Medical English teaching has problems such as language and content detachment and insufficient cultivation of practical application ability, which require innovative assessment methods. This study adopts clustering-based multidimensional data processing technology to construct CSSAQP algorithm to analyze and evaluate medical English teaching data. The algorithm deals with the extreme value problem through K-Means clustering, and adopts a two-phase strategy: the pre-constructed sample phase and the query execution phase for stratified sampling and precise analysis of teaching data. The experimental results show that on the medical English vocabulary teaching dataset (about 0.5 billion data), the query accuracy of the CSSAQP algorithm reaches 0.0122%, 0.0141%, and 0.0085% for the SUM, COUNT, and AVG metrics, respectively, which is better than the existing methods. Meanwhile, the algorithm excels in query response time, with SUM, COUNT, and AVG query times of 1.52 seconds, 1.24 seconds, and 1.34 seconds respectively, realizing real-time response. The research results provide an accurate assessment tool for medical English teaching, help optimize the structure of medical English courses and the construction of teaching resources, and provide data support for cultivating medical talents with a global perspective.
