The invention belongs to the field of data processing, and particularly relates to an ontology-based fuzzy evaluation search engine advertisement optimization method, which comprises the following steps: S1, constructing a search engine advertisement semantic model of an ontology, describing search engine advertisement field knowledge on a semantic level, reusing and integrating an existing ontology model, and realizing information exchange and sharing; and S2, based on a multi-attribute entropy weight fuzzy comprehensive evaluation algorithm, calculating attribute weights by using informationentropy, constructing a membership matrix by using a triangular fuzzy number, constructing a multi-attribute comment evaluation coordinate system according to an optimization target and an optimization rule, and performing calculation through a fuzzy operator to obtain a final optimization subset. By means of the technology, early-stage work (rough optimization) of search engine advertisement optimization can be automatically achieved, and further deep optimization is completed to a certain extent, and the labor cost is effectively saved for enterprises, and the investment return rate of search engine popularization is increased.