Summarization V1 baseline model for chat and voice

The Agent Assist Summarization provides conversation summaries to your agents after each conversation completes. The summaries help agents create their conversation notes to review and understand end-user communication history.

There are two ways to implement the Summarization feature:

• You can train a custom model (chat or voice).
• You can use the out-of-the-box baseline model (chat and voice).

This page provides the steps required to implement the baseline model.

For example, here is a sample input conversation:

A baseline model summary output about the conversation might look similar to the following:

Note: Low quality summaries might get deleted. In these cases the returned summaries are empty.

Configure a conversation profile

A conversation profile configures a set of parameters that control the suggestions made to an agent during a conversation. The following steps create a ConversationProfile with a HumanAgentAssistantConfig object.

Create a conversation profile

Note: If using Agent Assist's generateStatelessSummary API, this step can be skipped to instead provide the fields of the conversation profile within the request.

To create a conversation profile, do the following:

1. Call the create method on the ConversationProfile resource.
2. Provide a name for the new conversation profile.
3. Enter your Google Cloud project ID.
4. Enter your model ID. To use the baseline summarization model, don't specify the model ID. Instead, set baseline_model_version to 1.0.
5. In the CreateConversationProfileRequest for the suggestion feature, specify CONVERSATION_SUMMARIZATION for chat or CONVERSATION_SUMMARIZATION_VOICE for voice.

Baseline model example for voice

The following is a JSON example that uses a baseline summarization model for voice:

{
  "parent": "projects/PROJECT_ID/locations/global",
  "conversationProfile": {
    "displayName": "CONVERSATION_PROFILE_NAME",
    "humanAgentAssistantConfig": {
      "humanAgentSuggestionConfig": {
        "featureConfigs": [{
          "suggestionFeature": {
            "type": "CONVERSATION_SUMMARIZATION_VOICE"
          },
          "conversationModelConfig": {
            "baseline_model_version": "1.0",
          }
        }]
      }
    },
    "languageCode": "en-US"
  }
}

The response is a ConversationProfile object containing the conversation profile name:

{
  "name": "projects/PROJECT_ID/locations/global/conversationProfiles/CONVERSATION_PROFILE_ID",
  "displayName": "CONVERSATION_PROFILE_NAME",
  "automatedAgentConfig": {
  },
  "humanAgentAssistantConfig": {
    "notificationConfig": {
    },
    "humanAgentSuggestionConfig": {
      "featureConfigs": [{
        "suggestionFeature": {
          "type": "CONVERSATION_SUMMARIZATION_VOICE"
        },
        "conversationModelConfig": {
        }
      }]
    },
    "messageAnalysisConfig": {
    }
  },
  "languageCode": "en-US",
  "createTime": "2022-06-06T21:06:46.841816Z",
  "updateTime": "2022-06-06T21:06:46.841816Z",
  "projectNumber": "344549229138"
}

Baseline model example for chat

The following is a JSON example that uses a baseline summarization model for chat:

{
  "parent": "projects/PROJECT_ID/locations/global",
  "conversationProfile": {
    "displayName": "CONVERSATION_PROFILE_NAME",
    "humanAgentAssistantConfig": {
      "humanAgentSuggestionConfig": {
        "featureConfigs": [{
          "suggestionFeature": {
            "type": "CONVERSATION_SUMMARIZATION"
          },
          "conversationModelConfig": {
            "baseline_model_version": "1.0",
          }
        }]
      }
    },
    "languageCode": "en-US"
  }
}

The response is a ConversationProfile object containing the conversation profile name:

{
  "name": "projects/PROJECT_ID/locations/global/conversationProfiles/CONVERSATION_PROFILE_ID",
  "displayName": "CONVERSATION_PROFILE_NAME",
  "automatedAgentConfig": {
  },
  "humanAgentAssistantConfig": {
    "notificationConfig": {
    },
    "humanAgentSuggestionConfig": {
      "featureConfigs": [{
        "suggestionFeature": {
          "type": "CONVERSATION_SUMMARIZATION"
        },
        "conversationModelConfig": {
        }
      }]
    },
    "messageAnalysisConfig": {
    }
  },
  "languageCode": "en-US",
  "createTime": "2022-06-06T21:06:46.841816Z",
  "updateTime": "2022-06-06T21:06:46.841816Z",
  "projectNumber": "344549229138"
}

Handle conversations at runtime

Conversations are handled the same at runtime whether you're using the baseline model or a custom model. See the Summarization custom model documentation for details.