Use Learnable Knowledge Graph in Dialogue System for Visually Impaired Macro Navigation

Dialogue in natural language is the most important communication method for visually impaired. Therefore, dialogue system main subsystem impaired navigation system. The purpose of to understand user’s intention, gradually establish context through multiple conversations, and finally provide an accurate destination We use knowledge graph as basis reasoning system, then update so that conforms background. Based on experience using impaired, we expect same framework can be applied more fields order improve practicality human–computer interaction.