An automatic feeding auxiliary monitoring method and system for pig houses

Abstract

The present invention belongs to the technical field of data processing, and proposes a method and system for automatically feeding and assisting monitoring in a pigsty. Specifically: First, an RFID tag system is arranged in the pigsty to identify the feeding unit in real time and read the tag distance. The feeding state is judged by the tag distance. Then, the total feeding duration is obtained through the feeding state of the pigs and the feeding deviation is calculated. The feeding frequency is obtained through the feeding state of the pigs. Subsequently, the strategy adaptation index is calculated according to the feeding deviation and feeding frequency of each pig in the same feeding unit, and the adaptability of the pigs to the automatic feeding strategy is judged through the strategy adaptation index. Finally, the pigs with excessive or insufficient herd adaptation are transferred out of the original feeding group, effectively quantifying the degree of repulsion between the feeding behaviors of different pigs in the same pigsty after the automatic feeding system is put into use in the pigsty, making the growth and development of each pig more uniform, so as to achieve the effect of improving the overall breeding quality.

Description

Technical Field

[0001] The present invention belongs to the technical field of automated breeding, and particularly relates to a method and system for automatically feeding and assisting in monitoring a pigsty. Background Art

[0002] Automatic feeding systems have been popularized and recognized in the field of pigsty breeding. Existing feeding systems usually allocate feed uniformly in stages based on the overall feeding needs of the pig group. However, for the breeding of smaller individual chickens and ducks in the pigsty, there are significant individual differences in the pigsty. The weight, health status, and feeding behavior of each pig are significantly different. This overall-based feeding mode leads to problems of feed waste and feeding efficiency. Especially in large-scale pigsties, the system needs to manage hundreds or thousands of pigs simultaneously. How to quickly process a large amount of data and make accurate feeding decisions under limited computing resources is very important. Currently, in this field, the method of multi-modal data fusion combined with individual identification is generally used to scientifically deduce the feeding amount of each pig, so as to dynamically decide the type and amount of feed to be fed according to the environment and the growth stage of the pig, and form feeding groups for each pig according to the feeding strategy to improve the feeding efficiency of the pigsty. However, this process often focuses on the grouping ability of pigs with the same type of feeding strategy, while ignoring the differences in the feeding efficiency of individual pigs. As a result, pigs with lower feeding efficiency in the same feeding group are in a relatively disadvantaged position in the existing feeding strategy for a long time, and their growth rate and health are affected, or pigs with higher feeding efficiency are in a relatively advantageous position in the existing feeding strategy for a long time and reduce the feeding efficiency of other pigs. This difference in feeding efficiency is caused by differences in feeding habits or personality behaviors between individual pigs. Therefore, there is an urgent need for a method and system for automatically feeding and assisting in monitoring a pigsty to identify pigs with specific feeding efficiency. Summary of the Invention

[0003] The purpose of the present invention is to provide a method and system for automatically feeding and assisting in monitoring a pigsty to solve one or more technical problems in the prior art and at least provide a beneficial choice or creation condition.

[0004] To achieve the above object, according to one aspect of the present invention, there is provided a method for automatically feeding and assisting in monitoring a pigsty, the method comprising the following steps:

[0005] S100, arranging an RFID tag system in the pigsty to identify the breeding unit in real time and read the tag distance;

[0006] S200, judging the feeding status through the tag distance;

[0007] S300, obtaining the total feeding duration through the feeding status of the pigs and calculating the feeding deviation, and obtaining the feeding frequency through the feeding status of the pigs;

[0008] S400. Calculate the strategy adaptation index based on the feeding deviation and feeding frequency of each pig in the same feeding unit.

[0009] S500. Judge the adaptability of pigs to the automatic feeding strategy through the strategy adaptation index.

[0010] Furthermore, in step S100, the method of arranging the RFID tag system in the pigsty to identify the feeding unit in real time and read the tag distance is as follows: The RFID tag system includes RFID tags and RFID readers.

[0011] Define each pen in the pigsty as a feeding unit. Each feeding unit includes several pigs and a pig feeder.

[0012] The RFID tags are installed on each pig in the pigsty. The installation position of the RFID tag is at the root of the pig's ear. The RFID reader is installed at the bottom of the pig feeder.

[0013] The distance between any pig in the feeding unit and the RFID tag and the RFID reader is defined as the tag distance.

[0014] Among them, the feeding unit is a feeding group established through a neural network model or a machine learning model. The feeding habits of each pig in the same feeding group are the same.

[0015] The reason for installing the RFID tag at a position slightly below the root of the pig's ear is that this position is a relatively stable position of the pig's ear, with little movement and not easily squeezed or bumped by other pigs, and at the same time, it has the effect of not being easily loosened.

