Skip to main content

Document cognition insights

In this section, you can view the insights generated by the documents uploaded on the Studio section (while training the bot). Doc cog can provide analytics about the search results performance, categories of searches, etc.

note

Detailed documentation on document cognition is available here.

In this article, you will learn about:

  1. Number of queries that went to document search: Number of queries answered and unanswered by document search for your bot over a period of time.
  2. User feedback: Cataloging the feedback received for search results for your bot into positive, negative and no feedback.
  3. User searches: Searches performed by the users that are grouped based on the similar queries under a clusters.
  4. Document performance statistics: Track the relevance of documents by inspecting the performance metrics - suggestion count of the document, click through rate and percentage of positive feedback.

To view Doc cog insights, open Insights > Doc cog.

Select the period and view the number of queries that were answered/unanswered during that range when the search was performed.

2. User feedback

After a query is answered by the bot using documents, users can give feedback for active learning. You can view the number of positive/negative responses provided by the user for the bot responses.

3. Group/categories that the users are searching for

Understand the category of user searches, answers provided and the feedback given for it.

4. Document performance statistics

Track the relevance of documents by inspecting the performance metrics - suggestion count of the document, click-through rate, and percentage of positive feedback. You can view High rated documents and Low rated documents by selecting the respective tabs.

info

All the insights can be filtered for a time period by selecting the required range/ custom dates.

  • 1. Number of queries that went to document search
  • 2. User feedback
  • 3. Group/categories that the users are searching for
  • 4. Document performance statistics