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...
Saved in:
Main Authors | , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
02.04.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
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 |