Video information auxiliary creation method and creation system

The invention discloses a video information auxiliary creation method and creation system, and relates to the technical field of auxiliary creation. The method comprises the following steps of 1, analyzing audio information and picture information by using a language model technology based on Prompt...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: CHEN TENGYANG, HUANG JIQI, GUO JUNNAN, REN YIBIN, ZHAO YINGCHUAN, CHENG SHAOXI, LUO LIEYI
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 discloses a video information auxiliary creation method and creation system, and relates to the technical field of auxiliary creation. The method comprises the following steps of 1, analyzing audio information and picture information by using a language model technology based on Prompt engineering; 2, generating titles, keywords, brief introductions and classifications by using a language model according to an analysis result, and filling video information needing to be uploaded with the titles, the keywords, the brief introductions and the classifications; and step 3, aiming at the characteristics of the website uploaded by the video, unifying the searching and recommending processes into rough calling, sorting and restructuring by using a searching and pushing integrated algorithm. According to the system, on the basis of traditional audio information and picture information, a set of process for automatically constructing video information by using a language large model through Prompt engine