[0016] The RFID tag contains a unique ID number for identifying the pig, which is used to identify the identity. The RFID tag also stores information such as the age, weight, and health of the pig. The RFID reader can communicate with the RFID tag through the Internet of Things.

[0017] Furthermore, in step S200, the method of judging the feeding state through the tag distance is as follows: Preset a distance as the feeding judgment threshold. When the tag distance of a pig at a certain moment is less than or equal to the feeding judgment threshold, it is judged that the feeding state of the pig is true; otherwise, the feeding state of the pig is false.

[0018] Alternatively, set the feeding judgment threshold as the sum of the depth disdp of the pig feeder and the reference distance dispf between the tip of the pig's snout and the bottom of the pig feeder. The depth range of the pig feeder in the automatic feeding system is between 25 cm and 30 cm, and the reference distance dispf between the tip of the pig's snout and the bottom of the pig feeder ranges from 15 cm to 35 cm. dispf is related to the specific age and weight of the pig, and dispf takes into account the error distance that appears in the actual distance between the tip of the pig's snout and the bottom of the pig feeder during the pig's feeding process; the error distance refers to the range of distance changes allowed for the pig's head-up or feeding pause behavior;

[0019] Since the automatic feeding system establishes different feeding units for each pig in the pigsty according to different feeding strategies, the feeding judgment threshold in the same feeding unit is a shared and identical threshold for the feeding states of each pig.

[0020] Further, in step S300, the total feeding duration is obtained through the pig's feeding state and the feeding deviation is calculated. The method for obtaining the feeding frequency through the pig's feeding state is: when the pig's feeding state is true at several consecutive moments, it is defined that a feeding behavior occurs in the time period composed of these several moments; the size of the time period of the defined feeding behavior is the feeding duration;

[0021] Taking a natural day as a feeding observation point; for the same pig, the total number of feeding behaviors at one feeding observation point is recorded as the feeding frequency, and the sum of the feeding durations of each feeding behavior is the total feeding duration; the average value of the total feeding durations corresponding to each pig in the same feeding unit is the average feeding duration, and the feeding deviation of any pig is the ratio of the total feeding duration of the pig to the average feeding duration.

[0022] Among them, the RFID reader performs distance detection every 1 second to 5 seconds.

[0023] Further, in step S400, the method for calculating the strategy adaptation index according to the feeding deviation and feeding frequency of each pig in the same feeding unit is: set a time period as the monitoring period RETW, RETW ∈ [20, 40] natural days; the feeding deviation and feeding frequency obtained by any pig form the characteristic binary group of the pig, and the characteristic binary groups at each feeding observation point within the current monitoring period form a sequence, and the correlation coefficient of the variables feeding deviation and feeding frequency in the characteristic binary group sequence is calculated and recorded as the first correlation coefficient;

[0024] Among them, the first correlation coefficient refers to the Pearson first correlation coefficient;

[0025] The average value of the feeding deviations of all pigs at the same feeding observation point is taken as the first feeding deviation mean value; for any pig, count the number of feeding observation points CntFV where the feeding deviation of this pig is greater than the first feeding deviation mean value, and the number of feeding observation points CntSV where the feeding deviation is less than the first feeding deviation mean value. If CntFV is greater than or equal to CntSV, record this pig as a strong fitness object, and CntFV is the adaptation monitoring quantity of this pig. Otherwise, record this pig as a weak fitness object, and record CntSV as the adaptation monitoring quantity of this pig;

[0026] Record the ratio of the adaptation monitoring quantity to the number of feeding observation points within the monitoring period as the second correlation coefficient; for any strong fitness object, take the maximum value between the second correlation coefficient and the corresponding first correlation coefficient of this pig as the quasi-correlation coefficient of this pig; for any weak fitness object, take the minimum value between the second correlation coefficient and the corresponding first correlation coefficient of this pig as the quasi-correlation coefficient of this pig;

[0027] The calculation principle of the quasi-correlation coefficient is as follows: Since pigs in the same feeding group will be significantly affected by the feeding behaviors of other pigs, by measuring the feeding level of each pig at the same feeding observation point and taking into account the correlation between the feeding frequency and the feeding level, that is, the influence of feeding habits, the feeding efficiency differences of individual pigs can be accurately quantified, and further, pigs with specific feeding efficiency can be effectively distinguished and identified;

[0028] At the current feeding observation point, record the range and minimum value of the feeding frequencies of all pigs as FSfag and FSmif respectively. Calculate the strategy adaptation index STraid according to the quasi-correlation coefficient and the feeding frequency FEquy:

[0029] ; where exp() is the exponential function with the natural constant e as the base, EAfin is the quasi-correlation coefficient, and FEquy is the feeding frequency.

