Keyword Generation for Content Verticals
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies face challenges in efficiently selecting and displaying relevant online content, particularly in identifying the most relevant information for content items within specific verticals, such as movies or video games, to match user interests and preferences.
Innovation Solution
A method and system that generate keywords for content items by receiving structured data indicating a category, retrieving stored data to identify domains and relationship types, forming queries based on data elements, and searching domains to determine relevant keywords for impression allocation decisions, ensuring that content items are selected and displayed effectively.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If general keyword generation methods are used for content items, then content selection can be performed, but the relevance and accuracy of keywords for specific verticals (e.g., movies, video games) is insufficient
Solution Approach 1:
The patent segments the keyword generation process by creating vertical-specific processing paths. Different verticals (movies, video games, etc.) have dedicated keyword generation modules that apply domain-specific rules and relationships, allowing precise keyword generation for each vertical without requiring a completely separate system for each domain.
Solution Approach 2:
The patent adds a vertical dimension to the keyword generation system. Instead of a single flat keyword generation process, the system introduces vertical-specific layers that incorporate domain knowledge, relationships, and rules specific to each content category, thereby improving accuracy without proportionally increasing overall system complexity.
2Measurement precision
If vertical-specific knowledge is incorporated into keyword generation, then content matching accuracy improves, but processing time and computational resources increase
Solution Approach 1:
The patent pre-computes and stores vertical-specific relationships, rules, and domain knowledge in structured formats before keyword generation is needed. This preliminary preparation allows the system to quickly retrieve and apply pre-validated vertical-specific information during actual keyword generation, reducing real-time processing requirements while maintaining high accuracy.
3Adaptability or versatility
If multiple domains are searched to generate comprehensive keywords, then keyword coverage improves, but search efficiency and processing speed decrease
Solution Approach 1:
The patent applies local quality by tailoring the search scope and depth to each specific vertical and content item. Instead of uniformly searching all domains for all content, the system selectively searches only the most relevant domains based on the content's vertical classification and specific characteristics, thereby maintaining comprehensive coverage where needed while improving efficiency elsewhere.
Data Source
AI summary
This specification describes technologies relating to generation of keywords. In general, one aspect of the subject matter described in this specification can be embodied in methods that include receiving structured data describing a content item, the structured data indicating a category for the content item. The methods may further include searching domains associated with the category using a first query, formed based on data elements in the structured data, to identify resources associated with the identified domains. The methods may further include determining one or more queries based on data reflecting past search queries, where each of the one or more determined queries resulted in one or more of the identified resources being returned as part of a search result, and determining keywords based on the one or more determined queries. The methods may further include transmitting or storing the keywords for use in impression allocation decisions.