Server-Side Active Dialogue Initiation for Voice Interaction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current voice interaction systems rely on user-initiated commands, limiting the ability of devices to actively initiate dialogues, which is necessary for more natural and intelligent interactions.

Innovation Solution

A server-side processing method and system that establishes a communication connection with a voice client, receives an information stream, and performs dialogue decision-making to adapt and output dialogue content, enabling active dialogue initiation based on real-time client status and semantic analysis.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If the cloud returns a dialogue script to the client side for active dialogue initiation, then the client can play the dialogue script, but the timeliness is low because the client may play outdated scripts that no longer match the current scenario

Engineering Contradiction:
Improveactive dialogue initiation capabilityVSAvoiddialogue script timeliness
Core Design Contradiction:
Ease of operationVSLoss of time

Solution Approach 1:

Instead of the client initiating dialogue and receiving scripts from the server, the invention inverts the roles: the server actively initiates dialogues by pushing dialogue scripts to the client. This allows the server to control the timing and relevance of dialogue scripts, ensuring they match current scenarios while maintaining ease of active dialogue initiation.

Inventive Principle:
Principle #13The other way round (Inversion)

Solution Approach 2:

The invention implements a feedback mechanism where the client sends status information to the server, and the server uses this feedback to determine when to initiate dialogues. This ensures dialogue scripts are pushed at appropriate times when they remain relevant to the current scenario, resolving the timeliness issue.

Inventive Principle:
Principle #23Feedback

2Adaptability or versatility

If the client performs conditional determination for active dialogue, then the client can initiate dialogues, but the scenario is limited because the client lacks semantic and dialogue information

Engineering Contradiction:
Improveactive dialogue scenario coverageVSAvoidclient-side processing complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The invention extracts the complex semantic analysis and dialogue decision-making functions from the client side and relocates them to the server side. The client only needs to send status information and receive dialogue scripts, significantly reducing client complexity while expanding the range of active dialogue scenarios through server-side semantic capabilities.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The server acts as an intermediary that receives status information from the client, performs comprehensive semantic analysis, and generates appropriate dialogue scripts. This intermediary role enables rich active dialogue scenarios without requiring complex processing at the client level.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentUS12211508B2Server-side processing method and server for actively initiating dialogue, and voice interaction system capable of initiating dialogue
Publication Date: 2025.01.28 AISPEECH CO LTD
  • US12211508B2 patent drawing
  • US12211508B2 patent drawing
  • US12211508B2 patent drawing

AI summary

A server-side processing method for implementing an active initiation of a dialogue is disclosed, comprising: establishing a communication connection with a voice client, in response to a received request for establishing a connection from the voice client; receiving an information stream sent by the voice client through the communication connection; performing a dialogue decision-making process according to the information stream, obtaining and outputting an adapted dialogue content to the voice client upon determining that it is an active dialogue scenario. A server and a system for implementing an active initiation of a dialogue are also provided. The disclosed solutions realize intelligent decision-making for voice interaction, and can actively initiate a dialogue based on server-side decision-making, improving interaction experience and realizing intelligent interaction.