Browse Prior Art Database

Personalized Learning and Yourself in Natural Gaming (PLAYING) Engine

IP.com Disclosure Number: IPCOM000250204D
Publication Date: 2017-Jun-09
Document File: 5 page(s) / 230K

Publishing Venue

The IP.com Prior Art Database

Abstract

Disclosed is a novel type of game recommendation engine that personalizes computer-based learning models by applying several types of metrics. The novel engine looks at the game from two distinct views, the playable and the educational standpoints, and identifies the educational game that allows the user to enjoy the experience while meeting learning objectives.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 36% of the total text.

Personalized Learning and Yourself in Natural Gaming (PLAYING) Engine

Within new and upcoming technologies, various companies are looking to “gamify” the educational process. This idea of gamification has been considered for teaching both students and machines. The idea is that students need to enjoy the learning process, and games that are specifically tailored to students’ interests can help. Machines can use a game-like approach that is specifically tailored to the task and learning objective. Due to this need for individualized learning games, the correct gamified approach to learning must be selected for each application. Today, a human or machine with a rigid set of logic rules is assigned to this task.

Although multiple game recommendation engines exist and address the idea of personal game recommendation engines, an approach other than a human or a basic machine being tasked with the educational process is needed.

The novel contribution is a machine learning model capable of learning the lessons presented by these games as well as the way the content is presented, and then making a recommendation for the game that is best suited for each user or each task. At its core, this solution is a game recommendation engine; however, where most systems use recommend games by only looking at a few metrics (e.g., genre, player, relationships between players, etc.) this new approach breaks down the game into the basic components, or the educational values, that are presented in the game.

The novel engine looks at the game from two distinct views: the playable and the educational standpoints. The playable standpoint breaks the games apart, looking at the individual characteristics of each game (e.g., genre, intuitiveness, mental intensity, topics or themes, etc.). These metrics are related to the student’s profile, which enables the system to link the best-suited game to the learner. The second standpoint determines the educational merit of the game based on the metrics most closely related to the different topics presented in the game (e.g., sight words, vocabulary, mathematics, sciences, etc.) Using these academic topics, the engine recommends a game that addresses the subject in which the student needs the most practice.

The playing engine functions in three distinct phases: 1. Determining which games best suit the learner 2. Determining which games have the greatest educational merit 3. Comparing the results from phases 1 and 2 to determine which games are

most enjoyable to the user and meet educational objectives

Phase 1: Determining which games best suit the learner: In this phase, the engine creates a list of the games that the learner might enjoy playing. The system performs the following steps:

1. Reviews the user’s profile 2. Reviews the list of accessible games 3. Identifies games that are enjoyable to the learner. Metrics and data points

considered include, but are not limited to: (Note: Many of these metrics are novel; however, some ha...