Semantic-based interpretable person-job matching method and system
The invention discloses a semantic-based interpretable person and job matching method and system, and the method comprises the steps: receiving a resume text of a job seeker and a recruitment information text of a recruiter, and vectorizing each text into a text embedded vector for representation; m...
Gespeichert in:
Hauptverfasser: | , , , , |
---|---|
Format: | Patent |
Sprache: | chi ; eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The invention discloses a semantic-based interpretable person and job matching method and system, and the method comprises the steps: receiving a resume text of a job seeker and a recruitment information text of a recruiter, and vectorizing each text into a text embedded vector for representation; modeling the embedded vector representation of each text to obtain the state representation of each sentence and the overall state representation of each text; simulating global semantics for the state representation of each sentence in each text through a similarity matrix method to obtain a specific representation of each sentence and an overall specific representation of each text; splicing the overall state representation and the overall aiming representation of each text to obtain a final representation of each text, and inputting the final representation into a multi-layer perceptron to calculate a matching degree; and giving recommendation and explanation. The method can be used for solving the problem that a |
---|