跳转至

Machinery（机械系统（Machinery））

Many real-world events can be thought of as processes, such as business workflows, government operations, or healthcare procedures. In a process, entities such as documents, equipment, or individuals undergo changes of state over time. The Machinery application enables you to understand and manage all aspects of a process, identify unwanted behavior, and make improvements toward a desired outcome. With support from AIP's LLM-powered functionality, you can use Machinery as a reliable framework for orchestrating multiple automations in multi-step AIP workflows. Supported workflows include:

  • Resolving process inefficiencies with the help of AIP and automation
  • Managing an AIP use case end to end by orchestrating several AI agents
  • Mining an ongoing process from external event logs to gain visibility into an existing process
  • Defining and monitoring performance metrics and expectations to identify process bottlenecks
  • Building operational applications to supervise AIP workflows with real-time human intervention

Example process graph.

Use cases

Example use cases and workflows for Machinery include:

  • Insurance: Capture the process of insurance claims from the initial filing to the final decision, including OCR on relevant documents, semi-automated processing, and human approval.
  • Hospital operations: Model the patient journey through hospital care from end to end. Support operations through medical document generation.
  • Purchase-to-pay: Consider the procurement process from requisition to payment and improve workflow efficiency.
  • Order-to-cash: Optimize the sales process from order receipt to payment collection for customer satisfaction and cash flow.

:::callout{theme="success" title="Palantir Learning portal"} Get started with Machinery in the "Mining your first business process" speedrun course ↗ at learn.palantir.com ↗. :::

中文翻译

机械系统（Machinery）

许多现实世界中的事件可以被视为流程，例如业务工作流、政府操作或医疗程序。在流程中，文档、设备或个人等实体（entity）会随时间经历状态变化。机械系统（Machinery）应用程序使您能够理解和管理流程的各个方面，识别不良行为，并朝着期望的结果进行改进。借助 AIP 的 LLM 驱动功能，您可以将机械系统（Machinery）用作一个可靠的框架，在多步骤 AIP 工作流中编排多个自动化操作。支持的工作流包括：

  • 借助 AIP 和自动化解决流程低效问题
  • 通过编排多个 AI 代理（agent）端到端管理 AIP 用例
  • 从外部事件日志中挖掘正在进行的流程，以获取对现有流程的可见性
  • 定义并监控性能指标和预期，以识别流程瓶颈
  • 构建运营应用程序，通过实时人工干预来监督 AIP 工作流

示例流程图。

用例

机械系统（Machinery）的示例用例和工作流包括：

  • 保险： 捕获从初始提交到最终决定的保险理赔流程，包括对相关文档的 OCR、半自动化处理以及人工审批。
  • 医院运营： 端到端建模患者在医院的诊疗流程。通过医疗文档生成支持运营操作。
  • 采购到付款： 考虑从请购到付款的采购流程，并提高工作流效率。
  • 订单到现金： 优化从订单接收到收款结算的销售流程，以提高客户满意度和现金流。

:::callout{theme="success" title="Palantir 学习门户"} 在 learn.palantir.com ↗ 的 "挖掘您的第一个业务流程"速通课程 ↗ 中开始使用机械系统（Machinery）。 :::