Stay organized with collectionsSave and categorize content based on your preferences.
Smart highlights automatically detects highlights in a contact center conversation without requiring any additional configuration. A conversation's highlights are the words or phrases that were important for determining the end user's intent. This feature analyzes each conversation turn and categorizes the user's intention, then labels any highlights present in a conversation.
How it works
Conversational Insights usesDialogflow intenttechnology to detect conversation highlights at the sentence level. When Conversational Insights detects a highlight, it creates acall annotationand includes that in the analysis with other annotations.
Supported smart highlights
Intent
Definition
Example highlight
AUTHENTICATION_INFO
Asking for information that can be used to authenticate a customer.
Can you please help me with your account number?
CHECK_ISSUE_RESOLVED
Checking if the issue is resolved and there are no further questions or problems.
Have I addressed your concern for today?
CONFIRM_ISSUE_RESOLVED
Confirming the issue was resolved.
All my questions were answered.
View smart highlights
You can view smart highlights labels in theConversational Insights consolealong with other labels, such as detected entities. When you export conversations to BigQuery, Conversational Insights automatically includes smart highlights labels in your exporter. This lets you perform a custom inspection of the data.
Smart highlights feedback
Smart highlights use natural language processing to identify intents within your conversation. This feature can incorrectly identify phrases or not identify an accurate phrase. If you find a
scenario in your data where a smart highlight is not working as described, you can provide feedback with one of the following methods:
Use theSend Feedbackoption from theHelpmenu in the Conversational Insights console.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-09-04 UTC."],[[["\u003cp\u003eSmart Highlights automatically identify key words or phrases in conversations, powered by Dialogflow intent technology, without needing manual setup.\u003c/p\u003e\n"],["\u003cp\u003eThe system analyzes each conversation turn to categorize the user's intention, and highlights the crucial words or phrases that determine this intent.\u003c/p\u003e\n"],["\u003cp\u003eSmart Highlights operates at the sentence level, creating call annotations that include labels like AUTHENTICATION_INFO, CHECK_ISSUE_RESOLVED, and CONFIRM_ISSUE_RESOLVED when highlights are found.\u003c/p\u003e\n"],["\u003cp\u003eThese highlights are viewable in the Insights console alongside other labels and are also automatically included in BigQuery exports for custom data inspection.\u003c/p\u003e\n"],["\u003cp\u003eFeedback on Smart Highlights' accuracy can be provided via the "Send Feedback" option in the Insights console or by directly contacting the feedback team.\u003c/p\u003e\n"]]],[],null,["# Smart highlights automatically detects highlights in a contact center conversation without requiring any additional configuration. A conversation's highlights are the words or phrases that were important for determining the end user's intent. This feature analyzes each conversation turn and categorizes the user's intention, then labels any highlights present in a conversation.\n\nHow it works\n------------\n\nConversational Insights uses [Dialogflow intent](/dialogflow/es/docs/intents-overview) technology to detect conversation highlights at the sentence level. When Conversational Insights detects a highlight, it creates a [call annotation](/contact-center/insights/docs/reference/rest/v1/projects.locations.conversations.analyses#Analysis.CallAnnotation) and includes that in the analysis with other annotations.\n\nSupported smart highlights\n--------------------------\n\nView smart highlights\n---------------------\n\nYou can view smart highlights labels in the\n[Conversational Insights console](https://ccai.cloud.google.com/insights) along with other labels, such as detected entities. When you export conversations to BigQuery, Conversational Insights automatically includes smart highlights labels in your exporter. This lets you perform a custom inspection of the data.\n| **Note:** [sentences.intentMatchData](/contact-center/insights/docs/export#bigquery_schema_data_dictionary_) represents smart highlights in the exporter schema.\n\nSmart highlights feedback\n-------------------------\n\nSmart highlights use natural language processing to identify intents within your conversation. This feature can incorrectly identify phrases or not identify an accurate phrase. If you find a\nscenario in your data where a smart highlight is not working as described, you can provide feedback with one of the following methods:\n\n- Use the **Send Feedback** option from the **Help** menu in the Conversational Insights console.\n- Reach out directly to the [Conversational Insights feedback team](/contact-center/insights/docs/contact-center-insights-feedback@google.com).\n\nIn your feedback, provide the name of the smart highlight, the phrase, and whether the phrase was missed or identified incorrectly."]]
