside the silkworm rearing room.

[0013] The specific positions of the respective visual detection components inside the silkworm rearing room are recorded, which is usually achieved through pre-installed position sensors (such as accelerometers, gyroscopes, magnetometers, etc.) or calibration through spatial reference points set inside the silkworm rearing room; at the same time, position sensors (for example, an IMU module integrating an accelerometer, a gyroscope, and a magnetometer) are installed on each camera, and these sensors can record the position and orientation of the camera in real time; in addition, some known spatial reference points (such as marks on the wall) are set inside the silkworm rearing room, and these reference points are used to calibrate the position and orientation of the camera to ensure that the collected images match the actual layout of the silkworm rearing room.

[0014] Furthermore, according to the spatial positions of the respective visual detection components relative to the silkworm rearing room and the visual detection ranges of the visual detection components, the real-time monitoring area of the silkworm rearing room is determined. At this time, the real-time monitoring area of the silkworm rearing room covers the activity trajectories of the silkworms and the surrounding environment of the silkworms, taking into account the overall consideration of the spatial positions of the respective visual detection components relative to the silkworm rearing room and the visual detection ranges of the visual detection components, ensuring the accuracy of the real-time monitoring area of the silkworm rearing room.

[0015] At this time, obtain the precise positions of each visual detection component (such as a camera) in the silkworm rearing room, which is usually achieved through pre-installed position sensors (such as GPS, Wi-Fi locators, Bluetooth beacons combined with mobile devices, inertial measurement units IMU, etc.) or calibration using spatial reference points set in the silkworm rearing room; the accuracy of the position information is crucial for subsequent determination of the monitoring area; at this time, the position sensor includes an accelerometer, a gyroscope, and a magnetometer, which can measure the three-dimensional position and orientation of the camera; the spatial reference points are marks on the wall, fixed points on the ground, or pre-installed beacons.

[0016] Understand parameters such as the field of view, focal length, and viewing angle of each camera, which determine the area of the silkworm rearing room that the camera can clearly capture; the visual detection range is usually determined through the camera's specification or actual on-site testing; at this time, the visual detection range of the camera is affected by factors such as the lens type (such as wide-angle lens, standard lens, telephoto lens), focal length adjustment, image sensor size, and resolution.

[0017] Combining the spatial position and visual detection range of the visual detection component, determine which areas in the silkworm rearing room are covered by the camera, and these areas constitute the real-time monitoring area, which should cover the main activity trajectories and the surrounding environment of the silkworms to ensure comprehensive monitoring of the silkworms' state; at the same time, it is necessary to use geographic information system (GIS) or computer-aided design (CAD) software to visualize the layout of the silkworm rearing room and the camera, as well as their relative positional relationships; through simulation or actual testing, optimize the position and focal length of the camera to ensure maximum coverage of the monitoring area and minimum overlap.

[0018] Specifically, assume that the silkworm rearing room is a rectangular room with a length of 10 meters, a width of 8 meters, and a height of 3 meters; to monitor the activities of the silkworms, four high-definition cameras (Camera A, B, C, D) are installed at the four corners of the room, and these cameras are all connected to a central control system; Camera A is located in the upper left corner of the room with coordinates (0,0,3); Camera B is located in the upper right corner of the room with coordinates (10,0,3); Camera C is located in the lower left corner of the room with coordinates (0,8,3); Camera D is located in the lower right corner of the room with coordinates (10,8,3), and these coordinates are obtained through calibration using spatial reference points (such as marks on the wall) pre-set in the room.

[0019] Each camera is equipped with a wide-angle lens with a viewing angle of 120 degrees and a fixed focal length. Through on-site testing, the visual detection range of each camera, that is, the area of the silkworm rearing room that they can clearly capture, was determined. Combining the spatial positions of the cameras and the visual detection ranges, a layout map of the silkworm rearing room and the cameras was generated using GIS software. By analyzing the layout map, the real-time monitoring areas in the silkworm rearing room were determined, and these areas cover the main activity tracks of the silkworms (such as the feed feeding area, the silkworm rack area) and the surrounding environment (such as near the walls and doors and windows). To ensure the continuity and non-blind spots of the monitoring, the positions and focal lengths of the cameras were fine-tuned to minimize the overlapping areas between adjacent cameras while maximizing the coverage of the key areas of the silkworm rearing room. Through these steps, the system can efficiently determine the real-time monitoring areas of the silkworm rearing room and provide comprehensive image data support for subsequent silkworm disease prediction.

[0020] Therefore, each visual detection component moves in a circular motion along the internal space of the silkworm rearing room to collect multiple internal images of the silkworm rearing room. At the same time, based on the position of the silkworm rearing room and the database of the silkworm rearing room, the internal distribution map of the silkworm rearing room is determined. Based on the synthesis of the internal distribution map of the silkworm rearing room and the multiple internal images, the silkworm rearing distribution map of the silkworm rearing room is determined, which takes into account the overall consideration of the position of the silkworm rearing room and the database of the silkworm rearing room, and ensures the accuracy of the internal distribution map of the silkworm rearing room.

[0021] At this time, the visual detection component (such as a camera) is moved in a circular motion along the internal space of the silkworm rearing room to collect internal images of the silkworm rearing room from multiple angles and positions, which is achieved by installing a track system, using technologies such as robots or drones, etc. The purpose of the circular motion is to ensure that every corner in the silkworm rearing room can be captured, so as to generate a comprehensive image data set. At this time, the circular motion requires precise control algorithms to ensure that the camera moves along the predetermined path and speed. In addition, to avoid image blurring or overlapping, it is necessary to control the shooting frequency and exposure time of the camera.

[0022] Based on the position of the silkworm rearing room and the known information in the database of the silkworm rearing room, the internal distribution map of the silkworm rearing room is determined, which usually includes the physical layout in the silkworm rearing room (such as silkworm racks, feed feeding areas, ventilation equipment, etc.) and obstacles or special areas. At this time, the database of the silkworm rearing room contains information such as architectural drawings, previous monitoring records, equipment layout maps, etc. By combining this information with the actual position of the silkworm rearing room, a detailed internal distribution map is generated.

[0023] Multiple collected internal images are synthesized to generate a silkworm rearing distribution map of the silkworm rearing room, which usually involves processing steps such as image stitching, duplicate removal, and enhancement; the synthesized image should be able to clearly show the distribution and density of silkworms in the silkworm rearing room; at the same time, image synthesis requires the use of image processing software or algorithms, such as image registration, image fusion, image segmentation, etc.; in addition, in order to improve the accuracy and efficiency of synthesis, high-performance computing resources or parallel processing technologies are needed.

[0024] Specifically, assume that the silkworm rearing room is a rectangular room, 10 meters long, 8 meters wide, and 3 meters high, with multiple silkworm racks and feed placement areas inside; in order to generate the silkworm rearing distribution map, it is decided to use a camera with an automatic movement function (such as a camera installed on a track) for image acquisition.

[0025] The camera is installed on a track that surrounds the inside of the silkworm rearing room. The height and angle of the track are designed to be able to capture the top and side views of the silkworm racks and feed placement areas; the camera moves along the track at a constant speed and stops at preset positions to take pictures; in order to ensure image quality, the shooting frequency of the camera is set to one picture per second, and the exposure time is automatically adjusted according to the indoor light conditions; in addition, in order to avoid image overlap, the distance between adjacent shooting points is accurately calculated and set.

[0026] Using the architectural drawings of the silkworm rearing room and previous monitoring records as references, combined with the image information collected by the camera, the physical layout inside the silkworm rearing room is determined, which includes the positions and quantities of the silkworm racks, the positions and sizes of the feed placement areas, the layout of the ventilation equipment, etc.; by combining this information with the actual position of the silkworm rearing room, a detailed internal distribution map is generated, which shows all the key areas and equipment inside the silkworm rearing room.

[0027] Multiple collected internal images are imported into image processing software, and they are aligned using an image registration algorithm; then, an image fusion algorithm is used to smoothly transition the overlapping parts of adjacent images to generate a seamless panoramic view of the silkworm rearing room; next, an image segmentation algorithm is used to segment the individual and group silkworms in the panoramic view, and a silkworm rearing distribution map is generated based on their positions and densities; this map shows the distribution of silkworms in the silkworm rearing room, as well as the dense or sparse areas; through these steps, the system can efficiently generate the silkworm rearing distribution map of the silkworm rearing room, providing strong data support for subsequent silkworm disease prediction and environmental regulation.

