Intelligent pig farming method, system and readable storage medium

Abstract

The present invention discloses an intelligent pig farming method, system and readable storage medium, the method comprising: obtaining pig growth sample data from different regions, wherein the pig growth sample data from each region includes emotion sample data, exercise sample data, food ratio sample data, weight sample data and body fat distribution sample data of pigs at different growth stages; training an initial model with the pig growth sample data from each region to obtain a pig growth model; collecting the breeding growth data of the farmed pigs, and searching for a target growth model in the pig growth model based on the breeding site of the farmed pigs; transmitting the breeding growth data to the target growth model for data analysis, obtaining analysis results, and monitoring the breeding status of the farmed pigs based on the analysis results. The present invention monitors the factors affecting the meat taste of pig farming in stages and multiple dimensions according to regions, ensuring that the meat taste of the pigs farmed in each region meets the requirements.

Description

Technical Field

[0001] The present invention relates to the field of animal husbandry technology, and in particular to an intelligent pig breeding system, method and readable storage medium. Background Art

[0002] As living standards improve, people's food requirements are becoming increasingly sophisticated. From initially focusing on filling their stomachs to becoming more concerned with food health and safety, as well as the quality and taste of meat, pork is a staple meat on the public's table. Pig farmers focus more on breeding efficiency to meet the high demand for pork, but pay far less attention to the texture and taste of the meat.

[0003] my country is a vast country, with numerous pig farmers across the country. Different regions have varying climates, resulting in varying pork textures. Even within the same region, the texture of the pork can be affected by the different diets provided to pigs during farming. Therefore, how to integrate regional and dietary factors to achieve intelligent pig farming and ensure optimal pork quality is a pressing technical challenge. Summary of the Invention

[0004] The main purpose of the present invention is to provide an intelligent pig farming method, system and readable storage medium, aiming to solve the technical problem of how to realize intelligent pig farming in the existing technology to ensure the meat quality and taste of pork.

[0005] To achieve the above objectives, the present invention provides an intelligent pig farming method, which includes:

[0006] Obtaining pig growth sample data from different regions, wherein the pig growth sample data from each region includes emotion sample data, exercise sample data, food ratio sample data, weight sample data, and body fat distribution sample data of pigs at different growth stages;

[0007] The initial model is trained using the pig growth sample data of each region to obtain a pig growth model corresponding to each region;

[0008] Collecting the breeding growth data of the farmed pigs, and searching for a target growth model corresponding to the breeding growth data in the pig growth model corresponding to each region according to the breeding area of ​​the farmed pigs;

[0009] The breeding growth data is transmitted to the target growth model for data analysis to obtain analysis results, and the breeding status of the farmed pigs is monitored based on the analysis results.

[0010] Optionally, the step of collecting the breeding and growth data of the farmed pigs includes:

[0011] Identify the identity information of the farmed pigs based on the image acquisition device of the pig house where the farmed pigs are located;

[0012] Based on the sound collection device of the pig house where the pigs are raised, audio data of the pigs are collected, and the audio data is pre-processed to obtain emotion data;

[0013] Based on the motion sensors installed on the farmed pigs, the motion data of the farmed pigs are collected;

[0014] Acquiring food ratio data corresponding to the identity information;

[0015] Based on the weight sensors in the piggeries where the pigs are raised, the weight data of the pigs are collected;

[0016] Based on the body fat sensors installed on the farmed pigs, the body fat distribution data of the farmed pigs are collected;

[0017] The emotional data, exercise data, food ratio data, weight data and body fat distribution data are associated with the identity information as a data group to generate the farming growth data.

[0018] Optionally, the step of transmitting the aquaculture growth data to the target growth model for data analysis to obtain analysis results includes:

[0019] Transmitting the breeding growth data to the target growth model, and analyzing the identity information in the breeding growth data based on the target growth model to determine the current growth stage of the farmed pigs;

[0020] Based on the target growth model, the reference weight data and reference body fat distribution data corresponding to the current growth stage are determined, and the weight data and body fat distribution data in the breeding growth data are analyzed to see whether they match the reference weight data and the reference body fat distribution data respectively, to generate an analysis result.

[0021] Optionally, the step of analyzing whether the weight data and the body fat distribution data in the farming growth data match the reference weight data and the reference body fat distribution data respectively, and generating an analysis result includes:

[0022] Comparing the weight data in the breeding and growth data with the reference weight data to determine whether the weight data matches the reference weight data, and comparing the body fat distribution data in the breeding and growth data with the reference body fat distribution data to determine whether the body fat distribution data matches the reference body fat distribution data;

[0023] If the weight data matches the reference weight data, and the body fat distribution data matches the reference body fat distribution data, an analysis result indicating that the breeding growth data is normal is generated;

[0024] If the weight data does not match the reference weight data and / or the body fat distribution data does not match the reference body fat distribution data, the emotion data, exercise data and food ratio data in the farming growth data are analyzed based on the target growth model to generate an analysis result of abnormal farming growth data.

[0025] Optionally, if the weight data matches the reference weight data, and the body fat distribution data matches the reference body fat distribution data, the step of generating an analysis result indicating that the breeding growth data is normal includes:

[0026] If the weight data matches the reference weight data, and the body fat distribution data matches the reference body fat distribution data, then based on the target growth model, respectively calculate a first score, a second score, a third score, a fourth score, and a fifth score for the emotion data, exercise data, food ratio data, weight data, and body fat distribution data in the farming growth data;

[0027] If the first score, the second score, and the third score are all normal, obtaining, based on the target growth model, a first weight value, a second weight value, a third weight value, a fourth weight value, and a fifth weight value corresponding to the emotion data, the exercise data, the food ratio data, the weight data, and the body fat distribution data, respectively;

[0028] weighting the first score, the second score, and the third score based on the first weight value, the second weight value, and the third weight value to obtain a first processing result;

[0029] weighting the fourth score and the fifth score based on the fourth weight value and the fifth weight value respectively to obtain a second processing result;

[0030] If the first processing result and the second processing result match, an analysis result indicating that the breeding growth data is normal is generated.

[0031] Optionally, the step of analyzing the emotion data, exercise data, and food ratio data in the farming growth data based on the target growth model to generate an analysis result of abnormal farming growth data includes:

[0032] Extracting emotional features from the emotional data based on the target growth model, and analyzing the emotional data according to the emotional features to generate an emotional analysis result;

[0033] reading reference motion data corresponding to the reference weight data and the reference body fat distribution data based on the target growth model, analyzing whether the motion data matches the reference motion data, and generating a motion analysis result;

[0034] reading reference food ratio data corresponding to the reference weight data and the reference body fat distribution data based on the target growth model, analyzing whether the food ratio data matches the reference food ratio data, and generating a food analysis result;

[0035] An analysis result of abnormal breeding growth data is generated based on the abnormalities of the emotion analysis result, the movement analysis result, and the food analysis result.

