Communications Mining 用户指南

上次更新日期 2025年10月20日

Elasticsearch 集成

Communications Mining™ 提供了一组丰富的内置分析工具。但是，有时需要将 Communications Mining 的预测与无法作为 Communications Mining 注释的一部分上传的数据加入一起。在这些情况下，常见的解决方案是将 Communications Mining 预测和任何其他数据编入 Elasticsearch 的索引，并使用 Kibana 等工具来驱动分析。本教程介绍如何将 Communications Mining 数据导入 Elasticsearch 并在 Kibana 中将其可视化。

本教程的示例中使用的数据是从保险域生成的虚拟电子邮件。

在 Elasticsearch 中存储数据

首先，我们来定义要导入 Elasticsearch 的数据。Communications Mining API 在嵌套 JSON 对象中提供注释文本、注释元数据、预测标签和预测通用字段。以下是 Communications Mining API 提供的原始注释示例。

注意：您可能会注意到不同的元数据字段，具体取决于将数据提取到 Communications Mining 的方式。要了解有关注释对象字段的更多信息，请查看注释。

{
  "comment": {
    "id": "c7a1c529-3f57-4be6-9102-c9f892b81ae51",
    "uid": "49ba2c56a945386c.c7a1c529-3f57-4be6-9102-c9f892b81ae51",
    "timestamp": "2021-03-29T08:36:25.607Z",
    "messages": [
      {
        "body": {
          "text": "The policyholder has changed their address to the new address: 19 Essex Gardens, SW17 2UL"
        },
        "subject": {
          "text": "Change of address - Policy SFG48807871"
        },
        "from": "[email protected]",
        "to": ["[email protected]"],
        "sent_at": "2021-03-29T08:36:25.607Z"
      }
    ]
    // (... more properties ...)
  },
  "labels": [
    {
      "name": ["Admin"],
      "probability": 0.9995054006576538
    },
    {
      "name": ["Admin", "Change of address"],
      "probability": 0.9995054006576538
    }
  ],
  "entities": [
    {
      "name": "address-line-1",
      "formatted_value": "19 Essex Gardens",
      "span": {
        "content_part": "body",
        "message_index": 0,
        "char_start": 63,
        "char_end": 79,
        "utf16_byte_start": 126,
        "utf16_byte_end": 158
      }
    },
    {
      "name": "post-code",
      "formatted_value": "SW17 2UL",
      "span": {
        "content_part": "body",
        "message_index": 0,
        "char_start": 81,
        "char_end": 89,
        "utf16_byte_start": 162,
        "utf16_byte_end": 178
      }
    },
    {
      "name": "policy-number",
      "formatted_value": "SFG48807871",
      "span": {
        "content_part": "subject",
        "message_index": 0,
        "char_start": 27,
        "char_end": 38,
        "utf16_byte_start": 54,
        "utf16_byte_end": 76
      }
    }
  ]
}{
  "comment": {
    "id": "c7a1c529-3f57-4be6-9102-c9f892b81ae51",
    "uid": "49ba2c56a945386c.c7a1c529-3f57-4be6-9102-c9f892b81ae51",
    "timestamp": "2021-03-29T08:36:25.607Z",
    "messages": [
      {
        "body": {
          "text": "The policyholder has changed their address to the new address: 19 Essex Gardens, SW17 2UL"
        },
        "subject": {
          "text": "Change of address - Policy SFG48807871"
        },
        "from": "[email protected]",
        "to": ["[email protected]"],
        "sent_at": "2021-03-29T08:36:25.607Z"
      }
    ]
    // (... more properties ...)
  },
  "labels": [
    {
      "name": ["Admin"],
      "probability": 0.9995054006576538
    },
    {
      "name": ["Admin", "Change of address"],
      "probability": 0.9995054006576538
    }
  ],
  "entities": [
    {
      "name": "address-line-1",
      "formatted_value": "19 Essex Gardens",
      "span": {
        "content_part": "body",
        "message_index": 0,
        "char_start": 63,
        "char_end": 79,
        "utf16_byte_start": 126,
        "utf16_byte_end": 158
      }
    },
    {
      "name": "post-code",
      "formatted_value": "SW17 2UL",
      "span": {
        "content_part": "body",
        "message_index": 0,
        "char_start": 81,
        "char_end": 89,
        "utf16_byte_start": 162,
        "utf16_byte_end": 178
      }
    },
    {
      "name": "policy-number",
      "formatted_value": "SFG48807871",
      "span": {
        "content_part": "subject",
        "message_index": 0,
        "char_start": 27,
        "char_end": 38,
        "utf16_byte_start": 54,
        "utf16_byte_end": 76
      }
    }
  ]
}

