---
格式版本: 2
标题: "Amazon Connect Customer now supports information extraction for agent voice and chat conversations"
原文链接: "https://aws.amazon.com/cn/about-aws/whats-new/2026/08/amazon-connect-customer-information/"
发布日期: "2026-08-24"
发布时间校准状态: "found"
发布时间需复核: "否"
发布时间来源: "llm:local:original_script_field"
发布时间证据: "postDateTime: 2026-08-24T14:46:00Z"
发布时间校准原因: "候选日期来自脚本字段的postDateTime，为文章明确标注的发布时间，且无其他冲突信息。"
发布时间校准置信度: "1"
发布时间候选数量: 1
发布时间严格候选数量: 0
发布时间原页读取状态: "source template page reused from URL open"
发布时间未找到原因: ""
发布时间校准时间: "2026-08-25T17:27:53+08:00"
发布时间仲裁状态: "confirmed"
发布时间仲裁尝试次数: 1
发布时间仲裁耗时毫秒: 5937
发现时间: "2026-08-25T17:27:42+08:00"
入库时间: "2026-08-25T09:27:59.901Z"
来源平台: "固定入口"
搜索渠道: "fixed_url"
搜索词: "https://aws.amazon.com/new"
匹配关键词:
  []
相关厂家:
  - "AWS"
相关专家:
  []
内容类型: "网页"
抓取工具: "Free Fetch + Defuddle"
清洗工具: "Defuddle Markdown + Defuddle/Readability 正文提取"
原始附件:
  []
AI优质: "否"
AI打分: 28
AI分档: "非优质"
AI质检状态: "不通过"
AI打分理由: "内容为Amazon Connect客服信息提取功能，属于AWS客服业务产品更新，与超节点、AI Rack、机柜级AI基础设施及关键技术完全无关，不涉及项目任何核心主题。"
AI质检模型: "ali-deepseek-v4-flash"
AI质检时间: "2026-08-25T17:28:55+08:00"
AI主题相关性: 0
AI来源权威性: 15
AI新颖性: 5
AI技术细节: 0
AI商业部署信号: 0
AI完整性: 8
AI摘要: "Amazon Connect Customer 新增信息抽取功能，可从语音和聊天交互中自动捕获账户号、预订 ID、产品名等关键数据及联系原因、解决情况等衍生洞察，减少人工录入并提升效率。"
AI摘要模型: "ali-deepseek-v4-flash"
AI摘要时间: "2026-09-07T02:09:53.290Z"
采集批次: "2026年8月25日17点27分36秒"
采集批次ID: "20260825-172736-501"
去重键: "https://aws.amazon.com/cn/about-aws/whats-new/2026/08/amazon-connect-customer-information"
---

Amazon Connect Customer now supports information extraction, which automatically captures key data from voice and chat interactions, reducing manual data capture and improving agent and supervisor productivity. Information extraction captures verbatim values like account numbers, reservation IDs, and product names, as well as derived insights inferred from the conversation such as reason for contact, resolution provided, and next steps promised.

You define conversational analytics rules for what to extract and when. Extraction operates on raw contact content before redaction, so you can capture specific data points while still redacting sensitive values from recordings and transcripts. Agents see extracted values during After Contact Work, supervisors use them to search and review contacts, and developers access them programmatically through APIs, Kinesis Data Streams, and S3 output files. You can also feed extracted values directly into rule actions like email notifications, task creation, and case creation, turning unstructured conversations into automated experiences. For example, a travel company can automatically extract "Hotel Name," "Reservation ID," and "Reason for call" from interactions, then populate outbound emails and create follow-up tasks, eliminating manual data entry and reducing handle time.  
  
To learn more, see [Information extraction](https://docs.aws.amazon.com/connect/latest/adminguide/information-extraction.html) in the Amazon Connect Customer Administrator Guide, or visit the [Amazon Connect Customer website](https://aws.amazon.com/connect/). For a complete list of conversational analytics capabilities available by AWS Region, refer to [Availability of Connect Customer features by Region](https://docs.aws.amazon.com/connect/latest/adminguide/regions.html#contactlens_region).