Search

CN-116958612-B - Clustering analysis method for abnormal data of piglets

CN116958612BCN 116958612 BCN116958612 BCN 116958612BCN-116958612-B

Abstract

The invention provides a clustering analysis method of abnormal data of piglets, which is characterized by comprising the following steps of S1, monitoring the piglets of each pig house, obtaining first data, S2, obtaining first data information of the piglets of the field in a preset historical period, S3, carrying out clustering processing on the first data information of the piglets of the field in the preset historical period to generate a plurality of data subsets, and S4, carrying out early warning according to the plurality of data subsets. According to the invention, the stool information, the body behavior information and the diet information of each field are subjected to cluster analysis, so that the variation of various abnormal conditions of each field is obtained, and the targeted early warning is carried out according to the variation. Therefore, automatic identification and early warning of unattended piglet death events can be realized.

Inventors

  • XUE SUJIN
  • LIU ZONGNING
  • YANG KUN

Assignees

  • 厦门农芯数字科技有限公司

Dates

Publication Date
20260512
Application Date
20230718

Claims (6)

  1. 1. The clustering analysis method for the abnormal data of the piglets is characterized by comprising the following steps of: The method comprises the steps of S1, monitoring piglets in each pig house field to obtain first data, wherein the first data comprise faecal information, physical behavior information and diet information of the piglets in the field, the faecal information is information of the number and the abnormal type of the faeces identified as abnormal faeces through a faecal identification model, the physical behavior information is information of the number and the abnormal type of whether the piglets are identified as shaking abnormality or extrusion abnormality through a OpenPose gesture identification algorithm, and the diet information is the drinking number and the time of each piglet; S2, acquiring first data information of the field piglets in a preset history period; s3, clustering the first data information of the field piglets in a preset history period to generate a plurality of data subsets; S4, early warning is carried out according to the data subsets.
  2. 2. The method for cluster analysis of litter size data of claim 1, wherein the predetermined history period is a continuous 3-5 day period.
  3. 3. The method of clustering abnormal data of piglets according to claim 1, wherein in step S3, the step of clustering the first data information of the piglets in the field for a predetermined history period to generate a plurality of data subsets comprises: And carrying out standardization processing on the first data information under the preset history period, and then carrying out clustering processing to generate a plurality of data subsets.
  4. 4. The method of cluster analysis of litter abnormality data according to claim 2, wherein in step S4, the step of pre-warning based on the plurality of data subsets comprises: S41, early warning is carried out when the number of abnormal feces in the plurality of data subsets is continuously increased, when the number of shaking abnormality in the plurality of data subsets is continuously increased, when the number of extrusion abnormality in the plurality of data subsets is continuously increased, and when the number of diet times in the plurality of data subsets is continuously reduced, at least one condition is met.
  5. 5. The method of cluster analysis of litter abnormality data according to claim 2, wherein in step S4, the step of pre-warning based on the plurality of data subsets comprises: s42, acquiring thresholds of various anomalies, and carrying out early warning when at least one anomaly exceeds a set threshold.
  6. 6. The method for clustering abnormal data of piglets according to claim 1, wherein in the step S1, the diet information is the number of times and time of diet of piglets, whether the head bone joint point of the piglets is close to the nipple of the sow within a preset distance range or not is obtained through a camera according to the number of times of diet, and if the head bone joint point is within the preset distance range, the number of times of diet is counted.

Description

Clustering analysis method for abnormal data of piglets Technical Field The invention relates to a clustering analysis method for abnormal data of piglets. Background At present, a large-scale pig farm generally counts the number of live piglets and the number of dead piglets at the time of birth of piglets, because the number of live piglets and the number of dead piglets are related to the profitability and the breeding plan of the pig farm. However, young piglets are likely to be alive and healthy at birth, but die after their birth for a variety of reasons. In normal production practice in pig farms, the biggest new-born piglets die usually in good conditions during production but within the first few days of their life. However, in the prior art, there is no effective analysis method for abnormal data of piglets which are good in body condition at the time of production but die in the first few days of life, so that early warning is performed in advance. Disclosure of Invention The invention provides a clustering analysis method for abnormal data of piglets, which can effectively solve the problems. The invention is realized in the following way: The invention discloses a clustering analysis method for abnormal data of piglets, which comprises the following steps: S1, monitoring piglets in each pig house to obtain first data, wherein the first data comprise faecal information, physical behavior information and diet information of the piglets in the field; S2, acquiring first data information of the field piglets in a preset history period; s3, clustering the first data information of the field piglets in a preset history period to generate a plurality of data subsets; S4, early warning is carried out according to the data subsets. The method has the beneficial effects that the method obtains the variation of various abnormal conditions of each column through the cluster analysis of the faeces information, the body behavior information and the diet information of the piglets of each column, and carries out targeted early warning according to the variation. Therefore, automatic identification and early warning of unattended piglet death events can be realized. Drawings In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some examples of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. Fig. 1 is a flowchart of a cluster analysis method for abnormal data of piglets according to an embodiment of the invention. Fig. 2 is a photograph of different feces collected in a cluster analysis method of abnormal data of piglets according to an embodiment of the invention. Fig. 3 is a flowchart of a cluster analysis method for abnormal data of piglets according to an embodiment of the invention. Detailed Description For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, based on the embodiments of the invention, which are apparent to those of ordinary skill in the art without inventive faculty, are intended to be within the scope of the invention. Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, based on the embodiments of the invention, which are apparent to those of ordinary skill in the art without inventive faculty, are intended to be within the scope of the invention. In the description of the present invention, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise. Referring to fig. 1, an embodiment of the present invention provides a cluster analysis method for abnormal data of piglets, including the following steps: S1, monitoring piglets in each pig house to obtain first data, wherein the first data comprise faecal informat