[0036] Optionally, after the step of generating an analysis result of abnormal breeding growth data based on the abnormalities of the emotion analysis result, the movement analysis result, and the food analysis result, the following steps are performed:

[0037] If the emotion analysis result is abnormal, analyzing the abnormal points of the emotion feature based on the target growth model, and outputting prompt information corresponding to the abnormal points;

[0038] If the movement analysis result is abnormal, the movement abnormality type is analyzed based on the target growth model, and when the movement abnormality type is insufficient exercise type, the farmed pigs are guided to increase exercise, and when the movement abnormality type is excessive exercise type, the farmed pigs are guided to reduce exercise;

[0039] If the food analysis result is abnormal, the food ratio improvement points of the food ratio data are analyzed based on the target growth model, and prompt information corresponding to the ratio improvement points is output.

[0040] Optionally, the step of analyzing abnormal points of the emotional features based on the target growth model and outputting prompt information corresponding to the abnormal points includes:

[0041] Analyzing abnormal points of the emotional characteristics based on the target growth model to determine whether the abnormal points are abnormal symptoms;

[0042] If the disease is abnormal, outputting an acquisition request for acquiring biological information corresponding to the disease abnormality;

[0043] When the biological information obtained based on the acquisition request is received, the biological information is detected based on the target growth model, a detection result is generated, and the detection result is added to the prompt information output corresponding to the abnormal point.

[0044] Furthermore, to achieve the above-mentioned object, the present invention also provides an intelligent pig farming system, the intelligent pig farming system comprising: a cloud server, and data collection devices in various regions that are communicatively connected to the cloud server;

[0045] The cloud server is pre-deployed with pig growth models corresponding to various regions;

[0046] The data acquisition device at least includes an image acquisition device, a sound acquisition device, a weight sensor installed in the pig house, and a motion sensor and a body fat sensor installed on the farmed pigs;

[0047] The data collection device in each region transmits the collected breeding growth data to the cloud server;

[0048] The cloud server also includes a memory, a processor, and a control program stored in the memory and executable on the processor. When the control program is executed by the processor, the steps of the intelligent pig farming method described above are implemented.

[0049] Furthermore, to achieve the above-mentioned purpose, the present invention also provides a readable storage medium, on which a control program is stored, and when the control program is executed by a processor, the steps of the intelligent pig breeding method as described above are implemented.

[0050] The intelligent pig breeding method, system and readable storage medium of the present invention first obtain pig growth sample data from different regions, and the pig growth sample data of each region includes emotion sample data, exercise sample data, food ratio sample data, weight sample data and body fat distribution sample data of pigs at different growth stages; then the initial model is trained with the pig growth sample data of each region to obtain a pig growth model corresponding to each region; in the actual pig breeding process, the breeding growth data of the breeding pigs are collected, and according to the breeding site of the breeding pigs, the target growth model corresponding to the breeding growth data is searched; then the breeding growth data is transmitted to the target growth model for data analysis to obtain analysis results, so as to monitor the breeding status of the breeding pigs based on the analysis results. In this way, the growth data of the pig farming process is analyzed according to the pig growth model divided by region, ensuring that the analysis results are consistent with the regional factors affecting pig farming, and can more accurately analyze whether the growth data is abnormal, which is conducive to the accurate monitoring of pig farming and ensures the meat taste of pigs raised in various regions; at the same time, the analysis dimensions include at least emotional data, exercise data, food ratio data, weight data and body fat data, realizing multi-dimensional monitoring of the factors affecting the meat taste of pig farming, and ensuring that the meat taste of pigs raised in various regions meets the requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 This is a schematic diagram of the structure of the hardware operating environment involved in the embodiment of the intelligent pig farming system of the present invention;

[0052] Figure 2 This is a flow chart of the first embodiment of the intelligent pig farming method of the present invention.

[0053] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0054] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0055] The present invention provides an intelligent pig breeding system. Figure 1 , Figure 1 This is a structural diagram of the hardware operating environment involved in the embodiment of the intelligent pig farming system of the present invention.

[0056] The intelligent pig farming system may include: a cloud server (not shown in the figure), and data acquisition devices in various regions (not shown in the figure) that are communicatively connected to the cloud server; pig growth models corresponding to various regions are pre-deployed in the cloud server; the data acquisition devices include at least an image acquisition device, a sound acquisition device, and a weight sensor installed in the pig house, as well as motion sensors and body fat sensors installed on the farmed pigs; the data acquisition devices in each region transmit the collected farming growth data to the cloud server.

[0057] like Figure 1 As shown, the intelligent pig farming system may further include a processor 1001, such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory, or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may optionally be a storage device independent of the aforementioned processor 1001.

[0058] Those skilled in the art will understand that Figure 1The hardware structure of the intelligent pig farming system shown in the figure does not constitute a limitation of the intelligent pig farming system, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0059] like Figure 1 As shown, the memory 1005, which is a readable storage medium, may include an operating system, a network communication module, a user interface module, and a control program. The operating system is a program that manages and controls the intelligent pig farming system and software resources, supporting the operation of the network communication module, the user interface module, the control program, and other programs or software. The network communication module is used to manage and control the network interface 1004; the user interface module is used to manage and control the user interface 1003.

[0060] exist Figure 1 In the hardware structure of the intelligent pig farming system shown, the network interface 1004 is mainly used to connect to the backend server and communicate data with the backend server; the user interface 1003 is mainly used to connect to the client (user end) and communicate data with the client; the processor 1001 can call the control program stored in the memory 1005 and perform the following operations:

[0061] Obtaining pig growth sample data from different regions, wherein the pig growth sample data from each region includes emotion sample data, exercise sample data, food ratio sample data, weight sample data, and body fat distribution sample data of pigs at different growth stages;

[0062] The initial model is trained using the pig growth sample data of each region to obtain a pig growth model corresponding to each region;

[0063] Collecting the breeding growth data of the farmed pigs, and searching for a target growth model corresponding to the breeding growth data in the pig growth model corresponding to each region according to the breeding area of ​​the farmed pigs;

[0064] The breeding growth data is transmitted to the target growth model for data analysis to obtain analysis results, and the breeding status of the farmed pigs is monitored based on the analysis results.

[0065] Furthermore, the step of collecting the breeding and growth data of the farmed pigs includes:

[0066] Identify the identity information of the farmed pigs based on the image acquisition device of the pig house where the farmed pigs are located;

[0067] Based on the sound collection device of the pig house where the pigs are raised, audio data of the pigs are collected, and the audio data is pre-processed to obtain emotion data;

[0068] Based on the motion sensors installed on the farmed pigs, the motion data of the farmed pigs are collected;

[0069] Acquiring food ratio data corresponding to the identity information;

[0070] Based on the weight sensors in the piggeries where the pigs are raised, the weight data of the pigs are collected;

[0071] Based on the body fat sensors installed on the farmed pigs, the body fat distribution data of the farmed pigs are collected;

[0072] The emotional data, exercise data, food ratio data, weight data and body fat distribution data are associated with the identity information as a data group to generate the farming growth data.

