Livestock delivery detecting method and device

Abstract

The invention provides a livestock delivery detecting method. The livestock delivery detecting method comprises the steps of, firstly, collecting data before and after livestock delivery; secondly, through the collected data and delivery results corresponding to the data, training a delivery detecting model, which can automatically select channel data facilitating delivery discrimination and provide a discrimination result through the channel data; thirdly, inputting newly-collected data with the answer unknown, and performing discrimination through the delivery detecting model to acquire a delivery result. According to the livestock delivery detecting method, a long short-term memory neural network model and a first feedforward neural network model cooperate to automatically select channels facilitating detection; a second feedforward neural network model is applied to selecting channel data with high data discrimination capacity, which is applied as the final basis for determining the delivery result, so that the delivery detecting precision can be improved. The livestock delivery detecting method is wide in application range and applicable to various complex situations.

Description

technical field [0001] The invention relates to the field of breeding technology, in particular to a livestock delivery detection method and device. Background technique [0002] At present, cattle raising is an important part of the generation of farmers in some areas. In Inner Mongolia, Heilongjiang and other regions, there are many plains, relatively broad grasslands and fields, and a large number of farmers are engaged in cattle raising. Most of these farmers have dozens or hundreds of cattle, and some have a few cattle. They mainly adopt the free-range method, driving the cattle to a relatively open place for grazing, and penning the cattle to a relatively closed place for overnight at night. An important part of raising cattle is the cow giving birth. Due to the specific situation of farmers raising cattle and the characteristics of cattle giving birth, the time of cow giving birth cannot be obtained in advance. Therefore, a period of time before the cows give birth...

AI Technical Summary

Problems solved by technology

This method obviously has two major disadvantages. One is that the data of each channel is more reliable than other channels under certain characteristics. Reporting rate, if all are selected, but based on the existing statistical rules or empirical rules, it cannot automatically distinguish which channel data is better under the given conditions, which will reduce the detection accuracy

The second is data replication, and the simple rule method has a high false positive rate

Direct use of the existing deep neural network method does not distinguish between the input of different channel data and its delivery prediction ability, which will lead to many false positives

Images