Auxiliary monitoring method and system for automatic feeding of hog house

Abstract

The invention belongs to the technical field of data processing, and provides an auxiliary monitoring method and system for automatic feeding of a hog house, and the method specifically comprises the steps: firstly, arranging an RFID tag system in the hog house, recognizing a feeding unit in real time, reading a tag distance, and judging a feeding state through the tag distance; the method comprises the following steps: firstly, obtaining a pig feeding state, then obtaining a total feeding duration according to the pig feeding state and calculating a feeding deviation, obtaining a feeding frequency according to the pig feeding state, then calculating a strategy adaptation index according to the feeding deviation and the feeding frequency of each pig in the same feeding unit, and judging the adaptability of the pigs to an automatic feeding strategy according to the strategy adaptation index. Finally, the pigs with over-excitation feeding group adaptation or over-weak feeding group adaptation are called out of the original feeding group, the rejection degree of different pigs in the same pigsty in the feeding behavior after the automatic feeding system is put into the pigsty for use is effectively quantified, growth and development of each pig are more uniform, and therefore the effect of improving the overall breeding quality is achieved.

Description

Technical Field

[0001] The invention belongs to the technical field of automated breeding, and in particular relates to an automatic feeding auxiliary monitoring method and system for a piggery. Background Art

[0002] Automatic feeding systems are generally promoted and recognized in the field of pig house farming. Existing feeding systems are usually based on the overall feeding needs of the pig herd and uniformly distribute feed according to stages. However, in pig houses, the individual differences in pig houses are large, and the weight, health status and eating behavior of each pig are significantly different. This overall feeding mode leads to problems of feed waste and feeding efficiency. Especially in large-scale pig houses, the system needs to manage hundreds or thousands of pigs at the same time. It is very important to quickly process a large amount of data and make accurate feeding decisions under the premise of limited computing resources. At present, this field generally uses multimodal data fusion combined with individual identification methods 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 feed together to improve the feeding efficiency of the pig house. However, this process often focuses on the grouping ability of pigs with the same feeding strategy, while ignoring the differences in feeding efficiency of individual pigs, which results in the pigs with lower feeding efficiency in the same feeding group being at a relative disadvantage in the existing feeding strategy for a long time, and their growth rate and health are affected, or the pigs with higher feeding efficiency are at a relative advantage 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 eating habits or personality and behavior between individual pigs. Therefore, there is an urgent need for an automatic feeding auxiliary monitoring method and system for pig houses to identify pigs with specific feeding efficiency. Summary of the invention

[0003] The purpose of the present invention is to propose a method and system for automatic feeding auxiliary monitoring of pig houses to solve one or more technical problems existing in the prior art and at least provide a beneficial choice or create conditions.

[0004] In order to achieve the above object, according to one aspect of the present invention, a method for automatically monitoring the feeding of a piggery is provided, the method comprising the following steps: S100, deploys RFID tag system in pig house to identify feeding units in real time and read tag distance; S200, judging the eating status by tag distance; S300, obtaining the total eating time according to the eating status of the pigs and calculating the eating deviation, and obtaining the eating frequency according to the eating status of the pigs; S400, calculating the strategy adaptation index based on the feeding deviation and feeding frequency of each pig in the same feeding unit; S500, the adaptability of pigs to the automatic feeding strategy was determined by the strategy adaptation index; Further, in step S100, an RFID tag system is arranged in a piggery, and a method for real-time identification of a feeding unit and reading a tag distance is as follows: the RFID tag system includes an RFID tag and an RFID reader; Define each stall in the pig house as a feeding unit, each feeding unit includes a number of pigs and a pig trough; RFID tags are installed on each pig in the pig house. The RFID tags are installed at the base of the pig's ears, and the RFID reader is installed at the bottom of the pig trough. The distance between the RFID tag and the RFID reader corresponding to any pig in the breeding unit is defined as the tag distance.

[0005] The feeding unit is a feeding group established by a neural network model or a machine learning model, and each pig in the same feeding group has the same feeding habits; The RFID tag is installed at the lower part of the root of the pig's ear because it is a relatively stable position of the pig's ear, with little movement and is not easily squeezed by other pigs, and it is not easy to get loose. The RFID tag contains a unique ID number for identifying the pig, which is used to identify the pig; the RFID tag also stores information such as the pig's age, weight, and health; the RFID reader can communicate with the RFID tag through the Internet of Things.

