Smart Device Speech Control via Cloud-Matched Interface Entries
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current speech control systems for smart devices are limited in flexibility and accuracy, as they can only perform operations defined in the instruction set and struggle to accurately interpret user intentions when interacting with specific interface elements or media content.
Innovation Solution
The method involves receiving user-input speech information, determining scenario elements associated with the speech recognition result, generating entries for these elements, and sending them to a cloud server for matching, allowing the system to perform interface operations beyond the predefined instruction set and improving accuracy by selecting the best-matched entry based on edit distance calculations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a fixed instruction set is used for speech control, then the system structure is simple, but the flexibility and adaptability of speech control are limited
Solution Approach 1:
The patent implements dynamic speech control by allowing the system to adaptively generate and update instruction sets based on real-time speech recognition results and interface elements, rather than relying on a static fixed instruction set. This enables the system to flexibly handle various speech commands while maintaining manageable complexity through automated adaptation.
Solution Approach 2:
The system performs self-service by automatically generating appropriate instructions from speech recognition results and matching them with interface elements without requiring manual configuration of a comprehensive fixed instruction set. The system serves itself by dynamically creating the necessary control logic based on the current interface state and user intent.
2Adaptability or versatility
If speech control is limited to predefined instructions, then the system is easy to implement, but it cannot perform operations for instructions absent from the instruction set
Solution Approach 1:
The patent implements a universal speech control mechanism where the system can generate instructions for any interface element rather than being limited to predefined instructions. The speech recognition result is matched with various interface elements (buttons, text fields, media content) based on spatial and semantic relationships, enabling the system to handle diverse operations without requiring separate predefined instructions for each element.
Solution Approach 2:
The patent introduces an intermediary matching mechanism that bridges speech recognition results and interface elements. This intermediary process analyzes the spatial relationship between the speech input and interface elements to determine the user's intended target, allowing the system to perform operations on elements without having explicit predefined instructions for each specific element.
3Measurement precision
If the cloud server searches for movie names without context, then the search scope is broad, but the accuracy of speech control is reduced
Solution Approach 1:
The patent applies local quality by incorporating contextual information from the current interface into the speech matching process. Instead of performing a global search across all possible content, the system narrows the search scope to relevant interface elements based on their spatial and semantic context, thereby improving speech control accuracy without requiring overly complex matching processes.
Solution Approach 2:
The system performs preliminary action by pre-processing and analyzing the interface layout and element relationships before executing the speech matching. This preliminary analysis of the interface context enables the cloud server to perform more accurate and targeted searches, improving speech control accuracy while managing complexity through advance preparation.
Data Source
Figure 1
Figure 2~3
Figure 4
AI summary
The present disclosure provides an interface intelligent interaction control method, apparatus and system, and a storage medium, wherein the method comprises: receiving user-input speech information, and obtaining a speech recognition result; determining scenario elements associated with the speech recognition result; generating an entry corresponding to each scenario element and sending the speech recognition result and the entry to a cloud server; receiving an entry which is best matched with the speech recognition result, returned by the cloud server and selected from the received entries; performing an interface operation corresponding to the best-matched entry. The solution of the present disclosure can be applied to improve flexibility and accuracy of the speech control.