[0073] Furthermore, the step of transmitting the aquaculture growth data to the target growth model for data analysis to obtain analysis results includes:

[0074] Transmitting the breeding growth data to the target growth model, and analyzing the identity information in the breeding growth data based on the target growth model to determine the current growth stage of the farmed pigs;

[0075] Based on the target growth model, the reference weight data and reference body fat distribution data corresponding to the current growth stage are determined, and the weight data and body fat distribution data in the breeding growth data are analyzed to see whether they match the reference weight data and the reference body fat distribution data respectively, to generate an analysis result.

[0076] Furthermore, the step of analyzing whether the weight data and body fat distribution data in the farming growth data match the reference weight data and the reference body fat distribution data respectively, and generating an analysis result includes:

[0077] Comparing the weight data in the breeding and growth data with the reference weight data to determine whether the weight data matches the reference weight data, and comparing the body fat distribution data in the breeding and growth data with the reference body fat distribution data to determine whether the body fat distribution data matches the reference body fat distribution data;

[0078] If the weight data matches the reference weight data, and the body fat distribution data matches the reference body fat distribution data, an analysis result indicating that the breeding growth data is normal is generated;

[0079] If the weight data does not match the reference weight data and / or the body fat distribution data does not match the reference body fat distribution data, the emotion data, exercise data and food ratio data in the farming growth data are analyzed based on the target growth model to generate an analysis result of abnormal farming growth data.

[0080] Furthermore, if the weight data matches the reference weight data, and the body fat distribution data matches the reference body fat distribution data, the step of generating an analysis result indicating that the breeding growth data is normal includes:

[0081] If the weight data matches the reference weight data, and the body fat distribution data matches the reference body fat distribution data, then based on the target growth model, respectively calculate a first score, a second score, a third score, a fourth score, and a fifth score for the emotion data, exercise data, food ratio data, weight data, and body fat distribution data in the farming growth data;

[0082] If the first score, the second score, and the third score are all normal, obtaining, based on the target growth model, a first weight value, a second weight value, a third weight value, a fourth weight value, and a fifth weight value corresponding to the emotion data, the exercise data, the food ratio data, the weight data, and the body fat distribution data, respectively;

[0083] weighting the first score, the second score, and the third score based on the first weight value, the second weight value, and the third weight value to obtain a first processing result;

[0084] weighting the fourth score and the fifth score based on the fourth weight value and the fifth weight value respectively to obtain a second processing result;

[0085] If the first processing result and the second processing result match, an analysis result indicating that the breeding growth data is normal is generated.

[0086] Furthermore, the step of analyzing the emotion data, exercise data, and food ratio data in the farming growth data based on the target growth model to generate an analysis result of abnormal farming growth data includes:

[0087] Extracting emotional features from the emotional data based on the target growth model, and analyzing the emotional data according to the emotional features to generate an emotional analysis result;

[0088] reading reference motion data corresponding to the reference weight data and the reference body fat distribution data based on the target growth model, analyzing whether the motion data matches the reference motion data, and generating a motion analysis result;

[0089] reading reference food ratio data corresponding to the reference weight data and the reference body fat distribution data based on the target growth model, analyzing whether the food ratio data matches the reference food ratio data, and generating a food analysis result;

[0090] An analysis result of abnormal breeding growth data is generated based on the abnormalities of the emotion analysis result, the movement analysis result, and the food analysis result.

[0091] Furthermore, after the step of generating an analysis result of abnormal breeding growth data based on the abnormalities of the emotion analysis result, the motion analysis result, and the food analysis result, the processor 1001 may call the control program stored in the memory 1005 and perform the following operations:

[0092] If the emotion analysis result is abnormal, analyzing the abnormal points of the emotion feature based on the target growth model, and outputting prompt information corresponding to the abnormal points;

[0093] If the movement analysis result is abnormal, the movement abnormality type is analyzed based on the target growth model, and when the movement abnormality type is insufficient exercise type, the farmed pigs are guided to increase exercise, and when the movement abnormality type is excessive exercise type, the farmed pigs are guided to reduce exercise;

[0094] If the food analysis result is abnormal, the food ratio improvement points of the food ratio data are analyzed based on the target growth model, and prompt information corresponding to the ratio improvement points is output.

[0095] Furthermore, the step of analyzing the abnormal points of the emotional features based on the target growth model and outputting prompt information corresponding to the abnormal points includes:

[0096] Analyzing abnormal points of the emotional characteristics based on the target growth model to determine whether the abnormal points are abnormal symptoms;

[0097] If the disease is abnormal, outputting an acquisition request for acquiring biological information corresponding to the disease abnormality;

[0098] When the biological information obtained based on the acquisition request is received, the biological information is detected based on the target growth model, a detection result is generated, and the detection result is added to the prompt information output corresponding to the abnormal point.

[0099] The present invention provides an intelligent pig breeding method, referring to Figure 2 , Figure 2 This is a flow chart of the first embodiment of the intelligent pig farming method of the present invention.

[0100] The embodiments of the present invention provide an embodiment of an intelligent pig farming method. It should be noted that although the logical order is shown in the flowchart, in some cases, the steps shown or described can be performed in a different order than here. Specifically, the intelligent pig farming method of this embodiment includes:

[0101] Step S10, obtaining pig growth sample data from different regions, wherein the pig growth sample data from each region includes emotion sample data, exercise sample data, food ratio sample data, weight sample data, and body fat distribution sample data of pigs at different growth stages;

[0102] The intelligent pig farming method in this embodiment is applied to the cloud server within the intelligent pig farming system. The cloud server analyzes and processes the growth data of the farmed pigs in multiple dimensions, monitors the farming status of the farmed pigs, ensures that the farmed pigs have better meat taste, and realizes intelligent pig farming.

[0103] Specifically, considering that different regions have different climates, which have different impacts on pig farming. Therefore, in order to breed pigs with better taste and meat quality in each region, this embodiment classifies them according to regions and obtains pig growth sample data from different regions. Among them, the pig growth sample data is the breeding data at different growth stages in the pig breeding process, and at least includes emotion sample data, exercise sample data, food ratio data, weight sample data and body fat distribution sample data. Emotion sample data, exercise sample data and food ratio sample data exist as factors that affect weight sample data and body fat distribution sample data. That is, whether the emotion sample data reflects happy emotions, whether the exercise sample data reflects a reasonable amount of exercise, and whether the food ratio sample data reflects a reasonable food ratio will affect whether the pig's weight sample data is healthy and whether the body fat distribution sample data is reasonable. Therefore, we can screen out weight sample data and body fat distribution sample data that meet the health requirements of different growth stages from a large amount of pig growth sample data, and then analyze the characteristics of pigs with such weight sample data and body fat distribution sample data in terms of emotion sample data, exercise sample data and food ratio sample data, to form the relationship between the emotion sample data, exercise sample data, food ratio sample data and weight sample data, body fat distribution sample data of pigs in various regions at different growth stages, and realize intelligent guidance of pig farming.