[0028] Reference Figure 3 , in step S12, the silkworm activity trajectory and the silkworm environment area are determined according to the recognition of the silkworm rearing distribution map; In the specific implementation process of the present invention, the specific steps are as follows: S121: Mark the current positions of multiple silkworms based on the detection of the silkworm rearing distribution map. At this time, each silkworm has a corresponding identity mark; determine multiple position nodes passed by each silkworm according to the current position of each silkworm and the image corresponding to each silkworm, and determine the corresponding silkworm activity trajectory according to the synthesis of the multiple position nodes passed by each silkworm; S122: Determine the silkworm activity area according to the silkworm activity trajectory and the current position of each silkworm, and determine the remaining area by comparing the silkworm activity area with the silkworm rearing distribution map; S123: Determine the silkworm environment area based on the division of the remaining area. At this time, the silkworm environment area is on the periphery of the silkworm activity area and covers the silkworm activity area.

[0029] In the embodiment of the present application, mark the current positions of multiple silkworms based on the detection of the silkworm rearing distribution map. At this time, each silkworm has a corresponding identity mark; determine multiple position nodes passed by each silkworm according to the current position of each silkworm and the image corresponding to each silkworm, and determine the corresponding silkworm activity trajectory according to the synthesis of the multiple position nodes passed by each silkworm, which is compatible with the overall consideration of the synthesis of the multiple position nodes passed by each silkworm, and ensures the accuracy of the corresponding silkworm activity trajectory.

[0030] At this time, use the silkworm rearing distribution map (which is generated from the images of the silkworm rearing room captured by the camera through image processing technology) to detect the current position of the silkworm; the silkworm rearing distribution map is usually a two-dimensional plan, which marks the key elements in the silkworm rearing room, such as the silkworm racks, the feed feeding areas, etc., as well as the positions of the silkworms detected through image processing technology; detecting the positions of the silkworms involves image processing technologies, such as object detection, image segmentation or machine learning algorithms, which can identify the individual silkworms in the image and give their position coordinates; each detected silkworm will be assigned a unique identity mark, which is in the form of numbers, letters or two-dimensional codes, etc., for subsequent tracking and analysis.

[0031] Optionally, assume that there is a high-definition camera in the silkworm rearing room, which regularly captures images of the silkworm rearing room and transmits these images to a computer for processing; the image processing software on the computer uses the object detection algorithm to identify the positions of the silkworms from each image and mark them on the silkworm rearing distribution map; for example, in an image, the software identifies three silkworms, located at coordinates (x1, y1), (x2, y2) and (x3, y3) respectively, and these three silkworms are marked as Silkworm A, Silkworm B and Silkworm C respectively.

[0032] Using the distribution map of silkworms at consecutive time points (or a sequence of continuously captured images), along with the identity markers of each silkworm, to determine the movement paths of silkworms; by comparing the images at different time points, tracking the position changes of each silkworm from the previous time point to the current time point, and these position change points (i.e., position nodes) constitute the key points of the movement paths of silkworms; each position node records the position coordinates of the silkworm at a certain time point.

[0033] Connecting the sequence of position nodes of each silkworm in chronological order synthesizes the corresponding silkworm activity trajectory; the activity trajectory is usually represented as a series of consecutive position points, which are connected by lines to form a curve representing the movement path of the silkworm; the activity trajectory is used to analyze the behavior patterns, activity ranges, and interactions with other silkworms or environmental factors of the silkworms.

[0034] Furthermore, determine the silkworm activity area based on the silkworm activity trajectory and the current positions of each silkworm, and determine the remaining area by comparing the silkworm activity area with the silkworm rearing distribution map, taking into account the overall situation of the silkworm activity trajectory and the current positions of each silkworm, ensuring the accuracy of the silkworm activity area.

[0035] At this time, use the silkworm activity trajectory obtained in the previous steps and the current position information of each silkworm to determine the main activity areas of silkworms in the silkworm rearing room; the activity areas are usually one or more two-dimensional areas that cover the positions where silkworms frequently appear and move; methods for determining the activity areas include cluster analysis, spatial statistical analysis, or density-based grid division, etc., which can identify the areas in the silkworm rearing room where silkworm activities are the most intensive; the size and shape of the activity areas vary depending on the species and quantity of silkworms, the environmental conditions of the silkworm rearing room, and the management strategies.

[0036] Optionally, assume that the activity trajectories of multiple silkworms have been obtained through the previous steps and the current positions of each silkworm are known; by analyzing these trajectories and position information, it is found that the silkworms are mainly concentrated in a certain corner of the silkworm rearing room, where there are multiple silkworm racks and it is close to the feed delivery area; use the cluster analysis method to divide this corner into a silkworm activity area; this area is an oval or irregular shape, depending on the actual distribution of the silkworms.

[0037] After determining the silkworm activity area, it is necessary to compare it with the silkworm rearing distribution map to determine the remaining parts of the silkworm rearing room that are not covered by the silkworm activity area; the remaining areas are the blank areas, edge areas or other functional areas (such as ventilation openings, doorways, etc.) in the silkworm rearing room, where there is little or no silkworm activity; the methods for determining the remaining areas include spatial subtraction, image masking operations or rule-based partitioning, etc., which can remove the activity areas from the silkworm rearing distribution map to obtain the remaining areas; understanding the remaining areas is of great significance for optimizing the silkworm rearing environment, preventing the spread of diseases and improving the silkworm rearing efficiency, etc.

[0038] Optionally, the silkworm activity area has been determined to be an oval area located in a corner of the silkworm rearing room; now, compare this activity area with the silkworm rearing distribution map and remove the activity area through spatial subtraction operations to obtain the remaining areas; the remaining areas include other corners of the silkworm rearing room, areas near the doorway and ventilation openings, and the gaps between the silkworm racks, etc., which are represented by different colors or markings on the silkworm rearing distribution map for subsequent analysis and management.

[0039] Therefore, based on the division of the remaining areas, the silkworm environment area is determined. At this time, the silkworm environment area is on the periphery of the silkworm activity area and covers the silkworm activity area, introducing the coverage of the silkworm activity area.

[0040] At this time, further divide the silkworm environment area according to the remaining areas determined in the previous steps; the silkworm environment area refers to those areas that, although silkworms do not directly move in them, have an important impact on their growth, development and health. These areas are usually on the periphery of the silkworm activity area and include ventilation openings, doorways, areas near light sources, temperature and humidity control equipment, etc.

[0041] The methods for determining the environment area involve spatial analysis, environmental factor assessment or judgment based on silkworm rearing management experience; by analyzing the spatial layout, environmental factors of the remaining areas and the biological characteristics of silkworms, identify those environmental areas that have an important impact on silkworms; the size and shape of the environment area vary depending on the specific conditions of the silkworm rearing room and different management strategies; importantly, ensure that these areas can effectively cover the silkworm activity area and provide a suitable growth environment for it.

[0042] Optionally, assume that the remaining areas in the silkworm rearing room have been determined through the previous steps. These areas include the edges of the silkworm rearing room, the areas near the door, the areas around the ventilation openings, and the gaps between some of the silkworm racks. When analyzing these remaining areas, it is found that the areas near the door and around the ventilation openings are the areas where the air flow, temperature, and humidity changes are most obvious in the silkworm rearing room. At the same time, these areas are also close to the silkworm activity areas, so they have an important impact on the growth environment of silkworms. Based on these analyses, the areas near the door and around the ventilation openings are designated as the environmental areas for silkworms, and these areas are marked or colored in a specific way in the silkworm rearing room for subsequent environmental monitoring and management.

[0043] When determining the silkworm environmental areas, it is necessary to ensure that these areas are located on the periphery of the silkworm activity areas and can effectively cover the activity areas. This means that the environmental areas should be large enough to include all the important factors around the activity areas and ensure that the silkworms in the activity areas can obtain a suitable growth environment. Covering the activity areas does not mean that the environmental areas must completely surround the activity areas, but rather that the environmental areas should extend to the edges of the activity areas and, if necessary, extend slightly beyond to ensure that no important environmental factors are missed. Through reasonable planning and layout, ensure that the spatial relationship between the silkworm environmental areas and the activity areas is optimized, thus providing the best growth conditions for silkworms.

[0044] Optionally, when determining the silkworm environmental areas, ensure that these areas are located on the periphery of the silkworm activity areas and extend to the edges of the activity areas. For example, for the environmental area near the door, it is designated as an area extending a certain distance outward from the door to ensure that all silkworms affected by the air flow at the door are covered.

[0045] Similarly, for the environmental area around the ventilation opening, it is also designated as an area extending a certain range outward from the ventilation opening to ensure that all silkworms affected by the air flow and temperature and humidity changes at the ventilation opening are covered. Through such a layout, ensure that the silkworm environmental areas can effectively cover the silkworm activity areas and provide a suitable growth environment for silkworms.

