Zhejiang Lab

Taihao Li

Guanxiong Pei

Yulong Liu

Shukai Zheng

Shijie Ma

Jiantao Huang

A real-time evaluation method and system for a virtual reality (VR) immersion effect are provided. An electroencephalogram signal is collected while a VR video is played, a degree of emotional arousal and a degree of cognitive absorption are calculated in real time based on energy of frequency bands α, β, and θ that is obtained after wavelet transform, and finally, an immersion effect index is dynamically monitored for objective evaluation on an immersion effect. The method and the system realize real-time measurement and analysis, dynamically monitors a VR video immersion effect, adopts a multi-dimensional comprehensive calculation strategy and takes individual differences into account when calculating an index, effectively resolves problems such as after-fact reporting, social desirability biases, and strong subjectivity in questionnaire measurement and other measurement means, and has a broad market application prospect.

Real-time evaluation method and system for virtual reality immersion effect

The present invention discloses a real-time evaluation method and evaluation system for group emotion homogeneity. The method comprises the steps as follows: enabling testees to be in the same emotion induction environment, and collecting the original electroencephalograph (EEG) signals of multiple persons at the same time through online multichannel EEG equipment; and based on the average instantaneous phase per second of the beta frequency band and the energy value per second of the alpha frequency band obtained after wavelet transformation, calculating the time synchronization degree and the valence consistency degree in real time, and finally obtaining a group emotion homogeneity index for the objective evaluation of group emotion homogeneity.

Real-time evaluation method and evaluation system for group emotion homogeneity

An open domain dialog reply method and a system based on thematic enhancement are provided. The method includes: collecting and pre-processing text corpuses to obtain Chinese dialog corpus dataset, performing sentence breaking, word separation, and lexical annotation of dialogs and extracting noun words, performing enhancement of semantic and thematic information on each sentence, and learning vector representations of original sentences and enhanced sentences by a pre-trained sentence representation model, performing thematic aggregation enhancement by a graph convolutional neural network, and inputting the sentence vector after the thematic aggregation enhancement into a pre-trained generative model, generating a candidate set of dialog replies, and training a reply ranking selection model with a contrast learning manner to select the most suitable reply.

Open domain dialog reply method and system based on thematic enhancement

The present invention discloses a speech emotion recognition method and system based on fused population information. The method includes the following steps: S: acquiring a user's audio data; S: preprocessing the audio data, and obtaining a Mel spectrogram feature; S: cutting off a front mute segment and a rear mute segment of the Mel spectrogram feature; S: obtaining population depth feature information through a population classification network; S: obtaining Mel spectrogram depth feature information through a Mel spectrogram preprocessing network; S: fusing the population depth feature information and the Mel spectrogram depth feature information through SENet to obtain fused information; and S: obtaining an emotion recognition result from the fused information through a classification network.

Growing community of inventors

Zhejiang, China

Taihao Li