[0104] Step S20, training the initial model using the pig growth sample data of each region to obtain a pig growth model corresponding to each region;

[0105] Furthermore, the cloud server is pre-configured with multiple initial models, preferably neural network models. Pig growth sample data from each region is transmitted to different initial models for training, thereby obtaining a pig growth model suitable for each region. Specifically, after receiving the pig growth sample data, the initial model divides the sample data into sample data for each growth stage based on the stage labels carried by each pig growth sample data. The sample data for each growth stage is then screened to select weight sample data that meets health requirements and body fat distribution sample data that meets body fat distribution requirements. The weight sample data and body fat distribution sample data that are screened are then searched for emotion sample data, exercise sample data, and food ratio sample data from the same pig. The initial model is configured with a loss function to evaluate the effectiveness of training. The loss function is calculated based on the results of the screening and searching, and a determination is made as to whether the calculated result is less than a preset value. If so, the screening and searching results are determined to be accurate, indicating that the initial model has good performance, and the initial model is generated as the pig growth model. Conversely, if the calculated result is not less than the preset value, it indicates that the initial model's screening and search results are inaccurate. The initial model is then iteratively trained until the loss function is less than the preset value, at which point the initial model is converted into a pig growth model. The initial model is trained on pig growth sample data from various regions. Once the loss function values ​​of each initial model are less than the preset value, a pig growth model corresponding to each region is obtained, which can be used to monitor pig farming in different regions.

[0106] Step S30, collecting the breeding growth data of the farmed pigs, and searching for a target growth model corresponding to the breeding growth data in the pig growth model corresponding to each region according to the breeding area of ​​the farmed pigs;

[0107] Furthermore, for pigs raised in a certain area, in order to monitor their breeding status, breeding and growth data of the pigs are collected. The collected breeding and growth data is data reflecting the status of the pigs at the current stage of breeding. The collection method includes but is not limited to installing collection devices in the pig house where the pigs are active and on the pigs. In addition, the collected breeding and growth data contains information representing the identity of the pigs, and the breeding location of the pigs is determined based on this identity information. For example, the identity information can be a string of numbers or a QR code, in which some numbers or QR code information is used to reflect the breeding location, other numbers or QR code information is used to reflect the pig species, and some numbers or QR code information is used to reflect the pig growth stage. By identifying the identity information, the breeding location can be determined. Then, based on the correspondence between the trained pig growth models and the regions, the pig growth model corresponding to the breeding location is found from the pig growth models and used as the target growth model corresponding to the breeding and growth data.

[0108] Step S40: transmitting the breeding growth data to the target growth model for data analysis to obtain analysis results, and monitoring the breeding status of the farmed pigs based on the analysis results.

[0109] Furthermore, the breeding growth data is transmitted to the target growth model, which performs data analysis to obtain analysis results. Reproductive growth data includes at least emotional data, exercise data, food ratio data, weight data, and body fat distribution data. The target growth model analyzes whether the weight data meets the healthy weight requirements for the current growth stage, and whether the body fat distribution data meets the body fat distribution requirements for the current growth stage. Based on whether the weight and body fat distribution data meet their respective requirements, the emotional data, exercise data, and food ratio data are analyzed to obtain analysis results, thereby monitoring the breeding status of the farmed pigs. If all data meet their respective requirements, the current breeding growth data indicates that the pigs are in good condition and can continue to be farmed in this state. Conversely, if any data does not meet the requirements, the current breeding growth data indicates that the pigs are in an abnormal condition and require manual or automatic improvement based on the cause of the abnormality. In this way, by monitoring various factors affecting pig farming, intelligent pig farming is achieved, ensuring that the farmed pigs have a good meat quality and taste.

[0110] The intelligent pig breeding method of the present invention first obtains pig growth sample data from different regions, and the pig growth sample data of each region includes emotion sample data, exercise sample data, food ratio sample data, weight sample data and body fat distribution sample data of pigs at different growth stages; then the initial model is trained with the pig growth sample data of each region to obtain a pig growth model corresponding to each region; in the actual pig breeding process, the breeding growth data of the breeding pigs are collected, and according to the breeding place of the breeding pigs, the target growth model corresponding to the breeding growth data is found; then the breeding growth data is transmitted to the target growth model for data analysis to obtain analysis results, so as to monitor the breeding status of the breeding pigs based on the analysis results. In this way, the growth data of the pig farming process is analyzed according to the pig growth model divided by region, ensuring that the analysis results are consistent with the regional factors affecting pig farming, and can more accurately analyze whether the growth data is abnormal, which is conducive to the accurate monitoring of pig farming and ensures the meat taste of pigs raised in various regions; at the same time, the analysis dimensions include at least emotional data, exercise data, food ratio data, weight data and body fat data, realizing multi-dimensional monitoring of the factors affecting the meat taste of pig farming, and ensuring that the meat taste of pigs raised in various regions meets the requirements.

[0111] Furthermore, based on the first embodiment of the intelligent pig breeding method of the present invention, a second embodiment of the intelligent pig breeding method of the present invention is proposed.

[0112] The difference between the second embodiment of the intelligent pig breeding method and the first embodiment of the intelligent pig breeding method is that the step of collecting breeding and growth data of the breeding pigs includes:

[0113] Step S31, identifying the identity information of the farmed pigs based on the image acquisition device of the pig house where the farmed pigs are located;

[0114] Step S32, collecting audio data of the farmed pigs based on a sound collection device in the piggery where the farmed pigs are located, and pre-processing the audio data to obtain emotion data;

[0115] Step S33, collecting motion data of the farmed pigs based on motion sensors installed on the farmed pigs;

[0116] Step S34, obtaining food ratio data corresponding to the identity information;

[0117] Step S35, collecting weight data of the farmed pigs based on the weight sensor of the pig house where the farmed pigs are located;

[0118] Step S36, collecting body fat distribution data of the farmed pigs based on the body fat sensors installed on the farmed pigs;

[0119] Step S37 , associating the emotion data, exercise data, food ratio data, weight data and body fat distribution data as a data group with the identity information to generate the farming growth data.

[0120] In order to collect the breeding and growth data of the farmed pigs, this embodiment provides a collection device that is connected to the cloud server in the pig house of the farmed pigs and on the bodies of the farmed pigs. This type of collection device includes an image collection device, a sound collection device, a weight sensor installed in the pig house, and a motion sensor and a body fat sensor installed on the pigs. Specifically, the image collection device can be used to collect information representing the identity of the pigs and transmit it to the cloud server, and the cloud service can identify and obtain the identity information of the farmed pigs. Among them, the information representing the identity of the pigs can at least reflect the breeding place, type and age (i.e., growth stage) of the pigs, which can exist in the form of a QR code label or a string of numbers. The QR code or number is printed on a plastic plate, and then the plastic plate is fixed on the farmed pigs. The image collection device can obtain information representing the identity of the farmed pigs by shooting the plastic plate.

