Automatic grading and grouping system and method for boars

Abstract

The invention relates to the technical field of breeding, in particular to an automatic grading and grouping system and method for boars, and the system comprises a data collection module, a data processing and analysis module, an automatic execution module, a system management and monitoring module, and a system integration and interface module. Compared with the defects of time and labor consumption, large error and difficulty in real-time updating due to the fact that the equipment is installed and positioned by depending on manual measurement and marking in the prior art, the scheme comprises the following steps: firstly, connecting and numbering the equipment and a plurality of routers, recording the equipment Mac address and the signal intensity by utilizing the routers, converting the Mac address and the signal intensity into distance information through a signal propagation model, according to the scheme, the positioning precision and efficiency are greatly improved, the rapid and automatic determination of the equipment installation position is realized, the real-time updating capability is realized, the labor cost is effectively reduced, and the flexibility and accuracy of the deployment of the data acquisition module are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of breeding, in particular to a system and method for automatic classification and grouping of boars. BACKGROUND

[0002] In traditional boar breeding management, equipment installation and positioning often rely on manual measurement and marking. This method not only consumes time and effort, but is also easily affected by human factors, resulting in large positioning errors. In addition, since the breeding environment may change at any time (such as equipment moving, adding new equipment, etc.), the traditional method is difficult to update the equipment position information in time, which brings inconvenience to subsequent data collection and analysis.

[0003] In terms of data collection, the traditional method usually relies on manual recording or simple sensor equipment, which often lacks comprehensiveness and accuracy, and is difficult to update in real time. This makes it difficult for breeding management personnel to accurately understand the growth status, health status and behavior patterns of boars, thereby affecting the scientificity and accuracy of breeding decisions.

[0004] In terms of classification and grouping management, the traditional method also has the problems of strong subjectivity and low efficiency. Breeding management personnel often classify and group boars based on personal experience, which not only makes it difficult to ensure the accuracy and consistency of the results, but also may lead to uneven resource allocation and low breeding efficiency.

[0005] Therefore, in view of the problems existing in traditional boar breeding management, the industry has begun to explore new technical solutions to realize the automation and intelligent management of boar breeding. Among them, a system and method for automatic classification and grouping of boars has emerged. The system integrates advanced Internet of Things technology, big data technology and artificial intelligence technology to realize fast and automatic positioning of equipment installation, as well as real-time collection, processing and analysis of data. At the same time, the system can also accurately classify and group boars according to their growth status, health status and behavior patterns, providing more scientific and accurate decision support for breeding management personnel.

[0006] In summary, the background technology of the present application is mainly derived from the problems existing in traditional boar breeding management, such as inaccurate equipment installation and positioning, incomplete data collection, and strong subjectivity in classification and grouping management. In order to solve these problems, the industry has begun to explore new technical solutions to realize the intelligent and fine management of boar breeding. SUMMARY

[0007] In order to overcome the problems raised in the background technology, the present application proposes a system and method for automatic classification and grouping of boars.

[0008] The technical solution of the present application is: a system for automatic classification and grouping of boars, comprising: The data acquisition module is used for collecting the growth data of the boars in real time by using various sensors deployed. The data processing and analysis module is used for processing and analyzing the raw data collected by the data acquisition module, so as to realize the classification and grouping of the boars. The automatic execution module is used for automatically managing the boars by using automatic equipment according to the data results of the data processing and analysis module. The system management and monitoring module is used for realizing the user permission management, real-time monitoring, real-time alarm and data visualization of the system. The system integration and interface module is used for supporting the integration of the system and other management systems of the pig farm, so as to realize the data sharing and business process collaboration.

[0009] As a preferred, the data acquisition module includes a temperature sensor, a humidity sensor, an illumination sensor, a gas sensor, a weight sensor, a body temperature sensor, a high-definition camera, a data collector and a router, wherein the temperature sensor is used for monitoring the temperature parameter in the pig house, the humidity sensor is used for monitoring the humidity parameter in the pig house, the illumination sensor is used for monitoring the illumination parameter in the pig house, the gas sensor is used for monitoring the gas parameter in the pig house, the weight sensor is used for measuring the weight of the boar, the body temperature sensor is used for measuring the body temperature of the boar, the high-definition camera is used for collecting the image data in the pig house, the data collector is used for receiving the data of each sensor, and the router is used for constructing a data transmission network to realize the wireless transmission of data.

