Calendar Event Content Serving With Dynamic Relevance Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing content serving systems fail to effectively utilize calendar events to provide relevant third-party content to users, as they rely solely on browsing history, which may not capture future-oriented event-related topics.
Innovation Solution
A system and method that creates a data structure with relevancy scores for keyword clusters based on event parameters, adjusting scores over time periods relative to events, and selects content based on these scores and calendar events to provide timely and relevant third-party content.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If content serving systems rely solely on browsing history, then the system complexity is reduced, but the relevance of third-party content to future-oriented events deteriorates
Solution Approach 1:
The system performs preliminary actions by accessing calendar events and determining event parameters before content selection occurs. It proactively identifies upcoming events and pre-determines relevant keyword clusters and relevancy scores, allowing the system to serve contextually relevant content without increasing operational complexity during the content delivery moment.
Solution Approach 2:
The patent introduces an intermediary data structure that bridges browsing history and calendar events. This data structure contains keyword clusters with relevancy scores that mediate between available data sources and content selection, enabling the system to incorporate future-oriented event information without directly complicating the core content serving mechanism.
2Loss of information
If the system creates a data structure with relevancy scores for multiple keyword clusters over multiple time periods, then the relevance of content to events is improved, but the device complexity increases
Solution Approach 1:
The system applies parameter changes by dynamically adjusting relevancy scores based on time periods relative to events. Different keyword clusters have different relevancy scores at different times (e.g., pre-event vs. post-event), allowing the system to optimize content relevance without creating entirely separate data structures for each scenario.
Solution Approach 2:
The data structure is designed to be dynamic, with relevancy scores that automatically adjust based on the time period relative to the event. This dynamic approach allows the system to handle multiple time periods and keyword clusters within a single flexible structure rather than requiring multiple static structures.
3Measurement precision
If the system determines event parameters and generates relevancy scores for multiple time periods, then the precision of content selection is improved, but the processing time increases
Solution Approach 1:
The system performs event parameter determination and relevancy score generation as preliminary actions before the actual content selection request is processed. By pre-processing calendar events and establishing the data structure with keyword clusters and scores in advance, the system reduces the processing time required at the moment of content delivery while maintaining high precision.
Data Source
AI summary
A method includes identifying an event category, identifying content serving opportunities associated with the event category, and, for each content serving opportunity, determining a calendar event for which content was served, identifying a time period between when the content was served and when the event was scheduled to occur, and determining a keyword cluster that effected selection of the served content. The method also includes identifying a subset of the content serving opportunities and determining, for each content serving opportunity of the subset, performance of the served content. The method also includes adjusting, based on the performance, a relevancy score corresponding to the keyword cluster that effected selection of the served content, receiving a request to serve content at a computing device associated with the calendar event, selecting additional content using the adjusted relevancy score, and transmitting the additional content to the computing device.