Insights

This section discusses various insights available with Quality Management.

Interactions

The Interactions menu is the central location to review conversations and insights generated by Quality Management

Supervisors and administrators can centrally review all conversations analyzed by Quality Management through the Interactions sub-menu on the web portal.

Heads Up

You must be an authorized user to view interactions.

1

On the Interactions sub-menu, click the blue Interaction ID in any row to open a detailed view of that Interaction.

2

Play the recording, read the transcript, and view the associated analytics, comments, and details.

3

After selecting an Interaction ID, Quality Management’s conversational analysis is displayed on-screen.

The Analytics tab provides a conversational summary, including an engagement and sentiment score, next steps, Indicators and Topics identified, and more

When viewing an interaction, the Analytics tab provides a summary of conversational insights identified by Quality Management. These insights include:\

• Engagement: A rated score based on various factors, including talk-time ratio, response time lag, and frequency of speaker changes. These are used to estimate how engaged a consumer is throughout the entirety of the conversation.

• Sentiment: A rated score based on the entire meeting’s analysis, primarily focused on the sentiment of the conversation. Higher scores indicate a more positive effect and scores around 50 indicate a neutral sentiment.

• Next Steps: Identified next steps with action items or conclusions based on the conversation’s transcript. Agents can use this information to ensure they understand where their conversation should proceed and what is required before their next contact. Managers or supervisors can use this to coach agents on effective next steps planning.

• Call Outs: Specific words or phrases that were noted as significant within the conversation. These are determined by an account’s configured Indicators, discussed below. Also notes Good Questions and Next steps identified by AI analysis.

• Topic Highlights: Broad, large-scale themes identified within a conversation. These are determined by an account’s configured Topics.

• Speech Events: The number of identified instances where conversational silence or crosstalk exceeded defined thresholds and the number of times the call was put on hold.

Analytics also include an Agent Summary, providing details about how the agent interacts with the consumer, like the talk-to-listen ratio, filler words used, and more

Each conversation analyzed by Quality Management includes an Agent Summary, providing insight into how agents interact with consumers. Details provided by the Agent Summary include a user’s talk-to-listen ratio, the longest uninterrupted spiel, the number of filler words used per minute, average talking speed, and the average time the agent waits to respond. With these metrics, managers can create helpful coaching opportunities to improve agent performance over time.

Supervisors can use the Speaker Metrics report to see an overview of a team’s or individual agent’s performance over time

While supervisors can view an agent’s performance on a per-interaction basis, as seen above, the Speaker Metrics report helps supervisors see an overview of an individual agent’s performance over time. This can help supervisors track agent performance, including changes as a result of coaching and feedback, and identify trends over time, such as if an agent reduces (or increases) their speech events, talking speed, talk-to-listen ratio, or other Agent Summary metrics.

Each interaction includes a graph of the conversation’s sentiment over time, with links to the transcript and recorded sections for context

Interactions analyzed by Quality Management include a graph of the conversation’s sentiment over time. Each time a conversation’s sentiment changes, users can interact with the insight’s pop-up window, which includes a link to sections of the transcript for additional context, as well as an embedded play button to hear or watch that section of the conversation.

Sentiment score is currently determined through transcript analysis

At this time, Quality Management’s sentiment scores are calculated solely through AI analysis of a conversation’s transcript and do not account for other factors like tone, volume, or talk speed. For example, AI models may interpret a response of great as positive, while okay may be neutral, and whatever may be seen as negative in some contexts.

Indicators (Call Outs)

Indicators (Call Outs) are custom keywords or phrases that note critical moments in a conversation, like competitive brands, features, or products mentioned

Indicators, identified under the Call Outs section, are customizable keywords or phrases that are highlighted within a conversation’s analysis. Indicators can be used to capture critical moments of a conversation or track mentions of a specific competitor, feature, product, or phrase. Accounts can use indicators to identify specific elements of conversation that are worth reviewing or tracking.

Consider a business that is focused on reducing churn compared to competitors. The business can create Indicators for their products and those of their competitors. Consequently, if an Indicator is mentioned within a conversation, the business can quickly identify the context of the Indicator’s mention and proactively work to meet the consumer’s need or concern if one exists.

For example, if a business specializes in candy, they can create Indicators for the various types of candy, like Gummy Candy, along with specific examples of those candies, like gummy worms or gummy bears.

The following images provide an example of Indicators noted in a conversation’s analysis. Within this image, the Indicators Hard Candy and Gummy Candy are noted, because Indicator-specific keywords or phrases, like gummy bears and gummy worms were noted in the conversation’s transcript. After clicking an Indicator (i.e., gummy candy), the transcript will reflect sections in the conversation where the Indicators were noted.

Indicators are grouped under custom categories, with each category supporting multiple indicators

Accounts can create multiple, custom categories to group and track Indicators mentioned within conversation. This allows each account flexibility to create systems of information in ways that work best for their needs, environment, or sector.

For example, if a business specializes in chocolate candy, they could create a Competitors category, with an Indicator for each of their primary competitors’ candy types, like hard candy or gummy candy. Using Quality Management they could now create an Indicator for Hard Candy, with keywords for lollipops, candy canes, butterscotch, or other similar candies. Additionally, they could create a second Indicator for Gummy Candy, with keywords for gummy worms, gummy bears, fruit slices, or other soft candies.

When combined, account administrators can review which Indicators are most commonly mentioned, along with which of their competitors is mentioned, in addition to the specific product that is being mentioned. This can provide key context to a consumer’s sentiment and if they are interested in a competitor’s product(s).