[0046] In some embodiments of the present application, a collection area matching table is collected, and the area matching table is shown in Table 1: Table 1 Area Matching Table

[0047] Reference Figure 4 , in step S13, determine the silkworm rearing environment based on the environmental detection of the silkworm environmental areas, and determine the abnormal areas in the silkworm rearing room according to the silkworm rearing environment and the silkworm activity trajectories, and mark the abnormal images of the silkworms. In the specific implementation process of the present invention, the specific steps are as follows: S131: Collect the mulberry silkworm environmental area, determine multiple environmental detection nodes according to the mulberry silkworm environmental area and the mulberry silkworm activity trajectory, determine the corresponding environmental parameters according to the environmental detection of the multiple environmental detection nodes, and determine the mulberry silkworm rearing environment according to the locations of the multiple environmental detection nodes, the corresponding environmental parameters, and the regional shape of the mulberry silkworm environmental area; S132: Collect the mulberry silkworm activity trajectory, determine multiple mulberry silkworm activity nodes according to the division of the mulberry silkworm activity trajectory, and determine the corresponding mulberry silkworm activity events according to the traceability of the multiple mulberry silkworm activity nodes. The mulberry silkworm activity events cover the activity postures, rest postures, and excretion actions of the mulberry silkworm; S133: Determine the first abnormal parameter according to the multiple mulberry silkworm activity events and the mulberry silkworm rearing environment, determine the second abnormal parameter according to the multiple mulberry silkworm activity events and the mulberry silkworm species, determine the abnormal area of the rearing room based on the first abnormal parameter, the second abnormal parameter, and the abnormal area mapping relationship, and collect the abnormal images of the mulberry silkworm based on the real-time monitoring of the abnormal area of the rearing room.

[0048] In the embodiment of the present application, by collecting the mulberry silkworm environmental area, determining multiple environmental detection nodes according to the mulberry silkworm environmental area and the mulberry silkworm activity trajectory, determining the corresponding environmental parameters according to the environmental detection of the multiple environmental detection nodes, and determining the mulberry silkworm rearing environment according to the locations of the multiple environmental detection nodes, the corresponding environmental parameters, and the regional shape of the mulberry silkworm environmental area, it takes into account the overall situation of the locations of the multiple environmental detection nodes, the corresponding environmental parameters, and the regional shape of the mulberry silkworm environmental area, ensuring the accuracy of the mulberry silkworm rearing environment.

[0049] At this time, when collecting the mulberry silkworm environmental area and based on the information of the mulberry silkworm environmental area and the mulberry silkworm activity trajectory, a series of key environmental detection nodes need to be determined. These nodes are usually areas where the mulberry silkworms are active frequently and are vulnerable to environmental impacts; when determining the nodes, the biological characteristics of the mulberry silkworms (such as sensitivity to temperature, humidity, and light), the structural characteristics of the rearing room, and the spatial distribution of environmental factors should be considered.

[0050] Optionally, in the rearing room, according to the mulberry silkworm activity trajectory, determine the positions near the silkworm racks, under the ventilation equipment, near the door, and in the corners of the rearing room, etc. as environmental detection nodes. These positions can reflect the environmental conditions of the mulberry silkworm activity areas and are easy to deploy sensors.

[0051] After determining the environmental detection nodes, corresponding sensors need to be deployed on each node to monitor key environmental parameters in real time. These parameters include temperature, humidity, light intensity, gas concentration (such as carbon dioxide, oxygen), etc.; the selection and deployment of sensors should consider their measurement range, accuracy, stability, and compatibility with the environmental detection nodes. At this time, on the environmental detection nodes near the silkworm racks, temperature and humidity sensors are deployed to monitor the temperature and humidity changes in the silkworm activity area; on the nodes under the ventilation equipment, gas concentration sensors are deployed to monitor the gas environment in the silkworm rearing room.

[0052] Based on the positions of multiple environmental detection nodes, the corresponding environmental parameters, and the morphology of the silkworm environment area, comprehensively evaluate and determine the silkworm rearing environment. This usually involves performing spatial analysis, time series analysis, or statistical analysis on the collected environmental data to identify environmental hotspots, cold spots, or abnormal areas in the silkworm rearing room; according to the analysis results, adjust the environmental conditions in the silkworm rearing room, such as adjusting temperature and humidity, improving ventilation, etc., to ensure that the silkworms are in the best growth environment. Optionally, by analyzing the temperature and humidity data of each environmental detection node in the silkworm rearing room, it is found that the temperature and humidity fluctuations near a certain silkworm rack are relatively large, which is not conducive to the growth of silkworms; therefore, adjust the temperature and humidity control device in this area to reduce the fluctuations and maintain suitable temperature and humidity conditions.

[0053] Specifically, assume that there are three rows of silkworm racks in the silkworm rearing room with appropriate intervals between each row; according to the activity trajectories of the silkworms and the structural characteristics of the silkworm rearing room, six environmental detection nodes are determined: three are near the silkworm racks (denoted as A, B, and C respectively), two are in the corners of the silkworm rearing room (denoted as D and E), and one is under the ventilation equipment (denoted as F); on each node, temperature and humidity sensors and gas concentration sensors are deployed; by real-time monitoring the data of these sensors, it is found that the temperature and humidity fluctuations near node A are relatively large, and the carbon dioxide concentration is relatively high under node F; based on these data, the temperature and humidity control device near node A is adjusted to reduce the fluctuations; at the same time, the ventilation volume in the silkworm rearing room is increased to reduce the carbon dioxide concentration under node F; through this series of operations, the environmental conditions in the silkworm rearing room are successfully optimized, providing a more suitable growth environment for the silkworms.

[0054] Furthermore, collect the silkworm activity trajectories, determine multiple silkworm activity nodes according to the division of the silkworm activity trajectories, and determine the corresponding silkworm activity events according to the tracing of multiple silkworm activity nodes. The silkworm activity events cover the activity postures, resting postures, and excretion actions of the silkworms, taking into account the overall tracing of multiple silkworm activity nodes and ensuring the accuracy of the corresponding silkworm activity events.

[0055] At this time, use technical means such as image recognition, video tracking, or RFID to collect the activity trajectories of silkworms in the silkworm rearing room in real time; the collected data should include the position information of the silkworms (such as x, y coordinates) and time information (such as time stamps) to facilitate subsequent analysis of the activity patterns and frequencies of silkworms; during the collection process, it is necessary to ensure the accuracy and continuity of the data to avoid information loss caused by missed collection or miscollection. Optionally, capture images of silkworms through a camera, and use computer vision algorithms to identify the positions and postures of silkworms; perform frame-by-frame analysis on the videos captured by the camera to track the movement trajectories of silkworms; attach RFID tags to the silkworms, and read the tag information through an RFID reader to obtain the position data of the silkworms.

[0056] Based on the collected activity trajectories of silkworms, it is necessary to divide the trajectories into multiple key activity nodes; activity nodes are usually areas where silkworms stay for a long time, are active frequently, or have specific behavior patterns; when dividing activity nodes, consider factors such as the activity density, activity speed, and direction change of silkworms; at this time, according to the density distribution of silkworms in the activity area, divide the high-density areas into activity nodes; by analyzing the behavior patterns of silkworms (such as foraging, resting, excreting, etc.), divide the areas with similar behaviors into the same activity node.

[0057] After determining the silkworm activity nodes, it is necessary to trace each node to determine the specific activity events of silkworms at these nodes; activity events should cover various behaviors of silkworms, including activity postures (such as crawling, foraging), resting postures (such as staying still), and excretion actions, etc.; the tracing process needs to use technical means such as image recognition and behavior analysis to classify and identify the behaviors of silkworms in detail; at this time, use machine learning algorithms to classify the collected images to identify different postures and behaviors of silkworms; by analyzing the behavior sequences of silkworms at activity nodes, identify activity events with specific meanings.

[0058] Specifically, assume that in the silkworm rearing room, the activity trajectories of silkworms are collected using image recognition technology; by analyzing the trajectory data, it is found that silkworms are mainly concentrated in three areas for activities: near the silkworm rack, near the feed area, and near the rest area; use a camera to capture the activity images of silkworms in the silkworm rearing room, and record the position and time information of each silkworm; through density clustering methods, divide the areas near the silkworm rack, near the feed area, and near the rest area into three key activity nodes.

