Modern dairy farms generate vast amounts of data, with different sections of the operation having the ability to produce its own uniquely structured data stream depending on the specific hardware and software used. As a result of this heterogeneity, these streams are difficult to link to each other, thus it is rarely done. This creates an opportunity to add value to the data by integrating and homogenizing data from the different sources, with the end result of enriching analyses and helping to improve farm management decisions. Within a proposed project, a two component modular system is being developed. One component collects, cleans, and integrates data from on-farm systems into a centralized hub (AgDH). This system provides data to a framework designed to deploy and operationalize existing research-derived analytical tools and provide access to these tools and data via a user interface. The AgDH follows five steps to ingest different data streams available at the dairy farm: 1) transporting raw data into a centralized system; 2) decoding and storing data in a database; 3) cleaning data to ensure its validity; 4) homogenization of data by extracting the common features among the different software and farms; and 5) integration of data from the different systems. Each of these steps is crucial to make data available from different sources in a consistent manner, ease algorithmic development and its implementation, and facilitate the deployment of new tools that utilize the integrated data. In order to automate the process and make the data continuously available an open source workflow management platform was used. Both historical and current data can be made available to authenticated users via an application programming interface hosted through a web service. This framework needs to be designated to be flexible and able to adapt quickly to the changes and new technologies that are continuously being developed in the dairy industry. The integration and accessibility of data can facilitate a wide range of descriptive, predictive, and prescriptive analytics that can be developed and deployed directly on farms to increase animal performance, efficiency, health and welfare, profit margins, and decrease the environmental impact of dairy farming.

现代奶牛场产生大量数据，运营的不同部分能够根据所使用的特定硬件和软件产生自己独特的结构化数据流。由于这种异质性，这些流很难相互链接，因此很少这样做。这创造了通过整合和统一来自不同来源的数据来增加数据价值的机会，最终结果是丰富分析并帮助改进农场管理决策。在一个提议的项目中，正在开发一个由两部分组成的模块化系统。一个组件收集、清理农场系统中的数据并将其集成到集中式中心 (AgDH) 中。该系统向旨在部署和操作现有研究衍生分析工具的框架提供数据，并通过用户界面提供对这些工具和数据的访问。AgDH 遵循五个步骤来摄取奶牛场可用的不同数据流：1) 将原始数据传输到中央系统；2) 将数据解码并存储在数据库中；3) 清洗数据以确保其有效性；4）通过提取不同软件和农场之间的共同特征来实现数据的同质化；5) 整合来自不同系统的数据。这些步骤中的每一个对于以一致的方式从不同来源提供数据、简化算法开发及其实施以及促进利用集成数据的新工具的部署都至关重要。为了自动化流程并使数据在开源工作流管理平台上持续可用。历史数据和当前数据都可以通过 Web 服务托管的应用程序编程接口提供给经过身份验证的用户。该框架需要具有灵活性，并能够快速适应乳制品行业不断发展的变化和新技术。数据的集成和可访问性可以促进广泛的描述性、预测性和规范性分析，这些分析可以直接在农场开发和部署，以提高动物性能、效率、健康和福利、利润率，并减少奶牛养殖对环境的影响. 历史数据和当前数据都可以通过 Web 服务托管的应用程序编程接口提供给经过身份验证的用户。该框架需要具有灵活性，并能够快速适应乳制品行业不断发展的变化和新技术。数据的集成和可访问性可以促进广泛的描述性、预测性和规范性分析，这些分析可以直接在农场开发和部署，以提高动物性能、效率、健康和福利、利润率，并减少奶牛养殖对环境的影响. 历史数据和当前数据都可以通过 Web 服务托管的应用程序编程接口提供给经过身份验证的用户。该框架需要具有灵活性，并能够快速适应乳制品行业不断发展的变化和新技术。数据的集成和可访问性可以促进广泛的描述性、预测性和规范性分析，这些分析可以直接在农场开发和部署，以提高动物性能、效率、健康和福利、利润率，并减少奶牛养殖对环境的影响. 该框架需要具有灵活性，并能够快速适应乳制品行业不断发展的变化和新技术。数据的集成和可访问性可以促进广泛的描述性、预测性和规范性分析，这些分析可以直接在农场开发和部署，以提高动物性能、效率、健康和福利、利润率，并减少奶牛养殖对环境的影响. 该框架需要具有灵活性，并能够快速适应乳制品行业不断发展的变化和新技术。数据的集成和可访问性可以促进广泛的描述性、预测性和规范性分析，这些分析可以直接在农场开发和部署，以提高动物性能、效率、健康和福利、利润率，并减少奶牛养殖对环境的影响.