2results about How to "Reduction factor" patented technology

The application discloses an enzymatic shrimp paste compound water product feeding attractant and application thereof, and belongs to the technical field of water animal feed additives, characterized in that the compound water product feeding attractant is composed of the following components in percentage by weight: 85% to 98% of enzymatic shrimp paste, 2% to 15% of food-grade eugenol, wherein the enzymatic shrimp paste is obtained by directional enzymolysis of shrimp head endocrine fluid through a four-component complex flavor protease containing endoprotease, aminopeptidase, carboxypeptidase and glutamine transaminase; the application further provides a preparation method of the enzymatic shrimp paste and application of the compound water product feeding attractant; and the advantages are that the enzymatic shrimp paste is rich in flavor peptides, after being compounded with eugenol, the eugenol can activate the olfactory receptor ion channel of water animals, amplify the sensing signal of flavor substances, and form a significant synergistic feeding effect, so that the feeding amount of the water animals can be effectively improved, and the feed coefficient can be reduced.

The application provides a sparse medical entity recognition method based on an attention mechanism, and comprises the following steps: S1, extracting a word vector through a BERT model and further extracting features by using a Bi-LSTM; S2, using an Attention mechanism to extract deep connections inside the word vector; S3, dynamically adjusting entity category weights and fusion weights in ensemble learning according to the entity sparsity characteristics of each batch; and S4, outputting a prediction result through a CRF layer. The named entity recognition model provided by the application can not only dynamically focus on difficult-to-identify samples to improve learning efficiency, but also introduce a reduction factor to reduce the interference caused by sparse entities during parameter updating. This makes the model have significantly improved performance in dealing with the problems of unbalanced entity quantity and sparse entities in medical named entity recognition.