[0030] Since the above quasi-correlation coefficient is obtained by accurately dividing the feeding level of any pig based on the feeding deviation, and the feeding deviation accurately shows the degree of deviation of the feeding level of the pig from the average feeding level of all pigs in the same feeding group, the feeding competition and feeding adaptation level of pigs within a period of time can be characterized according to the fluctuation range of the feeding deviation of each pig; however, in data scenarios that require accurate identification of individual differences, relying solely on the average level attribute of the feeding deviation for division is too rough, and using all the data information of all individuals for more accurate division is inefficient, resulting in insufficient accuracy of the quasi-correlation coefficient provided for each pig. In order to obtain a more accurate strategy adaptation index, the present invention proposes a more optimal solution;

[0031] Further, in step S400, the method for calculating the strategy adaptation index based on the feeding deviation and feeding frequency of each pig in the same feeding unit is as follows: Set a time period as the monitoring period RETW, where RETW ∈ [21, 56] natural days;

[0032] Taking different feeding observation points as columns and different pigs as rows, and using the feeding deviation and feeding frequency as matrix elements to construct a matrix, denoted as the original matrix. Perform column range normalization transformation on the original matrix, and denote them as the first transformed deviation FSnod and the first transformed frequency FSfqc respectively. When the feeding deviation and feeding frequency are used as matrix elements, they are stored in the form of a binary data structure. Performing column range normalization transformation on the original matrix is to scale the feeding deviation and feeding frequency respectively according to the range (maximum value minus minimum value) in each column of feeding observation points, so that the data in each column are within the same range, that is, the feeding deviation and feeding frequency of each pig in each feeding observation point are within the same range;

[0033] For any feeding monitoring point, construct a coordinate system fncXOY from the first transformed deviation and the first transformed frequency. Respectively take the first transformed deviation and the first transformed frequency of each pig as the coordinate values corresponding to the x-axis and y-axis of the coordinate system to form the monitoring coordinates of the pig. Perform average-linkage hierarchical clustering on the monitoring coordinates of all pigs. Set the number of clusters as KClst, define the centroid of the cluster as the initial cluster seed, and sort each cluster according to the ascending order of the Euclidean distance between the initial cluster seed and the origin. Denote the serial number of the cluster sorting as the cluster order value. Among them, the average-linkage hierarchical clustering is implemented using the hclust function in the R software, and the origin refers to the origin of the coordinate system fncXOY. Write the cluster order values of the clusters where the pigs are located at each feeding monitoring point into a sequence, denoted as the cluster value sequence;

[0034] The calculation principle of the cluster value sequence is: By effectively using all the information of the feeding deviation and feeding frequency of each pig, separate the pigs with different feeding habits, and further capture the characteristics of the pigs with the same feeding habit in a small group, so as to accurately locate the unique label of each pig, and finally be able to accurately identify whether it is in a long-term disadvantage or advantage during feeding, providing a reference for the adjustment direction of the subsequent feeding strategy;

[0035] Calculate the frequency of occurrence of each cluster sequence value in the cluster value sequence of each pig and record it as the sequence value frequency. The cluster sequence value corresponding to the maximum sequence value frequency is used as the pointing cluster sequence of the pig. Denote the median value of all first transformation deviations and the median value of all first transformation frequencies of any pig as the second transformation deviation FSmqy and the second transformation frequency FSvia respectively. The second transformation deviation and the second transformation frequency form a binary group, which is denoted as the pointing array. The average array of all pointing arrays under the same pointing cluster sequence is the centroid of the pointing cluster group. The centroid of the pointing cluster group consists of the membership deviation FSmed and the membership frequency FSreq. Denote the Euclidean distance between the pointing array of the pig and the centroid of the pointing cluster group to which it belongs as the feeding adaptation membership degree FEadm. The average array of all pointing arrays under the same pointing cluster sequence means that pigs with the same pointing cluster sequence are selected, and the average value of the second transformation deviations of the corresponding pointing arrays of the obtained pigs, that is, the membership deviation FSmed, and the average value of the second transformation frequencies, that is, the membership frequency FSreq, are calculated respectively. The binary group reconstructed from the obtained average values is the required average array, that is, the centroid of the pointing cluster group.

[0036] The calculation principle of the feeding adaptation membership degree is as follows: after separating and clustering pigs as much as possible by using the feeding behavior characteristic information of pigs within a period of time, the difference between an individual pig and the most representative individual within the same cluster group is refined and calculated, and the membership degree of each pig within the cluster group is effectively quantified, that is, the similarity degree between any pig and the representative pig individual, and further the feeding efficiency specificity of the pig can be measured.

[0037] Calculate the strategy adaptation index STraid of the pig according to the feeding adaptation membership degree, the membership deviation and the membership frequency:

[0038] ; where ln() is the logarithmic function with the natural constant e as the base.

