Speech Message Routing via Text Recognition and Recipient Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional speech message routing in communication networks requires users to enter telephone numbers or addresses of recipients, which is inconvenient, especially when sending messages to multiple recipients or in situations where this information is not readily available.
Innovation Solution
A message server that receives spoken messages, converts them into text using speech recognition, and identifies recipients based on the text content, allowing messages to be routed without requiring explicit recipient information, using contact lists and contextual information for accurate routing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If users enter telephone numbers or addresses of recipients manually, then message routing accuracy is improved, but ease of operation deteriorates
Solution Approach 1:
The system performs automatic recipient identification by analyzing the speech message content itself. The message server extracts recipient information from the spoken message without requiring manual user input, allowing the system to serve itself in the information gathering process.
Solution Approach 2:
The patent replaces the mechanical manual entry process with automated speech recognition and natural language processing. The system uses speech-to-text conversion and AI-based interpretation to automatically extract recipient information from spoken messages, substituting manual typing with automated digital processing.
2Ease of operation
If speech recognition is used to convert spoken commands to text, then ease of operation is improved, but loss of information may occur due to interpretation errors
Solution Approach 1:
The system employs feedback mechanisms where the speech recognition entity translates speech to text, the AI function interprets the meaning, and the system can verify or refine the interpretation based on contextual information and contact lists, creating a feedback loop that improves accuracy.
Solution Approach 2:
The patent introduces an AI function as an intermediary between speech recognition and message routing. This intermediary layer interprets the meaning of the converted text and deduces the intended recipient, acting as a mediator that reduces information loss by adding contextual understanding.
3Adaptability or versatility
If speech messages are sent to multiple recipients, then communication versatility is improved, but operation complexity increases due to separate address entry requirements
Solution Approach 1:
The message server is designed with universal functionality to handle speech messages intended for single or multiple recipients through the same automated process. The system can identify and route to one or many recipients based solely on the speech message content, making the routing mechanism multi-functional.
Solution Approach 2:
The system automatically identifies multiple recipients by analyzing the speech message content and cross-referencing with contact lists, eliminating the need for users to manually specify multiple addresses. The routing process serves itself by extracting all necessary recipient information from the message content.
Data Source
AI summary
A method and message server (204) for routing a speech message, received (2:1) from a user equipment (200) of a sending user, to at least one recipient (208, 210) in a communication network. After obtaining (2:2) a text version created by speech recognition (206) of the received speech message, the at least one recipient is identified (2:3) by the message server based on the obtained text version, and the speech message is then routed (2:5) to the identified at least one recipient.