Robot Voice Interaction Using Semantic Recognition and Knowledge Base

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current robots lack high-degree interactive capabilities, failing to effectively simulate character interactions with interactive objects due to limited recognition and feedback mechanisms.

Innovation Solution

An interactive method for robots that involves obtaining voice information, performing semantic recognition to determine conversation intentions, retrieving feedback information from a pre-configured knowledge base, and converting it into voice feedback to simulate user interactions, enhancing interaction freedom and intelligence.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If robots use simple voice recognition and playback mechanisms, then device complexity is reduced, but interactive capability and character simulation are limited

Engineering Contradiction:
Improveinteractive capabilityVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system segments the interaction process into distinct modules: voice information acquisition, semantic recognition, knowledge base retrieval, and voice playback. This modular segmentation allows each component to be optimized independently while maintaining overall system complexity at manageable levels.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

A conversation scenario knowledge base acts as an intermediary between the simple voice recognition system and the desired complex character simulation. The knowledge base pre-stores conversation patterns, character traits, and response templates, enabling the robot to simulate characters without requiring complex real-time decision-making algorithms.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If robots implement comprehensive semantic recognition and knowledge base retrieval, then conversation understanding improves, but processing time increases

Engineering Contradiction:
Improveconversation recognition accuracyVSAvoidresponse time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The conversation scenario knowledge base is pre-configured with character information, conversation patterns, and response templates before actual interaction begins. This preliminary preparation allows the system to retrieve pre-processed information during interaction, significantly reducing real-time processing time while maintaining high recognition accuracy.

Inventive Principle:
Principle #10Preliminary action

3Extent of automation

If robots use pre-configured knowledge bases, then interaction intelligence improves, but system adaptability to new scenarios decreases

Engineering Contradiction:
Improveinteraction intelligenceVSAvoidscenario flexibility
Core Design Contradiction:
Extent of automationVSAdaptability or versatility

Solution Approach 1:

The knowledge base is designed with a universal structure that can store multiple character profiles, conversation scenarios, and interaction patterns. This universal design allows the same system framework to handle diverse interaction scenarios by simply loading different knowledge base configurations, maintaining both intelligence and flexibility.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentUS11551673B2Interactive method and device of robot, and device
Publication Date: 2023.01.10 BEIJING BAIDU NETCOM SCI & TECH CO LTD
  • US11551673B2 patent drawing
  • US11551673B2 patent drawing
  • US11551673B2 patent drawing

AI summary

Embodiments of the present disclosure provide an interactive method of a robot, an interactive device of a robot and a device. The method includes: obtaining voice information input by an interactive object, and performing semantic recognition on the voice information to obtain a conversation intention; obtaining feedback information corresponding to the conversation intention based on a conversation scenario knowledge base pre-configured by a simulated user; and converting the feedback information into a voice of the simulated user, and playing the voice to the interactive object.