[0121] Furthermore, audio data from the farmed pigs is collected through a sound collection device and transmitted to a cloud server. The data is then preprocessed by a pig growth model within the cloud server to obtain emotional data representing the emotional well-being of the pigs being farmed. Preprocessing includes filtering and classification. Filtering removes audio from the audio data that is not produced by the pigs based on characteristics of the pig audio, such as frequency. Classification involves classifying the audio data based on its source when it contains data from multiple pigs, such as audio from the current piggery and from neighboring piggeries. This allows the audio data within the current piggery to reflect the emotional well-being of the pigs within it.

[0122] Furthermore, motion sensors monitor the movement data of the farmed pigs. This movement data can include movement quantity, such as the number of steps, and movement amplitude, such as the amplitude of each step. This monitored movement data is transmitted to a cloud server, where it is analyzed by a pig growth model within the cloud server to determine whether the movement data meets requirements. Furthermore, to optimize the meat's taste, pigs from different regions, species, and growth stages require different food combinations. To obtain the current food ratio for the farmed pigs, the farmer's terminal, which can be a mobile phone, tablet, desktop computer, or laptop, is connected to the cloud server. This terminal records the pigs' farming status, including their identity information, regular physical examinations, and disease treatment. Furthermore, the food ratio fed each time is recorded under the pig's name and associated with the pig's identity information, reflecting the food ratios tailored to the pig's location, species, and growth stage. The terminal uploads the food ratio of this type to the cloud server through the communication connection with the cloud server, so that the cloud server obtains the food ratio data corresponding to the identity information and analyzes the rationality of the dietary structure of the farmed pigs.

[0123] Furthermore, a weight sensor is installed on the ground inside the pig house, and multiple sensors can be installed for the convenience of weighing. For example, a rectangular pig house can be divided into grids such as four, six or nine squares, and a weight sensor is set in each grid. The weight of the farmed pigs can be detected in any grid. The weight sensor transmits the detected weight data of the farmed pigs to the cloud server, which is analyzed and processed by the pig growth model in the cloud server. In addition, the body fat sensor installed on the pig collects the body fat distribution data of the farmed pigs. The collected body fat distribution data includes the overall body fat rate, the visceral body fat rate, and the body fat rate of each part. The collected body fat distribution data is uploaded to the cloud server, and the pig growth model in the cloud server analyzes whether the body fat of the pigs meets the requirements.

[0124] It is understandable that different pigs have different emotional data, exercise data, food ratio data, weight data and body fat distribution data. In order to avoid confusion of such data between different pigs, this embodiment is provided with an association mechanism. That is, the collected emotional data, exercise data, food ratio data, weight data and body fat distribution data are all associated with the identity information of the farmed pigs, and the collected data of the farmed pigs are reflected through the relationship. Moreover, the association can be a separate association of each collected data, or a unified association after the collection of each collected data. For separate association, each collection device associates the collected data with the identity data, generates breeding and growth data, and transmits it to the cloud server for processing. For unified association, each collection device is connected to a transfer device, which is in communication with the cloud server. Each collection device transmits the collected data to the transfer device, and the transfer device uniformly associates it with the identity information to generate breeding and growth data and transmits it to the cloud server for processing.

[0125] Furthermore, the step of transmitting the aquaculture growth data to the target growth model for data analysis to obtain analysis results includes:

[0126] Step S41, transmitting the breeding growth data to the target growth model, and analyzing the identity information in the breeding growth data based on the target growth model to determine the current growth stage of the farmed pigs;

[0127] Step S42: Determine the reference weight data and reference body fat distribution data corresponding to the current growth stage based on the target growth model, and analyze whether the weight data and body fat distribution data in the breeding growth data match the reference weight data and the reference body fat distribution data respectively, and generate an analysis result.

[0128] Furthermore, after receiving the pig growth data and finding the target growth model for processing the data based on the farm location included in the identity data, the cloud server transmits the data to the target growth model for analysis. Specifically, the target growth model first analyzes the identity information in the pig growth data, searches for the field representing age, and uses the age to determine the current growth stage of the pig.

[0129] Understandably, healthy pigs have different weights and body fat distributions at different growth stages. After determining the current growth stage of the farmed pig, the target growth model searches for reference weight and body fat data corresponding to that stage. The reference weight and body fat data represent the ideal weight and body fat distribution for the current growth stage, respectively. The model then analyzes the weight and body fat distribution data in the farmed growth data to determine whether they match the reference weight and body fat distribution data, respectively, to generate analysis results.

[0130] Specifically, the step of analyzing whether the weight data and the body fat distribution data in the farming growth data match the reference weight data and the reference body fat distribution data respectively, and generating an analysis result includes:

[0131] Step S421, comparing the weight data in the breeding and growth data with the reference weight data to determine whether the weight data matches the reference weight data, and comparing the body fat distribution data in the breeding and growth data with the reference body fat distribution data to determine whether the body fat distribution data matches the reference body fat distribution data;

[0132] Step S422: If the weight data matches the reference weight data, and the body fat distribution data matches the reference body fat distribution data, then generating an analysis result indicating that the breeding growth data is normal;

[0133] Step S423: If the weight data does not match the reference weight data and / or the body fat distribution data does not match the reference body fat distribution data, the emotion data, exercise data and food ratio data in the farming growth data are analyzed based on the target growth model to generate an analysis result of the abnormal farming growth data.

[0134] Furthermore, the weight data in the farmed pig data is compared with the reference weight data to determine whether they match; and the body fat distribution data in the farmed growth data is compared with the reference body fat distribution data to determine whether they match. If the comparison determines that the weight data matches the reference weight data, and the body fat distribution data matches the reference body fat distribution data, then it indicates that the farmed pigs are growing normally at the current growth stage, and an analysis result indicating that the farmed growth data is normal is generated.

[0135] On the contrary, if there is any mismatch between the weight data and the reference weight data, and between the body fat distribution data and the reference body fat distribution data, it means that the growth of the farmed pigs is abnormal in the current growth stage. At this time, the emotional data, exercise data and food ratio data in the farming growth data are further analyzed through the target growth model to generate an analysis result of the abnormal farming growth data to reflect the reasons for the abnormal growth of the farmed pigs in the current growth stage.

[0136] It should be noted that for the analysis results that show normal growth represented by weight data and body fat distribution data, there may be a problem of unbalanced influence among emotional data, exercise data and food ratio data. For example, if the negative impact of emotional data is too large, resulting in weight loss; while the positive impact of food ratio data is too large, resulting in weight gain; the combined result of the two tends to be normal. Because, in order to avoid the influence of such factors, this embodiment provides a mechanism for continuing to analyze emotional data, exercise data and food ratio data for the analysis results of normal growth, so as to ensure the high quality of the farmed pigs in all dimensions. Specifically, if the weight data matches the reference weight data, and the body fat distribution data matches the reference body fat distribution data, then the steps of generating the analysis results of normal farming growth data include:

[0137] Step a1: If the weight data matches the reference weight data, and the body fat distribution data matches the reference body fat distribution data, then based on the target growth model, respectively calculate a first score, a second score, a third score, a fourth score, and a fifth score for the emotion data, exercise data, food ratio data, weight data, and body fat distribution data in the farming growth data;

[0138] Step a2: If the first score, the second score, and the third score are all normal, obtaining, based on the target growth model, a first weight value, a second weight value, a third weight value, a fourth weight value, and a fifth weight value corresponding to the emotion data, the exercise data, the food ratio data, the weight data, and the body fat distribution data, respectively;

[0139] Step a3: weighting the first score, the second score, and the third score based on the first weight value, the second weight value, and the third weight value to obtain a first processing result;

[0140] Step a4, weighting the fourth score and the fifth score based on the fourth weight value and the fifth weight value respectively to obtain a second processing result;

[0141] Step a5: If the first processing result and the second processing result match, an analysis result indicating that the breeding growth data is normal is generated.

