Audience Keyword Suggestion Using Engagement-Scored Search Terms
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Content providers face challenges in selecting relevant keywords for their content items, leading to missed opportunities in presenting content to users or overwhelming them with irrelevant results, and struggle to predict user search terms and correlations between different products.
Innovation Solution
A computer system generates seed keywords, expands them into candidate keywords using machine learning, scores them based on engagement metrics, and suggests the best keywords to define an audience for content recommendations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If content providers select a set of keywords for their content items, then the content items can be found and presented to users, but when the keywords are too few or specific, the content provider will miss the opportunity to have their content items presented to users
Solution Approach 1:
The patent segments keyword selection into multiple dimensions: core keywords (exact matches), synonyms (alternative terms), and related keywords (associative terms). This segmentation allows the system to provide a comprehensive keyword set that covers various search scenarios without overwhelming the content provider with a single monolithic keyword list.
Solution Approach 2:
The system performs preliminary keyword generation and expansion before the content provider needs to select or verify keywords. By pre-generating a comprehensive list of candidate keywords including synonyms and related terms, the system eliminates the need for manual brainstorming and provides ready-to-use keyword sets that maximize visibility.
2Quantity of substance
If content providers select a set of keywords for their content items, then the content items can be found and presented to users, but when the keywords are too many or too broad, the users may be overwhelmed with voluminous irrelevant results
Solution Approach 1:
The patent applies local quality by differentiating between types of keywords with distinct functions: core keywords for exact matches, synonyms for alternative terminology, and related keywords for associative searches. Each keyword type is optimized for specific search scenarios, allowing the system to maintain relevance while providing comprehensive coverage.
Solution Approach 2:
The system introduces an intermediary layer of keyword expansion that mediates between the content provider's original keywords and the user's search queries. By generating and presenting multiple expanded keyword variants, the system acts as a buffer that translates diverse user search terms into relevant content matches without exposing users to irrelevant results.
3Reliability
If content providers manually select keywords, then they can ensure relevance, but it is difficult to predict what search term a user may input when they try to find a particular content item
Solution Approach 1:
The patent creates a universal keyword expansion system that serves multiple functions simultaneously: it provides exact match keywords, synonym variations, and related term suggestions all within a single integrated output. This multi-functional approach ensures the system adapts to various user search behaviors and predicts diverse search terms without requiring separate manual processes.
Solution Approach 2:
The system incorporates feedback mechanisms where user search patterns and engagement data continuously refine the keyword generation algorithms. By analyzing actual user behavior and search results, the system improves its predictions of what terms users will input, making the keyword suggestions increasingly accurate and adaptable over time.
Data Source
AI summary
A computer-implemented method for suggesting keywords as a search term of a content item includes receiving, from a content provider, information about the content item in a database of content items. The method further includes generating a set of seed keywords related to the content item, and expanding the set of seed keywords to a plurality of candidate keywords. The plurality of candidate keywords are then scored based, at least in part, on an engagement metric measuring a user engagement with the content item in response to being presented with results from a search query comprising the candidate keyword. A candidate keyword is then selected from the plurality of candidate keywords based on the scoring, and stored relationally to the content item to define an audience for a recommendation about the content item, providing a suggestion to the content provider.