Method and device for identifying persons mentioned in conversation

A technology of in-dialogue and person names, applied in speech recognition, data processing applications, special data processing applications, etc., can solve the problem of not being able to uniquely identify, not being able to identify the person being mentioned with sufficient accuracy, etc.

Inactive Publication Date: 2014-01-15
CANON KK
View PDF5 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] However, the prior art presented above cannot identify the person being mentioned (i.e. the person being mentioned) with sufficient accuracy
In many cases, the person mentioned cannot be uniquely identified

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
  • Method and device for identifying persons mentioned in conversation
  • Method and device for identifying persons mentioned in conversation
  • Method and device for identifying persons mentioned in conversation

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example ）

[0122] Figure 5 An input dialog is shown. It can be seen that the speaker Adam mentioned the name "Lee-san".

[0123] First, recognize that the person name "Lee-san" is mentioned, and then identify the name entity related to the mentioned person name based on the dialogue:

[0124] Speaker: Adam

[0125] Audience (next speaker): George.

[0126] Next, a set of candidate identifiers is obtained by searching the alias database for the mentioned person's name. Part of the alias database is shown in Table 2.

[0127] Table 2: Alias ​​database

[0128]

[0129] According to the alias database shown in Table 2 above, two candidate identifiers can be found:

[0130] Candidate Identifier: David Lee (ID 001, the identifier for the name of the person mentioned)

[0131] Candidate Identifier: Alex Lee (ID 002)

[0132] Next, relational features are extracted for each candidate identifier. In this embodiment, the relationship features are the title gap feature and the common ...

no. 2 example ）

[0188] The above-mentioned method or device for identifying persons mentioned in a conversation can be applied to a device for managing meeting minutes.

[0189] Figure 7 The structure of the apparatus for managing conference minutes according to the second embodiment of the present invention is illustrated.

[0190] Such as Figure 7 As shown, the apparatus for managing meeting minutes includes a receiving unit 711 , a preprocessing unit 712 , a processor 713 and an integrating unit 714 .

[0191] The receiving unit 711 receives external meeting minutes and sends the meeting minutes to the preprocessing unit 712 .

[0192] The preprocessing unit 712 will preprocess the conference records, for example, perform word segmentation, part-of-speech tagging and syntactic analysis on the conference records. Such preprocessing has been widely used during the preprocessing of natural language and is well known to those skilled in the art. Therefore, the preprocessing is not descri...

no. 3 example ）

[0202] In another embodiment, the method or device for identifying the name of a mentioned person can also be applied to the device for managing a conference. Figure 10 The structure of the apparatus for managing conferences according to the third embodiment of the present invention is illustrated.

[0203] Such as Figure 10 As shown, the device for managing conferences includes a receiving unit 1011 , a speech recognition unit 1015 , a preprocessing unit 1012 , a processor 1013 and an integration unit 1014 .

[0204] The receiving unit 1011 receives an external voice signal and forwards the voice signal to the voice recognition unit 1015 . The speech signal may be generated by, for example, a microphone or other device that captures the speaker's speech.

[0205] The speech recognition unit 1015 performs speech recognition to convert the speech into text, and then the text is sent to the preprocessing unit 1012 .

[0206] The preprocessing unit 1012 performs preprocessin...

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 relates to a method and device for identifying persons mentioned in a conversation. The method for identifying the persons mentioned in the conversion includes the steps of identifying at least one person name entity related to mentioned person names obtained from the conversation, obtaining a set of candidate identifiers related to the mentioned person names, obtaining at least one relation characteristic for each candidate identifier from internal resources and external resources, and based on the at least one relation characteristic, selecting one identifier from the set of candidate identifiers to serve as the identifier of the mentioned person names, wherein the relation characteristics represent the relations between the candidate identifiers and the at least one person name entity. According to the method and device, the mentioned persons can be accurately identified.

Description

technical field [0001] The present invention relates to a method and apparatus for identifying a person mentioned in a conversation, and more particularly, to a method and apparatus capable of accurately identifying a person name entity of a mentioned person in natural language processing. Background technique [0002] With the development of computer technology, there is a need to automatically recognize the names of people in a conversation. Usually, each name in a conversation can be divided into Mentioned Person Name (MPN) and Non-Mentioned Person Name (NMPN). Herein, mentioned names refer to the names of people mentioned during the conversation of the conversation, while unmentioned people names refer to the names of people mentioned in the context of the conversation but not during the conversation. To make these terms clearer, figure 1 An example of meeting minutes is shown. This meeting minutes is an example of a conversation. Such as figure 1 As shown, the minu...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/30G10L15/26
CPCG06F40/295G10L15/18G06F40/30G06F40/279G06Q50/01
Inventor 黄耀海李荣军胡钦谙
Owner CANON KK
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
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap