I-Corps: A flexible learning and assessment tool based on a skill mastery approach

I-Corps项目的广泛影响/商业潜力将通过提高大学培养具有全球竞争力的STEM（科学、技术、工程和数学）劳动力的能力，为国家利益服务。该项目的核心技术为学生提供了在个性化环境中练习问题的机会，直到掌握为止。该技术还使教师可以轻松地将频繁的第二次测试纳入其中，同时扩展以支持更多的学生。这些教学策略已被证明可以降低STEM课程的失败率，并可能对女性、少数民族、第一代学生和社会经济地位较低的学生产生不成比例的好处。一般来说，帮助这些学生可以提高他们的记忆力，对不同类型的学生来说尤其如此。该项目的商业潜力包括抓住快速增长的大学教育技术市场的很大一部分，其潜在市场遍及全球以及非大学教育部门。I-Corps项目旨在开发一个软件即服务（SaaS）在线平台，为学生创建和提供学习体验和评估，重点是大学水平的STEM（科学、技术、工程和数学）课程。该平台允许教师轻松地将自适应、基于规则和人工智能（AI）算法结合起来，生成和评分不同的随机版本的活动和评估。它包括用于复杂问题类型的新型人工智能自动评分算法，包括符号数学、交互式学生绘图、实时编码和自然语言输入。核心算法在三个关键方面推进了最先进的技术：(1)使用人工智能自动评分可以完全消除大学课程中人工评分的使用，大大降低了人员配备水平和成本，并能够扩展到更大、更多样化的学生群体；(2)平台通过一套新颖的算法阻止作弊；(3)该平台使用复杂的评分算法来激励掌握学习，从而大大提高学习成果。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact/commercial potential of this I-Corps project will serve the national interest by improving the ability of universities to train a globally competitive STEM (Science, Technology, Engineering, and Mathematics) workforce. The core technology in this project provides students with the opportunity to practice questions in a personalized environment until mastery is achieved. The technology also makes it easy for instructors to incorporate frequent and second chance testing while scaling to support more students. These pedagogical strategies have been shown to reduce the failure rates in STEM classes and could disproportionately benefit women, minorities, first-generation students, and students of low socio-economic status. Helping these students can improve retention efforts, in general, and for diverse students, in particular. The commercial potential of this project includes capturing a significant fraction of the rapidly-growing university education technology market with potential markets worldwide as well as in non-university education sectors.This I-Corps project aims to develop a Software as a Service (SaaS) online platform for creating and delivering learning experiences and assessments for students, with a focus on university-level STEM (Science, Technology, Engineering, and Mathematics) courses. The platform allows instructors to easily combine adaptive, rule-based and artificial intelligence (AI) algorithms to generate and grade different randomized versions of activities and assessments. It includes novel AI auto-grading algorithms for complex question types including symbolic mathematics, interactive student drawing, live coding, and natural language input. The core algorithms advance the state of the art in three key ways: (1) The use of AI auto-grading can entirely eliminate the use of human graders in university courses, dramatically reducing staffing levels and costs, and enabling expansion to larger and more diverse student populations; (2) The platform deters cheating with a set of novel algorithms; and (3) The platform uses sophisticated grading algorithms that incentivize mastery learning and that lead to substantial improvements in learning outcomes.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.