[0010] As a preferred, when installing the data acquisition module, the following steps are included: S11: pig house map import, drawing a plane map of the pig house and inputting corresponding parameters to form a 3D model map of the pig house, wherein the plane map of the pig house is completed by one of manual drawing and software import; S12: router installation and positioning, installing multiple routers inside the pig house and marking the positions of the routers in the 3D model map of the pig house; S13: high-definition camera installation and positioning, installing multiple high-definition cameras inside the pig house, connecting the high-definition cameras with the routers, positioning the high-definition cameras through the routers, and finally confirming and modifying the positions of the high-definition cameras in the 3D model map; S14: installation of the remaining devices, installing the remaining devices, connecting the installed devices with the routers, positioning the installed devices through the routers, and finally correcting and confirming the positions of the devices through the data collected by the high-definition cameras.

[0011] As a preferred, when positioning the installed devices through the routers, the following steps are included: S21: First, connect the installed devices with multiple routers, and number the installed devices, wherein each number corresponds to a device, and the type and function information of the device is attached; S22: Record the Mac address of the device and the corresponding signal strength using the router; S23: Convert the signal strength to the distance between the device and the router through the signal propagation model; S24: Estimate the position of the device through the multilateration algorithm to realize the positioning of the device, wherein the principle equation of the multilateration algorithm is: ; ; ……; ; wherein, is the coordinate of the nth router in the 3D model map of the pig house, is the distance between the nth router and the installed device, is the coordinate of the installed device in the 3D model map of the pig house.

[0012] As a preferred, when the position of the device is corrected and confirmed by the data collected by the high-definition camera, the following steps are included: S31: Obtain image information of the device through the high-definition camera, and pre-process the collected image, wherein the pre-processing method includes denoising, enhancement and filtering; S32: Extract feature information of the device using edge detection algorithm, and classify and identify the extracted feature information using machine learning model to identify the device; S33: Determine the specific number of the device in combination with the fuzzy positioning of the router to the installed device; S34: Calculate the specific position of the device in combination with the background image of the position of the device, the parameters of the buildings in the 3D model map of the pig house, and the internal and external parameters and distortion parameters of the camera.

[0013] As a preferred, when the specific position of the device is calculated in combination with the background image of the position of the device, the parameters of the buildings in the 3D model map of the pig house, and the internal and external parameters and distortion parameters of the camera, the principle is: select the center point of the device in the image as the coordinate point of the device, obtain a plurality of sets of building images closest to the device, calculate the distance between the device and the plurality of sets of buildings according to the image scaling ratio of the camera through the parameters of the buildings in the 3D model of the pig house, and accurately position the position of the device through the multilateration method.

[0014] As preferred, the data processing and analysis module, when processing and analyzing the raw data collected by the data collection module to realize the classification and grouping of the boars, comprises the following steps: S41: data processing, first, the received data is cleaned, and the abnormal values, missing values and repeated values in the data are checked and processed, then the data is standardized, and finally the data is merged to form a complete data set; S42: data analysis, first, the key features are extracted from the data set using feature extraction technology, and the key features are analyzed using clustering algorithm to obtain the growth characteristics, health status indicators and behavior pattern characteristics of the boars; S43: classification and grouping, according to the set classification and grouping rules, according to the data analysis results, each boar is assigned a corresponding level and group, and the classification and grouping results are output to the user in the form of tables and charts.

[0015] As preferred, when each boar is assigned a corresponding level and group according to the set classification and grouping rules according to the data analysis results, the classification and grouping rules are set by the following steps: S51: boar information acquisition, the specific type, growth stage and historical health record of the boar are acquired; S52: setting classification and grouping rules, according to the acquired boar information, setting classification and grouping rules; S53: classification and grouping rule adjustment, according to the current average state of the boar, the classification and grouping rules are adjusted.

