Live pig excretion behavior judgment method and system based on behavior monitoring

Abstract

The invention relates to the technical field of live pig monitoring, and discloses a live pig excretion behavior judgment method based on behavior monitoring, which comprises the following steps of: firstly, installing a monitoring equipment real-time positioning device in a specified to-be-monitored live pig house, wearing an RFID (Radio Frequency Identification) tag on each pig, and then judging the excretion behavior, the temperature and the urine and excrement of the pig through a live pig behavior analysis model; if various data are abnormal, information is fed back to the main controller module, the main controller module drives the corresponding safety early warning module, and if no abnormal behavior exists, the information is imported into the information storage module for temporary storage. According to the live pig excretion behavior judgment system based on behavior monitoring, the main controller module is arranged, other modules are controlled in a wireless connection mode, various data of live pigs can be mastered in time, all devices are accurately driven to work cooperatively, and the system is more intelligent; image data and information of live pigs in a real-time positioning module are collected, so that a database of the live pigs is conveniently formed.

Description

Technical Field

[0001] The present invention relates to the technical field of pig monitoring, and in particular to a method and system for determining the excretion behavior of pigs based on behavior monitoring. Background Art

[0002] Live pigs are living pigs. They are a general term for domestic pigs that have not been slaughtered except breeding pigs. Pigs are omnivorous animals. Pigs generally refer to livestock. Raw pork is edible and its skin can be made into leather. Pigs have fat bodies and short limbs, are docile in nature, have strong adaptability, are easy to raise, and reproduce quickly. They come in colors such as black, white, maroon, or black and white.

[0003] The rapid development of information science and technology is having a profound impact on the traditional livestock farming methods. In recent years, the concept of "precision farming" is gaining more and more attention, and behavior monitoring is the main physiological indicator for observing the survival and health of animals such as pigs, and is also a means of precision farming. The traditional method of monitoring animal behavior activities is mostly to monitor the pens through monitoring equipment 24 hours a day, and then manually judge the excretion status of pigs. This makes the behavior monitoring of pigs low in accuracy, high in labor consumption, and poor in monitoring effect. It is impossible to prevent and isolate sick pigs in time, which is easy to cause a large number of pigs to be sick, thereby reducing the number of pigs on hand. Therefore, a method and system for determining pig excretion behavior based on behavior monitoring is proposed to solve the above-mentioned problems. Summary of the invention

[0004] 1. Technical issues to be solved

[0005] In view of the shortcomings of the prior art, the present invention provides a method and system for determining the excretion behavior of pigs based on behavior monitoring, which has the advantages of efficient, rapid and highly automated behavior judgment, and solves the problem that most traditional methods for monitoring animal behavior activities are to monitor the pens through monitoring equipment 24 hours a day, and then manually determine the excretion status of pigs, which results in low accuracy in pig behavior monitoring, high labor consumption, poor monitoring effect, and inability to prevent and isolate sick pigs in time, which easily causes large-scale pig losses and thus reduces the number of pigs on hand.

[0006] (II) Technical solution

[0007] In order to achieve the above-mentioned purpose of efficient, rapid and highly automated behavior judgment, the present invention provides the following technical solution: a method for determining the excretion behavior of pigs based on behavior monitoring, characterized in that it comprises the following steps:

[0008] Step 1: First, install the real-time positioning device of the monitoring equipment in the designated pig pen to be monitored;

[0009] Step 2: Number all pigs in the pen in sequence and attach RFID tags to them;

[0010] Step 3: Use the pig behavior analysis model to judge the pig's excretion behavior, temperature, and defecation;

[0011] Step 4: The image data of each pig is imported into the behavior analysis model through the monitoring equipment to make behavioral judgments, where abnormal movements include the pig's circling, sudden advance and retreat, rolling, etc.

[0012] Step 5: Determine the excretion behavior of the pigs. If there is any abnormality, the abnormal information will be fed back to the main controller module, and the main controller module will drive the early warning module to issue an alarm;

[0013] Step 6: If there is no abnormal behavior, the information will be imported into the information storage module for temporary storage and automatically deleted after expiration;

[0014] Step 7: The color and shape of each pig's feces and urine are imported into the behavior judgment model through the data acquisition model. If there is any abnormality in the feces and urine, the information will be fed back to the main controller module, and the main controller module will drive the early warning module to sound an alarm. If there is no abnormality, repeat step 6.

[0015] Step 8: Import the temperature of each pig into the behavior analysis model. When the temperature rises or drops abnormally, the abnormal information will be fed back to the main controller module and the early warning module will issue an alarm. If there is no abnormality, repeat step 6.