[0142] Furthermore, under the premise that the weight data matches the reference weight data and the body fat distribution data matches the reference body fat distribution data, the cloud server invokes the target growth model to score the emotion data, exercise data, food ratio data, weight data, and body fat distribution data in the farming growth data based on the differences between the emotion data, exercise data, food ratio data, weight data, and body fat distribution data and the reference data, thereby obtaining a first score for the emotion data, a second score for the exercise data, a third score for the food ratio data, a fourth score for the weight data, and a fifth score for the body fat distribution data. The cloud server then determines whether the first, second, and third scores are all within their corresponding normal score ranges. If they are all within their corresponding normal score ranges, the first, second, and third scores are determined to be normal.

[0143] Thereafter, a first weight value, a second weight value, a third weight value, a fourth weight value, and a fifth weight value corresponding to the emotion data, exercise data, food ratio data, weight data, and body fat distribution data, respectively, are obtained through the target growth model. The first weight value, the second weight value, the third weight value, the fourth weight value, and the fifth weight value respectively represent the importance of the emotion data, exercise data, food ratio data, weight data, and body fat distribution data in the growth process of the farmed pigs.

[0144] Furthermore, the first, second, and third scores are weighted using a first weight value, a second weight value, and a third weight value, respectively, to obtain a first processing result. Simultaneously, the fourth and fifth scores are weighted using a fourth weight value and a fifth weight value, respectively, to obtain a second processing result. The first processing result and the second processing result are then compared to determine whether they match. If they match, it indicates that the farmed pigs are growing normally at their current stage, influenced by the emotion data, exercise data, and food ratio data. If they do not match, it indicates that while the individual scores of the emotion data, exercise data, and food ratio data are normal, the combined effect is abnormal, and a prompt message is output to prompt the user to identify the cause of the abnormality and make improvements. It should be noted that during the process of determining the normality of the first, second, and third scores, if any of them is abnormal, it indicates that the abnormal factor will affect the growth of the farmed pigs. Therefore, a prompt message is output for the abnormal factor to prompt the user to make improvements to promote normal growth of the farmed pigs in terms of various factors.

[0145] In this embodiment, multiple collection devices are used to collect growth data of farmed pigs in different dimensions, generating growth data that is transmitted to a cloud server. A target growth model within the cloud server then performs a multi-dimensional analysis to determine the status of the farmed pigs at their current growth stage. If the status is normal, the current farming method is maintained. If the status is abnormal, the cause of the abnormality is analyzed from various dimensions to improve the farming method accordingly. This ensures that the farmed pigs maintain a normal status at all stages, ensuring superior meat quality and taste from all dimensions.

[0146] Furthermore, based on the second embodiment of the intelligent pig breeding method of the present invention, a third embodiment of the intelligent pig breeding method of the present invention is proposed.

[0147] The third embodiment of the intelligent pig farming method differs from the second embodiment of the intelligent pig farming method in that the step of analyzing the emotion data, exercise data, and food ratio data in the farming growth data based on the target growth model to generate an analysis result of abnormal farming growth data includes:

[0148] Step b1, extracting emotional features from the emotional data based on the target growth model, and analyzing the emotional data according to the emotional features to generate an emotional analysis result;

[0149] Step b2, reading reference motion data corresponding to the reference weight data and the reference body fat distribution data based on the target growth model, analyzing whether the motion data matches the reference motion data, and generating a motion analysis result;

[0150] Step b3, reading reference food ratio data corresponding to the reference weight data and the reference body fat distribution data based on the target growth model, analyzing whether the food ratio data matches the reference food ratio data, and generating a food analysis result;

[0151] Step b4: generating an analysis result of abnormal breeding growth data based on the abnormalities of the emotion analysis result, the movement analysis result, and the food analysis result.

[0152] In this embodiment, when the analysis result of the breeding growth data is abnormal, the cause of the abnormality is deeply analyzed so as to improve the breeding method according to the cause of the abnormality. Specifically, the target growth model obtained by training the emotional sample data has the ability to identify different emotional characteristics. Therefore, the emotional data can be analyzed by the target growth model to extract emotional characteristics. The extracted emotional characteristics include both the characteristics of positive emotions such as happiness and joy, and the characteristics of negative emotions such as sadness and frustration. Then, based on the emotional characteristics, the bias of the emotional data is analyzed to obtain an emotional analysis result that characterizes the bias. Among them, the bias of the emotional data characterizes whether the farmed pigs are in a positive or negative emotion as a whole. If the features representing positive emotions in the emotional characteristics are more than the features representing negative emotions, it means that the bias of the emotional data is positive, and a positive emotional analysis result is generated; on the contrary, if the features representing negative emotions are more than the features representing positive emotions, it means that the bias of the emotional data is negative, and a negative emotional analysis result is generated.

[0153] It should be noted that emotion data includes time points, reflecting the emotions of the pigs at different times on the timeline. This embodiment, while analyzing emotion data based on emotion characteristics, also analyzes the frequency of fluctuations in the emotion data based on the time points corresponding to the emotion characteristics. A higher frequency of fluctuation indicates a more severe emotional abnormality in the pigs, thus generating a fluctuating emotion analysis result to prompt attention to the causes of emotional fluctuations.

[0154] It is understandable that weight, body fat distribution and exercise are all related. The reference weight data and reference body fat distribution data of the ideal state have corresponding reference exercise data. When the target growth model is obtained by training the pig growth sample data, while determining the reference weight data and reference body fat distribution data, the reference exercise data corresponding to the reference weight data and reference body fat distribution data are also recorded. Therefore, the corresponding reference exercise data can be read through the target growth model, and the exercise data in the breeding growth data can be compared with the reference exercise data to analyze whether the two match. If they match, it means that the exercise of the farmed pigs meets the requirements of the reference exercise data, and an exercise analysis result of the exercise meeting the standard is generated; if they do not match, it means that the exercise of the farmed pigs does not meet the requirements of the reference exercise data, and an exercise analysis result of the exercise not meeting the standard is generated.