[0059] At the activity nodes near the mulberry silkworm racks, through image classification and behavioral sequence analysis, the foraging postures and activity events of mulberry silkworms are identified; at the activity nodes near the feeding area, the foraging postures of mulberry silkworms are also identified, but it also includes behavioral events such as scrambling for feed; at the activity nodes near the rest area, the resting events such as the motionless postures and excretion actions of mulberry silkworms are identified; through this series of steps, the activity trajectories of mulberry silkworms are successfully collected, the key activity nodes are determined, and the specific activity events at each node are traced. This information is of great significance for understanding the behavioral patterns of mulberry silkworms, optimizing the silkworm-raising environment, and improving the breeding efficiency, etc.

[0060] Therefore, determine the first abnormal parameter according to multiple mulberry silkworm activity events and the mulberry silkworm-raising environment, determine the second abnormal parameter according to multiple mulberry silkworm activity events and the species of mulberry silkworms, determine the abnormal area of the silkworm-raising room based on the first abnormal parameter, the second abnormal parameter and the abnormal area mapping relationship, and collect the abnormal images of mulberry silkworms based on the real-time monitoring of the abnormal area of the silkworm-raising room. It takes into account the overall consideration of the first abnormal parameter, the second abnormal parameter and the abnormal area mapping relationship, ensures the accuracy of the abnormal area of the silkworm-raising room, takes into account the overall consideration of the mulberry silkworm-raising environment and the mulberry silkworm activity trajectory, ensures the accurate detection of the abnormal area of the silkworm-raising room, and further ensures the accuracy of the abnormal images of mulberry silkworms.

[0061] At this time, determine the first abnormal parameter that does not conform to the normal state according to multiple mulberry silkworm activity events and the mulberry silkworm-raising environment; the first abnormal parameter includes the activity frequency, activity range, activity intensity, etc. of mulberry silkworms, as well as the temperature, humidity, light, gas concentration, etc. related to the silkworm-raising environment; when determining the first abnormal parameter, it is necessary to establish the standard range or threshold of the normal state for comparison with the current state.

[0062] Optionally, conduct statistical analysis on multiple mulberry silkworm activity events, calculate statistical quantities such as the average value and standard deviation of the activity frequency, activity range, etc., and compare them with the standard range of the normal state; conduct real-time monitoring and analysis on the data such as the temperature, humidity, light, gas concentration, etc. of the silkworm-raising environment, and compare them with the threshold of the normal state.

[0063] Determine the second abnormal parameter that does not conform to the normal behavior pattern according to multiple mulberry silkworm activity events and the species of mulberry silkworms; the second abnormal parameter includes the abnormal manifestations of behaviors such as the activity postures, resting postures, excretion actions, etc. of mulberry silkworms; when determining the abnormal parameter, it is necessary to consider the biological characteristics and behavior patterns of the mulberry silkworm species.

[0064] At this time, use technical means such as image recognition and machine learning to identify and analyze the behaviors such as the activity postures, resting postures, excretion actions, etc. of mulberry silkworms, and compare them with the normal behavior pattern; analyze the activity sequence of mulberry silkworms to identify abnormal behaviors or changes in behavior patterns.

[0065] Based on the first abnormal parameter, the second abnormal parameter, and the abnormal area mapping relationship, determine the abnormal area in the silkworm rearing room; the abnormal area mapping relationship refers to associating the abnormal parameters with specific areas in the silkworm rearing room to quickly locate the abnormal area; at the same time, using Geographic Information System (GIS) or spatial data analysis technology, associate the abnormal parameters with the spatial positions in the silkworm rearing room to determine the abnormal area; generate a heat map of the silkworm rearing room according to the intensity or frequency of the abnormal parameters to visually display the abnormal area.

[0066] Based on the real-time monitoring of the abnormal area in the silkworm rearing room, collect abnormal images of the silkworms; the abnormal images should be able to clearly show the abnormal behaviors or abnormal states of the silkworms for subsequent analysis and processing; at the same time, use cameras or image acquisition devices to conduct real-time monitoring of the abnormal area; when an abnormality occurs, capture the abnormal images in a timely manner and save them for subsequent analysis.

[0067] Specifically, assume that in the silkworm rearing room, real-time monitoring and analysis of the silkworm activity events and the silkworm rearing environment are carried out using image recognition technology and environmental monitoring equipment; at this time, determine the first abnormal parameter: through data statistical analysis, it is found that the activity frequency of silkworms in a certain area is significantly reduced, and at the same time, the temperature and humidity data in this area also deviate from the normal threshold; therefore, the reduction of activity frequency and abnormal temperature and humidity are determined as the first abnormal parameters.

[0068] Determine the second abnormal parameter: through behavior pattern recognition and behavior sequence analysis, it is found that the silkworms in this area show abnormal resting postures and excretion actions, such as staying still for a long time, abnormal excrement, etc.; therefore, the abnormal resting postures and abnormal excretion actions are determined as the second abnormal parameters.

[0069] Combining the first abnormal parameter, the second abnormal parameter, and the abnormal area mapping relationship, determine the specific area where abnormalities occur in the silkworm rearing room; through spatial analysis and heat map analysis, visually see the degree and scope of the abnormality in this area; at the same time, after determining the abnormal area, use a camera to conduct real-time monitoring of this area; when the abnormality occurs again, capture the abnormal images in a timely manner and save the relevant video materials for subsequent analysis.

[0070] In some embodiments of the present application, collect the first abnormal parameter matching table, and the first abnormal parameter matching table is shown in Table 2: Table 2 First Abnormal Parameter Matching Table

[0071] At this time, determine the first abnormal parameter as: reduced activity frequency, expanded activity range, low temperature and humidity, insufficient light.

[0072] Collect the second abnormal parameter matching table, and the second abnormal parameter matching table is shown in Table 3: Table III Second Abnormal Parameter Matching Table

[0073] At this time, it is determined that the second abnormal parameter is: crawling slowly during foraging, stretching the body during rest, and frequent excretion; Collect the abnormal area mapping table, and the abnormal area mapping table is shown in Table IV: Table IV Abnormal Area Mapping Table

[0074] It is determined that the abnormal areas in the silkworm rearing room are: Area A (decreased activity frequency, low temperature and humidity), Area B (expanded activity range, insufficient light), and Area C (crawling slowly during foraging, frequent excretion).

[0075] Reference Figure 5 , in step S14, based on the abnormal images of the silkworms, determine the skin abnormal characteristics and posture abnormal characteristics of the silkworms, and determine the excrement form of the silkworms along the detection of the silkworm activity trajectory; In the specific implementation process of the present invention, the specific steps are as follows: S141: Collect the abnormal images of the silkworms, and determine the skin area and the action area of the silkworms according to the division of the abnormal images of the silkworms. At this time, the skin area and the action area of the silkworms are within the same abnormal image; S142: Determine multiple skin color characteristics based on the recognition of the skin area of the silkworms, and determine the abnormal color characteristics according to the matching of the multiple skin color characteristics and the database of the silkworm rearing room. Determine the skin abnormal characteristics of the silkworms based on the position, form of the abnormal color characteristics and the species of the silkworms; S143: Determine multiple posture characteristics based on the recognition of the action area of the silkworms, and determine the posture abnormal characteristics according to the matching of the multiple posture characteristics and the database of the silkworm rearing room; S144: Collect the silkworm activity trajectory, and perform detection along the silkworm activity trajectory to collect the images of the excrement in the silkworm activity trajectory. Determine the excrement form of the silkworms according to the recognition of the excrement images, and determine the abnormal feature combination based on the matching of the excrement form, posture abnormal characteristics and skin abnormal characteristics of the silkworms, and perform autonomous update of the features in the abnormal feature combination.

[0076] In the embodiment of the present application, collect the abnormal images of the silkworms, and determine the skin area and the action area of the silkworms according to the division of the abnormal images of the silkworms. At this time, the skin area and the action area of the silkworms are within the same abnormal image, and it is introduced that the skin area and the action area of the silkworms are within the same abnormal image.

[0077] At this time, abnormal images are collected and preprocessed, including denoising, contrast enhancement, etc., to improve image quality; the preprocessed images should be clearer to facilitate the subsequent division of skin areas and action areas. At the same time, image processing techniques such as image segmentation and edge detection are used to identify the skin area of ​​the silkworm; the skin area usually includes the body part of the silkworm, and its color, texture and other characteristics can be used for subsequent analysis.

[0078] Image processing technology is also used to identify the action area of ​​the silkworm; the action area usually includes the limbs, head and other parts of the silkworm that can reflect its activity state; by analyzing the morphological changes of the action area, it is determined whether the silkworm has abnormal behavior; at this time, the divided skin area and action area are integrated into the same abnormal image for subsequent comprehensive analysis.

[0079] Specifically, suppose that in a silkworm breeding room, a high-definition camera is used to monitor silkworms in real time. One day, it is observed that the body color of a silkworm suddenly becomes abnormally dark, and its movements become slow. Therefore, this abnormal image is immediately captured.