[0016] As preferred, the automatic execution module comprises: A11: intelligent feeding system, for automatically adjusting the feeding amount according to the classification results of the boars, to ensure that boars of different growth stages, health states and body types obtain appropriate nutrient intake; A12: automatic separation fence, for separating boars into different feeding areas according to the grouping results; A13: environmental monitoring equipment, for real-time monitoring of environmental parameters in the pig farm to provide decision basis for the automatic execution module; A14: intelligent cleaning equipment, for cleaning the boar feeding area according to the set period, wherein the set period includes fixed period and period set according to demand; A15: health monitoring equipment, for real-time monitoring of the health status of the boar, and timely sending alarm information when the boar has abnormal conditions.

[0017] A method for automatic classification and grouping of boars, comprising the following steps: S61: System initialization and configuration, first import pig house map, draw and input parameters to form 3D model map, on the basis of 3D model map, install and automatically position the equipment; S62: Data acquisition and processing, real-time acquisition of growth data, health status and behavior pattern of boars by using deployed sensors, and preprocessing of collected data; S63: Data analysis, feature extraction of collected data, analysis of extracted features, adjustment of classification and grouping rules according to extracted features, and finally classification and grouping according to adjusted classification and grouping rules; S64: Automatic execution and management, automatic classification and grouping management according to classification and grouping rules.

[0018] The beneficial effects of the present application are: 1. Compared with the prior art which relies on manual measurement and marking for equipment installation and positioning, the present application has the disadvantages of time-consuming, labor-intensive, large error and difficulty in real-time updating. The present application connects and numbers the equipment with multiple routers first, records the equipment Mac address and signal strength by using the router, converts the distance information by using the signal propagation model, and accurately estimates the equipment position by using the multi-point positioning algorithm (combined with the known coordinates of the router in the pig house 3D model map and the distance of the equipment to each router). The present application not only greatly improves the positioning accuracy and efficiency, realizes the rapid and automatic determination of the equipment installation position, but also has real-time updating capability, effectively reduces the labor cost, and improves the flexibility and accuracy of the data acquisition module deployment; 2. Compared with the prior art which only relies on single visual information or physical measurement for equipment positioning, the present application has the disadvantages of being easily affected by environmental interference and limited positioning accuracy. The present application innovatively combines the background image of the equipment location, the building parameters in the pig house 3D model, and the camera internal and external parameters and distortion parameters, selects the center point of the equipment in the image as the coordinate point, calculates the relative distance between the equipment and the surrounding buildings by using the pig house 3D model and camera parameters, and then realizes the accurate positioning of the equipment by using the multi-point positioning method. The present application not only significantly enhances the robustness and environmental adaptability of the positioning system, effectively reduces the influence of environmental factors on the positioning accuracy, but also realizes the high-precision and automatic calculation of the equipment position, and provides strong technical support for the intelligent monitoring and management of boar breeding environment; 3. Compared to existing technologies that rely solely on experience or fixed standards for grading and grouping boars, which lack flexibility and personalization and may lead to inaccurate grading and unreasonable grouping, this solution first obtains detailed information such as the boar's specific breed, growth stage, and historical health records. Based on this, grading and grouping rules are scientifically set, and these rules are flexibly adjusted according to the boar's current average condition. This solution not only improves the accuracy and scientific nature of grading and grouping, ensuring the targeted and effective management of grouping, but also enhances the system's flexibility and adaptability. It can better meet the actual management needs of boars of different breeds and growth stages, providing strong support for the refined management of boar farming. Attached Figure Description

[0019] Figure 1 The diagram shown is a structural schematic of the automated grading and grouping system for boars according to the present invention. Figure 2 The diagram shown is a flowchart of the method for automated grading and grouping of boars according to the present invention. Detailed Implementation

[0020] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0021] Please see Figure 1 The present invention provides an embodiment: an automated grading and grouping system for boars, comprising: The data acquisition module utilizes multiple deployed sensors to collect real-time growth data, health status, and behavioral patterns of boars. The data processing and analysis module is used to process and analyze the raw data collected by the data acquisition module to achieve the grading and grouping of boars; The automated execution module is used to automatically manage boars using automated equipment based on the data results from the data processing and analysis module. The system management and monitoring module is used to implement user permission management, real-time monitoring, real-time alarms, and data visualization of the system. The system integration and interface module is used to support the integration of the system with other management systems in pig farms, enabling data sharing and business process collaboration.