The following image provides an example of the previous example’s Indicators and their associated keywords grouped under the common Competitors category.

Indicators match against the spoken language of an interaction

Quality Management will match Indicators against the spoken language of an interaction and its associated transcript. For this reason, Indicators should be developed in the language(s) your business expects to encounter.

Indicators can be retroactively applied to historical conversations

After adding new indicators to an account, interactions will retroactively reflect the new Indicators upon analysis, helping businesses quantify common themes over time as trends become clear.

Accounts are allowed up to 250 indicators

As of the date of this document’s publication, accounts are currently allowed up to 250 unique indicators.

Indicators can be set up to be triggered by agents, consumers, or both

When creating an Indicator, account admins can configure if the Indicator will be noted in a conversation’s analysis based on who mentioned the keyword or phrase in the conversation.

For example, a contact center agent might regularly reference a product or set of features, which may skew analytics for Indicators mentioned. However, these data points may prove valuable if a consumer mentions these products or features, indicating their sentiment or business needs. Alternatively, an account may choose to always highlight indicator mentions, by either an agent or consumer, for quality assessment and complete coverage.

The Indicator Mentions report provides insight into Indicator frequency and can help proactively identify trends

Account admins and supervisors can gain insight into Indicator frequency through the Indicator Mentions report. This dynamic report displays the frequency and percentage of interactions containing configured Indicators, phrases, or keywords, and can be used to view trends over time. This can help supervisors proactively monitor interactions and quickly identify issues and trends without manual searching, as seen in the following image.

After drilling into an Indicator’s analytics, additional information can be seen in line or bubble view for different perspectives of the same information. For example, the following image shows additional information for the Churn risk Indicator.

From there, supervisors can drill further into Indicator analysis and see specific conversations and moments in the transcript where the Indicator was mentioned. This includes the ability to filter data by account or user and drill down into specific keywords to see transcript snippets for context. For example, the following image shows mentions of the keyword Cancel, which is configured as a part of the Churn risk Indicator.

Subscriptions

Supervisors and administrators can subscribe to Indicator mentions.

Quality Management supervisors and administrators can subscribe to Indicator mentions via email to track or monitor specific themes or trends. When subscribing, the user can choose to receive subscription notifications on a daily, weekly, monthly, or continuous (i.e., as-it-happens), basis.

For instance, a contact center manager may subscribe to an Indicator for escalation requests that track the frequencies of consumers requesting to speak or escalate a situation to a manager.

Subscriptions can be specific to a keyword, phrase, or the entire Indicator.

When subscribing, a user can choose to subscribe to the Indicator with all associated keywords and phrases, or, the user can subscribe to an individual or limited set of keywords.

For example, if the Indicator Cancel Service is selected, and contains the keywords cancel, terminate, discontinue, end contract, and termination, a user can subscribe to all keywords, or specific phrases that raise significant concern, like end contract.

Topics

This section discusses Topic highlights within conversations.

Topics track broad, predefined themes in a conversation and can provide insight to consumer concerns

Unlike Indicators, which focus on specific phrases or keywords, Topics highlight broader themes within a conversation. For instance, some subjects are discussed thematically from multiple perspectives, like a product’s security, privacy, or pricing. Instead of tracking these themes from a keyword-specific approach—as is done with Indicators—Quality Management uses artificial intelligence (AI) and machine learning (ML) algorithms to identify questions or statements that are relevant to a predefined theme.

For example, if a consumer is subject to an array of compliance or security regulations, they may commonly discuss or ask questions surrounding those topics. Consequently, when reviewing a conversation’s analysis within Quality Management, the analytics section may highlight portions of the conversation’s transcript that are related to those topics.

The following image provides an example of Topics noted under the Topic Highlights section. Within this image, the topics Variety, Quality, Regulation, Business Requirements, and Cost are highlighted, indicating that the conversation’s transcript included discussion around these topics.

Quality Management includes seven default topics and supports up to 10 additional custom topics.

Quality Management includes seven default Topics it will automatically track within a conversation, including Pricing, Legal, Privacy, Security, User Requirements, Hardware, and Licensing. Account admins can additionally create up to 10 custom topics, but must provide a variety of guided sentences by which the Topic’s theme can be understood through AI and ML algorithms. The following image contains an example of the Privacy Topic and its foundational guiding sentences.

Topics match exclusively against the transcript of an interaction.

Unlike Indicators, which identify spoken words within the spoken language, Quality Management matches Topics process through an AI/ML engine that currently exclusively supports the English language. Consequently, conversations in other support languages (e.g., Spanish) are first transcribed into English before matching Topics. When a Topic is created in a supported language other than English, it is translated to English for storage and used to match the translated transcript accordingly.

Speech Events

This section discusses Speech Events within an interaction.

Speech Events note when an interaction had a period of silence or crosstalk above an account’s defined threshold(s), and if a call was put on hold

Speech Events help supervisors identify moments in an interaction where there was an extended moment of silence or crosstalk beyond an account’s defined threshold settings, in addition to the number of times a call was put on hold. This can help supervisors identify and confirm that interactions are meeting an organization’s standards, in addition to helping supervisors identify when in an interaction these events occurred.

Speech Events are outlined and labeled below the interaction’s media player

When viewing an interaction, supervisors can see an outline and chronology of the conversation’s Speech Events below the media player. This provides visual cues showing who spoke, when they spoke, and the type and duration of each event triggered, helping supervisors quickly identify these moments for review.