[0080] In the image preprocessing stage, the images were denoised and contrast enhanced to make the appearance features of the silkworm more obvious; then, image processing technology was used to identify the silkworm's skin area (including its body part) and action area (including its limbs and head); in the skin area, it was clearly seen that the silkworm's body color became dull, in sharp contrast to the bright color of the normal silkworm; in the action area, it was observed that the silkworm's limbs were sluggish and lacked vitality.

[0081] Finally, the divided skin area and movement area are integrated into the same abnormal image to facilitate subsequent comprehensive analysis of the abnormal conditions of the silkworms. Through this abnormal image, it is intuitively seen that the skin color and movement status of the silkworms are abnormal, so as to further judge their health status and take corresponding treatment measures.

[0082] Furthermore, multiple skin color features are determined based on the identification of the skin area of ​​the silkworm, and abnormal color features are determined based on the matching of the multiple skin color features with the database of the silkworm breeding room. The abnormal skin features of the silkworm are determined based on the position, form and type of the abnormal color features, which is compatible with the overall consideration of the position, form and type of the abnormal color features, thereby ensuring the accuracy of the abnormal skin features of the silkworm.

[0083] At this time, in the divided silkworm skin area, color recognition technology (such as RGB color space analysis, HSV color space conversion, etc.) is used to extract multiple skin color features. These color features include the overall skin hue, brightness, saturation, etc.; ensure that the extracted color features can accurately reflect the true color state of the silkworm skin.

[0084] Match the extracted skin color features with the normal skin color features stored in the silkworm rearing room database. The normal skin color features in the database are obtained based on the observation data of a large number of healthy silkworms and represent the normal skin color range of silkworms at different growth stages and in different environments. At the same time, through comparison, identify the color features that do not match the normal skin color features in the database, that is, abnormal color features. Abnormal color features are manifested as deviations in hue, abnormalities in brightness, and excessive or insufficient saturation, etc.

[0085] Carefully observe the position distribution and morphological features of the abnormal color features on the silkworm's skin. The position distribution involves the whole body or part of the body, and the morphological features include spots, stripes, fading, etc. At the same time, according to the species of silkworms, consider their unique skin color features and abnormalities. Different species of silkworms are more sensitive to certain color changes or have specific skin color abnormal patterns. Combine the position, morphology of the abnormal color features and the species of silkworms to comprehensively judge the skin abnormal features of silkworms.

[0086] Specifically, assume that an abnormal skin color of a silkworm is observed in the silkworm rearing room. In the already divided skin area, the skin color features of the silkworm are extracted using color recognition technology, and it is found that its overall hue is yellowish, the brightness is low, and the saturation has also decreased. Then, these color features are matched with the normal skin color features stored in the silkworm rearing room database. Through comparison, it is found that the skin color features of this silkworm are significantly different from the normal features stored in the database, especially the yellowish hue is very obvious.

[0087] Therefore, it is determined that this silkworm has abnormal color features. Further observation shows that the abnormal color features are mainly distributed on the abdomen and back of the silkworm, and the morphology presents as a uniform yellow covering. Finally, combined with the species of this silkworm (assumed to be a certain silkworm variety that is abnormally sensitive to yellow), it is judged that its skin abnormal features are caused by a certain disease or malnutrition. Then, corresponding treatment measures are taken, and the environment in the silkworm rearing room is adjusted in order to improve the health status of the silkworms.

[0088] Furthermore, determine multiple posture features according to the recognition of the action area of the silkworm, and determine the posture abnormal features according to the matching of multiple posture features and the database of the silkworm rearing room. Considering the overall compatibility of the matching of multiple posture features and the database of the silkworm rearing room, ensure the accuracy of the posture abnormal features.

[0089] At this time, within the already demarcated action area of the mulberry silkworms, multiple pose features are extracted using pose recognition technologies (such as skeleton extraction, key point detection, action classification, etc.). These pose features include the limb angles, movement trajectories, action speeds, action durations, etc. of the mulberry silkworms, ensuring that the extracted pose features can accurately reflect the true action states of the mulberry silkworms.

[0090] Match the extracted pose features with the normal pose features stored in the mulberry silkworm rearing room database. The normal pose features in the database are obtained based on the observation data of a large number of healthy mulberry silkworms in different situations, representing the normal pose ranges of mulberry silkworms in different growth stages and different activity states. At the same time, through comparison, identify the pose features that do not match the normal pose features in the database, that is, abnormal pose features. Abnormal pose features are manifested as uncoordinated actions, abnormal speeds, overly long or short durations, etc.

[0091] Specifically, assume that an abnormal action of a mulberry silkworm is observed in the mulberry silkworm rearing room. Within the already demarcated action area, the pose features of the mulberry silkworm are extracted using pose recognition technologies. Through skeleton extraction and key point detection, it is found that the limb actions of this mulberry silkworm appear uncoordinated, especially the movement trajectories of the front and hind limbs show obvious deviations. In addition, it is also noted that the action speed of this mulberry silkworm is significantly slower than that of other healthy mulberry silkworms.

[0092] Then, these pose features are matched with the normal pose features stored in the mulberry silkworm rearing room database. Through comparison, it is found that the pose features of this mulberry silkworm are significantly different from the normal features stored in the database. Especially the uncoordination of the limb actions and the slowness of the action speed, both of these features are significantly deviated from the normal range. Therefore, it is determined that this mulberry silkworm has abnormal pose features. Combining the previous observations, it is speculated that this mulberry silkworm suffers from a certain disease that affects its motor ability, or its physical discomfort is caused by an unsuitable environment (such as too high or too low temperature, too high or too low humidity), which in turn affects its normal actions.

[0093] To verify this speculation, other behavioral characteristics of this mulberry silkworm are further observed, and relevant physiological index data are collected. At the same time, the environment in the mulberry silkworm rearing room is also inspected to ensure the suitability of the environmental conditions. Finally, based on comprehensive information from multiple aspects, corresponding treatment measures are formulated, and the environment in the mulberry silkworm rearing room is adjusted as necessary.

[0094] Therefore, collect the activity trajectories of mulberry silkworms, and conduct detections along the activity trajectories of mulberry silkworms to collect images of excreta in the activity trajectories of mulberry silkworms. Determine the form of the excreta of mulberry silkworms based on the recognition of the images of the excreta, and determine the abnormal feature combination based on the matching of the form of the excreta of mulberry silkworms, posture abnormal features, and skin abnormal features. And perform autonomous updates of features in the abnormal feature combination, which accommodates the overall consideration of the matching of the form of the excreta of mulberry silkworms, posture abnormal features, and skin abnormal features, and ensures the accuracy of the abnormal feature combination.

[0095] At this time, use devices such as video tracking technology or infrared sensors to continuously record the activity trajectories of mulberry silkworms in the silkworm rearing room; ensure the continuity and accuracy of the activity trajectories for subsequent analysis of the behavior patterns and habits of mulberry silkworms.

[0096] According to the collected activity trajectories, plan the detection path and detect the areas passed by mulberry silkworms along the path; the key areas for detection are the areas where mulberry silkworms excrete, such as mulberry leaf piles, silkworm excrement basins, etc.; at the same time, during the detection process, use a high-resolution camera or other image acquisition devices to capture images of excreta on the activity trajectories of mulberry silkworms; ensure that the images are clear and can accurately reflect the characteristics of the excreta, such as shape, color, texture, etc.

[0097] Use image processing technology to identify and analyze the collected images of excreta; identify the form of the excreta (such as shape, size, color, etc.) and compare it with the normal form of excreta stored in the database; at this time, match the identified form of the excreta with the previously determined posture abnormal features and skin abnormal features; comprehensively consider the abnormal features in these three aspects to form an abnormal feature combination to comprehensively reflect the health status of mulberry silkworms.

[0098] Furthermore, as time goes by and the health status of mulberry silkworms changes, continuously update the features in the abnormal feature combination; through continuous monitoring and data analysis, timely discover new abnormal features and incorporate them into the abnormal feature combination.

[0099] Specifically, assume that the activity trajectory of a mulberry silkworm is continuously monitored in the silkworm rearing room, and it is found that its activity range gradually decreases and its movement becomes sluggish; use video tracking technology to record the activity trajectory of this mulberry silkworm and find that it frequently moves near the mulberry leaf pile but rarely moves to other areas; then, conduct detections along the activity trajectory, especially near the mulberry leaf pile and the silkworm excrement basin; during the detection process, capture a clear image of the excreta and find that the form of the excreta is abnormal, showing a dry and lumpy state, which is significantly different from the wet and loose form of normal excreta.