[0039] Beneficial effects: By analyzing the feeding deviation and the feeding frequency, the degree of repulsion between different pigs in the same pigsty after the automatic feeding system is put into use is effectively quantified, thus providing effective mathematical support for identifying pigs with abnormal feeding, and being able to identify pigs with strong feeding ability and pigs with weak feeding ability in the pigsty with the same feeding strategy, thereby reducing the risk of low feeding efficiency caused by individual feeding deviations between pigs during the application of the feeding strategy.

[0040] Further, in step S500, the method for judging the adaptability of pigs to the automatic feeding strategy by the strategy adaptation index is as follows: Define the average value of the strategy adaptation indexes of each pig in the same feeding unit as the adaptation uniformity. When the ratio of the strategy adaptation index of a pig to the adaptation uniformity is greater than the first preset value, and its value is between 1.3 and 1.8, it is determined that the adaptability of the pig belongs to over - adaptation in the feeding group; when the ratio of the strategy adaptation index of a pig to the adaptation uniformity is less than the second preset value, and its value is between 0.75 and 0.55, it is determined that the adaptability of the pig belongs to under - adaptation in the feeding group. Pigs with over - adaptation and under - adaptation in the feeding group are judged as pigs with abnormal feeding.

[0041] When a pig is considered to have over - adaptation in the feeding group, it means that the pig has a high degree of occupation and appropriation of the food put in the current feeding unit, which is likely to reduce the feeding efficiency of other pigs; while when the adaptability belongs to under - adaptation in the feeding group, it is considered that the pig cannot obtain sufficient feeding resources or be fully fed in the feeding unit under the current feeding strategy.

[0042] Further, it also includes step S600 of redistributing the pigs with abnormal feeding to different feeding units. The specific method is as follows: Move the pigs with abnormal feeding out of the current feeding unit, and form new feeding units for the pigs with under - adaptation and over - adaptation in the feeding group respectively for feeding.

[0043] Preferably, all variables not defined in the present invention, if not clearly defined, can be artificial - set thresholds.

[0044] The present invention also provides an auxiliary monitoring system for automatic feeding in a pigsty. The auxiliary monitoring system for automatic feeding in a pigsty includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps in the method for auxiliary monitoring of automatic feeding in a pigsty. The auxiliary monitoring system for automatic feeding in a pigsty can run on computing devices such as desktop computers, laptop computers, palmtop computers, and cloud data centers. The operable system can include, but is not limited to, a processor, a memory, and a server cluster. The processor executes the computer program and runs in the following units of the system:

[0045] A tag distance reading unit, used to arrange an RFID tag system in the pigsty to identify the feeding unit in real - time and read the tag distance;

[0046] A state judgment unit, used to judge the feeding state by the tag distance;

[0047] A dynamic merging unit, used to obtain the total feeding duration through the feeding state of pigs and calculate the feeding deviation, and obtain the feeding frequency through the feeding state of pigs;

[0048] A strategy adaptation analysis unit for calculating a strategy adaptation index according to the feeding deviation and feeding frequency of each pig in the same feeding unit;

[0049] An adaptability judgment unit for judging the adaptability of pigs to the automatic feeding strategy through the strategy adaptation index;

[0050] The beneficial effects of the present invention are as follows : The present invention provides a method and system for auxiliary monitoring of automatic feeding in a pigsty. By analyzing the feeding deviation and feeding frequency, it effectively quantifies the degree of repulsion between the feeding behaviors of different pigs in the same pigsty after the automatic feeding system is put into use in the pigsty, thereby providing effective mathematical support for identifying pigs with abnormal feeding. It can identify pigs with strong feeding ability and pigs with weak feeding ability in pigsties with the same feeding strategy, thereby reducing the risk of low feeding efficiency caused by individual feeding deviations between pigs during the application of the feeding strategy. By using RFID technology and an automated system to monitor and analyze the feeding behaviors of the pig group, the efficiency and accuracy of the monitoring process are greatly improved. On the premise of ensuring the breeding cost, the breeding is made more scientific and efficient. At the same time, the problems of feed waste and uneven distribution are avoided, and the growth and development of each pig are made more uniform, so as to achieve the purpose of improving the overall breeding quality. Brief Description of the Drawings

[0051] By describing the embodiments shown in the accompanying drawings in detail, the above and other features of the present invention will become more obvious. The same reference numerals in the drawings of the present invention represent the same or similar elements. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings. In the drawings:

[0052] Figure 1 Shown is a flowchart of a method for auxiliary monitoring of automatic feeding in a pigsty;

[0053] Figure 2 Shown is a structural diagram of a system for auxiliary monitoring of automatic feeding in a pigsty. Detailed Embodiments

[0054] The following will clearly and completely describe the concept, specific structure and technical effects of the present invention in combination with the embodiments and the drawings to fully understand the purpose, solution and effects of the present invention. It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0055] As Figure 1 Shown is a flowchart of a method for auxiliary monitoring of automatic feeding in a pigsty. The following will be combined with Figure 1To describe an automatic feeding assistance monitoring method for pig houses according to an embodiment of the present invention, the method includes the following steps:

