activities
latest
false
  • Release Notes
      • June 2024
      • May 2024
      • January 2024
  • Overview
    • The nature of communications
    • The anatomy of an extraction
    • General fields
    • Automation architecture
  • Uploading data to Communications Mining
  • Using the Dispatcher Framework
  • Activities reference
Communications Mining Activities
Last updated Oct 11, 2024

The anatomy of an extraction

An extraction is a structured representation of one of the requests made within a communication. Communications Mining will provide a list of these extractions for use in an automation.

Note: The extractions are defined by the model trainer when they configure the taxonomy.
Each extraction has two crucial properties that guide its interpretation. The first is the extraction name, which indicates the subject of the extraction. For instance, an extraction name could be Address Change or Account Update > Contact Number.
The second important property is fields. Fields represent the specific data points we aim to extract from a communication. For example, for the Address Change extraction, relevant fields might include AccountNumber, FirstLineOfAddress and PostCode.

Each extraction also comes with an occurrence_confidence score. This score indicates our confidence in the accuracy of the extraction. A threshold is applied to this score. Typically, predictions with a confidence score above the threshold will be automated, while those below will be flagged for manual review. The thresholds field displays each threshold that the prediction has surpassed.
Note: To determine if your prediction confidence has exceeded the threshold set on the stream, check for the stream threshold.

An example extraction

This is an example in which a Policy > Amendment > Address Change extraction has been predicted and the confidence of this prediction has exceeded the confidence threshold called stream.
{
  "name": "Policy > Amendment > Address Change",
  "occurrence_confidence": {
    "value": 0.9909818768501282,
    "thresholds": ["stream"]
  },
  "fields": [
    {
      "name": "Address Line",
      "value": {
        "formatted": "45 Brillington Lane"
      }
    },
    {
      "name": "Excess Amount",
      "value": null
    },
    {
      "name": "Policy Number",
      "value": {
        "formatted": "XE-182943"
      }
    },
    {
      "name": "Town / City",
      "value": {
        "formatted": "Doncaster"
      }
    },
    {
      "name": "UK Postcode",
      "value": {
        "formatted": "S45 9UX"
      }
    }
  ]
}{
  "name": "Policy > Amendment > Address Change",
  "occurrence_confidence": {
    "value": 0.9909818768501282,
    "thresholds": ["stream"]
  },
  "fields": [
    {
      "name": "Address Line",
      "value": {
        "formatted": "45 Brillington Lane"
      }
    },
    {
      "name": "Excess Amount",
      "value": null
    },
    {
      "name": "Policy Number",
      "value": {
        "formatted": "XE-182943"
      }
    },
    {
      "name": "Town / City",
      "value": {
        "formatted": "Doncaster"
      }
    },
    {
      "name": "UK Postcode",
      "value": {
        "formatted": "S45 9UX"
      }
    }
  ]
}
  • An example extraction

Was this page helpful?

Get The Help You Need
Learning RPA - Automation Courses
UiPath Community Forum
Uipath Logo White
Trust and Security
© 2005-2024 UiPath. All rights reserved.