[0100] Then, image processing technology was used to identify and analyze the excrement images, and the abnormalities in the excrement morphology were confirmed. At the same time, the previously determined abnormal posture characteristics (such as slow movement and limb incoordination) and skin abnormal characteristics (such as dull skin color and spots) were also reviewed. Considering these three aspects of abnormal characteristics comprehensively, an abnormal characteristic combination was formed, and it was considered that this silkworm suffered from a certain disease or malnutrition. To verify this speculation, physiological index data of the silkworm were further collected and silkworm-raising experts were consulted. Finally, based on the new monitoring data and analysis results, the abnormal characteristic combination was updated independently. It was found that the health condition of the silkworm had improved, but there were still some abnormal characteristics. Therefore, the treatment measures and environmental conditions were adjusted, and the silkworm was continuously monitored and analyzed in order to comprehensively and accurately reflect its health condition.

[0101] In some embodiments of the present application, an abnormal characteristic category matching table is collected, and the abnormal characteristic category matching table is shown in Table 5 as follows: Table 5 Abnormal Characteristic Category Matching Table

[0102] According to the abnormal characteristics of the silkworm, it is evaluated by referring to the weight and score table. For example, dry and caked excrement gets 4 points (assuming it is at a medium to upper level in the score range), slow movement gets 5 points (severe), and dull skin color gets 2 points (mild). The scores of all abnormal characteristics are added up to obtain the total health score of the silkworm. In this example, the total score = 4 (excrement) + 5 (posture) + 2 (skin) = 11 points.

[0103] According to the total score, the health condition of the silkworm is divided into different grades (such as excellent, good, average, poor, extremely poor). In this example, it is assumed that the total score of 11 points belongs to the "poor" grade. At the same time, the silkworm is continuously monitored, and the weight and score table are adjusted according to the changes in its health condition. The total health score and grade of the silkworm are re-evaluated regularly. Through the above two methods, the health condition of the silkworm can be understood more comprehensively and accurately, and corresponding treatment measures and environmental adjustment strategies can be taken.

[0104] Reference Figure 6 , in step S15, based on the skin abnormal characteristics, posture abnormal characteristics of the silkworm and the excrement morphology of the silkworm, the types of silkworm diseases are predicted, and according to the types of silkworm diseases and the silkworm-raising environment of the silkworm, the environmental control logic of the silkworm-raising room is triggered; In the specific implementation process of the present invention, the specific steps are as follows: S151: Collect the skin abnormal characteristics, posture abnormal characteristics of the silkworm and the excrement morphology of the silkworm, determine the first silkworm disease parameter according to the excrement morphology of the silkworm and the skin abnormal characteristics of the silkworm, and determine the second silkworm disease parameter according to the excrement morphology of the silkworm and the posture abnormal characteristics of the silkworm; S152: Predict the silkworm disease type based on the mapping relationship between the first silkworm disease parameter, the second silkworm disease parameter, and the silkworm disease type. Determine the silkworm disease impact behavior according to the traceability of the silkworm disease type, and dynamically match the silkworm disease impact behavior with the activity behavior corresponding to the silkworm activity trajectory to further review the silkworm disease type of the silkworm. S153: After the review of the silkworm disease type of the silkworm is completed, determine the silkworm disease optimization measures based on the silkworm disease type of the silkworm and the database of the silkworm rearing room. Form multiple sub-optimization measures according to the classification of the silkworm disease optimization measures, and determine the environmental control logic of the silkworm rearing room according to the content of the multiple sub-optimization measures, the type of the silkworm, and the silkworm rearing environment of the silkworm, so as to trigger the environmental control event of the silkworm rearing room.

[0105] In the embodiment of the present application, collect the skin abnormality characteristics, posture abnormality characteristics of the silkworm, and the excrement form of the silkworm. Determine the first silkworm disease parameter according to the excrement form of the silkworm and the skin abnormality characteristics of the silkworm, and determine the second silkworm disease parameter according to the excrement form of the silkworm and the posture abnormality characteristics of the silkworm. It takes into account the overall consideration of the excrement form of the silkworm and the posture abnormality characteristics of the silkworm, and ensures the accuracy of the second silkworm disease parameter.

[0106] At this time, collect the skin abnormality characteristics of the silkworm. At this time, use equipment such as a high-definition camera or a microscope to carefully observe the skin of the silkworm; record changes in skin color, texture, gloss, etc., and pay special attention to whether there are abnormal phenomena such as spots, ulcers, swelling, etc. These abnormal characteristics indicate that the silkworm has a certain skin disease or is invaded by external parasites.

[0107] Collect the posture abnormality characteristics of the silkworm. At this time, record the walking, eating, resting postures of the silkworm through video tracking or manual observation; pay attention to observing whether the silkworm has abnormal postures such as slow movement, uncoordinated limbs, and body distortion. These abnormal characteristics indicate that the silkworm has nervous system problems, muscle diseases, or poisoning, etc.

[0108] Collect the excrement form of the silkworm. At this time, collect the excrement sample of the silkworm and use equipment such as a microscope or a chemical analyzer for detection; observe the characteristics of the excrement color, texture, shape, etc., and pay special attention to the presence of abnormal substances (such as blood, pus); the change of the excrement form reflects the digestive system health status of the silkworm or whether it has a certain infectious disease.

[0109] Combined with the excrement morphology and skin abnormality characteristics of mulberry silkworms, comprehensive analysis is carried out; according to the corresponding relationship between known silkworm diseases and these characteristics, the types of silkworm diseases suffered by mulberry silkworms are initially judged; this judgment result is used as the first silkworm disease parameter for subsequent silkworm disease prediction and formulation of optimization measures; optionally, assume that during the collection process, it is found that the skin color of a certain mulberry silkworm is dull, with irregular spots, and at the same time its excrement presents a dry and caked state; combined with these characteristics, it is initially judged that the mulberry silkworm suffers from malnutrition combined with skin disease, and this judgment result is the determined first silkworm disease parameter.

[0110] Determine the second silkworm disease parameter. Similarly, comprehensive analysis is carried out by combining the excrement morphology and posture abnormality characteristics of mulberry silkworms; according to the corresponding relationship between silkworm diseases and these characteristics, the types of silkworm diseases suffered by mulberry silkworms are further judged; this judgment result is used as the second silkworm disease parameter to corroborate with the first silkworm disease parameter and improve the accuracy of silkworm disease prediction.

[0111] Furthermore, based on the mapping relationship between the first silkworm disease parameter, the second silkworm disease parameter, and the silkworm disease types, predict the silkworm disease types of mulberry silkworms, determine the silkworm disease impact behaviors according to the traceability of the silkworm disease types of mulberry silkworms, and dynamically match the silkworm disease impact behaviors with the activity behaviors corresponding to the mulberry silkworm activity trajectories, so as to further review the silkworm disease types of mulberry silkworms, taking into account the overall traceability of the silkworm disease types of mulberry silkworms and ensuring the accuracy of the silkworm disease impact behaviors.

[0112] At this time, establish a mapping relationship database between silkworm disease types, the first silkworm disease parameter, and the second silkworm disease parameter. This database should include the characteristic descriptions of various known silkworm diseases, the corresponding silkworm disease parameters, and the silkworm disease types; after collecting the first silkworm disease parameter and the second silkworm disease parameter of mulberry silkworms, compare them with the mapping relationship in the database to predict the silkworm disease types suffered by mulberry silkworms; the prediction result is one or more silkworm disease types, depending on the similarity of the silkworm disease parameters and the accuracy of the database.

[0113] According to the predicted silkworm disease types, trace and determine the specific impacts of the silkworm diseases on the behaviors of mulberry silkworms, which include the abnormal behaviors of mulberry silkworms, changes in activity patterns, and behavioral differences from other healthy mulberry silkworms. These impact behaviors include decreased appetite, slow movement, weakened response to external stimuli, etc.

[0114] Using technical means such as video tracking and sensor monitoring, record the activity trajectories and corresponding activity behaviors of mulberry silkworms; dynamically match the recorded activity behaviors of mulberry silkworms with the predicted silkworm disease impact behaviors, which includes comparing the similarity between the actual behavior patterns of mulberry silkworms and the predicted abnormal behavior patterns; the purpose of dynamic matching is to verify whether the predicted silkworm disease types are accurate and whether the mulberry silkworms are indeed affected by the silkworm diseases.

