1. Home
  2. Kore.ai Conversational Platform
  3. Natural Language Processing (NLP)
  4. Bot Analysis

Bot Analysis

Kore.ai records and presents all the information as part of the Bot Analyze section. Developers can gain in-depth insights into their bot’s performance at identifying and executing tasks. It lets you view necessary information for user utterances that matched and didn’t match with intents.

The Analyze section contains the following sections:

  • Successfully handled User utterances: Contains all the user utterances that were successfully mapped to a trained intent. The utterances are grouped together based on similarity
    • You can filter the information based on various criteria such as Intent, user, date-period, channel of use, and language.
    • Complete meta information is stored for later analysis including the original user utterance, the channel of communication entities extracted if any, detailed NLP analysis with scores returned from each engine and the ranking and resolver scores.
    • Ability to view the chat transcript to the point of the user utterance.

  • Un-handled User utterances: Contains all the user utterances that platform was not able to map to a bot intent/FAQ. These are grouped together based on similarity for the developer to train based on occurrence count.
    • You can filter information based on various criteria such as user, date-period, channel of use, and language.
    • Complete meta information is stored for later analysis including the original user utterance, the channel of communication, system entities extracted if any, detailed NLP analysis with scores returned from each engine and the ranking and resolver scores.
    • Ability to view the chat transcript to the point of the user utterance.
    • The developer will have an option to train the utterance and once trained the utterance will be marked. The developer can also filter based on trained / untrained utterances.
  • Task Execution Failure: All the user utterances that were successfully identified to an intent, but the task could not be completed are listed under this section. The developer can group based on task and failure types to analyze and solve issues with the bot.
    • The supported platform failure types are:
      • Task aborted by user
      • Alternate task initiated
      • Chat Interface refreshed
      • Human agent transfer
      • Authorization attempt failure – Max attempts reached
      • Incorrect entity failure – Max attempts reached
      • Script failure
      • Service failure
    • Information can be filtered as above
    • In addition to the meta information as in handled and unhandled scenarios, the platform also captures the path of traversal of the user in the dialog.
  • Script and Service Performance: Developers can monitor all the scripts and API services across the bot tasks from a single window. The platform stores the following meta information:
    • Total number of runs
    • Response times
    • Success or failure
      • For service the response JSON from Integration provider
    • Appropriate alerts if a script or a service is failing consecutively

Was this article helpful to you? Yes 2 No