Interaction Insights table

  • リリースバージョン: Australia
  • 更新日 2026年03月12日
  • 所要時間：2分

    • User sentiment analysis prepares agents for the tone of incoming conversations. Business rules can be created based on this value and agents can take appropriate actions on the chat, whether it comes from Virtual Agent, another live agent, or from a queue.

    Both synchronous and asynchronous channels support sentiment analysis. Use Task Intelligence to set up sentiment analysis.

    When configured, sentiment analysis is performed at the end of a Virtual Agent or live agent conversation. The user sentiment is stored in the Interaction Insights [sys_cs_interaction_insight] table.

    表 : 1. Interaction Insights table
    Field Description
    Interaction The sys ID for the conversation in the Interactions [interaction] table.
    Sentiment Shows the sentiment level of the interaction, if sentiment analysis is enabled on the instance. This value can be shown to agents in the Agent Chat interface. Business rules can be created based on this value at handoff (Virtual Agent to live agent, live agent to live agent, or live agent to queue). Valid values are as follows:
    • Positive
    • Neutral
    • Negative
    • null (no value assessed)
    Sentiment Normalized Sentiment score between -0.5 (negative sentiment) and 0.5 (positive sentiment).

    You can modify these values by adjusting the com.glide.cs.neutral_sentiment_max_value and com.glide.cs.neutral_sentiment_min_value system parameters.
    Type Type of analysis performed. For example, Sentiment.
    User Name of the agent or Virtual Agent.
    User Type Type of user. For example, Agent.