Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Intelligent conference summary generation method and system

A meeting minutes and intelligent technology, applied in neural learning methods, biological neural network models, speech analysis, etc., can solve problems such as relying on the clerk's concentration and clerk's omission, so as to reduce the text processing process, reduce the workload, The effect of improving execution efficiency

Active Publication Date: 2020-01-21
南京摄星智能科技有限公司
View PDF6 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The more traditional way to realize the meeting minutes is to arrange the clerk to record the meeting process, which is more dependent on the clerk's concentration, and the clerk will miss the record when he is absent.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Intelligent conference summary generation method and system
  • Intelligent conference summary generation method and system
  • Intelligent conference summary generation method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033] refer to figure 1 The schematic diagram shows the error correction process of a method for generating intelligent meeting minutes proposed in this embodiment. In order to find out the words that may be wrong in the text, including words with wrong fonts and wrong pronunciations, and then perform error correction, the current technology usually The error correction process adopted includes: error detection, using rules or deep models to detect errors in the text and forming a candidate set of suspected error positions, usually with word granularity and word granularity detection; error correction, for the candidate set of suspected error positions Generate a corresponding candidate set for each error point, and then replace and calculate ppl one by one to determine the correct word.

[0034] The current error correction methods mainly have the following problems: (1) In the process of using rules, ngram language models and other methods to detect wrong words, compared wi...

Embodiment 2

[0087] refer to Figure 2-6 For the sake of illustration, this embodiment proposes a system for generating intelligent meeting minutes, and the generation method of the foregoing embodiment is implemented based on this embodiment. Specifically, this embodiment includes a collection module 100 , a voiceprint feature extraction module 200 , a role separation module 300 , a voice transcription module 400 , a text processing module 500 and a summary generation module 600 .

[0088] Further, wherein the collection module 100 is used to obtain conference audio and video signals; the voiceprint feature extraction module 200 is connected to the collection module 100 for extracting the voiceprint features of real-time voice signals; The feature matching performed by the preset voiceprint database recognizes the voice signals of different speakers and separates the voice signals; the voice transcription module 400 is connected with the role separation module 300 and is used to transcrib...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an intelligent conference summary generation method and system, and the method comprises the following steps: obtaining conference audio and video signals; extracting voiceprint features of the real-time voice signals; performing feature matching on the voiceprint features and a preset voiceprint database, identifying speaker identities corresponding to different voice signals, and separating speaking voices of different speakers; respectively transliterating the separated voice signals into characters, and generating a preliminary text corresponding to the speaker; performing error correction and optimization processing on the preliminary text to obtain a target text; and extracting important sentences in the target text to form an abstract, and arranging the abstract into the conference summary according to a preset template. The beneficial effects of the method are that the method can improve the detection time, improves the execution efficiency of an algorithm, and reduces the operation time, and responsible text processing flows are reduced, and the reusability of codes is improved. The workload of algorithm researchers is reduced, and bidirectional semantic dependence can be better captured.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence natural language processing, in particular to a method and system for generating intelligent meeting minutes. Background technique [0002] In recent years, in the daily office process, almost every working day may be faced with various meetings. During the process of participating in the meeting, the participants generally focus on following up the content and progress of the meeting. After the meeting is over, the meeting minutes often need to be Relying on dedicated staff to collect and organize according to the participation process, the minutes taker needs to follow up on the feedback of all the people at the meeting to make records and then organize, forward, and even follow up, which leads to the process of organizing meeting minutes requires human cost input , labor-intensive and time-consuming. [0003] At present, meeting minutes are usually recorded by the recorder, alt...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F16/338G06F16/35G06N3/04G06N3/08G10L15/26G10L17/02
CPCG06F16/338G06F16/35G06N3/08G10L17/02G10L15/26G06N3/044G06N3/045
Inventor 杨理想王云甘周亚张侨王银瑞
Owner 南京摄星智能科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products