This invention relates to the field of
information retrieval technology, specifically to a retrieval enhancement generation method based on
machine learning for second-level retrieval of user data. This method solves the technical problems in existing technologies where structured medical data suffers severe loss of key clinical
semantics during vectorization and fixed-length segmentation, and cannot support cross-indicator
correlation analysis and low-latency feedback. The method includes: acquiring user queries against a structured user
database; determining the semantic loss of at least one candidate
data segment corresponding to the user query in the
temporal continuity and medical relevance dimensions; using the semantic loss to characterize the degree of clinical semantic loss caused by segmentation of the candidate
data segment; determining the completeness of the indicator association between the candidate
data segment and the user query based on the semantic loss; and adjusting the retrieval results for the user query based on the indicator association completeness.