Pictorial Communication Event Identification Using Speech Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current phone log features on mobile devices only provide limited information about communication events, such as time and caller identity, without visual representation of the call content.
Innovation Solution
The method involves using speech or text recognition to identify words during a communication event and matching them with a library of reference pictures and colors, allowing for the display and storage of pictorial representations of these events, enabling users to visually identify conversation topics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If speech or text recognition is used to identify words from communication events and match them with reference pictures, then visual identification of conversation topics is improved, but device complexity increases
Solution Approach 1:
The system segments the communication event processing into distinct modules: speech recognition module, text recognition module, picture matching module, and background color identification module. Each module handles a specific task, making the overall complex system manageable and maintainable while achieving comprehensive visual identification of call content.
Solution Approach 2:
The patent introduces an intermediary picture library that stores pre-defined pictures with associated key words. The speech/text recognition results are matched against this intermediary library to identify relevant pictures, avoiding the need for complex real-time image generation while still achieving visual representation of conversation topics.
2Measurement precision
If a library of reference pictures and colors is maintained for matching with identified words, then pictorial representation accuracy is improved, but memory requirements increase
Solution Approach 1:
Instead of maintaining a comprehensive library of all possible pictures, the system applies local quality by creating targeted picture entries only for commonly discussed topics. Each picture in the library is associated with specific key words, ensuring high matching accuracy for relevant topics while minimizing overall library size and memory consumption.
3Loss of information
If speech and text recognition are implemented to capture communication content, then information completeness is improved, but processing time increases
Solution Approach 1:
The system performs preliminary action by pre-processing and storing speech and text recognition models before actual communication events. During calls, the pre-trained models can quickly transcribe and analyze content, significantly reducing real-time processing time while maintaining complete information capture of conversation topics.
Data Source
AI summary
The specification and drawings present a new method, apparatus and software product for pictorial identification of a communication event using speech or text recognition in an electronic device. The communication can be (but is not limited to) a telephone call, an electronic mail message, MMS, SMS, an instant message, etc. Words from the communication event are identified using the speech or text recognition by the electronic device and at least one picture out of a library of reference pictures is identified by comparing the identified words with the key picture words using a predetermined criterion. Color background of the identified standard picture can be also identified using the identified words and a further predetermined criterion. The identified picture can be displayed during the communications event or can be stored so the user can identify the topic of the communication event later on.