[0155] Furthermore, in addition to being related to exercise, weight and body fat distribution are also related to food ratios; as ideal reference weight data and reference body fat distribution data, in addition to corresponding reference exercise data, they also have corresponding reference food ratio data. The corresponding reference food ratio data can also be read through the target growth model, and the food ratio data in the breeding growth data can be compared with the reference food ratio data to analyze whether the two match. If they match, it means that the food ratio supplied to the farmed pigs meets the requirements of the reference food ratio data, and a food analysis result with a standard ratio is generated; if they do not match, it means that the food ratio supplied to the farmed pigs does not meet the requirements of the reference food ratio data, and a food analysis result with a standard ratio is generated.

[0156] Furthermore, based on the abnormalities among the emotion analysis results, the motion analysis results, and the food analysis results, an analysis result of abnormal breeding and growth data is generated. That is, when any one of the emotion analysis results, the motion analysis results, and the food analysis results indicates abnormality, the abnormal analysis result is generated as an analysis result of abnormal breeding and growth data; if any two of the analysis results indicate abnormality, the two abnormal analysis results are generated as analysis results of abnormal breeding and growth data; if all three analysis results indicate abnormality, the three abnormal analysis results are generated as analysis results of abnormal breeding and growth data. Moreover, if none of the three analysis results are abnormal, it is necessary to search for the reasons for the mismatch between the weight data and the reference weight data and / or the mismatch between the body fat distribution data and the reference body fat distribution data from other dimensions. At this time, analysis results of other abnormal breeding and growth data can be generated to remind people to search for the reasons for the abnormalities from other dimensions.

[0157] It is understandable that for the analysis results of abnormal aquaculture growth data generated based on the abnormalities among the emotion analysis results, the movement analysis results, and the food analysis results, it is necessary to output prompt information for the specific abnormal analysis results, so as to quickly and promptly find the cause of the abnormality based on the specific abnormal analysis results. Specifically, the step of generating the analysis results of abnormal aquaculture growth data based on the abnormalities among the emotion analysis results, the movement analysis results, and the food analysis results includes:

[0158] Step b5: if the emotion analysis result is abnormal, analyzing the abnormal points of the emotion feature based on the target growth model, and outputting prompt information corresponding to the abnormal points;

[0159] Step b6: If the movement analysis result is abnormal, analyzing the movement abnormality type based on the target growth model, and guiding the farmed pigs to increase exercise if the movement abnormality type is insufficient exercise, and guiding the farmed pigs to reduce exercise if the movement abnormality type is excessive exercise;

[0160] Step b7: If the food analysis result is abnormal, analyzing the ratio improvement points of the food ratio data based on the target growth model, and outputting prompt information corresponding to the ratio improvement points.

[0161] Furthermore, if an abnormal analysis result is generated based on the sentiment analysis result, that is, if an abnormal sentiment analysis result leads to an abnormal analysis result of the farming growth data, the target growth model is called to analyze the abnormal points in the sentiment characteristics. These abnormal points are features in the sentiment characteristics that represent negative emotions or emotional fluctuations. The abnormal points are added to the prompt information, forming a prompt information output corresponding to the abnormal points, prompting the user to investigate the cause of the abnormality based on the abnormal points.

[0162] Furthermore, if an abnormal analysis result is generated based on the movement analysis result, that is, an abnormal analysis result of the breeding growth data is generated due to the abnormal movement analysis result, then the target growth model is called to analyze the movement abnormality type. This movement abnormality type indicates whether the movement data in the breeding pig data is too little or too much relative to the reference movement data. If it is too little, it indicates insufficient exercise, and the movement abnormality type is insufficient exercise type. In this case, the breeding pigs are guided to increase exercise; if it is too much, it indicates excessive exercise, and the movement abnormality type is excessive exercise type. In this case, the breeding pigs are guided to reduce exercise. In addition, the smell of promoting excitement can be used to encourage increased exercise; or the smell of calming and tranquilizing effect can be used to reduce exercise.

[0163] Furthermore, if an abnormal analysis result is generated based on the food analysis result, i.e., if the abnormal food analysis result leads to an abnormal analysis result in the pig growth data, the target growth model is invoked to analyze the food ratio data for a ratio improvement point. This ratio improvement point represents a difference in the food ratio data relative to the reference food ratio data. This ratio improvement point is added to the prompt information, resulting in a prompt message output corresponding to the ratio difference point, prompting the user to improve the food ratio of the pigs being farmed based on the difference from the reference food ratio data as reflected by the ratio difference point.

[0164] It is understandable that abnormalities in emotional data may be caused by illness, so when outputting prompt information for such abnormalities, a factor judgment of illness is provided. Specifically, the steps of analyzing abnormal points of the emotional characteristics based on the target growth model and outputting prompt information corresponding to the abnormal points include:

[0165] Step b51, analyzing abnormal points of the emotional characteristics based on the target growth model to determine whether the abnormal points are abnormal symptoms;

[0166] Step b52: If the disease is abnormal, outputting an acquisition request for acquiring biological information corresponding to the abnormal disease;

[0167] Step b53: When the biological information obtained based on the acquisition request is received, the biological information is detected based on the target growth model, a detection result is generated, and the detection result is added to the prompt information output corresponding to the abnormal point.

[0168] Furthermore, when the target growth model is trained by the pig growth sample data, the pig growth sample data is marked with data representing the disease, so that the trained target growth model has the ability to identify the disease. Therefore, after the abnormal point in the emotional characteristics is analyzed by the target growth model, the target growth model continues to determine whether the abnormal point belongs to the disease abnormality. If it is a disease abnormality, an acquisition request is output to obtain the biometric information corresponding to the disease abnormality. Among them, different disease abnormalities have different corresponding acquisition requests for different biometric information; if the disease abnormality is a type A disease, the biometric information requested by the acquisition request is blood; if the disease abnormality is a type B disease, the biometric information requested by the acquisition request is urine.

[0169] Furthermore, the cloud server outputs the acquisition request to the farmer's terminal. After viewing the acquisition request, the farmer obtains the corresponding biological entity information and tests it using a detection instrument. The test results are uploaded to the cloud server as biological information. After receiving this biological information, the cloud server uses the target growth model to test it and generates a test result that represents the type of disease. The test result is then added to the prompt information corresponding to the abnormal point, indicating that the abnormal point in the farmed pig is caused by the disease represented by the test result, and timely treatment is required to eliminate the abnormal point.

[0170] This embodiment analyzes the causes of abnormal breeding and growth data from the dimensions of emotions, exercise, and food ratio, and outputs the causes obtained from the analysis in the form of prompt information, so that the causes of the abnormalities can be quickly found according to the prompt information, so that the breeding pigs can be restored to normal as soon as possible, ensuring normal breeding and growth data at all growth stages and guaranteeing the meat quality and taste of the breeding pigs.

[0171] The embodiment of the present invention further provides a readable storage medium having a control program stored thereon, which, when executed by the processor, implements the steps of the intelligent pig farming method described above.

[0172] The readable storage medium of the present invention can be a computer-readable storage medium, and its specific implementation method is basically the same as the various embodiments of the above-mentioned intelligent pig breeding method, and will not be repeated here.

[0173] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims. Any equivalent structure or equivalent process transformation made using the contents of the description and drawings of the present invention, or directly or indirectly used in other related technical fields, all fall within the protection of the present invention.

