| Dairy cattle breeding played a important role in animal production, Cow include human was threated by cow epidemic diseases, especially some cow major diseases. We designed the system aimed at helping the veterinarians especially grass-roots veterinarians and cattle breeding managers increase their skills of diagnosis, who limited by their knowledge and diagnostic conditions ,and it also made the greatest use of the expert knowledge and experience, solving the shortage of grass-roots veterinarians and low accuracy disease diagnosis, at the same time, providing high-quality basic data for the cow disease early warning system, enhancing communication among the experts, breeding managers and veterinarians.The knowledge of cow diseases obtained by cooperation with experts and knowledge engineers, which suited for both of computer processing and clinical diagnosis.And after analysis the characteristics of cow disease, the knowledge was grouped by symptoms set, and it has all symptoms of a disease .Disease represents the name of one disease ,and every disease has its own number of symptoms.A new way of inference with both forward and backward chains is presented in the paper,this inference contains two parts.On the first stage,forward chain will be used.A set of hypothesis will be got from the information provided by user through forward chain of this stage.Then the inference will mechanism will turn to the second stage to test the hypothesis be presented to user.Otherwise,the inference will repeat this proeess,and different knowledge base are used for live cattle and dead cow.The system is based on B/S (Browser/Server) model, combined with the diagnostic data , experts and expert systems through the network,it's convenient and economic for system's maintenance and upgrades.The user can make diagnosis and query of main diseases of the cow on-line; also, the user can solve the production problems of cow interaction with experts on line. |
PDF Full Text Request