Dialogue template generation method and device, and computer readable storage medium
By segmenting, tagging, converting, and determining the relevance of voice segments in dialogue recordings, efficient and relevant dialogue templates are generated, solving the problem of tedious manual input and improving the user experience.
CN116187292BActive Publication Date: 2026-06-19VOICEAI TECH CO LTD +1
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- VOICEAI TECH CO LTD
- Filing Date
- 2022-12-09
- Publication Date
- 2026-06-19
AI Technical Summary
Technical Problem
In existing technologies, the manual input process for generating dialogue templates is cumbersome, resulting in low efficiency and poor relevance of dialogue content to the topic, which affects user experience.
Method used
By acquiring the dialogue recording file, segmenting the voice segments and tagging users, performing text conversion and sorting, determining the relevance of sentences, and generating the target dialogue template.
Benefits of technology
It improves the efficiency of dialogue template generation, enhances the relevance of dialogue content to the topic, and improves the user experience in simulated dialogue scenarios.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN116187292B_ABST
Abstract
The embodiment of the application discloses a dialogue template generation method and device and a computer readable storage medium. A dialogue recording file can be obtained. Speech segments in the dialogue recording file are segmented according to sound characteristics, and a plurality of speech segments are obtained. Each speech segment corresponds to a dialogue user label. Each speech segment is converted into text to obtain a text sentence corresponding to each speech segment. The text sentences are sorted according to a speech time sequence to obtain a text sentence sequence. The correlation between the text sentences of different dialogue user labels is determined, and a target dialogue template corresponding to the dialogue recording file is determined according to the correlation and the text sentence sequence. In this way, the generation efficiency of the dialogue template can be improved, the relevance of dialogue content and themes in the dialogue template can be improved, the effect of simulating a dialogue scene by using the dialogue template by a user can be ensured, and the experience of the user can be improved.
Need to check novelty before this filing date? Find Prior Art