Abstract: Based on the relativity between domain knowledge and purchase trends 3 typical areas including knowledge representation，knowledge acquisition and system achievement are studied for personalized collaborative commerce recommendation system.Knowledge representation studied ontology representation of natural language，which includes knowledge ontology representation，fuzzy relationship design，concept connection abstract and axiom revises.Knowledge acquisition studied formalization and structurization of domain knowledge through multi-level domain knowledge acquisition and intelligent knowledge acquisition based on data mining.In order to develop collaborative commerce system，a model including client，server and storage system is designed based on J2EE.To demonstrate the practical usefulness of this methodology，a real-life case is illustrated.