The Conversation Analyzer - projections dashboard presents conversational insights about category and subcategory occurrences. Information includes insights for inbound and outbound interactions showing usage, trends, and durations.
The other Conversation Analyzer historical dashboards show historical data; this dashboard shows projections to help businesses anticipate what will be talked about in the future and plan for that. The dashboard can predict which agents may or may not use certain language in interactions and thus where the coaches and supervisors should focus their time to help improve sales and compliance.
The forecast model uses Forecasting in visualizations (Looker documentation). According to Google, the Forecast feature uses the data results in an Explore's data table to calculate future data points. Forecast calculations include only the displayed results of an Explore query; any results that are not displayed because of row limits are not included. For more information about the algorithm that is used to calculate forecasts, see the ARIMA algorithm section.
At the top of the dashboard, you can set global filters for this dashboard:
- Interaction start date — the period of time you want to analyze data for. You can choose different preset ranges or you can specify your own custom data range. By default, Interaction start date is set to seven days ago.
- Language — the languages spoken in the interactions you want to analyze data in. Select the language using the ISO language code format, for example, en-us or fr-fr. By default, the Language filter contains all languages.
- Profile — the profiles (sets of categories, subcategories, and rules) used to transcribe the interactions you want to analyze data in. You can choose different profiles to narrow down the interactions in the dashboard. By default, the Profile filter contains all profiles.
- Category — the categories found in the transcriptions of the interactions you want to analyze data in. You can choose different categories to narrow down what was discussed in the dashboard. By default, the Category filter contains all categories.
- Subcategory — the subcategories found in the transcriptions of the interactions you want to analyze data in. You can choose different subcategories to narrow down what was discussed in the dashboard. By default, the Subcategory filter contains all subcategories.
- Disposition code — the outcomes of the interactions you want to analyze data in. Choose from different disposition codes available in your account. By default, the Disposition code filter contains all disposition codes.
- Initial direction — the direction of the interactions you want to analyze data in when they started. Initial direction can be either inbound (initiated by an external party), outbound (initiated by an agent to an external party), or internal (initiated by an agent to another agent). By default, the Initial direction filter contains all directions.
- Group name — the groups (identified by name) of the agents you want to analyze data for. You can choose different rules to narrow down the agents (assigned to the selected groups) in the dashboard. By default, the Group name filter contains all groups and displays data for all agents.
- Agent name — the agents (identified by name) you want to analyze data for. You can choose different rules to narrow down the agents in the dashboard. By default, the Agent name filter contains all agents.
- Skill name — the skills (identified by name) of the agents you want to analyze data for. You can choose different rules to narrow down the agents (assigned to the selected skill or skills) in the dashboard. By default, the Skill name filter contains all skills and displays data for all agents.
- First queue — the first queue (identified by name) entered by interactions that you want to analyze data in. The first queue is where the interaction was initially routed. By default, the First queue filter contains all queues.
- Subcategory matches — the number of times subcategories were matched during the conversations you want to analyze data in. By default, the Subcategory matches filter is set to allow for greater than zero matches, that is, at least one match was found.
- Interaction transferred — the transfer states of the interactions you want to analyze data in. You can choose to analyze interactions that have been transferred, not transferred, or either. By default, the Interaction transferred filter contains all transfer states.
- Recording time — the total duration of the recording of the interactions you want to analyze data in. The actual value of Recording time is determined by the Duration unit, for example, a Recording time of 10 might be 10 minutes, 10 hours, 10 days, and so on. Recording time includes the time the interaction recording started until it ended. The time can include IVR and queuing time. By default, the Recording time filter allows for all durations.
- Duration unit — the unit you want to use for the Recording time of the interactions you want to analyze data in. You can choose duration units of milliseconds, seconds, minutes, hours, or days. By default, the Duration unit filter is set to minutes.
- Customer hold time (ms) — the average duration the agent put the interaction on hold in the interactions you want to analyze data in. Hold time is in milliseconds. By default, the Customer hold time (ms) filter allows for all time.
- Agent talk time (%) — the amount of time that an agent was talking as a percentage of the total duration of the interactions you want to analyze data for. By default, the Agent talk time (%) filter allows for all percentage amounts.