[0006] Further, in step S200, the method of judging the eating status by the label distance is: presetting a distance as the eating judgment threshold, when the label distance of the pig at a certain moment is less than or equal to the eating judgment threshold, the eating status of the pig is judged to be true, otherwise the eating status of the pig is false.

[0007] Or the feeding judgment threshold is set to be the sum of the depth disdp of the pig trough and the reference distance dispf between the tip of the pig's mouth and the bottom of the pig trough. The depth range of the pig trough in the automatic feeding system is between 25cm and 30cm, and the reference distance dispf between the tip of the pig's mouth and the bottom of the pig trough is between 15cm and 35cm. Dispf is related to the specific age and weight of the pig, and dispf takes into account the error distance of the actual distance between the tip of the pig's mouth and the bottom of the pig trough during the pig's feeding process; the error distance refers to the distance variation range allowed for the pig to raise its head or stop eating; Since the automatic feeding system establishes different feeding units for each pig in the pig house according to different feeding strategies, the feeding judgment threshold in the same feeding unit is a threshold shared and the same by each pig's feeding status.

[0008] Further, in step S300, the total eating time is obtained through the eating state of the pigs and the eating deviation is calculated. The method of obtaining the eating frequency through the eating state of the pigs is: when the eating state of the pigs is true at a number of consecutive moments, it is defined that a time period composed of the several moments occurs once; the time period of the eating behavior is defined as the eating time; Take a natural day as a feeding observation point; for the same pig, the total number of eating behaviors at one feeding observation point is recorded as the eating frequency, and the sum of the eating time of each eating behavior is the total eating time; the average value of the total eating time of each pig in the same feeding unit is the average eating time, and the eating deviation of any pig is the ratio of the total eating time of the pig to the average eating time.

[0009] The RFID reader performs distance detection every 1 second to 5 seconds.

[0010] Further, in step S400, the method for calculating the strategy adaptation index according to the eating deviation and eating frequency of each pig in the same feeding unit is: set a time period as a monitoring period RETW, RETW∈[20,40] natural days; the eating deviation and eating frequency obtained by any pig constitute the characteristic binary group of the pig, the characteristic binary groups under each eating observation point in the current monitoring period constitute a sequence, and the correlation coefficient of the variables eating deviation and eating frequency in the characteristic binary group sequence is calculated and recorded as the first correlation coefficient; The first correlation coefficient refers to the Pearson first correlation coefficient; The average value of the eating deviations of all pigs at the same eating observation point is taken as the first eating deviation mean; for any pig, the number of eating observation points CntFV where the eating deviation of the 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 are counted. If CntFV is greater than or equal to CntSV, the pig is recorded as a strong fitness object, and CntFV is the adaptation monitoring amount of the pig. Otherwise, the pig is recorded as a weak fitness object, and CntSV is recorded as the adaptation monitoring amount of the pig. The ratio of the adaptive monitoring amount to the number of feeding observation points during the monitoring period is recorded as the second correlation coefficient; for any object with strong fitness, the maximum value of the second correlation coefficient and the first correlation coefficient corresponding to the pig is taken as the quasi-correlation coefficient of the pig; for any object with weak fitness, the minimum value of the second correlation coefficient and the first correlation coefficient corresponding to the pig is taken as the quasi-correlation coefficient of the pig; The calculation principle of the quasi-correlation coefficient is: since pigs in the same feeding group will be significantly affected by the eating behavior of other pigs, by measuring the eating level of each pig at the same eating observation point, while taking into account the correlation between eating frequency and eating level, that is, the influence of eating habits, the difference in eating efficiency of individual pigs can be accurately quantified, and further effectively distinguish and identify pigs with specific eating efficiency; At the current feeding observation point, the range and minimum value of the feeding frequency of all pigs are recorded as FSfag and FSmif respectively. The strategy adaptation index STraid is calculated based on the quasi-correlation coefficient and the feeding frequency FEquy: ; Where exp() is an exponential function with the natural constant e as the base, EAfin is the quasi-correlation coefficient, and FEquy is the frequency of eating.