[0056] Example 1

[0057] S100, Arrange an RFID tag system in the pig house to identify the feeding unit in real time and read the tag distance;

[0058] S200, Judge the feeding status through the tag distance;

[0059] S300, Obtain the total feeding duration through the feeding status of the pigs and calculate the feeding deviation, and obtain the feeding frequency through the feeding status of the pigs;

[0060] S400, Calculate the strategy adaptation index according to the feeding deviation and feeding frequency of each pig in the same feeding unit;

[0061] S500, Judge the adaptability of the pigs to the automatic feeding strategy through the strategy adaptation index;

[0062] Further, in step S100, the method of arranging an RFID tag system in the pig house to identify the feeding unit in real time and read the tag distance is: The RFID tag system includes an RFID tag and an RFID reader;

[0063] Define each pen in the pig house as a feeding unit, and each feeding unit includes several pigs and a pig feeder;

[0064] The RFID tags are installed on each pig in the pig house, and the installation position of the RFID tag is at the root of the pig's ear. The RFID reader is installed at the bottom of the pig feeder;

[0065] The distance between the RFID tag corresponding to any pig in the feeding unit and the RFID reader is defined as the tag distance.

[0066] Further, in step S200, the method of judging the feeding status through the tag distance is: Preset a distance as the feeding judgment threshold. When the tag distance of a pig at a certain moment is less than or equal to the feeding judgment threshold, it is judged that the feeding status of the pig is true, otherwise the feeding status of the pig is false.

[0067] Further, in step S300, the method of obtaining the total feeding duration through the feeding status of the pigs and calculating the feeding deviation, and obtaining the feeding frequency through the feeding status of the pigs is: When the feeding status of a pig is true at several consecutive moments, it is defined that a feeding behavior occurs in the time period composed of these several moments; Define the size of the time period of the feeding behavior as the feeding duration;

[0068] Take one natural day as an eating observation point; for the same pig, the total number of eating behaviors at one eating observation point is recorded as the eating frequency, and the sum of the eating durations of each eating behavior is the total eating duration; the average value of the total eating durations corresponding to each pig in the same breeding unit is the average eating duration, and the eating deviation of any pig is the ratio of the total eating duration of this pig to the average eating duration.

[0069] Further, in step S400, the method for calculating the strategy adaptation index according to the eating deviations and eating frequencies of each pig in the same breeding unit is as follows: Set a time period as the monitoring period RETW, with a value of 30 natural days; the eating deviation and eating frequency obtained by any pig form the characteristic binary group of this pig. The characteristic binary groups at each eating observation point within the current monitoring period form a sequence, and the correlation coefficient between the variable eating deviation and eating frequency in the characteristic binary group sequence is calculated and recorded as the first correlation coefficient.

[0070] Take the average value of the eating deviations of all pigs at the same eating observation point as the first eating deviation mean; for any pig, count the number of eating observation points CntFV where the eating deviation of this pig is greater than the first eating deviation mean, and the number of eating observation points CntSV where the eating deviation is less than the first eating deviation mean. If CntFV is greater than or equal to CntSV, then record this pig as a strong fitness object, and CntFV is the adaptation monitoring quantity of this pig; otherwise, record this pig as a weak fitness object, and record CntSV as the adaptation monitoring quantity of this pig.

[0071] Record the ratio of the adaptation monitoring quantity to the number of eating observation points within the monitoring period as the second correlation coefficient; for any strong fitness object, take the maximum value between the second correlation coefficient and the first correlation coefficient corresponding to this pig as the quasi-correlation coefficient of this pig; for any weak fitness object, take the minimum value between the second correlation coefficient and the first correlation coefficient corresponding to this pig as the quasi-correlation coefficient of this pig.

[0072] At the current eating observation point, record the range and minimum value of the eating frequencies of all pigs as FSfag and FSmif respectively. Calculate the strategy adaptation index STraid according to the quasi-correlation coefficient and the eating frequency FEquy:

[0073] ; where exp() is the exponential function with the natural constant e as the base, EAfin is the quasi-correlation coefficient, and FEquy is the eating frequency.

[0074] Further, in step S500, the method for judging the adaptability of pigs to the automatic feeding strategy by the strategy adaptation index is as follows: Define the average value of the strategy adaptation indexes of each pig in the same feeding unit as the adaptation uniformity. When the ratio of the strategy adaptation index of a pig to the adaptation uniformity is greater than 1.3, it is determined that the adaptability of the pig belongs to over - adaptation in the feeding group; when the ratio of the strategy adaptation index of a pig to the adaptation uniformity is less than 0.75, it is determined that the adaptability of the pig belongs to under - adaptation in the feeding group. Pigs with over - adaptation and under - adaptation in the feeding group are judged as pigs with abnormal feeding.

