Game Video Scoring Model for User Appeal Evaluation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for assessing game and interactive content development are inaccurate and lack effective tools for evaluating user appeal, making it difficult to design engaging gameplay and promotional materials.
Innovation Solution
A system and method for analyzing video data using a video analysis model to generate scoring parameters, leveraging popular video content for training, and applying machine learning techniques to evaluate and modify game content for improved user appeal.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional methods are used to assess game content by showing draft elements to a select group, then some evaluation can be obtained, but the accuracy of review for the intended audience is poor and it is difficult to obtain a desired focus group
Solution Approach 1:
The patent replaces the mechanical system of manual focus group recruitment and human evaluation with an automated machine learning model that processes video content and generates evaluation scores. The video analysis model automatically assesses game content without requiring physical focus groups, thereby improving evaluation accuracy while eliminating the operational difficulty of obtaining and managing focus groups.
2Adaptability or versatility
If no automated analysis system is used, then manual evaluation can be performed, but the process lacks effective tools for evaluating user appeal and designing engaging gameplay
Solution Approach 1:
The video analysis model performs self-service by automatically processing video content, extracting features, and generating evaluation scores without requiring manual intervention. The system trains on diverse video data and independently applies learned patterns to assess game content, providing versatile evaluation capabilities while eliminating the need for additional manual tools or processes.
3Loss of time
If promotional material is assessed prior to release using conventional methods, then some feedback can be obtained, but the assessment is difficult and time-consuming
Solution Approach 1:
The system performs preliminary action by training the video analysis model in advance on diverse video data before it is needed for actual game content assessment. This pre-training enables the model to quickly and accurately evaluate promotional material and game content when needed, reducing assessment time while the trained model handles the complexity internally without requiring complex manual processes at assessment time.
Data Source
AI summary
System, process and device configurations are provided for analyzing video data, such as electronic game data, and generating scoring data for video data. Processes and device configurations include training a video data analysis model to generate scoring parameters, and for an evaluation tool for video data. Highly viewed and popular videos may be used as training input to the video analysis model. At least one score parameter may be determined for scoring videos. For electronic games, at least one score may be associated with a game scene, gameplay storylines, and for scoring video data in general. Analysis of game titles and game design may be performed during design to ensure that game scenes will have a high likelihood of user interest. Embodiments may also include modifying gameplay and gameplay storylines, and evaluating game promotional videos.