Detection and management of disease outbreaks in livestock using health graph networks

摘要

Sensor data captured over time and associated with a plurality of livestock animals can be analyzed to determine health conditions associated with a plurality of livestock animals and to determine interactions of the livestock animals. The interactions specify at least distances between the livestock animals, duration of the distances, and frequency of the interactions. A health graph network is constructed, which includes nodes and edges, a node in the nodes representing a livestock animal and specifying at least a health condition of the represented livestock animal, an edge connecting at least two of the nodes and representing an interaction between at least two animals represented by said at least two of the nodes. Based on the health graph network, a potential outbreak among a subgroup of the livestock animals can be predicted.