[0115] If the dynamic matching result shows that the actual behavior of the mulberry silkworm is highly consistent with the predicted behavior affected by silkworm diseases, then it is confirmed that the predicted silkworm disease type is accurate; if the matching result is inconsistent or shows significant differences, then the predicted silkworm disease type needs to be rechecked, which includes re - collecting and analyzing silkworm disease parameters, consulting silkworm - raising experts or conducting more in - depth medical examinations; the purpose of the recheck is to ensure the accuracy of the silkworm disease type in order to formulate effective treatment and optimization measures.

[0116] Bringing together the world. Suppose that in step S151, it is predicted that a certain mulberry silkworm has malnutrition combined with nervous system damage (based on the first silkworm disease parameter and the second silkworm disease parameter); in step S152, first, according to the predicted silkworm disease type, the behaviors affected by the silkworm disease are determined, such as decreased appetite, slow movement, weakened response to external stimuli, etc.; then, using video tracking technology, the activity trajectory and corresponding activity behaviors of this mulberry silkworm are recorded; it is found that this mulberry silkworm indeed shows abnormal behaviors such as decreased appetite and slow movement, and these behaviors are highly consistent with the predicted behaviors affected by the silkworm disease. Therefore, it is confirmed that the predicted silkworm disease type is accurate, that is, this mulberry silkworm has malnutrition combined with nervous system damage, and this result provides an important basis for formulating effective treatment and optimization measures in the follow - up; however, if during the dynamic matching process, it is found that there are significant differences between the actual behavior of the mulberry silkworm and the predicted behavior affected by the silkworm disease (for example, the mulberry silkworm shows extreme activity instead of slowness), then the predicted silkworm disease type will be immediately rechecked to ensure accuracy and adjust the subsequent treatment and optimization measures.

[0117] Therefore, after the recheck of the silkworm disease type of the mulberry silkworm is completed, based on the silkworm disease type of the mulberry silkworm and the database of the silkworm - raising room, the optimization measures for the silkworm disease of the mulberry silkworm are determined. Multiple sub - optimization measures are formed according to the classification of the silkworm disease optimization measures, and the environmental control logic of the silkworm - raising room is determined according to the content of the multiple sub - optimization measures, the type of the mulberry silkworm, and the silkworm - raising environment of the mulberry silkworm, so as to trigger the environmental control event of the silkworm - raising room. Considering the overall situation of the content of the multiple sub - optimization measures, the type of the mulberry silkworm, and the silkworm - raising environment of the mulberry silkworm, it ensures the accuracy of the environmental control logic of the silkworm - raising room, realizes the accurate prediction of the silkworm disease type of the mulberry silkworm, triggers the environmental control logic of the silkworm - raising room, and timely optimizes the silkworm - raising environment of the mulberry silkworm in the silkworm - raising room.

[0118] At this time, after the recheck of the silkworm disease type of the mulberry silkworm is completed, according to the diagnosed silkworm disease type, consult the database of the silkworm - raising room or professional silkworm - raising guides to determine the optimization measures for this silkworm disease. These optimization measures include adjusting the feed formula, increasing or decreasing the intake of specific nutrients, improving the sanitary conditions of the silkworm - raising environment, adjusting the temperature and humidity of the silkworm - raising room, etc.; the goal of the optimization measures is to promote the health recovery of the mulberry silkworm, prevent the further deterioration of the silkworm disease, and improve the yield and quality of the silkworm cocoons.

[0119] The determined optimized measures for silkworm diseases are further broken down into multiple specific sub-optimized measures, which should be more operational and facilitate implementation and monitoring. For example, if the optimized measure is to adjust the feed formula, the sub-optimized measures include increasing the protein content, adding specific vitamins or minerals, etc. The division of sub-optimized measures helps to more precisely control various variables in the silkworm rearing process, thus more effectively treating silkworm diseases.

[0120] Based on the content of multiple sub-optimized measures, the types of mulberry silkworms (such as varieties, growth stages, etc.), and the actual situation of the silkworm rearing environment (such as current temperature and humidity, light conditions, etc.), determine the environmental control logic for the silkworm rearing room. The environmental control logic should clarify which environmental control events are triggered under what conditions to achieve the goals of the sub-optimized measures. For example, if the sub-optimized measure is to reduce the humidity in the silkworm rearing room to reduce the growth of pathogens, the environmental control logic is to automatically start the dehumidification equipment when the humidity exceeds a certain threshold.

[0121] According to the determined environmental control logic, use an automated control system or manual operation to trigger the corresponding environmental control events, which include adjusting environmental factors such as temperature and humidity, light intensity, ventilation rate, etc. to meet the requirements of the sub-optimized measures. After triggering the environmental control events, continuously monitor the reactions of the mulberry silkworms and the changes in the silkworm rearing environment to ensure the effectiveness of the optimized measures and make adjustments as needed.

[0122] Specifically, assume that in step S152, it is confirmed that a certain batch of mulberry silkworms has bacterial gastroenteritis; in step S153, first, according to the characteristics of bacterial gastroenteritis, search for the corresponding optimized measures from the silkworm rearing room database; it is determined that it is necessary to improve the hygienic quality of the feed, increase the antibacterial components of the feed, and strengthen the disinfection work in the silkworm rearing room; then, break down these optimized measures into multiple sub-optimized measures. For example, improving the hygienic quality of the feed includes using fresh and pollution-free mulberry leaves and adding an appropriate amount of antibacterial agents to the feed; strengthening the disinfection work includes thoroughly cleaning and disinfecting the silkworm rearing room regularly and using ultraviolet lamps to kill the pathogens in the air.

[0123] Then, based on the content of the sub-optimized measures and the growth environment of the mulberry silkworms, the environmental control logic for the silkworm rearing room is determined. For example, it is decided to strictly wash and disinfect the mulberry leaves before feeding every day, and install ultraviolet lamps in the silkworm rearing room to automatically turn on at night to kill the pathogens; finally, the corresponding environmental control events are triggered; manually adjust the disinfection equipment in the silkworm rearing room to ensure that it works at the predetermined time interval; at the same time, also adjust the feed formula and add an appropriate amount of antibacterial agents to improve the immunity of the mulberry silkworms; by implementing these optimized measures and environmental control events, the spread of bacterial gastroenteritis is successfully controlled, the healthy recovery of the mulberry silkworms is promoted, and ultimately the yield and quality of the cocoons are improved.

[0124] Please refer toFigure 7 , Figure 7 is a schematic structural composition diagram of a prediction system for silkworm diseases based on the silkworm rearing environment in an embodiment of the present invention; the prediction system for silkworm diseases based on the silkworm rearing environment includes: A silkworm rearing distribution map module 21 for real-time monitoring of the silkworm rearing room and collecting the silkworm rearing distribution map of the silkworm rearing room; A mulberry silkworm recognition module 22 for determining the activity trajectory of mulberry silkworms and the mulberry silkworm environment area based on the recognition of the silkworm rearing distribution map; An anomaly detection module 23 for determining the silkworm rearing environment of mulberry silkworms based on the environmental detection of the mulberry silkworm environment area, determining the abnormal area of the silkworm rearing room according to the silkworm rearing environment of mulberry silkworms and the activity trajectory of mulberry silkworms, and marking the abnormal images of mulberry silkworms; A morphological detection module 24 for determining the skin abnormality characteristics and posture abnormality characteristics of mulberry silkworms based on the abnormal images of mulberry silkworms, and determining the excrement morphology of mulberry silkworms along the detection of the activity trajectory of mulberry silkworms; A prediction module 25 for predicting the types of silkworm diseases based on the skin abnormality characteristics, posture abnormality characteristics of mulberry silkworms and the excrement morphology of mulberry silkworms, and triggering the environmental regulation logic of the silkworm rearing room according to the types of silkworm diseases of mulberry silkworms and the silkworm rearing environment of mulberry silkworms.

[0125] For any combination of the technical features of the above embodiments, for the sake of brevity of description, not all combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

Claims

1. A prediction method for silkworm diseases based on the silkworm rearing environment, characterized in that, Including: Real-time monitoring of the silkworm rearing room and collecting the silkworm rearing distribution map of the silkworm rearing room; Determining the silkworm activity trajectory and the silkworm environment area according to the recognition of the silkworm rearing distribution map; Determining the silkworm rearing environment based on the environmental detection of the silkworm environment area, determining the abnormal area of the silkworm rearing room according to the silkworm rearing environment and the silkworm activity trajectory, and marking the abnormal images of the silkworms; Determining the skin abnormality characteristics and posture abnormality characteristics of the silkworms according to the abnormal images of the silkworms, and determining the excrement form of the silkworms along the detection of the silkworm activity trajectory; Predicting the types of silkworm diseases based on the skin abnormality characteristics, posture abnormality characteristics and excrement form of the silkworms, and triggering the environmental regulation logic of the silkworm rearing room according to the types of silkworm diseases and the silkworm rearing environment of the silkworms.

