Keyword Spotting is designed to detect relevant keywords in spoken and written text. This article is about the spoken word – and specifically on the telephony channel. The complex data that travels over the voice channel in real time can be interpreted live by AI. The recognized topics can be used immediately, but also completely anonymized later for evaluations.
Real-time support
Today, keyword spotting is at the heart of modern agent assist solutions: Systems that display information to service employees in real time, suggest relevant follow-up actions or actively support the course of a conversation. Instead of relying on intuition and experience alone, the technology helps to provide the right content in a matter of seconds at crucial moments in conversations. ECCO, our real-time AI for voice channels, makes exactly that possible – live, context-based and seamlessly integrated.
We will show you three examples of keyword spotting for both real-time and historical evaluations that are already being used by our customers today.
Live Spotting: Three real-time advantages
With real-time recognition, customer dialogs take on a new dynamic. Predefined keywords are immediately recognized in ongoing telephone calls. If, for example, the word “offer” is mentioned, ECCO takes notice: all currently valid offers are immediately listed in the CRM system’s softphone. The following three scenarios show further possibilities.
#1 Useful links and information on the tablet
In the contact center, every second counts. So if a service agent first has to search for information in knowledge databases, valuable time is always wasted. Wouldn’t it be much more practical if relevant links were suggested automatically? This is exactly what real-time keyword spotting can be used for.
For example, if the system hears that a caller is complaining about insurance premium adjustments, the AI automatically suggests the table with the current index adjustments and other information to the service agent. This way, the customer is immediately informed about how the price adjustment came about. This saves time and improves the customer experience.
#2 Tips for cross- & upselling
Keyword spotting can also keep its ears pricked during sales calls. For example, if the keyword spotting agent notices that the customer has just decided to buy a fitted sheet, the service agent’s screen will immediately show that matching comforter covers from the same series are available as an offer. In this way, an agent never misses an opportunity to arouse maximum buying interest.
#3 Seamless CRM integration
What is recognized does not remain isolated: Ideally, keyword spotting is integrated directly into existing CRM systems. As soon as relevant terms are mentioned, the system automatically displays suitable tickets or cases for the person you are talking to – without any additional time spent searching. If, for example, a specific product or an open order is discussed, links to the relevant customer file appear, including the history.
In addition, shortcuts can be offered depending on the situation: for the quick creation of a ticket, a quotation or an internal note. Besides saving time, it also ensures that conversational content is processed immediately – exactly where it belongs.
Data protection
Keyword spotting is fully compliant with data and privacy protection regulations, as the keyword are extracted from the live transcript in real time.
These transcripts can be discarded at the end of the conversation. This means that completely anonymous evaluations are automatically available at the end of the day.
Evaluations: Three new perspectives
The possibility to draw helpful conclusions from the recognized keywords is partly linked to live spotting. Each recognized term can also be analyzed in its quantity afterwards. Of course, additional keywords can also be defined that do not trigger an event live and instead only affect statistics.
#1 Detect trends with new KPIs
The most obvious benefit of quantifying addressed topics is, of course: comparisons. Which topic was addressed most often this month? What did the numbers look like the month before? In which projects were which topics relevant? So there is an automatic categorization of conversations – with the quality of this assignment going much deeper into detail than would be the case with manually selectable categories. Every mention, every detail and every cross-reference is counted. A corresponding weighting of keywords per project then enables detailed analyses at a previously unattainable level.
For example, a question might be: How did call duration change for certain topics compared to the previous month with new strategies? Keyword spotting provides the answers fully automatically by paying attention in the background during the conversations in both months.
#2 Linking with telephony data
Since the AI system is fed with information from the telephony channel, the keywords counted can also be assigned to a queue, hotline or project in retrospect. And this without drawing conclusions about individual callers.
Top keywords can be calculated in absolute or percentage terms and compared with the telephony key figures. Which keywords were used in calls with particularly long waiting times? At which time of the day did the number of positive or negative keywords increase? Did the topics discussed change with increasing call time? With flexible reporting, we enable you to draw exactly the conclusions that are important to you.
#3 Keywords, summaries & solutions
Keyword spotting works automatically as a way to tag conversations. When used in combination with other AI features – namely the generation of conversation summaries and solutions – it opens up new possibilities. One concrete example: fully automated knowledge management. For each keyword, the best solution can be automatically derived from previous calls.
Conclusion
Keyword spotting is much more than just a tool for analyzing conversations: It’s the foundation for agent assist solutions – and thus a direct lever for efficiency, quality, and customer satisfaction. The technology provides targeted support to emloyees exactly where information is needed – without detours, without research, without distractions. And the best part: it works from day one – no model training based on your own conversation data required.
Our keyword spotting is part of LinkThat ECCO. Feel free to have a look at our product page to learn more.