An empathetic reply generation method based on dynamic interaction of utterance-level features

By using a dynamic interaction-based empathic response generation method based on discourse-level features, and leveraging a Transformer encoder and a multi-layer heterogeneous graph attention network, this method addresses the problems of coarse-grained modeling and context-detached reasoning in existing technologies. This enables computer systems to better understand human emotions and generate natural, context-appropriate responses.

CN117808103BActive Publication Date: 2026-06-02NORTHEASTERN UNIV CHINA
2 Cites 0 Cited by

Patent Information

Application Number
CN202410014923.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-01-04
Publication Date
2026-06-02
Estimated Expiration
2044-01-04

AI Technical Summary

Technical Problem

Existing methods for generating empathic responses suffer from coarse-grained dialogue history modeling and context-detached common-sense reasoning, resulting in responses that are not fluent, have low consistency, and lack empathy.

Method used

We employ a dynamic interaction method based on discourse-level features. By combining a Transformer encoder and a multi-layer heterogeneous graph attention network with a DIALeCT contextualized common sense inferencer, we construct a two-stage heterogeneous graph attention network to capture the interaction of emotional and intentional features in the context in a fine-grained manner. This allows us to train the model to generate more natural and human-like responses.

Benefits of technology

This enables computer systems to better understand human emotions, generate more context-appropriate response texts that resonate with users' emotions, adapt to different fields and cultural backgrounds, and improve the naturalness and readability of responses.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The application provides a kind of empathetic reply generation method based on speech level feature dynamic interaction, it is related to artificial intelligence technical field.The method of artificial intelligence and natural language processing enables computer system to understand, identify and simulate human emotion, and replies in the way of emotional, considerate and understanding.By the method of the application, computer system can better understand human emotion, and communicate and interact with people in a more natural and more humanized way, which overcomes the problems of incoherent reply content, low consistency and poor empathy caused by coarse-grained dialogue history modeling and context-independent common sense reasoning in the prior art.
Need to check novelty before this filing date? Find Prior Art