[0011] Since the above-mentioned 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 pig's feeding level from the average feeding level of all pigs in the same feeding group, the feeding competition and feeding adaptation level of the pigs over a period of time can be characterized according to the fluctuation range of the feeding deviation of each pig; however, in data scenarios where individual differences need to be accurately identified, it is too rough to divide based only on the attribute of the average level of feeding deviation, and it is inefficient to use all the data information of all individuals for more accurate division, so that the accuracy of the quasi-correlation coefficient provided for each pig is insufficient. In order to obtain a more accurate strategy adaptation index, the present invention proposes a more preferred solution; Further, in step S400, the method of calculating the strategy adaptation index according to the eating deviation and eating frequency of each pig in the same feeding unit is: set a time period as a monitoring period RETW, RETW∈[21,56] natural days; A matrix is ​​constructed with different eating observation points as columns, different pigs as rows, eating deviation and eating frequency as matrix elements and recorded as the original matrix. The original matrix is ​​subjected to column range normalization transformation and recorded as the first transformation deviation FSnod and the first transformation frequency FSfqc respectively; wherein the eating deviation and eating frequency are used as matrix elements and are stored in the form of a binary data structure. The column range normalization transformation of the original matrix is ​​to scale the eating deviation and eating frequency according to the range (maximum value minus minimum value) in the eating observation point column, so that the data in each column are in the same range, that is, the eating deviation and eating frequency of each pig in each eating observation point are in the same range; For any feeding monitoring point, a coordinate system fncXOY is constructed by the first transformation deviation and the first transformation frequency, and the first transformation deviation and the first transformation frequency of each pig are respectively used as the coordinate values ​​of the coordinate system corresponding to the x-axis and the y-axis to form the monitoring coordinates of the pig; the monitoring coordinates of all pigs are clustered by average connection hierarchical clustering, the cluster quantity is set as KClst, the centroid of the cluster is defined as the initial cluster seed, and the clusters are sorted in order from small to large according to the Euclidean distance between the initial cluster seed and the origin, and the cluster sorting sequence is recorded as the cluster sequence value, wherein the average connection hierarchical clustering is implemented by the hclust function of the R software, and the origin refers to the origin of the coordinate system fncXOY; the cluster sequence values ​​of the clusters of the pigs at each feeding monitoring point are written into a sequence recorded as a cluster value sequence; The calculation principle of the cluster value sequence is: by effectively utilizing all the information of each pig's eating deviation and eating frequency, pigs with different eating habits are separated, and the characteristics of pigs with the same eating habits are further captured in small groups, so as to accurately locate the unique label of each pig, and finally accurately identify whether it is in a long-term disadvantage or advantage in eating, providing a reference for the adjustment direction of subsequent feeding strategies; Calculate the frequency of occurrence of each cluster sequence value in the cluster value sequence of each pig and record it as the sequence frequency. The cluster sequence value corresponding to the maximum sequence frequency is the pig's pointing cluster sequence; record the median of all first transformation deviations and the median 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 constitute a tuple recorded as a pointing array; the average array of all pointing arrays under the same pointing cluster sequence is the pointing cluster group centroid, and the pointing cluster group centroid is composed of the membership deviation FSmed and the membership frequency FSreq; record the Euclidean distance between the pig's pointing array and the pointing cluster group centroid of its pointing cluster sequence as the feeding adaptation membership degree FEadm; the average array of all pointing arrays under the same pointing cluster sequence refers to selecting all pigs with the same pointing cluster sequence, calculating the average membership deviation FSmed of the second transformation deviation of the corresponding pointing array of the pig, and the average membership frequency FSreq of the second transformation frequency, and the tuple reconstructed by the obtained average values ​​is the required average array, that is, the pointing cluster group centroid; The calculation principle of the feeding adaptation membership is: by using the feeding behavior characteristics of pigs over a period of time to separate and cluster the pigs as much as possible, the difference between individual pigs and the most representative individuals in the cluster is calculated in detail within the same cluster, and the membership of each pig in the cluster is effectively quantified, that is, the degree of similarity between any pig and the representative individual pig, which can further measure the efficiency specificity of pigs' feeding; The pigs’ strategic adaptation index STraid is calculated based on the feeding adaptation membership, membership deviation and membership frequency: ; Wherein ln() is a logarithmic function with the natural constant e as the base.

