Patent
Emotion recognition-based smart chat method, device, and computer apparatus
Feng Hui
- 18 Mar 2021
TL;DR: In this paper, an emotion recognition-based smart chat method, a device, a computer apparatus, and a storage medium are used to achieve combined user emotion recognition on the basis of current user voice data, preceding text corresponding to the current user's voice data and text data of a current utterance, thereby pushing an optimal response to a user terminal.
read more
Abstract: An emotion recognition-based smart chat method, a device, a computer apparatus, and a storage medium. The method comprises: performing emotion recognition on the basis of a voice of current user voice data to obtain a first emotion recognition result; performing combined recognition on the basis of text data corresponding to the current user voice data and a historical text data set existing within an interval value of a time-sequence ordered interval of current text data to obtain a second emotion recognition result; using a minimum value of recognition values respectively corresponding to the first emotion recognition result and the second emotion recognition result as a corresponding current emotion recognition result; acquiring, according to the current text data and the current emotion recognition result, current response text having a maximum level of similarity thereto from a response database; and converting the current response text into current response voice data, and sending the current response voice data to a user terminal. The method achieves combined user emotion recognition on the basis of current user voice data, preceding text corresponding to the current user voice data, and text data of a current utterance, thereby pushing an optimal response to a user terminal.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
References
Patent
Intelligent dialogue method and system based on emotion and semantics
Jian Renxian,Bai Zuo +1 more
- 17 May 2017
TL;DR: In this paper, an intelligent dialogue method and system based on emotion and semantics is proposed, which includes the steps of first obtaining multi-round dialogue information between a user and an intelligent dialog system; secondly determining the current emotions and semantics of the user based on the multiround dialog information; and thirdly, making a response conforming to the current emotion this paper.
24
Patent
System and Method for Monitoring and Visualizing Emotions in Call Center Dialogs by Call Center Supervisors
Thomas G. Zimmerman
- 02 Nov 2016
TL;DR: In this paper, a method, system, and a computer program product are provided for monitoring an emotional state of a conversation by monitoring a communication between first and second persons to determine the emotional states of the communication, providing a visual representation of the emotional state for display to a person having access to the communication.
9
Patent
Acoustic signal emotional information analysis method and device
Wang Futian,Li Jian,Zhang Lianyi,Wu Weidong +3 more
- 15 May 2018
TL;DR: In this paper, the authors presented an acoustic signal emotional information analysis method and device, which comprises the steps that when the emotional information expressed by the acoustic signal produced by the user is analyzed, the text information and the voice parameter information of the acoustic signals are extracted; text emotional analysis is performed on the text and voice emotional analysis on the voice parameters so as to obtain the emotions expressed by text information.
3
Patent
Scene and emotion oriented Chinese speech synthesizing method and device, and storage medium
Peng Huayi,Wang Jianzong +1 more
- 06 Sep 2019
TL;DR: In this paper, a scene and emotion oriented Chinese speech synthesizing method is described, where the input speech is subjected to emotion state analysis, the emotionstate of the synthesized speech is obtained according to the emotion state of input speech, and during speech synthesis, emotion state and scene analysis are added, thus the tone and mood of synthesised speech accord with the current interaction scene, the fixed tones and mood do not exist any more, in the human-computer interaction process, the output synthesizer sounds more like real people, and thus the user experience is enhanced.
3
Patent
Emotion recognition device, method and program
Fujimoto Atsushi,Nakajima Asami,Hodoshima Nao +2 more
- 15 Nov 2018
TL;DR: In this article, an autocorrelation processing unit 20 outputs a normalized autocorecrelation signal for a segment decomposed by a segmentation unit 10 and a feature quantity extraction unit 40 extracts a quantity of an analysis frame from the normalized autorecorrelation signal and a sound intensity measurement unit 30, using a period of several 10 ms to several 100 ms including one or more segments as an analysis frames.
2