[0022] As described above, the data collection module utilizes the deployed weight sensors, temperature sensors, and activity monitoring sensors to collect real-time growth data and health status, behavioral pattern information of boars at an interval of every minute, such as body weight, body temperature, and activity state; the data processing and analysis module cleans, integrates, and analyzes these raw data based on machine learning algorithms, and automatically classifies boars into different grades and groups according to parameters such as body weight, health status, and behavioral characteristics; the automatic execution module performs precise feeding management and grouping isolation of boars through automatic feeding and separation equipment according to the analysis results; the system management and monitoring module provides multi-user permission management functions, supports real-time monitoring of boar state, triggers alarms in abnormal situations, and simultaneously displays key indicators through a data visualization interface; the system integration and interface module adopts a standard API interface to ensure that the system can seamlessly integrate with the ERP, CRM, and other management systems of pig farms, realize unified management of breeding data and efficient collaboration of business processes, and thus improve the overall operational efficiency of pig farms.

[0023] As a preferred, the data collection module includes temperature sensors, humidity sensors, light sensors, gas sensors, weight sensors, body temperature sensors, high-definition cameras, data collectors, and routers, wherein the temperature sensors are used to monitor the temperature parameters in the pig house, the humidity sensors are used to monitor the humidity parameters in the pig house, the light sensors are used to monitor the light parameters in the pig house, the gas sensors are used to monitor the gas parameters in the pig house, the weight sensors are used to measure the body weight of boars, the body temperature sensors are used to measure the body temperature of boars, the high-definition cameras are used to collect image data in the pig house, the data collectors are used to receive data from various sensors, and the routers are used to build a data transmission network to realize wireless data transmission.

[0024] Specifically, the data acquisition module integrates a high-precision temperature sensor (accuracy ±0.5°C) to monitor the temperature in the pig house in real time, ranging from -5°C to 40°C; a humidity sensor (accuracy ±3%RH) to monitor the humidity in the pig house, maintaining it in the appropriate range of 30%RH to 80%RH; a light sensor to detect the light intensity and maintain it at 50 to 500 lux to optimize the boar's activity environment; a gas sensor (including ammonia and carbon dioxide sensors, both with an accuracy of ±5%) to ensure that the concentration of harmful gases in the pig house does not exceed the safety threshold; a weight sensor (accuracy ±0.1kg) to accurately measure the boar's body weight, ranging from 50kg to 300kg; a body temperature sensor (accuracy ±0.2°C) to non-contact measure the boar's body temperature, ranging from 37°C to 40°C; a high-definition camera (resolution 1920x1080p, frame rate 30fps) to capture dynamic images in the pig house all day long; a data collector to aggregate all sensor data and build a stable data transmission network through a high-speed router (supporting Wi-Fi 6 standard, transmission rate up to 9.6Gbps), realizing real-time and wireless transmission of all monitoring data to the central processing system, providing accurate data support for the health management of boars and the optimization of breeding environment.

[0025] As preferred, when installing the data acquisition module, the following steps are included: S11: Pig house map import, draw the plan map of the pig house and input the corresponding parameters to form the 3D model map of the pig house, wherein the plan map of the pig house is completed by one of manual drawing and software import; S12: Router installation and positioning, install multiple routers inside the pig house and mark the positions of the routers in the 3D model map of the pig house; S13: High-definition camera installation and positioning, install multiple high-definition cameras inside the pig house, connect the high-definition cameras with the routers, position the high-definition cameras through the routers, and finally confirm and modify the positions of the high-definition cameras in the 3D model map; S14: Installation of the remaining devices, install the remaining devices, connect the installed devices with the routers, position the installed devices through the routers, and finally correct and confirm the positions of the devices through the data collected by the high-definition cameras.

[0026] As described above, compared to existing technologies that rely on manual measurement and marking for data acquisition module installation, which suffers from low installation efficiency, inaccurate location positioning, and cumbersome rectification, this solution employs an automated installation and positioning approach. This involves first creating a 3D model of the pigsty, then sequentially installing and positioning the router, high-definition camera, and other equipment. The router enables wireless connection and positioning of the devices, and finally, data collected by the high-definition camera is used to precisely correct and confirm the device positions. This solution significantly improves installation efficiency and accuracy, effectively eliminating the tedious installation and rectification steps of traditional methods, and enabling rapid and accurate deployment of the data acquisition module.

