This API is in Beta Phase.
This API performs best when the audio is clear and the meeting length is greater than 10 minutes. Longer length meetings are broken down by our algorithm in contextually relevant parts which helps in producing high-quality topic hierarchy.
In the sample diagram below that we created for your understanding. This shows how one conversation can have multiple parent (global) topics and each parent topic can have multiple child-topics in it.
For example, if in a meeting “Sales Conversation” was talked about and after it “Activity Call logs”, “Salesforce”, “Draft”, “Custom Integration” and “Jira” were talked.
So, the topic hierarchy algorithm will find a pattern in the conversation and make Sales Conversation as the parent topics and the rest of the topics as the child topics under it.
Topic hierarchy understands customer conversation and returns the parent (global) topic and its child topics.
- Parent Topic: Identify the highest-level abstraction of a meeting. These are the key points on which the speakers of the meeting expanded and discussed at length.
- Child topic: These are the subtopics that aggregate or are originated from the parent topic itself. Child Topics are the topics that are linked to the parent topic as they form the time chunks of the parent topics in a certain way.
|No||true||Gives you topic hierarchy when passed in Topic API.|
|For each topic in the response, it has a parentRefs field that points to its parent topic. If parentRefs is NULL it signifies that the topic is a parent.|
To see Topics Hierarchy in action, you need to process a conversation using Symbl. After you process a meeting, you'll receive a Conversation ID. A Conversation ID is the key to receiving conversational insights from any conversation. As an example, here's a simple API call which grabs the detected topics from the conversation.
Remember to replace the
conversationId in the API call with the Conversation ID you get from the previous API call.