The schema of the raw comments returned by the Communications Mining API is inconvenient for filtering and querying this data in Elasticsearch, so you should change the schema before ingesting the data into Elasticsearch. The following is an example flattened schema you can use. You should add all fields that you need for your use-case.

{
  "id": "c7a1c529-3f57-4be6-9102-c9f892b81ae51",
  "uid": "49ba2c56a945386c.c7a1c529-3f57-4be6-9102-c9f892b81ae51",
  "timestamp": "2021-03-29T08:36:25.607Z",
  "subject": "Change of address - Policy SFG48807871",
  "body": "The policyholder has changed their address to the new address: 19 Essex Gardens, SW17 2UL",
  // (... more fields ...)
  "labels": ["Admin", "Admin > Change of address"],
  "entities": {
    "policy_number": ["SFG48807871"],
    "address-line-1": ["19 Essex Gardens"],
    "post-code": ["SW17 2UL"]
  }
}{
  "id": "c7a1c529-3f57-4be6-9102-c9f892b81ae51",
  "uid": "49ba2c56a945386c.c7a1c529-3f57-4be6-9102-c9f892b81ae51",
  "timestamp": "2021-03-29T08:36:25.607Z",
  "subject": "Change of address - Policy SFG48807871",
  "body": "The policyholder has changed their address to the new address: 19 Essex Gardens, SW17 2UL",
  // (... more fields ...)
  "labels": ["Admin", "Admin > Change of address"],
  "entities": {
    "policy_number": ["SFG48807871"],
    "address-line-1": ["19 Essex Gardens"],
    "post-code": ["SW17 2UL"]
  }
}

请注意，注释可以有零个、一个或多个标签，因此labels字段必须是数组。此外，如果为数据集配置了一个或多个常规字段类型，则每种常规字段类型的注释将包含零个、一个或多个常规字段。原始 API 响应中的层次结构标签名称本身就是数组 ( ["Admin", "Change of address"] )，应转换为字符串 ( "Admin > Change of address" )。

正在获取数据

要获取数据，我们建议使用。有关所有可用的数据下载方法的概述，请查看下载数据。创建流时，您应该为每个标签设置阈值，以便丢弃置信度分数低于阈值的标签。最简单的方法是从 Communications Mining™ 用户界面转到数据集的“流”页面。使用置信度分数确定标签是否适用后，您可以仅将标签名称导入 Elasticsearch。有关我们建议删除或保留标签置信度分数的信息，请查看分析标签。

通用字段没有置信度分数，因此不需要特殊处理。

备注：

模型变更管理

创建流时，请指定模型版本。此模型版本用于在从流中获取注释时提供预测。即使用户继续在平台中训练新的模型版本，您的流也将使用您指定的模型版本，为您提供确定性结果。

要升级到新的模型版本，您必须创建使用该模型版本的新流，然后更新代码以使用新的流。（因此，我们建议您在代码中配置可配置的流名称。）为确保使用预测的分析保持一致，您应使用更新后的模型版本重新提取历史数据的预测。您可以将流分配到最早注释之前的时间戳，并从头开始重新提取数据。

在 Kibana 中可视化数据

在 Elasticsearch 中为数据建立索引后，您就可以开始构建可视化。本节提供了 Kibana 中许多常见可视化工具的简单示例。

泰美利安

您可以使用以下表达式生成前 5 个最常用标签随时间变化的图表。请注意，这会同时显示顶级类别和子类别标签。

.es(index=example-data,split=labels:5,timefield=@timestamp)
    .label("$1", "^.* > labels:(.+) > .*").es(index=example-data,split=labels:5,timefield=@timestamp)
    .label("$1", "^.* > labels:(.+) > .*")