[0012] Beneficial effects: By analyzing the eating deviation and eating frequency, the degree of rejection between the eating behaviors of different pigs in the same pen after the automatic feeding system was put into use in the pig house was effectively quantified, thereby providing effective mathematical support for identifying pigs with abnormal eating. It can identify strong and weak eating pigs in the pig pens with the same feeding strategy, thereby reducing the risk of low feeding efficiency caused by eating personality deviations among pigs during the application of feeding strategies.

[0013] Further, in step S500, the method of judging the adaptability of the pigs to the automatic feeding strategy by the strategy adaptation index is: defining the average value of the strategy adaptation index of each pig in the same feeding unit as the adaptation mean; when the ratio of the strategy adaptation index of the pig to the adaptation mean is greater than the first preset value, which is between 1.3-1.8, it is judged that the adaptability of the pig belongs to excessive herd adaptation; when the ratio of the strategy adaptation index of the pig to the adaptation mean is less than the second preset value, which is between 0.75-0.55, it is judged that the adaptability of the pig belongs to weak herd adaptation, and the pigs with excessive herd adaptation and weak herd adaptation are judged as abnormal eating pigs.

[0014] When a pig is considered to be over-adapted, it means that the pig is highly dominant and occupied in the food provided in the current feeding unit, which easily reduces the feeding efficiency of other pigs; when the adaptability is considered to be too weak, it is considered that the pig cannot obtain sufficient food resources or be fed adequately in the feeding unit under the current feeding strategy.

[0015] Furthermore, the method further includes step S600, reallocating the abnormally eating pigs to feeding units, and the specific method is: moving the abnormally eating pigs out of the current feeding unit, and forming new feeding units for feeding the pigs with weak group adaptation and the pigs with excessive group adaptation.

[0016] Preferably, all undefined variables in the present invention, if not clearly defined, can be manually set thresholds.

[0017] The present invention also provides an automatic feeding auxiliary monitoring system for a pig house, the automatic feeding auxiliary monitoring system for a pig house comprises: a processor, a memory, and a computer program stored in the memory and executable on the processor, the processor implements the steps in the automatic feeding auxiliary monitoring method for a pig house when executing the computer program, the automatic feeding auxiliary monitoring system for a pig house can be run in computing devices such as desktop computers, laptop computers, PDAs, and cloud data centers, and the executable system may include, but is not limited to, a processor, a memory, and a server cluster, and the processor executes the computer program to run in the following system units: Tag distance reading unit, used to arrange RFID tag system in pig house, identify feeding unit in real time and read tag distance; A state judgment unit, used to judge the eating state by tag distance; A dynamic merging unit is used to obtain the total feeding time and calculate the feeding deviation according to the feeding status of the pigs, and to obtain the feeding frequency according to the feeding status of the pigs; A strategy adaptation analysis unit is used to calculate the strategy adaptation index based on the feeding deviation and feeding frequency of each pig in the same feeding unit; An adaptability judgment unit is used to judge the adaptability of pigs to the automatic feeding strategy through the strategy adaptation index; The beneficial effects of the present invention are :The present invention provides a method and system for auxiliary monitoring of automatic feeding in a pig house. By analyzing the eating deviation and eating frequency, the method effectively quantifies the degree of rejection between the eating behaviors of different pigs in the same pig pen after the automatic feeding system is put into use in the pig house, thereby providing effective mathematical support for identifying pigs with abnormal eating, and can identify strong eating pigs and weak eating pigs in pig pens with the same feeding strategy, thereby reducing the risk of low feeding efficiency caused by eating personality deviations between pigs during the application of feeding strategies. The RFID technology and the automation system are used to monitor and analyze the eating behavior of the pig herd, which greatly improves the efficiency and accuracy of the monitoring process, makes breeding more scientific and efficient while ensuring the cost of breeding, and avoids the problems of feed waste and uneven distribution, so that the growth and development of each pig are more uniform, thereby achieving the purpose of improving the overall breeding quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above and other features of the present invention will become more obvious by describing in detail the embodiments shown in the accompanying drawings. The same reference numerals in the accompanying drawings of the present invention represent the same or similar elements. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other accompanying drawings can be obtained based on these accompanying drawings without creative work. In the accompanying drawings: Figure 1 Shown is a flow chart of a method for automatically monitoring feeding assistance in a piggery; Figure 2 Shown is a structural diagram of an automatic feeding auxiliary monitoring system for pig houses. DETAILED DESCRIPTION

[0019] The following will be combined with the embodiments and drawings to clearly and completely describe the concept, specific structure and technical effects of the present invention, so as to fully understand the purpose, scheme and effect of the present invention. It should be noted that the embodiments and features in the embodiments of this application can be combined with each other without conflict.

