Approximate nearest text semantic retrieval method and device, equipment and storage medium

The invention relates to an approximate closest text semantic retrieval method and device, equipment and a storage medium, and the method comprises the steps: obtaining to-be-retrieved text data, and carrying out the preprocessing of the to-be-retrieved text data through a word bag strategy, and gen...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: LI BAORAN
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention relates to an approximate closest text semantic retrieval method and device, equipment and a storage medium, and the method comprises the steps: obtaining to-be-retrieved text data, and carrying out the preprocessing of the to-be-retrieved text data through a word bag strategy, and generating a text vector; calculating the weight of the text vector in a text library; performing product quantization coding processing on the text vector to generate product quantization coding data; and based on the weight and the product quantization coding data, processing the text vector by using a multi-table product quantization algorithm to generate an approximate nearest text semantic retrieval result set. According to the method, a rapid approximate nearest neighbor retrieval method is designed on the basis of the semantic text nearest neighbor retrieval problem, and the semantic text approximate nearest neighbor retrieval speed in a large-scale text database can be greatly increased on the premise that the