[0075] Further, it also includes step S600 of re - distributing the pigs with abnormal feeding to different feeding units. The specific method is as follows: Move the pigs with abnormal feeding out of the current feeding unit. Pigs with under - adaptation and over - adaptation in the feeding group are respectively grouped into new feeding units for feeding, and the new feeding units adopt the feeding strategy of the feeding unit from which the pigs are removed.

[0076] Example 2

[0077] Example 2 adopts the same method for auxiliary monitoring of automatic feeding in pig houses as in Example 1. The difference is that in step S400, the method for calculating the strategy adaptation index based on the feeding deviation and feeding frequency of each pig in the same feeding unit is as follows: Set a time period as the monitoring time period RETW, and the value is 30 natural days;

[0078] Taking different feeding observation points as columns and different pigs as rows, and using the feeding deviation and feeding frequency as matrix elements to construct a matrix, denoted as the original matrix. Perform column range normalization transformation on the original matrix, and denote them as the first - transformed deviation FSnod and the first - transformed frequency FSfqc respectively;

[0079] For any feeding monitoring point, construct a coordinate system fncXOY from the first - transformed deviation and the first - transformed frequency. Respectively take the first - transformed deviation and the first - transformed frequency of each pig as the coordinate values corresponding to the x - axis and y - axis of the coordinate system to form the monitoring coordinates of the pig. Perform average - linkage hierarchical clustering on the monitoring coordinates of all pigs. Set the number of clusters as KClst, define the centroid of the cluster as the initial cluster seed, sort each cluster in ascending order according to the Euclidean distance between the initial cluster seed and the origin, and denote the serial number of the cluster sorting as the cluster order value. Write the cluster order values of the clusters where the pigs are located at each feeding monitoring point into a sequence, denoted as the cluster value sequence;

[0080] Calculate the frequency of occurrence of each cluster order value in the cluster value sequence of each pig and record it as the order value frequency. The cluster order value corresponding to the maximum order value frequency is used as the pointing cluster order of the pig. Denote the median value of all the first transformation deviations and the median value of all the first transformation frequencies of any pig as the second transformation deviation FSmqy and the second transformation frequency FSvia respectively. The second transformation deviation and the second transformation frequency form a binary group and are denoted as the pointing array. The average array of all the pointing arrays under the same pointing cluster order is the centroid of the pointing cluster group, and the centroid of the pointing cluster group consists of the membership deviation FSmed and the membership frequency FSreq. Denote the Euclidean distance between the pointing array of the pig and the centroid of the pointing cluster group of its belonging pointing cluster order as the feeding adaptation membership degree FEadm.

[0081] Calculate the strategy adaptation index STraid of the pig according to the feeding adaptation membership degree, the membership deviation and the membership frequency:

[0082] ; where ln() is the logarithmic function with the natural constant e as the base.

[0083] An automatic feeding auxiliary monitoring system for a pigsty provided by an embodiment of the present invention, as Figure 2 shown in the structural diagram of an automatic feeding auxiliary monitoring system for a pigsty of the present invention. An automatic feeding auxiliary monitoring system of this embodiment includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above-mentioned embodiment of the automatic feeding auxiliary monitoring method for a pigsty are implemented.

[0084] The system includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it runs in the following units of the system:

[0085] A tag distance reading unit, used to arrange an RFID tag system in the pigsty to identify the feeding unit in real time and read the tag distance;

[0086] A state judgment unit, used to judge the feeding state through the tag distance;

[0087] A dynamic merging unit, used to obtain the total feeding duration through the feeding state of the pig and calculate the feeding deviation, and obtain the feeding frequency through the feeding state of the pig;

[0088] A strategy adaptation analysis unit, used to calculate the strategy adaptation index according to the feeding deviation and the feeding frequency of each pig in the same feeding unit;

[0089] An adaptability judgment unit, used to judge the adaptability of the pig to the automatic feeding strategy through the strategy adaptation index;

[0090] The described automatic feeding auxiliary monitoring system for pig houses can run on computing devices such as desktop computers, laptop computers, palmtop computers, and cloud servers. The described automatic feeding auxiliary monitoring system for pig houses, the operable system may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the above examples are only examples of an automatic feeding auxiliary monitoring system for pig houses, and do not constitute a limitation on an automatic feeding auxiliary monitoring system for pig houses. It may include more or fewer components than the examples, or combine certain components, or different components. For example, the automatic feeding auxiliary monitoring system for pig houses may also include input / output devices, network access devices, buses, etc.

[0091] The so-called processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the operating system of the automatic feeding auxiliary monitoring system for pig houses, and uses various interfaces and lines to connect all parts of the operable system of the automatic feeding auxiliary monitoring system for pig houses.