[0020] like Figure 1 The figure shows a flow chart of a method for automatically monitoring the feeding of pigs. Figure 1 A method for automatically monitoring the feeding of a piggery according to an embodiment of the present invention is described, and the method comprises the following steps:

[0021] Example 1 S100, deploys RFID tag system in pig house to identify feeding units in real time and read tag distance; S200, judging the eating status by tag distance; S300, obtaining the total eating time according to the eating status of the pigs and calculating the eating deviation, and obtaining the eating frequency according to the eating status of the pigs; S400, calculating the strategy adaptation index based on the feeding deviation and feeding frequency of each pig in the same feeding unit; S500, the adaptability of pigs to the automatic feeding strategy was determined by the strategy adaptation index; Further, in step S100, an RFID tag system is arranged in a piggery, and a method for real-time identification of a feeding unit and reading a tag distance is as follows: the RFID tag system includes an RFID tag and an RFID reader; Define each stall in the pig house as a feeding unit, each feeding unit includes a number of pigs and a pig trough; RFID tags are installed on each pig in the pig house. The RFID tags are installed at the base of the pig's ears, and the RFID reader is installed at the bottom of the pig trough. The distance between the RFID tag and the RFID reader corresponding to any pig in the breeding unit is defined as the tag distance.

[0022] Further, in step S200, the method of judging the eating status by the label distance is: presetting a distance as the eating judgment threshold, when the label distance of the pig at a certain moment is less than or equal to the eating judgment threshold, the eating status of the pig is judged to be true, otherwise the eating status of the pig is false.

[0023] Further, in step S300, the total eating time is obtained through the eating state of the pigs and the eating deviation is calculated. The method of obtaining the eating frequency through the eating state of the pigs is: when the eating state of the pigs is true at a number of consecutive moments, it is defined that a time period composed of the several moments occurs once; the time period of the eating behavior is defined as the eating time; Take a natural day as a feeding observation point; for the same pig, the total number of eating behaviors at one feeding observation point is recorded as the eating frequency, and the sum of the eating time of each eating behavior is the total eating time; the average value of the total eating time of each pig in the same feeding unit is the average eating time, and the eating deviation of any pig is the ratio of the total eating time of the pig to the average eating time.

[0024] Further, in step S400, the method for calculating the strategy adaptation index according to the eating deviation and eating frequency of each pig in the same feeding unit is: set a time period as a monitoring period RETW, taking a value of 30 natural days; the eating deviation and eating frequency obtained by any pig constitute a characteristic binary group of the pig, the characteristic binary groups at each eating observation point in the current monitoring period constitute a sequence, and the correlation coefficient of the variables eating deviation and eating frequency in the characteristic binary group sequence is calculated and recorded as the first correlation coefficient; The average value of the eating deviations of all pigs at the same eating observation point is taken as the first eating deviation mean; for any pig, the number of eating observation points CntFV where the eating deviation of the 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 are counted. If CntFV is greater than or equal to CntSV, the pig is recorded as a strong fitness object, and CntFV is the adaptation monitoring amount of the pig. Otherwise, the pig is recorded as a weak fitness object, and CntSV is recorded as the adaptation monitoring amount of the pig. The ratio of the adaptive monitoring amount to the number of feeding observation points during the monitoring period is recorded as the second correlation coefficient; for any object with strong fitness, the maximum value of the second correlation coefficient and the first correlation coefficient corresponding to the pig is taken as the quasi-correlation coefficient of the pig; for any object with weak fitness, the minimum value of the second correlation coefficient and the first correlation coefficient corresponding to the pig is taken as the quasi-correlation coefficient of the pig; At the current feeding observation point, the range and minimum value of the feeding frequency of all pigs are recorded as FSfag and FSmif respectively. The strategy adaptation index STraid is calculated based on the quasi-correlation coefficient and the feeding frequency FEquy: ; Where exp() is an exponential function with the natural constant e as the base, EAfin is the quasi-correlation coefficient, and FEquy is the frequency of eating.