[0016] Preferably, the RFID tag records basic information of the pig, such as date of birth, breed information, earring wearing date, pig farm location, pig pen, quarantine and immunization information, etc.

[0017] Preferably, the real-time positioning system adopts Ubiquitous real-time positioning technology sensing equipment.

[0018] Preferably, the body temperature of the pigs is between 37.5-38°C, and the temperature difference between morning and evening is within one degree.

[0019] Preferably, the RFID tag transmits a series of short wave signals at a frequency of 6 to 8 GHz.

[0020] The pig behavior analysis model training step in step 3 also includes:

[0021] Step 1: Obtain a sample set and establish a pig sample library, and use the pig's behavior, temperature, and urine and feces shape as labels;

[0022] Step 2: Establish the initial CNN convolutional neural network to extract labels;

[0023] Step 3: Establish student model and teacher model respectively and perform knowledge distillation;

[0024] Step 4: Import the data sample label of a single pig into the teacher model to obtain the first sample feature data;

[0025] Step 5: label the data sample of a single pig with the student model to obtain the second sample feature data;

[0026] Step 6: Determine the loss value of the first sample data and the second sample data, and adjust the student model;

[0027] Step 7 imports the data of each pig in the sample set into the adjusted student model, trains the student model, and thus generates a pig behavior analysis model.

[0028] Preferably, the pig excretion behavior determination system includes a main controller module, which controls other modules through wireless connection;

[0029] The data acquisition module collects information including image data and each pig in the real-time positioning module, and imports the information into the pig behavior judgment module;

[0030] The pig behavior judgment module can make real-time judgments on the pig's excretion behavior, the shape and color of urine and feces, and the temperature of the pig through a behavior analysis model. When the behavior is abnormal, the information can be fed back to the main controller module, and the main controller module drives the safety warning module to make the buzzer sound an alarm. If there is no abnormality, the information will be imported into the data storage module for temporary storage.

[0031] Preferably, the real-time positioning module is wirelessly connected to the RFID tag.

[0032] (III) Beneficial effects

[0033] Compared with the prior art, the present invention provides a method and system for determining the excretion behavior of pigs based on behavior monitoring, which has the following beneficial effects:

[0034] 1. The method for determining the excretion behavior of live pigs based on behavior monitoring can monitor the images of the pig pen in real time and accurately locate each pig by setting step one. By setting step two, the RFID tag can store basic information such as the birth date, breed information, earring wearing date, location of the pig farm, pig pen, quarantine and immunization information of the pigs. When abnormal pigs are found, they can be locked quickly and accurately with higher efficiency. By setting step three, a live pig behavior judgment model based on a convolutional neural network is established, which can more efficiently judge abnormal behaviors and reduce human interference. The above model has a learning function and can be continuously improved, thereby ensuring accurate judgment of abnormal behaviors of pigs. By setting steps four, five and seven, judgments are made from multiple aspects such as abnormal behaviors of pigs, color of feces and urine, and changes in body temperature of pigs, so that the judgment of live pig behavior is more accurate and efficient, and prevention and control can be achieved as soon as possible to avoid large-scale infection.

[0035] 2. The pig excretion behavior judgment system based on behavior monitoring, by setting up a main controller module, controls other modules through wireless connection, can timely grasp various data of pigs, and accurately drive various devices to work together, which is more intelligent. By setting up a data acquisition module, information of each pig in the image data and real-time positioning module is collected, so as to form a database of pigs and supplement the database of the behavior judgment model to ensure more accurate and efficient judgment. By setting up a pig behavior judgment module, the pig behavior judgment module can make real-time judgments on the pig's excretion behavior, the shape and color of urine and feces, and the temperature of the pig through the behavior analysis model. When the behavior is abnormal, the information can be fed back to the main controller module, and the main controller module drives the safety warning module to make the buzzer sound an alarm. If there is no abnormality, the information is imported into the data storage module for temporary storage. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 This is a schematic diagram of the method for determining the excretion behavior of pigs of the present invention;

[0037] Figure 2 This is a schematic diagram of the pig behavior analysis model training method of the present invention;

[0038] Figure 3 This is a schematic diagram of the pig excretion behavior determination system of the present invention; DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] See also Figure 1-3 A method for determining the excretion behavior of pigs based on behavior monitoring comprises the following steps:

[0041] Step 1: First, install the real-time positioning device of the monitoring equipment in the designated pig pen to be monitored;

[0042] Step 2: Number all pigs in the pen in sequence and attach RFID tags to them;

[0043] Step 3: Use the pig behavior analysis model to judge the pig's excretion behavior, temperature, and defecation;

[0044] Step 4: The image data of each pig is imported into the behavior analysis model through the monitoring equipment to make behavioral judgments, where abnormal movements include the pig's circling, sudden advance and retreat, rolling, etc.

