Sentiment-annotated video game fragment generation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The creation of video game fragments is challenging due to the difficulty in identifying desirable portions of a game that cater to different players' interests, such as humorous or exciting parts. Manual identification is time-consuming and may not produce optimal results for various players.
Innovation Solution
A computer-implemented method and system that record a video game session, identify locations where player or spectator interest exceeds a threshold, and use a trained machine learning model to determine sentiment based on live game feedback. An annotation of the sentiment is associated with the game state data at these locations, allowing for the fragmentation of the game into playable fragments that match player preferences.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual identification of desirable video game portions is used, then player preference accuracy is improved, but time consumption increases
Solution Approach 1:
The patent replaces manual mechanical identification of desirable game portions with an automated system that uses machine learning models and sentiment analysis. The system processes game state data, player feedback, and sentiment annotations automatically to identify interesting portions, eliminating the need for manual review while maintaining or improving accuracy through algorithmic analysis of multiple data sources.
Solution Approach 2:
The system enables self-service by allowing the video game system itself to automatically identify and fragment desirable portions through integrated sentiment analysis and machine learning. The game system uses its own collected data (game state, player feedback, sentiment annotations) to autonomously determine which portions are interesting, without requiring external manual intervention.
2Manufacturing precision
If manual generation of video game fragments is used, then fragment quality is improved, but productivity decreases
Solution Approach 1:
The patent segments the video game into multiple playable fragments based on sentiment annotations and identified interesting portions. The system divides the continuous game content into discrete, manageable fragments that can be independently generated and delivered, allowing parallel processing and automated assembly of high-quality segments without manual intervention for each fragment.
Solution Approach 2:
The system performs preliminary action by pre-identifying and annotating sentiment and interesting portions during or after game playback. This advance preparation of sentiment annotations and fragment identification enables rapid automated generation of high-quality fragments later, separating the analysis phase from the generation phase to improve overall productivity.
3Productivity
If automated sentiment analysis is implemented, then time efficiency is improved, but system complexity increases
Solution Approach 1:
The patent implements a multi-functional system where the video game system performs multiple roles: it plays the game, collects game state data, captures player feedback, performs sentiment analysis, identifies interesting portions, and generates fragments. This universal system approach consolidates multiple functions into one integrated platform, improving time efficiency while managing complexity through unified architecture rather than separate independent systems.
Solution Approach 2:
The system uses sentiment annotations as an intermediary layer between raw game data and fragment generation. The sentiment analysis component acts as a mediator that translates diverse input data (game state, player feedback) into structured annotations that guide the fragment identification process, simplifying the overall system architecture by introducing a standardized intermediate representation.
Data Source
AI summary
A system includes a game recorder that records a first session of a video game, the first session including game state data generated by processing player input data by a video game processor, an input processor that identifies a location within the video game at which interest of one or more players or spectators exceeds a predetermined threshold, a trained machine learning model that determines a sentiment of the one or more players or spectators at the location based on live game feedback, and a storage device that associates an annotation of the sentiment with the game state data at the location within the video game.