SpeechSense dialogs
Dialog is a SpeechSense object. There are two types of dialogs:
-
Audio: Agent's voice conversation with a customer recorded using contact center PBX. As soon as you upload a conversation's audio to SpeechSense, it will automatically recognize agent and customer speech.
-
Chat: Customer's text chat with an agent or bot. For chats, you need to manually specify message authors before uploading a chat to SpeechSense.
There are two dialog directions:
- Outgoing: Initiated by agent.
- Incoming: Initiated by customer.
Analyze dialogs in SpeechSense to evaluate the agents' performance. There are two ways to work with dialogs:
- In the dialog list, find the one you need and view its detailed info.
- Build a report on dialogs.
Detailed info about a dialog
You can get the following information for each dialog:
- Metadata, e.g., full names of agent and customer, call or message date, dialog language, etc. The metadata list is defined in the connection.
- Conversation audio (only for audio).
- Conversation contents.
- YandexGPT analysis.
Dialog contents
On the dialog page, see the Dialog tab for the dialog contents:
- For audio: Text transcript of the dialog, automatically generated by Yandex SpeechKit.
- For chats: Text messages.
You can search for a text fragment through an audio text transcript or text chat messages in either the customer's or the agent's channel. The search returns exact matches. The found fragments are highlighted in yellow.
The text is automatically tagged with agent and customer tags. These indicate things like whether the agent greeted the customer, whether the customer was in good humor, etc.
YandexGPT analysis
On the dialog page, you can see the YandexGPT analysis tab with an autogenerated summary of the dialog based on its semantic analysis. The summary has the following sections:
-
Call reasons: Why this dialog took place. Examples of reasons:
- Incoming contact: Customer has issues with a service.
- Outgoing contact: Agent is advertising a subscription for a service.
-
Results: The outcome of the conversation. The results are summed up for each of the listed reasons. Examples:
- Incoming contact: Agent helped to resolve the customer’s issue.
- Outgoing contact: Customer purchased the subscription.
-
Problems: Issues reported by the customer.
-
Summarization: Reasons for having the conversation and its results. This section also includes information on the evaluation criteria, e.g., the participants’ emotions or objections during the conversation.
-
Client keywords: Keywords in the customer's messages.
-
Agent keywords: Keywords in the agent's messages.
-
Theme: What the customer and agent discussed.
Dialog filtering
Filters define the conditions for filtering dialogs.
There are the following types of filters:
- Agent: Agent data.
- Customer: Customer data.
- Bot (only for chats): Bot data.
- Conversation statistics (only for audio): Agent and customer speech quality criteria, e.g., speech rate, mutual interruptions, etc.
- Shared metadata: Data about the conversation audio or text chat.
- Tags: Classifiers applied to conversation audio recognition results or text messages. To learn more about tags, see Concepts.
For each filter, you can specify one or more filtering conditions. These can be of four types:
- Date: Select a date range from the calendar.
- Text: Enter a line of text. The search will only return exact matches.
- Number: Specify a range of numbers. You can specify either both range boundaries or just one of them. To find a particular value, specify it for both the top and bottom boundaries. The boundary values are included into the filtering range.
- Logic: Select either Yes or No.
You can use multiple filters at the same time. They will be combined by the logical AND
operation to find the dialogs satisfying all the conditions that were specified.
Related dialogs
In some CRM systems, dialogs may be grouped by task. For example, you can group together all dialogs with a customer who has contacted support multiple times with the same request. When creating a connection to upload your data to SpeechSense, you can specify the ticket_id
additional parameter, and give it a name within SpeechSense, e.g., Task number
. The uploaded dialogs will then be regrouped as related dialogs. They will be grouped by task number specified in the ticket_id
parameter.
In each of the related dialogs, you will see the
- At the top of the page, the dialog metadata.
- On the Dialog tab, the contents of all related dialogs. It also displays a tag hierarchy for each of them. You can use text search within a single dialog.
- Dialog summaries autogenerated by YandexGPT Pro based on semantic analysis, on the YandexGPT analysis tab.