[0025] Further, in step S500, the method of judging the adaptability of the pigs to the automatic feeding strategy by the strategy adaptation index is: defining the average value of the strategy adaptation index of each pig in the same feeding unit as the adaptation mean; when the ratio of the strategy adaptation index of the pig to the adaptation mean is greater than 1.3, it is judged that the adaptability of the pig belongs to excessive herd adaptation; when the ratio of the strategy adaptation index of the pig to the adaptation mean is less than 0.75, it is judged that the adaptability of the pig belongs to weak herd adaptation, and the pigs with excessive herd adaptation and weak herd adaptation are judged as abnormal eating pigs.

[0026] Furthermore, the method also includes step S600, reallocating the abnormally eating pigs to the feeding units, and the specific method is: the abnormally eating pigs are removed from the current feeding units, and the pigs with weak group adaptation and the pigs with excessive group adaptation are respectively formed into new feeding units for feeding, and the new feeding units follow the feeding strategy of the feeding units where the pigs are removed.

[0027] Example 2 Example 2 adopts the same method for automatic feeding auxiliary monitoring of pig houses as Example 1, except that, 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: a time period is set as the monitoring period RETW, and the value is 30 natural days; The matrix is ​​constructed with different eating observation points as columns, different pigs as rows, eating deviation and eating frequency as matrix elements and recorded as the original matrix. The original matrix is ​​transformed by column range normalization and recorded as the first transformation deviation FSnod and the first transformation frequency FSfqc respectively. For any feeding monitoring point, a coordinate system fncXOY is constructed by the first transformation deviation and the first transformation frequency, and the first transformation deviation and the first transformation frequency of each pig are respectively used as the coordinate values ​​of the coordinate system corresponding to the x-axis and the y-axis to form the monitoring coordinates of the pig; the monitoring coordinates of all pigs are clustered by average connection hierarchical clustering, the cluster quantity is set to KClst, the centroid of the cluster is defined as the initial cluster seed, and the clusters are sorted in order from small to large according to the Euclidean distance between the initial cluster seed and the origin, and the cluster sorting sequence number is recorded as the cluster sequence value; the cluster sequence values ​​of the clusters of the pigs at each feeding monitoring point are written into a sequence recorded as a cluster value sequence; 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 the pig's pointing cluster order; record the median of all first transformation deviations and the median 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 tuple recorded as the pointing array. The average array of all pointing arrays under the same pointing cluster order is the pointing cluster group centroid. The pointing cluster group centroid is composed of the membership deviation FSmed and the membership frequency FSreq; record the Euclidean distance between the pig's pointing array and the pointing cluster group centroid of its pointing cluster order as the feeding adaptation membership degree FEadm; The pigs’ strategic adaptation index STraid is calculated based on the feeding adaptation membership, membership deviation and membership frequency: ; Wherein ln() is a logarithmic function with the natural constant e as the base.

[0028] An embodiment of the present invention provides an automatic feeding auxiliary monitoring system for a pig house, such as Figure 2 Shown is a structural diagram of an automatic feeding auxiliary monitoring system for pig houses of the present invention. An automatic feeding auxiliary monitoring system for pig houses 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 an automatic feeding auxiliary monitoring method for pig houses are implemented.

[0029] The system comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to run in the following units of the system: Tag distance reading unit, used to arrange RFID tag system in pig house, identify feeding unit in real time and read tag distance; A state judgment unit, used to judge the eating state by tag distance; A dynamic merging unit is used to obtain the total feeding time and calculate the feeding deviation according to the feeding status of the pigs, and to obtain the feeding frequency according to the feeding status of the pigs; A strategy adaptation analysis unit is used to calculate the strategy adaptation index based on the feeding deviation and feeding frequency of each pig in the same feeding unit; An adaptability judgment unit is used to judge the adaptability of pigs to the automatic feeding strategy through the strategy adaptation index; The automatic feeding auxiliary monitoring system for pig houses can be run on computing devices such as desktop computers, laptop computers, PDAs, and cloud servers. The automatic feeding auxiliary monitoring system for pig houses can be operated on systems that may include, but are not limited to, processors and memories. Those skilled in the art will appreciate that the example is merely an example of an automatic feeding auxiliary monitoring system for pig houses, and does not constitute a limitation on an automatic feeding auxiliary monitoring system for pig houses. It may include more or fewer components than the example, or a combination of certain components, or different components. For example, the automatic feeding auxiliary monitoring system for pig houses may also include input and output devices, network access devices, buses, and the like.

