Unlock instant, AI-driven research and patent intelligence for your innovation.

Method for performing emotion recognition on nature language

An emotion recognition and natural language technology, applied in the fields of natural language processing and machine learning, can solve problems such as difficult to correctly identify customers' emotional responses, and achieve the effect of natural communication

Inactive Publication Date: 2018-04-20
SHANDONG SYNTHESIS ELECTRONICS TECH
View PDF4 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when applied to a robot dialogue system with natural language interaction, it is often difficult to correctly identify the correct emotional response of the customer

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 for performing emotion recognition on nature language
  • Method for performing emotion recognition on nature language
  • Method for performing emotion recognition on nature language

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0020] Based on the intelligent interactive robot, this embodiment provides a method for emotion recognition in natural language, which uses a robot microphone to collect voices, and then conducts emotion recognition based on text content and voice, and then integrates the two aspects of information to determine whether the customer Emotion categories, which allow robots to interact more naturally. This method can also be applied to other devices capable of human-computer interaction, such as mobile phones, computers, etc., including but not limited to these devices.

[0021] Such as image 3 As shown, the method includes the following steps:

[0022] S01), collect voice information carrying natural language, convert it into text information through voice recognition, input it into the pre-established text sentiment classifier, judge whether ...

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 a method for performing emotion recognition on a nature language. The method comprehensively considers about information of voice and text, judges a correct emotion reaction ofa customer through a machine learning algorithm, and makes a robot communicate with the customer more intelligently and naturally according to the customer's question and the emotion recognition result.

Description

technical field [0001] The invention relates to a method for emotion recognition aimed at natural language, which belongs to the fields of natural language processing and machine learning. Background technique [0002] As the most direct and effective way of human-computer interaction, natural language is the most accurate and complex important medium for conveying and expressing information. The normal natural language interaction between people often contains emotional color. Under different emotions, the same sentence may express different meanings. Therefore, sound and language are important parameters for semantic understanding. The current chatbots basically use speech recognition technology to perform semantic understanding and interaction based on the speaker's text content. The response received by the user is either a text message or an emotionless feedback through TTS speech synthesis. This method of semantic understanding only relying on the text content withou...

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): G06F17/30G06F17/27G10L25/63
CPCG06F16/35G06F40/279G10L25/63
Inventor 申冲张传锋朱锦雷
Owner SHANDONG SYNTHESIS ELECTRONICS TECH