KModels：释放 AI 在商业应用中的潜力
KModels: Unlocking AI for Business Applications
AI总结：
本文提出基于 Kubeflow Pipelines 与 KServe 的 KModels 框架，以模板化方式降低 AI 模型本地生产部署和业务使用门槛，并在工单管理系统中验证其效果。
摘要：
随着人工智能（AI）持续快速发展，将 AI 能力集成到现有商业应用中的需求日益增长。然而，AI 的快速进步与其在商业环境中缓慢落地之间存在显著差距。将表现良好的实验室模型部署到生产环境（尤其是本地部署环境）通常需要专业知识，并带来沉重的模型管理负担，从而在实际应用中实施 AI 模型造成重大障碍。KModels 利用经过验证的库和平台（Kubeflow Pipelines、KServe），通过同时支持 AI 开发者和使用者来简化 AI 采用。它使模型开发者能够只专注于模型开发，并将模型作为可移植单元（Templates，模板）共享，从而抽象掉复杂的生产部署问题。KModels 使 AI 使用者无需专门的数据科学家，因为这些模板封装了大多数数据科学考量，同时提供面向业务的控制。本文介绍 KModels 的架构以及塑造该架构的关键决策。我们概述 KModels 的主要组件及其接口。此外，我们解释 KModels 为何非常适合本地部署，同时也可用于云环境。KModels 的有效性通过在现有 Work Order Management（工单管理）系统中成功部署三个 AI 模型得到证明。这些模型在客户的数据中心运行，并使用本地数据训练，无需数据科学家干预。其中一个模型将工单 Failure Code（故障代码）指定的准确率从 46% 提升到 83%，展示了可访问且本地化的 AI 解决方案所带来的显著收益。
英文摘要：
As artificial intelligence (AI) continues to rapidly advance, there is a growing demand to integrate AI capabilities into existing business applications. However, a significant gap exists between the rapid progress in AI and how slowly AI is being embedded into business environments. Deploying well-performing lab models into production settings, especially in on-premise environments, often entails specialized expertise and imposes a heavy burden of model management, creating significant barriers to implementing AI models in real-world applications. KModels leverages proven libraries and platforms (Kubeflow Pipelines, KServe) to streamline AI adoption by supporting both AI developers and consumers. It allows model developers to focus solely on model development and share models as transportable units (Templates), abstracting away complex production deployment concerns. KModels enables AI consumers to eliminate the need for a dedicated data scientist, as the templates encapsulate most data science considerations while providing business-oriented control. This paper presents the architecture of KModels and the key decisions that shape it. We outline KModels' main components as well as its interfaces. Furthermore, we explain how KModels is highly suited for on-premise deployment but can also be used in cloud environments. The efficacy of KModels is demonstrated through the successful deployment of three AI models within an existing Work Order Management system. These models operate in a client's data center and are trained on local data, without data scientist intervention. One model improved the accuracy of Failure Code specification for work orders from 46% to 83%, showcasing the substantial benefit of accessible and localized AI solutions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
