TEXT INFORMATION SIMILARITY MATCHING METHOD AND APPARATUS, COMPUTER DEVICE, AND STORAGE MEDIUM

摘要

Provided are a TF-IDF-based text information similarity matching method and apparatus. The method comprises: acquiring text information; carrying out word segmentation on the text information to obtain segmented words w₁, w₂,..., w_n-1 and w_n; using a CBOW model to calculate word vectors V(w₁), V(w₂),..., V(w_n-1) and V(w_n) of the segmented words; using a TF-IDF algorithm to calculate TF-IDF values k₁, k₂,..., k_n-1 and k_n of the segmented words; obtaining a sentence vector V according to products of the word vectors of the segmented words and the corresponding TF-IDF values; and calculating the cosine similarity between the sentence vector V and sentence vectors of pre-stored statements, and determining a pre-stored statement having the maximum cosine similarity. By means of the process, a pre-stored statement that is most similar to text information can be found, and the accuracy of problem recognition can be improved in the aspects of robot conversation, information classification, etc., thus improving the conversation efficiency or the classification efficiency. Further provided are a computer device and a storage medium.