[0092] The memory can be used to store the computer programs and / or modules. The processor realizes various functions of the automatic feeding auxiliary monitoring system for pig houses by running or executing the computer programs and / or modules stored in the memory, and by calling the data stored in the memory. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the mobile phone (such as audio data, phone book, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one magnetic disk storage device, flash device, or other volatile solid-state storage devices.

[0093] Although the description of the present invention has been rather detailed and particularly describes several of the described embodiments, it is not intended to be limited to any of these details or embodiments or any particular embodiment, so as to effectively cover the intended scope of the present invention. In addition, the present invention is described above in terms of embodiments foreseeable by the inventors for the purpose of providing a useful description, and non-substantive modifications to the present invention that are not currently foreseeable may still represent equivalent modifications of the present invention.

Claims

1. An automatic feeding auxiliary monitoring method for pig houses, characterized in that, The method includes the following steps: S100. Arrange an RFID tag system in the pigsty to identify the feeding unit in real time and read the tag distance; S200. Judge the feeding state according to the tag distance. The judgment method is that when the tag distance of a pig at a certain moment is less than or equal to the preset distance, it is judged that the feeding state of the pig is true, otherwise the feeding state of the pig is false; S300. Obtain the total feeding duration and calculate the feeding deviation through the feeding state of the pig, and obtain the feeding frequency through the feeding state of the pig; wherein, the feeding deviation and the feeding frequency take a natural day as a feeding observation point; the total number of feeding behaviors of the same pig at one feeding observation point is recorded as the feeding frequency, and the sum of the feeding durations of each feeding behavior is the total feeding duration; the average value of the total feeding durations corresponding to each pig in the same feeding unit is the average feeding duration, and the feeding deviation of any pig is the ratio of the total feeding duration of the pig to the average feeding duration; S400. Calculate the strategy adaptation index according to the feeding deviation and feeding frequency of each pig in the same feeding unit. Specifically: set a time period as the monitoring period RETW, RETW ∈ [20, 40] natural days; the feeding deviation and feeding frequency obtained by any pig form the characteristic binary group of the pig, and the characteristic binary groups at each feeding observation point within the current monitoring period form a sequence, and calculate the correlation coefficient between the feeding deviation and the feeding frequency in the characteristic binary group sequence and record it as the first correlation coefficient; the average value of the feeding deviations of all pigs at the same feeding observation point is used as the first feeding deviation mean value; for any pig, count the number of feeding observation points CntFV where the feeding deviation of the pig is greater than the first feeding deviation mean value, and the number of feeding observation points CntSV where the feeding deviation is less than the first feeding deviation mean value. If CntFV is greater than or equal to CntSV, record the pig as a strong fitness object, and CntFV is the adaptation monitoring quantity of the pig, otherwise record the pig as a weak fitness object, and record CntSV as the adaptation monitoring quantity of the pig; record the ratio of the adaptation monitoring quantity to the number of feeding observation points within the monitoring period as the second correlation coefficient; for any strong fitness object, take the maximum value of the second correlation coefficient and the first correlation coefficient corresponding to the pig as the quasi-correlation coefficient of the pig; for any weak fitness object, take the minimum value of the second correlation coefficient and the first correlation coefficient corresponding to the pig as the quasi-correlation coefficient of the pig; at the current feeding observation point, record the range and minimum value of the feeding frequencies of all pigs as FSfag and FSmif respectively, and calculate the strategy adaptation index of the pig according to the quasi-correlation coefficient, feeding frequency, FSfag and FSmif; S500. Judge the adaptability of the pig to the automatic feeding strategy through the strategy adaptation index.