[0027] Preferably, when locating the installed device through a router, the following steps are included: S21: First, connect the installed device to multiple routers and number the installed devices, with each number corresponding to a device, and attach the device type and function information; S22: Use the router to record the device's MAC address and corresponding signal strength; S23: Using a signal propagation model, the signal strength is converted into the distance between the device and the router; S24: The location of the device is estimated through a multi-point positioning algorithm, thereby achieving device localization. The principle equation of the multi-point positioning algorithm is as follows: ; ; ...; ; in, Let be the coordinates of the nth router in the 3D model of the pigsty. Let n be the distance between the nth router and the installed device. The coordinates of the installed equipment in the 3D model of the pigsty.

[0028] As described above, compared to existing technologies that rely on manual measurement and marking for equipment installation and positioning, which are time-consuming, labor-intensive, prone to errors, and difficult to update in real time, this solution first connects and numbers the equipment to multiple routers. The routers record the equipment's MAC address and signal strength, which is then converted into distance information using a signal propagation model. A multi-point positioning algorithm (combining the known coordinates of the routers in the 3D model of the pigsty with the distances from the equipment to each router) is then applied to accurately estimate the equipment's location. This solution not only significantly improves positioning accuracy and efficiency, enabling rapid and automated determination of equipment installation locations, but also provides real-time update capabilities, effectively reducing labor costs and enhancing the flexibility and accuracy of data acquisition module deployment.

[0029] As preferred, when the position of the device is corrected and confirmed by the data collected by the high-definition camera, the following steps are included: S31: Obtain image information of the device through the high-definition camera, and pre-process the collected image, wherein the pre-processing method includes denoising, enhancement and filtering; S32: Extract feature information of the device using an edge detection algorithm, and classify and identify the extracted feature information using a machine learning model to identify the device; S33: Combine the fuzzy positioning of the installed device by the router to determine the specific number of the device; S34: Combine the background image of the device location, the parameters of the buildings in the 3D model diagram of the pig house, and the internal and external parameters and distortion parameters of the camera to calculate the specific position of the device.

[0030] As described above, compared with the prior art which relies on manual visual inspection and manual adjustment to correct the device position, there are disadvantages of low efficiency, easy to be affected by subjective factors and limited accuracy. The present scheme uses a high-definition camera to collect images, improves image quality through preprocessing (denoising, enhancement, filtering), accurately identifies the device and determines its number using edge detection and machine learning model, and then combines the fuzzy positioning of the router with the internal and external parameters of the camera, the distortion parameters and the 3D model diagram of the pig house to calculate the accurate position of the device. This scheme not only significantly improves the automation and accuracy of device position correction, reduces human intervention, but also greatly improves work efficiency and positioning accuracy, laying a solid foundation for intelligent management of boar breeding environment.

[0031] As preferred, when the position of the device is corrected and confirmed by the data collected by the high-definition camera, the following steps are included:

[0032] As described above, compared with the prior art which only relies on single visual information or physical measurement for device positioning, there are disadvantages of being susceptible to environmental interference and limited positioning accuracy. The present scheme innovatively combines the background image of the device location, the building parameters in the pig house 3D model, and the internal and external parameters and distortion parameters of the camera. The center point of the device in the image is selected as the coordinate point, and the relative distance between the device and the surrounding buildings is calculated using the pig house 3D model and camera parameters. Then, the multi-point positioning method is used to realize the accurate positioning of the device. This scheme not only significantly enhances the robustness and environmental adaptability of the positioning system, effectively reduces the influence of environmental factors on the positioning accuracy, but also realizes high-precision and automated calculation of the device location, providing strong technical support for intelligent monitoring and management of the boar breeding environment.

[0033] As a preferred, when the data processing and analysis module processes and analyzes the original data collected by the data collection module to realize the classification and grouping of the boars, the following steps are included: S41: data processing, first, the received data is cleaned to check and process the abnormal values, missing values and repeated values in the data, then the data is standardized, and finally the data is merged to form a complete data set; S42: data analysis, first, the key features are extracted from the data set using feature extraction technology, and the key features are analyzed using clustering algorithm to obtain the growth characteristics, health status indicators and behavior pattern characteristics of the boars; S43: classification and grouping, according to the set classification and grouping rules, according to the data analysis results, each boar is assigned a corresponding grade and group, and the classification and grouping results are output to the user in the form of tables and charts.

