Display device and multi-round dialogue prediction generation method

The embodiment of the invention provides a display device and a multi-round dialogue prediction generation method. A display device can obtain a multi-round dialogue template in a multi-round dialogue template database, and select a target single-round dialogue template based on single-round dialogu...

Full description

Saved in:
Bibliographic Details
Main Authors ZHU SHOUQIN, WANG XIANJIAN, HU RENLIN
Format Patent
LanguageChinese
English
Published 02.04.2024
Subjects
CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:The embodiment of the invention provides a display device and a multi-round dialogue prediction generation method. A display device can obtain a multi-round dialogue template in a multi-round dialogue template database, and select a target single-round dialogue template based on single-round dialogue template information. The display device can acquire a target entity type of a slot position to be filled in the target single-round dialogue template, and acquire a target entity according to the target entity type. The display device can execute entity filling on the target single-round dialogue template based on the target entity to obtain a single-round dialogue corpus. And after the single-round dialogue corpora are combined, multi-round dialogue corpora are obtained. The display device can automatically generate multiple rounds of dialogue corpora, and the accuracy of speech recognition can be improved. 本申请一些实施例提供一种显示设备和多轮对话预料生成方法。显示设备可以在多轮对话模板数据库中获取多轮对话模板，并基于单轮对话模板信息选取目标单轮对话模板。显示设备可以获取目标单轮对话模板中待填充槽位的目标实体类型
Bibliography:Application Number: CN202310595623