Context-Aware Model for E-Sports Important Event Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies struggle to efficiently recognize and classify important events in complex game content, such as e-sports games, which generate large amounts of data including in-game situations, voice signals, and viewer interactions.
Innovation Solution
A context-aware model generating method that utilizes machine learning to analyze in-game data, game video data, and relay server data to determine the occurrence of important events in e-sports games. This method involves extracting in-game situation information, voice utterance information, and relay situation information to generate a context-aware model that identifies important events.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple data sources (in-game data, game video data, relay server data) are collected and analyzed to determine important events, then the accuracy of event identification is improved, but the device complexity and data processing requirements increase
Solution Approach 1:
The patent segments the complex data collection system into three distinct data sources: in-game data (game state, player actions), game video data (broadcast footage, commentary), and relay server data (viewer interactions, chat). Each data source is processed independently through dedicated modules before being integrated by the context-aware model, reducing overall system complexity while maintaining comprehensive analysis capability.
Solution Approach 2:
The patent introduces a context-aware model as an intermediary component that receives pre-processed data from multiple sources and integrates them to determine important events. This intermediary layer simplifies the architecture by providing a centralized processing point that coordinates between diverse data sources and output requirements, managing complexity while enabling multi-source analysis.
2Reliability
If machine learning is applied to analyze complex game data and generate context-aware models, then the reliability of event determination is improved, but the loss of time for data processing and model generation increases
Solution Approach 1:
The patent applies preliminary action by pre-processing and organizing data from multiple sources before feeding them to the context-aware model. Data are cleaned, formatted, and structured in advance, reducing the computational burden during real-time event determination. This preliminary preparation maintains high reliability while minimizing processing time during critical moments.
Solution Approach 2:
The patent implements partial action by focusing the machine learning model on specific important events rather than analyzing all game data comprehensively. The context-aware model is trained to identify and prioritize key events (e.g., game-winning moments, significant plays) rather than processing every data point, reducing time loss while maintaining reliability for critical determinations.
3Loss of information
If in-game situation information, voice utterance information, and relay situation information are extracted and analyzed, then the completeness of context understanding is improved, but the quantity of data to be processed increases
Solution Approach 1:
The patent extracts only the most relevant features and information from each data source rather than processing complete raw data. From in-game data, it extracts situation information (game state, player positions); from game video data, it extracts voice utterances and visual events; from relay server data, it extracts viewer reactions and chat sentiments. This selective extraction maintains contextual completeness while significantly reducing data volume.
Solution Approach 2:
The patent applies local quality by processing different types of data with specialized methods tailored to their specific characteristics. In-game structured data receives different treatment than unstructured voice data or viewer interaction data. Each data type is processed with appropriate techniques and filtered to retain only locally relevant information, optimizing the balance between completeness and volume.
Data Source
AI summary
Provided are a context-aware model generating method, an important event determining method, and an in-game context management server for performing the same methods. The context-aware model generating method includes generating a context-aware model which determines whether an important event of a video game occurs by using in-game data, utterance data, and chat data collected from the video game capable of being broadcasted as a sports game video. The important event determining method includes combining candidate events predictable from each of the in-game data, the utterance data, and the chat data based on the context-aware model, and determining, as an important event, a candidate event including a duplicate game content among candidate events.