[0034] As described above, in the embodiment of the data processing and analysis module, the system first performs in-depth processing on the raw data received from the data acquisition module: through the data cleaning step, remove or correct outliers in the data set (such as body temperature data exceeding the normal physiological range, set to NaN and later fill in), missing values (use mean interpolation method to handle) and repeated values (directly delete), to ensure data quality; then, perform standardization processing, convert various data (such as weight, body temperature, activity frequency) to a unified scale, to facilitate subsequent analysis; then, merge various data to form a complete data set, in the data analysis stage, the system uses feature extraction technology to identify and extract key features (such as weight gain rate, body temperature fluctuation range, active period proportion), and applies K-means clustering algorithm to group analysis of these features, to reveal the growth characteristics (such as rapid growth period, stable growth period) of boars, health status indicators (such as healthy, sub-healthy) and behavior pattern characteristics (such as active type, quiet type), finally, according to the pre-set grading and grouping rules (such as weight ≥ 200 kg and body temperature stable at 38.5°C ± 0.5°C as A level, activity frequency ≤ 5 times / hour as low active group), the system automatically assigns each boar a level (A, B, C, etc.) and group (high active group, low active group, etc.), and displays the grading and grouping results to the user in the form of intuitive tables and charts, to facilitate quick decision-making and management.

[0035] As a preferred, when assigning each boar a corresponding level and group according to the data analysis results according to the set grading and grouping rules, the grading and grouping rules are set by the following steps: S51: boar information acquisition, acquiring the specific species, growth stage and historical health record of the boar; S52: setting grading and grouping rules, setting grading and grouping rules according to the acquired boar information; S53: grading and grouping rule adjustment, adjusting the grading and grouping rules according to the current average state of the boar.

[0036] As described above, compared with the prior art which only grades and groups boars according to experience or fixed standards, lacking flexibility and individualization, which may lead to the shortcomings of inaccurate grading and unreasonable grouping, the present scheme acquires detailed information such as the specific species, growth stage and historical health record of the boar, sets grading and grouping rules scientifically accordingly, and flexibly adjusts these rules according to the current average state of the boar, which not only improves the accuracy and scientificity of grading and grouping, ensures the pertinence and effectiveness of grouping management, but also enhances the flexibility and adaptability of the system, better meets the actual management needs of boars of different species and different growth stages, and provides strong support for the fine management of boar breeding.

[0037] As a preferred, the automatic execution module comprises: A11: an intelligent feeding system for automatically adjusting the feeding amount according to the grading results of the boars, to ensure that boars in different growth stages, health states and body types obtain appropriate nutritional intake; A12: an automatic separation fence for separating boars into different feeding areas according to the grouping results; A13: an environmental monitoring device for monitoring environmental parameters in the pig farm in real time to provide decision basis for the automatic execution module; A14: an intelligent cleaning device for cleaning the boar feeding area according to a set period, wherein the set period includes a fixed period and a period set according to demand; A15: a health monitoring device for monitoring the health status of the boars in real time and timely sending an alarm information when the boars have abnormal conditions.

[0038] As described above, the intelligent feeding system (A11) automatically adjusts the feeding amount according to the grading (such as A, B, C) of the boars, to ensure that boars in different stages obtain precise nutritional ratio, such as A-level boars with a daily feeding amount of 4 kg, B-level boars with a daily feeding amount of 3.5 kg, and C-level boars with a daily feeding amount of 3 kg. The automatic separation fence (A12) quickly separates boars into different feeding areas according to the grouping results, such as high and low active groups being managed separately. The environmental monitoring device (A13) continuously monitors the temperature, humidity, ammonia concentration and the like in the pig house, to ensure that the environment is suitable (such as temperature maintained at 18-22°C, humidity 50%-70%, ammonia concentration ≤10 ppm). The intelligent cleaning device (A14) automatically performs cleaning tasks according to a fixed period (such as once a day) and a demand period (such as when the feces accumulation reaches a threshold). The health monitoring device (A15) monitors the physical signs of the boars for 24 hours, and triggers an alarm and notifies the management personnel for timely treatment once an abnormality (such as body temperature ≥40°C) is found. The coordinated work of these intelligent devices significantly improves the automation level and breeding efficiency of boar breeding.