[0045] Step 5: Determine the excretion behavior of the pigs. If there is any abnormality, the abnormal information will be fed back to the main controller module, and the main controller module will drive the early warning module to issue an alarm;

[0046] Step 6: If there is no abnormal behavior, the information will be imported into the information storage module for temporary storage and automatically deleted after expiration;

[0047] Step 7: The color and shape of each pig's feces and urine are imported into the behavior judgment model through the data acquisition model. If there is any abnormality in the feces and urine, the information will be fed back to the main controller module, and the main controller module will drive the early warning module to sound an alarm. If there is no abnormality, repeat step 6.

[0048] Step 8: Import the temperature of each pig into the behavior analysis model. When the temperature rises or drops abnormally, the abnormal information will be fed back to the main controller module and the early warning module will issue an alarm. If there is no abnormality, repeat step 6.

[0049] Specifically, the safety warning module is equipped with multiple buzzers with different sounds. Different buzzers are activated according to different behaviors, feces and body temperatures, so that users can judge the different conditions of each pig based on the different sounds.

[0050] exist Figure 1 In the system, the RFID tag records the basic information of the pig, such as the date of birth, breed information, earring wearing date, location of the pig farm, pig pen, quarantine and immunization information, etc.

[0051] Through RFID tags, the situation of each pig can be accurately located, avoiding the problem of not being able to accurately identify each pig during batch breeding, and achieving the goal of rapid positioning and precise treatment to save time and improve efficiency.

[0052] In addition, the real-time positioning system uses Ubi sense's real-time positioning technology sensing device. Ubi sense technology combines multiple wireless communication technologies and advanced positioning algorithms to achieve indoor positioning of people, objects or equipment.

[0053] It also includes that the body temperature of live pigs is between 37.5-38℃, and the temperature difference between morning and evening is within one degree. Through precise temperature preservation, early prevention of pigs' diseases can be achieved to avoid worsening of their disease.

[0054] It also includes that the RFID tag transmits a series of short-wave signals at a frequency of 6 to 8 GHz. The signal of the RFID tag is transmitted to the Ubi sense device to achieve accurate judgment of each pig.

[0055] exist Figure 2 In step 3, the pig behavior analysis model training step also includes:

[0056] Step 1: Obtain a sample set and establish a pig sample library, and use the pig's behavior, temperature, and urine and feces shape as labels;

[0057] Step 2: Establish the initial CNN convolutional neural network to extract labels;

[0058] Step 3: Establish student model and teacher model respectively and perform knowledge distillation;

[0059] Step 4: Import the data sample label of a single pig into the teacher model to obtain the first sample feature data;

[0060] Step 5: label the data sample of a single pig with the student model to obtain the second sample feature data;

[0061] Step 6: Determine the loss value of the first sample data and the second sample data, and adjust the student model;

[0062] Step 7 imports the data of each pig in the sample set into the adjusted student model, trains the student model, and thus generates a pig behavior analysis model.

[0063] exist Figure 3 In the present invention, the pig excretion behavior determination system includes a main controller module, which controls other modules through wireless connection;

[0064] The data acquisition module collects information including image data and each pig in the real-time positioning module, and imports the information into the pig behavior judgment module;

[0065] The pig behavior judgment module can make real-time judgments on the pig's excretion behavior, the shape and color of urine and feces, and the temperature of the pig through the behavior analysis model. When the behavior is abnormal, the information can be fed back to the main controller module, and the main controller module drives the safety warning module to make the buzzer sound an alarm. If there is no abnormality, the information will be imported into the data storage module for temporary storage.

[0066] It also includes that the real-time positioning module is wirelessly connected to the RFID tag.

[0067] In summary, the method and system for determining the excretion behavior of pigs based on behavior monitoring, the main controller module, controls other modules through wireless connection, can timely grasp various data of pigs, and accurately drive various devices to work together, which is more intelligent. By setting up a data acquisition module, information of each pig in the image data and real-time positioning module is collected, so as to form a database of pigs and supplement the database of the behavior judgment model to ensure more accurate and efficient judgment. By setting up a pig behavior judgment module, the pig behavior judgment module can make real-time judgments on the excretion behavior, shape and color of urine and feces, and temperature of pigs through the behavior analysis model. When the behavior is abnormal, the information can be fed back to the main controller module, and the main controller module drives the safety warning module to make the buzzer sound an alarm. If there is no abnormality, the information is imported into the data storage module for temporary storage.