Claims

1. An intelligent pig breeding method, characterized in that: The intelligent pig farming method includes: Obtaining pig growth sample data from different regions, wherein the pig growth sample data from each region includes emotion sample data, exercise sample data, food ratio sample data, weight sample data, and body fat distribution sample data of pigs at different growth stages; The initial model is trained using the pig growth sample data of each region to obtain a pig growth model corresponding to each region; Collecting the breeding growth data of the farmed pigs, and searching for a target growth model corresponding to the breeding growth data in the pig growth model corresponding to each region according to the breeding area of ​​the farmed pigs; Transmitting the breeding growth data to the target growth model for data analysis to obtain analysis results, and monitoring the breeding status of the farmed pigs based on the analysis results; The step of collecting the breeding and growth data of the raised pigs comprises: Identify the identity information of the farmed pigs based on the image acquisition device of the pig house where the farmed pigs are located; Based on the sound collection device of the pig house where the pigs are raised, audio data of the pigs are collected, and the audio data is pre-processed to obtain emotion data; Based on the motion sensors installed on the farmed pigs, the motion data of the farmed pigs are collected; Acquiring food ratio data corresponding to the identity information; Based on the weight sensors in the piggeries where the pigs are raised, the weight data of the pigs are collected; Based on the body fat sensors installed on the farmed pigs, the body fat distribution data of the farmed pigs are collected; Associating the emotion data, exercise data, food ratio data, weight data, and body fat distribution data as a data group with the identity information to generate the farming growth data; The step of transmitting the aquaculture growth data to the target growth model for data analysis to obtain analysis results comprises: Transmitting the breeding growth data to the target growth model, and analyzing the identity information in the breeding growth data based on the target growth model to determine the current growth stage of the farmed pigs; Based on the target growth model, the reference weight data and reference body fat distribution data corresponding to the current growth stage are determined, and the weight data and body fat distribution data in the breeding growth data are analyzed to see whether they match the reference weight data and the reference body fat distribution data respectively, to generate an analysis result.

2. The pig breeding method according to claim 1, characterized in that: The step of analyzing whether the weight data and the body fat distribution data in the breeding growth data match the reference weight data and the reference body fat distribution data respectively, and generating an analysis result includes: Comparing the weight data in the breeding and growth data with the reference weight data to determine whether the weight data matches the reference weight data, and comparing the body fat distribution data in the breeding and growth data with the reference body fat distribution data to determine whether the body fat distribution data matches the reference body fat distribution data; If the weight data matches the reference weight data, and the body fat distribution data matches the reference body fat distribution data, an analysis result indicating that the breeding growth data is normal is generated; If the weight data does not match the reference weight data and / or the body fat distribution data does not match the reference body fat distribution data, the emotion data, exercise data and food ratio data in the farming growth data are analyzed based on the target growth model to generate an analysis result of abnormal farming growth data.

3. The pig breeding method according to claim 2, characterized in that: If the weight data matches the reference weight data, and the body fat distribution data matches the reference body fat distribution data, the step of generating an analysis result indicating that the breeding growth data is normal includes: If the weight data matches the reference weight data, and the body fat distribution data matches the reference body fat distribution data, then based on the target growth model, respectively calculate a first score, a second score, a third score, a fourth score, and a fifth score for the emotion data, exercise data, food ratio data, weight data, and body fat distribution data in the farming growth data; If the first score, the second score, and the third score are all normal, obtaining, based on the target growth model, a first weight value, a second weight value, a third weight value, a fourth weight value, and a fifth weight value corresponding to the emotion data, the exercise data, the food ratio data, the weight data, and the body fat distribution data, respectively; weighting the first score, the second score, and the third score based on the first weight value, the second weight value, and the third weight value to obtain a first processing result; weighting the fourth score and the fifth score based on the fourth weight value and the fifth weight value respectively to obtain a second processing result; If the first processing result and the second processing result match, an analysis result indicating that the breeding growth data is normal is generated.

4. The pig breeding method according to claim 2, characterized in that: The step of analyzing the emotion data, exercise data, and food ratio data in the farming growth data based on the target growth model to generate an analysis result of abnormal farming growth data includes: Extracting emotional features from the emotional data based on the target growth model, and analyzing the emotional data according to the emotional features to generate an emotional analysis result; reading reference motion data corresponding to the reference weight data and the reference body fat distribution data based on the target growth model, analyzing whether the motion data matches the reference motion data, and generating a motion analysis result; reading reference food ratio data corresponding to the reference weight data and the reference body fat distribution data based on the target growth model, analyzing whether the food ratio data matches the reference food ratio data, and generating a food analysis result; An analysis result of abnormal breeding growth data is generated based on the abnormalities of the emotion analysis result, the movement analysis result, and the food analysis result.

5. The pig breeding method according to claim 4, characterized in that: After the step of generating an analysis result of abnormal breeding growth data based on the abnormalities of the emotion analysis result, the movement analysis result, and the food analysis result, the following steps are performed: If the emotion analysis result is abnormal, analyzing the abnormal points of the emotion feature based on the target growth model, and outputting prompt information corresponding to the abnormal points; If the movement analysis result is abnormal, the movement abnormality type is analyzed based on the target growth model, and when the movement abnormality type is insufficient exercise type, the farmed pigs are guided to increase exercise, and when the movement abnormality type is excessive exercise type, the farmed pigs are guided to reduce exercise; If the food analysis result is abnormal, the food ratio improvement points of the food ratio data are analyzed based on the target growth model, and prompt information corresponding to the ratio improvement points is output.

6. The pig breeding method according to claim 5, characterized in that: The step of analyzing the abnormal points of the emotional features based on the target growth model and outputting prompt information corresponding to the abnormal points includes: Analyzing abnormal points of the emotional characteristics based on the target growth model to determine whether the abnormal points are abnormal symptoms; If the disease is abnormal, outputting an acquisition request for acquiring biological information corresponding to the disease abnormality; When the biological information obtained based on the acquisition request is received, the biological information is detected based on the target growth model, a detection result is generated, and the detection result is added to the prompt information output corresponding to the abnormal point.

7. An intelligent pig breeding system, characterized in that: The intelligent pig farming system includes: a cloud server, and data collection devices in various regions that are communicatively connected to the cloud server; The cloud server is pre-deployed with pig growth models corresponding to various regions; The data acquisition device at least includes an image acquisition device, a sound acquisition device, a weight sensor installed in the pig house, and a motion sensor and a body fat sensor installed on the farmed pigs; The data collection device in each region transmits the collected breeding growth data to the cloud server; The cloud server also includes a memory, a processor, and a control program stored in the memory and executable on the processor. When the control program is executed by the processor, the steps of the intelligent pig farming method as described in any one of claims 1 to 6 are implemented.

8. A readable storage medium, characterized in that: The readable storage medium stores a control program, which, when executed by a processor, implements the steps of the intelligent pig farming method according to any one of claims 1 to 6.

Images