- Cross talk time (%) — the amount of time that the agent and contact were talking simultaneously as a percentage of the total duration of the interactions you want to analyze data for. By default, the Cross talk time (%) filter allows for all percentage amounts.
- Customer talk time (%) — the amount of time that the contact was talking as a percentage of the total duration of the interactions you want to analyze data for. By default, the Customer talk time (%) filter allows for all percentage amounts.
- Silence time (%) — the amount of time the agent and contact were both silent as a percentage of the total duration of the interactions you want to analyze data for. By default, the Silence time (%) filter allows for all percentage amounts.
| Panel | ||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ||||||||||||||
|
Category trends tile
The Category trends tile displays how category use has changed over time. This gives an insight into what high-level areas of the business have peaked or declined in terms of discussion. For example, an increase in complaints, but not the type of complaint — the type of complaint would be set in a subcategory.
The Category trends tile contains a line chart showing category names, the number of times each category was found, and the date of the interaction.
Subcategory trends tile
The Subcategory trends tile displays how subcategory usage has changed over time. This gives an insight into which specific areas of the business have peaked or declined in terms of discussion. For example, an increase in specific competitor mentions when the competition category is selected.
The Subcategory trends tile contains a line chart showing subcategory names, the number of times each subcategory was found, and the date of the interaction.
Category usage by agent over time tile
The Category usage by agent over time tile displays the number of categories that have been used by agents over time. This gives an insight into what high-level areas of the business are being, or not being, talked about at an agent level. At a quick glance, you can see which agents are, or aren't, using the correct and expected language.
The Category usage by agent over time tile contains a line chart showing agent names and the number of times those agents have used categories in interactions starting on each day.
Subcategory usage by agent over time tile
The Subcategory usage by agent over time tile displays the number of subcategories that have been used by agents over time. This gives an insight into what specific areas of the business are being, or not being, talked about at an agent level. At a quick glance, you can see which agents are, or aren't, using the correct and expected language. This tile is most useful when filtering by category and then you can see, for example, which agents mention which products the most or least and who is increasing or decreasing their use of the product names.
The Subcategory usage by agent over time tile contains a line chart showing agent names and the number of times those agents have used subcategories in interactions starting on each day.
Interaction details tile
The Interaction details tile displays details about the interactions and contains the following columns:
- Interaction ID — the unique identifier for the interaction.
- Name — the name of the agent as defined in the VCC admin portal during agent creation.
- Interaction start date — the date and time at which the interaction started to the nearest 15 minute period.
- Handle time — the duration that an agent spent working with the interaction in milliseconds.
- Talk time — the duration that an agent was connected to an external contact during the interaction in milliseconds.
- Recording time — the total duration of the recording of the interaction.
- Subcategories found (count) — the number of subcategories found in the transcriptions of the interaction.
- Wrap time — the duration the agent spent in the Wrap state after being disconnected from external parties in hh:mm:ss format.
- Customer hold time — the average duration the agent put the interaction on hold in. Hold time is in milliseconds.
- Agent talk time (%) — the amount of time the agent and contact were both silent as a percentage of the total duration of the interaction.
- Customer talk time (%) — the amount of time the agent and contact were both silent as a percentage of the total duration of the interaction.
- Silence time (%) — the amount of time the agent and contact were both silent as a percentage of the total duration of the interaction.
- Initial direction — the direction of the interaction when it started.
- Interaction transferred (yes/no) (Yes / No) — indicates whether the interaction was transferred.
- Transfer destination — where the interaction was transferred, if applicable.
- Interaction consulted (yes/no) (Yes / No) — indicates whether the interaction included a consult.
- Monitor type — the mode of monitoring that was performed during the interaction, if applicable.
- Monitored (Yes / No) — indicates whether the interaction was monitored.
- Target duration met (Yes / No) — indicates whether the duration of the interaction is within the target. is this applicable in the default dashboard? It doesn't look like the duration target is set.
- Media type — the mode or method of communication used, such as phone or chat.
- Profile — the profile (set of categories, subcategories, and rules) used to transcribe the interaction.
- Language — the language spoken in the interaction in ISO language code format.