[0068] When in use, the first step is to install the real-time positioning device of the monitoring equipment in the designated pig pen to be monitored, and put an RFID tag on each pig. Then, the pig's excretion behavior, temperature, and urination and defecation are judged through the pig behavior analysis model. If there is any abnormality in the data, the information will be fed back to the main controller module, and the main controller module will drive the corresponding safety warning module. If there is no abnormal behavior, the information will be imported into the information storage module for temporary storage and automatically deleted after expiration.

[0069] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0070] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for determining the excretion behavior of pigs based on behavior monitoring, characterized in that: The steps include: Step 1: First, install the real-time positioning device of the monitoring equipment in the designated pig pen to be monitored; Step 2: Number all pigs in the pen in sequence and attach RFID tags to them; Step 3: Use the pig behavior analysis model to judge the pig's excretion behavior, temperature, and defecation; Step 4: The image data of each pig is imported into the behavior analysis model through the monitoring equipment to make behavioral judgments, where abnormal movements include the pig's circling, sudden advance and retreat, rolling, etc. Step 5: Determine the excretion behavior of the pigs. If there is any abnormality, the abnormal information will be fed back to the main controller module, and the main controller module will drive the early warning module to issue an alarm; Step 6: If there is no abnormal behavior, the information will be imported into the information storage module for temporary storage and automatically deleted after expiration; Step 7: The color and shape of each pig's feces and urine are imported into the behavior judgment model through the data acquisition model. If there is any abnormality in the feces and urine, the information will be fed back to the main controller module, and the main controller module will drive the early warning module to sound an alarm. If there is no abnormality, repeat step 6. Step 8: Import the temperature of each pig into the behavior analysis model. When the temperature rises or drops abnormally, the abnormal information will be fed back to the main controller module and the early warning module will issue an alarm. If there is no abnormality, repeat step 6.

2. A method for determining the excretion behavior of pigs based on behavior monitoring according to claim 1, characterized in that: The RFID tag records the basic information of the pig, such as the birth date, breed information, earring wearing date, pig farm location, pig pen, quarantine and immunization information, etc.

3. The method for determining the excretion behavior of pigs based on behavior monitoring according to claim 1, characterized in that: The real-time positioning system uses Ubisense's real-time positioning technology sensing equipment.

4. The method for determining the excretion behavior of pigs based on behavior monitoring according to claim 1, characterized in that: The body temperature of the pigs is between 37.5-38°C, and the temperature difference between morning and evening is within one degree.

5. The method for determining the excretion behavior of pigs based on behavior monitoring according to claim 1, characterized in that: The RFID tag emits a series of short-wave signals at a frequency of 6 to 8 GHz.

6. The method for determining the excretion behavior of pigs based on behavior monitoring according to claim 1, characterized in that: The pig behavior analysis model training step in step 3 also includes: Step 1: Obtain a sample set and establish a pig sample library, and use the pig's behavior, temperature, and urine and feces shape as labels; Step 2: Establish the initial CNN convolutional neural network to extract labels; Step 3: Establish student model and teacher model respectively and perform knowledge distillation; Step 4: Import the data sample label of a single pig into the teacher model to obtain the first sample feature data; Step 5: label the data sample of a single pig with the student model to obtain the second sample feature data; Step 6: Determine the loss value of the first sample data and the second sample data, and adjust the student model; Step 7 imports the data of each pig in the sample set into the adjusted student model, trains the student model, and thus generates a pig behavior analysis model.

7. A pig excretion behavior determination system based on behavior monitoring, characterized in that: It includes a main controller module, which controls other modules through wireless connection; The data acquisition module collects information including image data and each pig in the real-time positioning module, and imports the information into the pig behavior judgment module; The pig behavior judgment module can make real-time judgments on the pig's excretion behavior, the shape and color of urine and feces, and the temperature of the pig through a behavior analysis model. When the behavior is abnormal, the information can be fed back to the main controller module, and the main controller module drives the safety warning module to make the buzzer sound an alarm. If there is no abnormality, the information will be imported into the data storage module for temporary storage.

8. The pig excretion behavior determination system based on behavior monitoring according to claim 7 is characterized in that: The real-time positioning module is wirelessly connected to the RFID tag.

Images