[0030] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the automatic feeding auxiliary monitoring system for pig houses, and uses various interfaces and lines to connect the various parts of the entire automatic feeding auxiliary monitoring system for pig houses.

[0031] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the automatic feeding auxiliary monitoring system for pig houses by running or executing the computer program and / or module stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0032] Although the description of the present invention has been quite detailed and has been described in particular with respect to several 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 with the embodiments foreseeable by the inventors, and its purpose is to provide a useful description, and those non-substantial changes to the present invention that are not currently foreseen may still represent equivalent changes of the present invention.

Claims

1. A method for automatically monitoring feeding in a pig house, characterized in that: The method comprises the following steps: S100, deploys RFID tag system in pig house to identify feeding units in real time and read tag distance; S200, judging the eating status by tag distance; S300, obtaining the total eating time according to the eating status of the pigs and calculating the eating deviation, and obtaining the eating frequency according to the eating status of the pigs; S400, calculating the strategy adaptation index based on the feeding deviation and feeding frequency of each pig in the same feeding unit; S500, the adaptability of pigs to the automatic feeding strategy was determined by the strategy adaptation index; The method for calculating the strategy adaptation index based on the eating deviation and eating frequency of each pig in the same feeding unit is: the eating deviation and eating frequency constitute a feature binary group, the first correlation coefficient is obtained through the feature binary group, the first eating deviation mean is calculated by the eating deviation in a preset time period, the adaptation monitoring amount is obtained by using the first eating deviation mean, and the second correlation coefficient is calculated from the adaptation monitoring amount; the quasi-correlation coefficient is obtained by selecting from the first correlation coefficient and the second correlation coefficient, and the strategy adaptation index is calculated according to the quasi-correlation coefficient and the eating frequency FEquy.

2. The method for automatic feeding auxiliary monitoring of a pig house according to claim 1, characterized in that: In step S100, the RFID tag system is arranged in the piggery, and the method for real-time identification of the feeding unit and reading the tag distance is as follows: the RFID tag system includes an RFID tag and an RFID reader; Define each stall in the pig house as a feeding unit, each feeding unit includes a number of pigs and a pig trough; RFID tags are installed on each pig in the pig house. The RFID tags are installed at the base of the pig's ears, and the RFID reader is installed at the bottom of the pig trough; the distance between the RFID tag and the RFID reader corresponding to any pig in the feeding unit is defined as the tag distance.

3. The method for automatic feeding auxiliary monitoring of a pig house according to claim 1, characterized in that: In step S200, the method of judging the eating status by the tag distance is: presetting a distance as the eating judgment threshold, when the tag distance of the pig at a certain moment is less than or equal to the eating judgment threshold, the eating status of the pig is judged to be true, otherwise the eating status of the pig is false.

4. The method for automatic feeding auxiliary monitoring of a pig house according to claim 1, characterized in that: In step S300, the total eating time is obtained through the eating state of the pigs and the eating deviation is calculated. The method of obtaining the eating frequency through the eating state of the pigs is: when the eating state of the pigs is true at several consecutive moments, it is defined that the time period formed by the several moments has one eating behavior; the time period of the eating behavior is defined as the eating time; One natural day was taken as one feeding observation point; the total number of times the same pig ate at one feeding observation point was recorded as the feeding frequency, and the sum of the feeding duration of each feeding behavior was the total feeding duration; The average value of the total eating time of each pig in the same feeding unit is the average eating time, and the eating deviation of any pig is the ratio of the total eating time of the pig to the average eating time.

