下载PDF
Provectus Delivers MLOps Platform on AWS for Global Healthcare Leader
技术
- 分析与建模 - 机器学习
- 平台即服务 (PaaS) - 应用开发平台
适用行业
- 水泥
- 药品
适用功能
- 维护
- 产品研发
用例
- 施工管理
- 基础设施检查
服务
- 数据科学服务
- 培训
挑战
我们的客户是一家全球医疗保健领导者,希望在其组织内加速和扩大 AI/ML 的采用。他们需要一个现代化的 MLOps 平台来简化 AI/ML 应用程序的开发和部署。
关于客户
该客户是消费者健康、医疗器械和制药领域的全球医疗保健领导者。他们在全球雇用了超过 130,000 名员工,并致力于创新和改善全球健康。
解决方案
Provectus 在 AWS 上实施了云原生 MLOps 平台,为客户的解决方案提供了基础。他们还为未来的项目准备了 AI/ML 项目模板,并为入职数据科学家和 ML 工程师提供了全面的文档。
运营影响
数量效益
相关案例.
Case Study
Case Study: Pfizer
Pfizer’s high-performance computing software and systems for worldwide research and development support large-scale data analysis, research projects, clinical analytics, and modeling. Pfizer’s computing services are used across the spectrum of research and development efforts, from the deep biological understanding of disease to the design of safe, efficacious therapeutic agents.
Case Study
System 800xA at Indian Cement Plants
Chettinad Cement recognized that further efficiencies could be achieved in its cement manufacturing process. It looked to investing in comprehensive operational and control technologies to manage and derive productivity and energy efficiency gains from the assets on Line 2, their second plant in India.
Case Study
Fusion Middleware Integration on Cloud for Pharma Major
Customer wanted a real-time, seamless, cloud based integration between the existing on premise and cloud based application using SOA technology on Oracle Fusion Middleware Platform, a Contingent Worker Solution to collect, track, manage and report information for on-boarding, maintenance and off-boarding of contingent workers using a streamlined and Integrated business process, and streamlining of integration to the back-end systems and multiple SaaS applications.
Case Study
Process Control System Support
In many automated production facilities, changes are made to SIMATIC PCS 7 projects on a daily basis, with individual processes often optimised by multiple workers due to shift changes. Documentation is key here, as this keeps workers informed about why a change was made. Furthermore, SIMATIC PCS 7 installations are generally used in locations where documentation is required for audits and certification. The ability to track changes between two software projects is not only an invaluable aid during shift changes, but also when searching for errors or optimising a PCS 7 installation. Every change made to the system is labour-intensive and time-consuming. Moreover, there is also the risk that errors may occur. If a change is saved in the project, then the old version is lost unless a backup copy was created in advance. If no backup was created, it will no longer be possible to return to the previous state if and when programming errors occur. Each backup denotes a version used by the SIMATIC PCS 7 system to operate an installation. To correctly interpret a version, information is required on WHO changed WHAT, WHERE, WHEN and WHY: - Who created the version/who is responsible for the version? - Who released the version? - What was changed in the version i.e. in which block or module of the SIMATIC PCS 7 installation were the changes made? - When was the version created? Is this the latest version or is there a more recent version? - Why were the changes made to the version? If they are part of a regular maintenance cycle, then is the aim to fix an error or to improve production processes? - Is this particular version also the version currently being used in production? The fact that SIMATIC PCS 7 projects use extremely large quantities of data complicates the situation even further, and it can take a long time to load and save information as a result. Without a sustainable strategy for operating a SIMATIC PCS 7 installation, searching for the right software version can become extremely time-consuming and the installation may run inefficiently as a result.
Case Study
Drug Maker Takes the Right Prescription
China Pharm decided to build a cloud-based platform to support the requirements of IT planning for the next five to ten years which includes a dynamic and scalable mail resource pool platform. The platform needed to have the following functions: all nodes support redundancy, ensuring service continuity and good user experience, simple and easy-to-use user interfaces for end users and administrators and good compatibility and supports smooth capacity expansion.