[0039] Please refer to Figure 2 , the present application provides an embodiment: a method for automatic grading and grouping of boars, comprising the following steps: S61: system initialization and configuration, first import pig house map, draw and input parameters to form 3D model diagram, on the basis of 3D model diagram, install and automatically position the equipment; S62: data acquisition and processing, use the deployed sensors to collect the growth data, health status and behavior patterns of the boars in real time, and pre-process the collected data; S63: data analysis, feature extraction is performed on the collected data, the extracted features are analyzed, the grading and grouping rules are adjusted according to the extracted features, and finally grading and grouping are performed according to the adjusted grading and grouping rules; S64: Automatic execution and management, according to the hierarchical and grouping rules, automatic hierarchical and grouping management is carried out.

[0040] As described above, compared with the traditional boar grading and grouping method relying on manual observation and manual operation, there are disadvantages of low efficiency, strong subjectivity and difficulty in ensuring accuracy, the technical scheme adopts system initialization and configuration to form a 3D model map auxiliary equipment installation positioning, through data acquisition and processing to obtain comprehensive information of the boar in real time, and through data analysis to accurately extract features and dynamically adjust the grading and grouping rules, and finally realize automatic grading and grouping management. The scheme significantly improves the efficiency and accuracy of grading and grouping, reduces human intervention, and provides strong support for intelligent and fine management of boar breeding.

[0041] The embodiments of the application are described in detail above in combination with the drawings, but the application is not limited to the above-mentioned embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the purpose of the application.

Claims

1. A system for automated classification and grouping of boars; characterized by: The system comprises: a data acquisition module for collecting growth data of boars in real time using various sensors deployed, health status and behavior patterns; a data processing and analysis module for processing and analyzing the raw data collected by the data acquisition module to achieve classification and grouping of boars; an automatic execution module for automatically managing boars using automated equipment based on the data results of the data processing and analysis module; a system management and monitoring module for implementing user permission management, real-time monitoring, real-time alarm, and data visualization of the system; a system integration and interface module for supporting integration of the system with other management systems of the pig farm to achieve data sharing and business process collaboration.

2. A system for automated classification and grouping of boars as claimed in claim 1, wherein: According to the acquisition module, it comprises temperature sensor, humidity sensor, light sensor, gas sensor, weight sensor, body temperature sensor, high-definition camera, data collector and router, wherein the temperature sensor is used to monitor the temperature parameter in the pig house, the humidity sensor is used to monitor the humidity parameter in the pig house, the light sensor is used to monitor the light parameter in the pig house, the gas sensor is used to monitor the gas parameter in the pig house, the weight sensor is used to measure the weight of the boar, the body temperature sensor is used to measure the body temperature of the boar, the high-definition camera is used to collect image data in the pig house, the data collector is used to receive data from each sensor, and the router is used to build a data transmission network to realize wireless data transmission.

3. A system for automated classification and grouping of boars as claimed in claim 2, wherein: When installing the data acquisition module, the following steps are included: S11: pig house map import, draw the plane map of the pig house and input the corresponding parameters to form the 3D model map of the pig house, wherein the plane map of the pig house is completed by one of manual drawing and software import; S12: router installation and positioning, install multiple routers inside the pig house and mark the positions of the routers in the 3D model map of the pig house; S13: high-definition camera installation and positioning, install multiple high-definition cameras inside the pig house, connect the high-definition cameras with the routers, position the high-definition cameras through the routers, and finally confirm and modify the positions of the high-definition cameras in the 3D model map; S14: installation of the remaining devices, install the remaining devices, connect the installed devices with the routers, position the installed devices through the routers, and finally correct and confirm the positions of the devices through the data collected by the high-definition cameras.

4. A system for automated classification and grouping of boars as recited in claim 3, wherein: When positioning the installed devices through the router, the following steps are included: S21: first, connect the installed devices with multiple routers and number the installed devices, wherein each number corresponds to a device and additional device type and function information is attached; S22: use the router to record the Mac address of the device and the corresponding signal strength; S23: convert the signal strength to the distance between the device and the router through the signal propagation model; S24: estimate the position of the device through the multi-point positioning algorithm to realize the positioning of the device, wherein the principle equation of the multi-point positioning algorithm is: ； ； ……； ； wherein, is the coordinate of the n-th router in the 3D model map of the pig house, is the distance between the n-th router and the installed device, is the coordinate of the installed device in the 3D model map of the pig house.