5. The method for automatic feeding auxiliary monitoring of a pig house according to claim 1, characterized in that: In step S400, the method of 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 a monitoring period RETW, RETW∈[20,40] natural days; The eating deviation and eating frequency obtained by any pig constitute the characteristic binary group of the pig. The characteristic binary groups under each eating observation point in the current monitoring period constitute a sequence. The correlation coefficient of the variables eating deviation and eating frequency in the characteristic binary group sequence is calculated and recorded as the first correlation coefficient. The average value of the eating deviations of all pigs at the same eating observation point is taken as the first eating deviation mean; for any pig, the number of eating observation points CntFV where the eating deviation of the 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 are counted. If CntFV is greater than or equal to CntSV, the pig is recorded as a strong fitness object, and CntFV is the adaptation monitoring amount of the pig. Otherwise, the pig is recorded as a weak fitness object, and CntSV is recorded as the adaptation monitoring amount of the pig. The ratio of the adaptive monitoring amount to the number of feeding observation points during the monitoring period is recorded as the second correlation coefficient; for any object with strong fitness, the maximum value of the second correlation coefficient and the first correlation coefficient corresponding to the pig is taken as the quasi-correlation coefficient of the pig; for any object with weak fitness, the minimum value of the second correlation coefficient and the first correlation coefficient corresponding to the pig is taken as the quasi-correlation coefficient of the pig; At the current feeding observation point, the range and minimum value of the feeding frequency of all pigs are recorded as FSfag and FSmif respectively, and the strategy adaptation index is calculated based on the quasi-correlation coefficient and the feeding frequency FEquy.

6. The method for automatic feeding auxiliary monitoring of a pig house according to claim 1, characterized in 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 can be replaced by: setting a time period as the monitoring period RETW, RETW∈[21,56] natural days; The matrix is ​​constructed with different eating observation points as columns, different pigs as rows, eating deviation and eating frequency as matrix elements and recorded as the original matrix. The original matrix is ​​transformed by column range normalization and recorded as the first transformation deviation FSnod and the first transformation frequency FSfqc respectively. For any feeding monitoring point, a coordinate system fncXOY is constructed by the first transformation deviation and the first transformation frequency, and the first transformation deviation and the first transformation frequency of each pig are respectively used as the coordinate values ​​of the coordinate system corresponding to the x-axis and the y-axis to form the monitoring coordinates of the pig; the monitoring coordinates of all pigs are clustered by average connection hierarchical clustering, the cluster quantity is set to KClst, the centroid of the cluster is defined as the initial cluster seed, and the clusters are sorted in order from small to large according to the Euclidean distance between the initial cluster seed and the origin, and the cluster sorting sequence is recorded as the cluster sequence value; The cluster sequence values ​​of the cluster groups of pigs at each feeding monitoring point are written into a sequence and recorded as a cluster value sequence; 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 the pig's pointing cluster order. The median of all first transformation deviations and the median of all first transformation frequencies of any pig are recorded as the second transformation deviation FSmqy and the second transformation frequency FSvia respectively. The second transformation deviation and the second transformation frequency form a tuple recorded as a pointing array. The average array of all pointing arrays under the same pointing cluster order is the pointing cluster group centroid. The pointing cluster group centroid is composed of the membership deviation FSmed and the membership frequency FSreq. The Euclidean distance between the pig's pointing array and the pointing cluster group centroid of its pointing cluster order is recorded as the feeding adaptation membership FEadm. The pig's strategy adaptation index is calculated based on the feeding adaptation membership, membership deviation and membership frequency.

7. The method for automatic feeding auxiliary monitoring of a pig house according to claim 1, characterized in that: In step S500, the method of judging the adaptability of the pigs to the automatic feeding strategy through the strategy adaptation index is as follows: define the average value of the strategy adaptation index of each pig in the same feeding unit as the adaptation mean; when the ratio of the strategy adaptation index of the pig to the adaptation mean is greater than the first preset value, which is between 1.3-1.8, it is judged that the adaptability of the pig belongs to excessive herd adaptation; when the ratio of the strategy adaptation index of the pig to the adaptation mean is less than the second preset value, which is between 0.75-0.55, it is judged that the adaptability of the pig belongs to weak herd adaptation, and the pigs with excessive herd adaptation and weak herd adaptation are judged as abnormal eating pigs.

8. The method for automatic feeding auxiliary monitoring of a pig house according to claim 1, characterized in that: The method further includes step S600, reallocating the abnormally eating pigs to the feeding units. The specific method is: moving the abnormally eating pigs out of the current feeding units, and forming new feeding units for feeding the pigs with weak group adaptation and the pigs with excessive group adaptation.

9. An automatic feeding auxiliary monitoring system for pig houses, characterized in that: The automatic feeding auxiliary monitoring system for pig houses comprises: 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 of the automatic feeding auxiliary monitoring method for pig houses described in any one of claims 1 to 8 are implemented. The automatic feeding auxiliary monitoring system for pig houses runs on computing devices such as desktop computers, laptop computers, PDAs, and cloud data centers.

Images