2. The prediction method of silkworm diseases based on the silkworm rearing environment according to claim 1, wherein, The real-time monitoring of the silkworm rearing room and collecting the silkworm rearing distribution map of the silkworm rearing room includes: Collecting the location of the silkworm rearing room, triggering the response of the corresponding visual detection component according to the location of the silkworm rearing room. At this time, the visual detection component is transformed from the standby state to the visual detection state during the response process, and collecting the spatial positions of each visual detection component relative to the silkworm rearing room; Determining the real-time monitoring area of the silkworm rearing room according to the spatial positions of each visual detection component relative to the silkworm rearing room and the visual detection range of the visual detection component. At this time, the real-time monitoring area of the silkworm rearing room covers the silkworm activity trajectory and the surrounding environment of the silkworms; Each visual detection component moves circularly along the internal space of the silkworm rearing room to collect multiple internal images of the silkworm rearing room. At the same time, determining the internal distribution map of the silkworm rearing room based on the location of the silkworm rearing room and the database of the silkworm rearing room, and determining the silkworm rearing distribution map of the silkworm rearing room based on the synthesis of the internal distribution map of the silkworm rearing room and the multiple internal images.

3. The prediction method of silkworm diseases based on the silkworm rearing environment according to claim 1, wherein, The determining of the silkworm activity trajectory and the silkworm environment area according to the recognition of the silkworm rearing distribution map includes: Marking the current positions of multiple silkworms based on the detection of the silkworm rearing distribution map. At this time, each silkworm has a corresponding identity mark; determining multiple position nodes passed by each silkworm according to the current position of each silkworm and the image corresponding to each silkworm, and determining the corresponding silkworm activity trajectory according to the synthesis of the multiple position nodes passed by each silkworm; Determining the silkworm activity area according to the silkworm activity trajectory and the current position of each silkworm, and determining the remaining area according to the comparison between the silkworm activity area and the silkworm rearing distribution map; Determining the silkworm environment area based on the division of the remaining area. At this time, the silkworm environment area is on the periphery of the silkworm activity area and covers the silkworm activity area.

4. The prediction method of silkworm diseases based on the silkworm rearing environment according to claim 1, wherein The determining of the silkworm rearing environment based on the environmental detection of the silkworm environment area, determining the abnormal area of the silkworm rearing room according to the silkworm rearing environment and the silkworm activity trajectory, and marking the abnormal images of the silkworms includes: Collecting the silkworm environment area, determining multiple environmental detection nodes according to the silkworm environment area and the silkworm activity trajectory, determining the corresponding environmental parameters according to the environmental detection of the multiple environmental detection nodes, and determining the silkworm rearing environment of the silkworms according to the locations of the multiple environmental detection nodes, the corresponding environmental parameters and the regional form of the silkworm environment area; Collect the activity trajectories of silkworms, determine multiple silkworm activity nodes according to the division of the silkworm activity trajectories, and determine the corresponding silkworm activity events according to the tracing of the multiple silkworm activity nodes. The silkworm activity events cover the activity postures, rest postures and excretion actions of silkworms.

5. The prediction method of silkworm diseases based on the silkworm rearing environment according to claim 4, wherein Determine the silkworm rearing environment based on the environmental detection of the silkworm environment area, determine the abnormal area of the silkworm rearing room according to the silkworm rearing environment and the silkworm activity trajectories, and mark the abnormal images of silkworms. It also includes: Determine the first abnormal parameter according to the multiple silkworm activity events and the silkworm rearing environment, determine the second abnormal parameter according to the multiple silkworm activity events and the silkworm species, determine the abnormal area of the silkworm rearing room based on the mapping relationship of the first abnormal parameter, the second abnormal parameter and the abnormal area, and collect the abnormal images of silkworms based on the real-time monitoring of the abnormal area of the silkworm rearing room.

6. The prediction method of silkworm diseases based on the silkworm breeding environment according to claim 1, wherein, Determine the skin abnormal characteristics and posture abnormal characteristics of silkworms according to the abnormal images of silkworms, and determine the excrement form of silkworms along the detection of the silkworm activity trajectories, including: Collect the abnormal images of silkworms, determine the skin area and the action area of silkworms according to the division of the abnormal images of silkworms. At this time, the skin area and the action area of silkworms are in the same abnormal image. Determine multiple skin color characteristics according to the recognition of the skin area of silkworms, determine the abnormal color characteristics according to the matching of the multiple skin color characteristics and the database of the silkworm rearing room, and determine the skin abnormal characteristics of silkworms based on the position, form of the abnormal color characteristics and the silkworm species. Determine multiple posture characteristics according to the recognition of the action area of silkworms, and determine the posture abnormal characteristics according to the matching of the multiple posture characteristics and the database of the silkworm rearing room.

7. The prediction method of silkworm diseases based on the silkworm rearing environment according to claim 6, characterized in that Determine the skin abnormal characteristics and posture abnormal characteristics of silkworms according to the abnormal images of silkworms, and determine the excrement form of silkworms along the detection of the silkworm activity trajectories. It also includes: Collect the silkworm activity trajectories, and detect along the silkworm activity trajectories to collect the images of the excrement in the silkworm activity trajectories. Determine the excrement form of silkworms according to the recognition of the excrement images, and determine the abnormal feature combination based on the matching of the excrement form of silkworms, the posture abnormal characteristics and the skin abnormal characteristics, and perform autonomous update of the features in the abnormal feature combination.

8. The prediction method of silkworm diseases based on the silkworm rearing environment according to claim 1, characterized in that, Predict the silkworm disease types based on the skin abnormal characteristics, posture abnormal characteristics and excrement form of silkworms, and trigger the environmental regulation logic of the silkworm rearing room according to the silkworm disease types and the silkworm rearing environment of silkworms, including: Collect the skin abnormal characteristics, posture abnormal characteristics and excrement form of silkworms, determine the first silkworm disease parameter according to the excrement form of silkworms and the skin abnormal characteristics of silkworms, and determine the second silkworm disease parameter according to the excrement form of silkworms and the posture abnormal characteristics of silkworms. Predict the silkworm disease types based on the mapping relationship of the first silkworm disease parameter, the second silkworm disease parameter and the silkworm disease types, determine the silkworm disease impact behaviors according to the tracing of the silkworm disease types, and perform dynamic matching of the silkworm disease impact behaviors with the activity behaviors corresponding to the silkworm activity trajectories to further review the silkworm disease types of silkworms.

9. The prediction method of silkworm diseases based on the silkworm rearing environment according to claim 8, wherein, Predict the types of silkworm diseases based on the abnormal skin characteristics, abnormal posture characteristics of silkworms, and the excrement morphology of silkworms, and trigger the environmental control logic of the silkworm rearing room according to the types of silkworm diseases and the silkworm rearing environment of silkworms. It further includes: After the review of the types of silkworm diseases is completed, determine the optimized measures for silkworm diseases based on the types of silkworm diseases and the database of the silkworm rearing room. Form multiple sub-optimized measures according to the classification of the optimized measures for silkworm diseases, and determine the environmental control logic of the silkworm rearing room based on the content of the multiple sub-optimized measures, the types of silkworms, and the silkworm rearing environment of silkworms, so as to trigger the environmental control event of the silkworm rearing room.

10. A prediction system for silkworm diseases based on the silkworm rearing environment, characterized in that, The prediction system for silkworm diseases based on the silkworm rearing environment is applied to the prediction method for silkworm diseases based on the silkworm rearing environment as described in any one of claims 1-9. The prediction system for silkworm diseases based on the silkworm rearing environment includes: A silkworm rearing distribution map module for real-time monitoring of the silkworm rearing room and collecting the silkworm rearing distribution map of the silkworm rearing room; A silkworm identification module for determining the silkworm activity trajectory and the silkworm environment area based on the identification of the silkworm rearing distribution map; An abnormality detection module for determining the silkworm rearing environment of silkworms based on the environmental detection of the silkworm environment area, determining the abnormal area of the silkworm rearing room according to the silkworm rearing environment and the silkworm activity trajectory of silkworms, and marking the abnormal images of silkworms; A morphology detection module for determining the abnormal skin characteristics and abnormal posture characteristics of silkworms based on the abnormal images of silkworms, and determining the excrement morphology of silkworms based on the detection along the silkworm activity trajectory; A prediction module for predicting the types of silkworm diseases based on the abnormal skin characteristics, abnormal posture characteristics of silkworms, and the excrement morphology of silkworms, and triggering the environmental control logic of the silkworm rearing room according to the types of silkworm diseases and the silkworm rearing environment of silkworms.

Images