5. A system for automated classification and grouping of boars as recited in claim 4, wherein: When the position of the device is corrected and confirmed by the data collected by the high-definition camera, the following steps are included: S31: Obtain image information of the device through the high-definition camera, and pre-process the collected image, wherein the pre-processing method includes denoising, enhancement and filtering; S32: Extract feature information of the device using edge detection algorithm, and classify and identify the extracted feature information using machine learning model to identify the device; S33: Combine the fuzzy positioning of the installed device by the router to determine the specific number of the device; S34: Combine the background image of the location of the device, the parameters of the buildings in the 3D model of the pig house, and the internal and external parameters and distortion parameters of the camera to calculate the specific position of the device.

6. A system for automated classification and grouping of boars as recited in claim 5, wherein: When the specific position of the device is calculated by combining the background image of the location of the device, the parameters of the buildings in the 3D model of the pig house, and the internal and external parameters and distortion parameters of the camera, the principle is: selecting the center point of the device in the image as the coordinate point of the device, obtaining several groups of building images closest to the device, calculating the distance between the device and several groups of buildings according to the image scaling ratio of the camera through the parameters of the buildings in the 3D model of the pig house, and accurately positioning the position of the device by multi-point positioning method.

7. A system for automated classification and grouping of boars as recited in claim 6, wherein: When the data processing and analysis module processes and analyzes the original data collected by the data collection module to realize the classification and grouping of boars, the following steps are included: S41: Data processing, first, data cleaning is performed on the received data, and abnormal values, missing values and repeated values in the data are checked and processed, then the data is standardized, and finally the data is merged to form a complete data set; S42: Data analysis, first, key features are extracted from the data set using feature extraction technology, and boar growth characteristics, health status indicators and behavior pattern characteristics are obtained by analyzing the key features using clustering algorithm; S43: Classification and grouping, according to the set classification and grouping rules, according to the data analysis results, each boar is assigned a corresponding level and group, and the classification and grouping results are output to the user in the form of tables and charts.

8. A system for automated classification and grouping of boars as recited in claim 7, wherein: When each boar is assigned a corresponding level and group according to the set classification and grouping rules according to the data analysis results, the classification and grouping rules are set by the following steps: S51: Boar information acquisition, the specific type, growth stage and historical health record of the boar are obtained; S52: Set classification and grouping rules, set the classification and grouping rules according to the obtained boar information; S53: Adjust the classification and grouping rules, adjust the classification and grouping rules according to the current average state of the boar.

9. A system for automated classification and grouping of boars as recited in claim 8, wherein: The automatic execution module includes: A11: Intelligent feeding system, for automatically adjusting the feeding amount according to the classification results of the boar to ensure that boars of different growth stages, health states and body types obtain appropriate nutrient intake; A12: Automatic partition fence, for separating boars into different feeding areas according to the grouping results; A13: Environmental monitoring equipment, for monitoring the environmental parameters in the pig farm in real time to provide decision basis for the automatic execution module; A14: A smart cleaning device for cleaning the boar feeding area according to a set period, wherein the set period includes a fixed period and a period set according to demand; A15: A health monitoring device for monitoring the health status of the boar in real time, and timely sending an alarm information when the boar has an abnormal condition.

10. A method for automated classification and grouping of boars, characterized in that: Comprising the following steps: S61: System initialization and configuration, first import the pig house map, draw and input parameters to form a 3D model diagram, on the basis of the 3D model diagram, install and automatically position the equipment; S62: Data acquisition and processing, using the deployed sensor to collect the growth data, health status and behavior pattern of the boar in real time, and pre-process the collected data; S63: Data analysis, feature extraction is performed on the collected data, and the extracted features are analyzed, then the classification and grouping rules are adjusted according to the extracted features, and finally classification and grouping are performed according to the adjusted classification and grouping rules; S64: Automatic execution and management, automatic classification and grouping management is performed according to the classification and grouping rules.

Images