Stage 1: Document Parsing

(PDF → Text Extraction)

Stage 2: Text Preprocessing

(Tokenize, Clean, Lemma)

Stage 3: Feature Extraction

(Embeddings Generation)

Stage 4: Entity Extraction

(Skills, Roles, Education)

Stage 5: Similarity Model

(BERT + Cosine Similarity)

Stage 6: Ranking & Feedback

(Match % and Suggestions)