Word-Score Based Keyword Selection for Content Relevance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current content delivery systems face challenges in selecting and displaying relevant online content items, such as advertisements, as they often rely on keyword matching that does not effectively account for the significance of individual words in search queries, leading to less focused and relevant results.
Innovation Solution
A method that determines a word-score for each word in a query based on past user interactions, using this score to derive and select relevant keywords, which are then used to identify and display more relevant content items, such as advertisements, by analyzing user click-through rates and interaction data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If keyword matching is used to select content items, then the process is simple and fast, but the relevance and effectiveness of search results deteriorates
Solution Approach 1:
The patent changes the parameter for keyword selection from simple keyword matching to word-score-based selection. The word-score is calculated based on user interaction data (clicks, views, conversions) and is used to rank and select keywords, thereby improving search result relevance while maintaining processing efficiency through automated scoring mechanisms
2Device complexity
If all words in a query are treated equally, then the processing is simple, but the focus on significant words deteriorates
Solution Approach 1:
The patent applies local quality by assigning different weights (word-scores) to different words in a query based on their individual significance. Instead of treating all words equally, the system calculates word-scores based on historical user interaction data and uses these scores to selectively emphasize important words during content matching, thereby improving precision without excessive complexity
3Measurement precision
If user interaction data is collected and analyzed to determine word-scores, then the search result relevance is improved, but the data processing complexity increases
Solution Approach 1:
The patent implements preliminary action by pre-calculating and storing word-scores based on historical user interaction data before actual search queries are processed. The system maintains a database of word-scores that can be quickly retrieved and applied to new queries, thereby improving measurement precision while avoiding the complexity of analyzing interaction data in real-time during each search operation
Data Source
AI summary
This specification describes technologies relating to displaying online content. In general, one aspect of the subject matter described in this specification can be embodied in methods that include receiving a first query associated with a user request. The methods may further include determining a score for a word in the first query based at least in part on user interaction with a content item served for display in response to a past query that includes the word. The methods may further include selecting a keyword derived from the first query based at least in part on the score. The methods may further include identifying candidate content items using the selected keyword. Other embodiments of this aspect include corresponding systems, apparatus, and computer program products.