2. An automatic feeding auxiliary monitoring method for pig houses, characterized in that, The method includes the following steps: S100. Arrange an RFID tag system in the pigsty to identify the feeding unit in real time and read the tag distance; S200. Judge the feeding state according to the tag distance. The judgment method is that when the tag distance of a pig at a certain moment is less than or equal to the preset distance, it is judged that the feeding state of the pig is true, otherwise the feeding state of the pig is false; S300. Obtain the total feeding duration based on the feeding status of pigs and calculate the feeding deviation, and obtain the feeding frequency based on the feeding status of pigs. Among them, the feeding deviation takes one natural day as one feeding observation point. The total number of feeding behaviors of the same pig under one feeding observation point is recorded as the feeding frequency, and the sum of the feeding durations of each feeding behavior is the total feeding duration. The average value of the total feeding durations corresponding to each pig in the same feeding unit is the average feeding duration, and the feeding deviation of any pig is the ratio of the total feeding duration of the pig to the average feeding duration. S400. Calculate the strategy adaptation index according to the feeding deviations and feeding frequencies of each pig in the same feeding unit. Specifically, set a time period as the monitoring time period RETW, where RETW ∈ [21, 56] natural days. Taking different feeding observation points as columns and different pigs as rows, construct a matrix with the feeding deviation and the feeding frequency as matrix elements, denoted as the original matrix. Perform column range normalization transformation on the original matrix, and denote them as the first transformation deviation FSnod and the first transformation frequency FSfqc respectively. For any feeding monitoring point, construct a coordinate system fncXOY from the first transformation deviation and the first transformation frequency. Respectively take the first transformation deviation and the first transformation frequency of each pig as the coordinate values corresponding to the x-axis and the y-axis of the coordinate system to form the monitoring coordinates of the pig. Perform average-linkage hierarchical clustering on the monitoring coordinates of all pigs, set the number of clusters as KClst, define the centroid of the cluster as the initial cluster seed, sort each cluster according to the ascending order of the Euclidean distance between the initial cluster seed and the origin, and denote the serial number of the cluster sorting as the cluster order value. Write the cluster order values of each pig in each feeding monitoring point into a sequence, denoted as the cluster value sequence. Calculate the frequency of occurrence of each cluster order value in the cluster value sequence of each pig and denote it as the order value frequency. The cluster order value corresponding to the maximum order value frequency is used as the pointing cluster order of the pig. Denote the median value of all the first transformation deviations and the median value of all the first transformation frequencies of any pig as the second transformation deviation FSmqy and the second transformation frequency FSvia respectively. The second transformation deviation and the second transformation frequency form a binary group, denoted as the pointing array. The average array of all the pointing arrays under the same pointing cluster order is the centroid of the pointing cluster group, and the centroid of the pointing cluster group consists of the membership deviation FSmed and the membership frequency FSreq. Denote the Euclidean distance between the pointing array of the pig and the centroid of the pointing cluster group to which it belongs as the feeding adaptation membership degree FEadm. Calculate the strategy adaptation index of the pig according to the feeding adaptation membership degree, the membership deviation and the membership frequency, the first transformation deviation, the first transformation frequency, the second transformation deviation, and the second transformation frequency. S500. Judge the adaptability of pigs to the automatic feeding strategy through the strategy adaptation index.

3. A method for automatically feeding and auxiliary monitoring of a pigsty according to claim 1 or 2, characterized in that, In step S100, arrange an RFID tag system in the pigsty. The method for real-time identifying the feeding unit and reading the tag distance is as follows: The RFID tag system includes RFID tags and RFID readers. Define each pen in the pigsty as a feeding unit. Each feeding unit includes several pigs and a pig feeder respectively. RFID tags are installed on each pig in the pigsty. The installation position of the RFID tag is at the root of the pig's ear, and the RFID reader is installed at the bottom of the pig feeder. The distance between the RFID tag corresponding to any pig in the feeding unit and the RFID reader is defined as the tag distance.

4. A method for automatically feeding and auxiliary monitoring of a pigsty according to claim 1 or 2, characterized in that, In step S300, the total feeding duration is obtained through the feeding state of the pig and the feeding deviation is calculated. Obtaining the feeding frequency through the feeding state of the pig further includes: when the feeding state of the pig is true at several consecutive moments, it is defined that a feeding behavior occurs in the time period composed of these several moments; the size of the time period of the feeding behavior is defined as the feeding duration.

5. The automatic feeding auxiliary monitoring method for pig houses according to claim 1, wherein In step S500, the method for judging the adaptability of the pig to the automatic feeding strategy by the strategy adaptation index is: defining the average value of the strategy adaptation indexes of each pig in the same feeding unit as the adaptation average. When the ratio of the strategy adaptation index of the pig to the adaptation average is greater than the first preset value, and its value is between 1.3 and 1.8, it is determined that the adaptability of the pig belongs to over-adaptation to the feeding group; when the ratio of the strategy adaptation index of the pig to the adaptation average is less than the second preset value, and its value is between 0.75 and 0.55, it is determined that the adaptability of the pig belongs to under-adaptation to the feeding group. The pigs with over-adaptation to the feeding group and under-adaptation to the feeding group are judged as pigs with abnormal feeding.

6. The automatic feeding auxiliary monitoring method for pig houses according to claim 5, characterized in that, It further includes step S600 of reassigning the feeding units for the pigs with abnormal feeding. The specific method is: moving the pigs with abnormal feeding out of the current feeding unit, and forming new feeding units for feeding the pigs with under-adaptation to the feeding group and the pigs with over-adaptation to the feeding group respectively.

7. An automatic feeding auxiliary monitoring system for pig houses, characterized in that, The automatic feeding auxiliary monitoring system for the pigsty includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps in the automatic feeding auxiliary monitoring method for the pigsty described in any one of claims 1-6. The automatic feeding auxiliary monitoring system for the pigsty runs on computing devices such as desktop computers, laptop computers, palmtop computers, and cloud data centers.

Images