Dynamic Ad Selection via Semantic Analysis of User Interactions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Mobile device users face ineffective advertising due to small screen sizes and imprecise user interactions, leading to irritation and lack of engagement with basic, static ads that do not spark user interest.
Innovation Solution
A method that identifies search candidates by analyzing displayed content, applying content styles, performing syntactic and morphological analysis, calculating weights, and selecting relevant information blocks based on user interaction points to display targeted and relevant information dynamically.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If conventional search and advertising methods are used on mobile devices, then basic advertisement data can be displayed, but user engagement is low and ads irritate users due to small screen sizes and imprecise interactions
Solution Approach 1:
The patent segments the advertisement delivery process into multiple stages: initial content display, user interaction detection, semantic analysis of interaction context, and dynamic ad selection. This segmentation allows the system to overcome screen size limitations by presenting ads only after confirming user interest through contextual analysis, rather than displaying basic ads immediately on limited screen space.
Solution Approach 2:
The system performs preliminary semantic analysis of the user's interaction context before selecting and displaying advertisements. By analyzing the meaning and context of user interactions in advance, the system prepares targeted ads that are relevant to the user's current needs, thereby improving engagement without requiring larger screens or more complex user operations.
2Productivity
If static advertisement blocks are displayed on mobile devices, then monetization can occur, but the ads do not attract attention or spark user interest
Solution Approach 1:
The patent transforms static advertisement blocks into dynamic, context-aware ad selections. The system continuously monitors user interactions, performs real-time semantic analysis, and dynamically selects advertisements that match the user's current context and interests. This dynamic approach ensures ads are relevant and engaging rather than static and irritating.
Solution Approach 2:
The system implements a feedback loop where user interactions are analyzed to understand user intent and context, which then informs subsequent ad selections. This feedback mechanism ensures that advertisements are continuously optimized based on actual user behavior and preferences, thereby increasing user interest and monetization effectiveness.
3Adaptability or versatility
If traditional advertising approaches are used, then each ad can be made different, but mobile users in on-the-go mode do not have time to recognize core meanings
Solution Approach 1:
The patent replaces manual ad creation and selection processes with automated semantic analysis and machine learning algorithms. The system automatically analyzes user interactions, extracts meaningful context, and selects appropriate advertisements without requiring users to spend time recognizing ad meanings. This substitution of mechanical processes with intelligent automation resolves the contradiction between ad variation and user time.
4Ease of operation
If semantic analysis and multiple processing steps are applied to select relevant information, then targeted advertisements can be displayed, but system resources and processing complexity increase
Solution Approach 1:
The system performs preliminary semantic analysis and content processing in advance, building indexes and understanding content structures before user interactions occur. This preliminary processing reduces the computational burden during actual ad selection, allowing complex semantic analysis to be conducted efficiently without overwhelming mobile device resources during critical user interaction moments.
Data Source
AI summary
Method for identifying search candidates, including receiving a content that includes unprocessed content, markup elements and element styles; identifying raw content; applying content styles to the markup elements to determine which sequence of parts of content produces compact logically linked and visually bounded parts of the content; performing syntactic analysis to generate parsing trees; performing morphological analysis to determine parts of speech and word morphology in bounded parts; performing stemming on the parts of speech and constructing chains that meet grammar rules; identifying zests and calculating weights of the zests; applying weights to the chains to determine zests; adjusting the weights based on a distance from a point of user interaction with the content; selecting zests with the highest weight and degree of belonging to a region around the point of interaction; adjusting zests near the point of interaction and using it for selection of information to display.