Snippet Extraction for Contextual Service Discovery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current web search and mobile app technologies fail to effectively respond to users' requests for services or apps available in their immediate location and time, requiring iterative computations that are infeasible on small mobile devices, and do not allow for contextual discovery and use of apps without prior download.
Innovation Solution
A method that deconstructs web pages into snippets based on visual and syntactical boundaries, establishes relationships between them, and uses machine learning to rank and display relevant snippets on mobile devices, allowing for contextual discovery and execution of apps without download, using push methods, scalable storage, and geographical and temporal indexing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If web pages are deconstructed into snippets and relationships are established between them, then the efficiency of discovering relevant services and apps is improved, but the complexity of the system increases
Solution Approach 1:
The patent deconstructs web pages into discrete snippets representing individual services or apps, establishing hierarchical relationships between them. This segmentation allows the system to present only relevant portions of web content to users, improving discovery efficiency while managing complexity through structured organization of information units.
Solution Approach 2:
The patent introduces a snippet accumulation component and relationship database as intermediaries between web pages and users. These components mediate the complex process of information retrieval by pre-processing and organizing web content into manageable snippets with defined relationships, thereby improving user-side efficiency without requiring complex processing on mobile devices.
2Measurement precision
If machine learning is used to rank and display relevant snippets, then the relevance of displayed information is improved, but the computational requirements increase
Solution Approach 1:
The patent performs machine learning-based ranking and relevance assessment in advance, during the snippet extraction and accumulation phase, rather than during user interaction. This preliminary processing creates pre-ranked snippet structures that can be efficiently queried without requiring intensive real-time computation on energy-constrained mobile devices, thus maintaining high relevance while reducing operational energy consumption.
3Measurement precision
If iterative computations are performed on mobile devices to find relevant services, then the accuracy of search results is improved, but the time required for discovery increases
Solution Approach 1:
The patent pre-processes web pages into structured snippets with established relationships and pre-ranks them using machine learning algorithms before user queries are submitted. This preliminary organization allows mobile devices to quickly retrieve and display relevant information without performing time-consuming iterative computations during user interaction, thereby maintaining accuracy while significantly reducing discovery time.
Solution Approach 2:
The patent extracts only the essential and relevant portions of web pages into discrete snippets, separating useful information from unnecessary content. This extraction process creates a streamlined data structure that enables fast querying and display on mobile devices, achieving high accuracy in result relevance while minimizing the time and computational resources needed for search operations.
Data Source
AI summary
A system and method is presented that extracts snippets form web pages according to specially designed logic. The extracted snippets might be made relevant to, i.e., indexed by, a location and time/day applicability. Such snippets may be thought of as apps or services that are defined only when a mobile terminal is in a pre-defined geographical area at a certain time and day (e.g., as defined by a calendar of events). Extracted snippets are stored and made searchable. Methods and a system are described to control the display of snippet search results. Snippets may be selected by user or by programmed logic and executed on the mobile terminal or in remote servers without the need to download the app or source code associated with the snippet.