Dynamic Event Tag Generation for Accurate Event Searching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Event platform systems face challenges in providing accurate event searching due to reliance on manually provided static metadata tags, which do not account for the dynamic and ever-changing linguistic context of real-time event traffic, leading to suboptimal search results.
Innovation Solution
The implementation of a machine learning model trained using both static event tags and dynamically-generated event tags, where dynamic tags are created through analysis of real-time event traffic using natural language processing and topic modeling, to enhance event searching accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If static event tags are used for event searching, then the system is simple to operate, but the search accuracy deteriorates due to inability to capture dynamic linguistic context
Solution Approach 1:
The patent applies dynamics by transitioning from static event tags to dynamic event tags that are continuously generated and updated based on real-time event traffic analysis. The event tags are no longer fixed but adapt over time to reflect changing linguistic contexts, thereby improving search accuracy while managing system complexity through automated processes.
Solution Approach 2:
The system implements self-service by automatically generating event tags through unsupervised learning models without requiring manual annotation. The model autonomously analyzes event traffic patterns and generates tags that capture linguistic context, eliminating the need for continuous human intervention while maintaining high search accuracy.
2Measurement precision
If dynamic event tags are generated through real-time analysis, then search accuracy improves, but the processing time increases
Solution Approach 1:
The patent applies preliminary action by pre-training the unsupervised learning model on historical event traffic data before deployment. This allows the model to learn patterns and generate tags more efficiently during real-time operation, reducing processing time while maintaining the accuracy benefits of dynamic tag generation.
Solution Approach 2:
The system implements continuity of useful action by continuously updating and refining event tags based on ongoing event traffic analysis. Rather than performing discrete, time-consuming analyses, the model operates continuously to generate and update tags in real-time, maintaining high search accuracy without significant processing delays.
3Adaptability or versatility
If manual categorization of events is used, then the implementation is straightforward, but the adaptability to changing event patterns deteriorates
Solution Approach 1:
The patent applies mechanics substitution by replacing manual categorization (mechanical human effort) with an unsupervised machine learning model. The model automatically analyzes event traffic patterns and generates tags without human intervention, significantly improving adaptability to changing event patterns while maintaining high levels of automation.
Solution Approach 2:
The system implements parameter changes by allowing event tags to dynamically change based on observed event patterns and linguistic contexts. Rather than fixed categories, the tags adapt their values and meanings based on real-time data, enhancing versatility while fully automating the categorization process.
Data Source
AI summary
An apparatus includes at least one processing device configured to obtain event metadata for events published by event sources to an event platform, the event metadata comprising static event tags for respective ones of the events. The at least one processing device is also configured to generate dynamic event tags having an association with event types based at least in part on analysis of real-time event traffic comprising a subset of the events published by the event sources to the event platform over a designated time period. The at least one processing device is further configured to train a machine learning model utilizing the static event tags and the association of the dynamic event tags with the event types, receive a query comprising event parameters, and provide a response to the query by utilizing the trained machine learning model to match events with the event parameters in the query.