Semantic Function Search for Electronic Device Features

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Users face difficulties in accurately finding desired functions on electronic devices due to varying naming conventions and the need for precise keyword entry, leading to inefficient search processes.

Innovation Solution

Employing a natural language model to generate semantic feature vectors for search queries and device functions, determining semantic similarity, and providing search results based on this similarity, allowing for flexible and accurate function discovery without exact keyword matching.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If users enter keywords to search for device functions, then search functionality is provided, but users need to accurately enter relevant keywords and may need to try multiple keywords before finding the desired function

Engineering Contradiction:
Improveease of function searchVSAvoidtime spent on multiple keyword entries
Core Design Contradiction:
Ease of operationVSLoss of time

Solution Approach 1:

The patent introduces semantic feature vectors as an intermediary between user search queries and device functions. Instead of directly matching keywords with function names, the system converts both the search query and function descriptions into semantic feature vectors using a natural language model, then compares these vectors to find matches. This intermediary representation enables more flexible and accurate matching without requiring users to know exact function names or try multiple keywords.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If traditional keyword matching is used for function search, then simple search implementation is achieved, but users cannot find desired functions when using different naming conventions or imprecise keywords

Engineering Contradiction:
Improveflexibility of function searchVSAvoidaccuracy of function search result
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The patent transforms the search problem from exact keyword matching to semantic similarity comparison by changing the parameter representation. Instead of comparing discrete keywords with function names, the system converts text into continuous semantic feature vectors that capture the meaning and context. This parameter transformation allows the system to handle different naming conventions, synonyms, and imprecise queries while maintaining high accuracy in finding the desired functions.

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If exact keyword matching is required for function search, then precise function identification is achieved, but users face difficulties when not familiar with the exact function name

Engineering Contradiction:
Improveprecision of function identificationVSAvoidconvenience of function search
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The patent replaces the mechanical keyword-matching system with a semantic understanding system based on natural language models. Instead of relying on users to input exact keywords that mechanically match function names, the system uses AI-based semantic analysis to understand the intent behind user queries. This substitution maintains precise function identification while dramatically improving ease of operation, as users can search using natural language descriptions rather than technical function names.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS12554729B2Electronic device and device function search method thereof
Publication Date: 2026.02.17 ASUSTEK COMPUTER INC
  • US12554729B2 patent drawing
  • US12554729B2 patent drawing
  • US12554729B2 patent drawing

AI summary

An electronic device and a device function search method thereof are provided. The method is adapted for the electronic device having a plurality of functions and includes the following steps. A search query is obtained through an input device. A first semantic feature vector of the search query is generated by using a natural language model. Semantic similarity between the first semantic feature vector of the search query and at least one second semantic feature vector of each function is determined. A search result corresponding to the search query is determined according to the semantic similarity between the first semantic feature vector of the search query and the at least one second semantic feature vector of each of the functions. The search result includes at least one of the functions.