From text to voice: how NEXERA revolutionized customer service with chatbots and voicebots
Business need
Our client, NEXERA, is a fiber optic network operator in central and northeastern Poland. The network was built, among other projects, as part of one of the most important government investment programs in recent years – the Digital Poland Operational Program. Based on NEXERA’s infrastructure, nationwide and local internet providers can offer services that are used by millions of users in hundreds of thousands of households, schools, and institutions.
As the business grew in scale and the network continued to expand, NEXERA’s customers and potential customers were directing more and more questions to the team each month. In the spring of 2021, it was already 55 cases a day, and after analyzing these requests, it turned out that as much as 52% of them concerned two matters:
- the need for information on the availability of the network at a given address
- the need to report irregularities, such as damage to infrastructure in a specific location, so that NEXERA could solve the problem
These inquiries were sent to the company by email. The trend observed and the increasingly time-consuming nature nature of handling these cases were a signal that it was worth implementing a solution that would relieve the NEXERA’s team and be able to independently – without their involvement – answer these questions.
It was possible, especially since the systems that NEXERA was already using were gathering the necessary information to handle the cases. What was missing, was a solution that would allow for the design of a scenario for an automatically held conversation, variants of responses, the appropriate tone of communication, and bringing everything together in a way that the solution would be easy to use for the client and convenient for the company in their day-to-day work.
Despite the fact that our clients are internet providers, we care about good relationships with internet users. Over time, the number of questions and requests from internet users became so large that we needed a solution that would allow us to handle them quickly and efficiently, without having to expand our team much.
Challenge
During the preparatory work, we came to the joint conclusion that it is not worth creating several bots for two problems handled in two communication channels. We decided to utilize the capabilities of the KODA platform and prepare a single, universal solution that will be able to communicate both by phone and through a dialogue window on the website. This solution means that most of the work – including integrations with external systems – will only need to be done once, and each subsequent integration and expansion of the bot’s knowledge will be more efficient and possible to do in one place.
This is possible because every voicebot is, in fact, a chatbot that bases its understanding on a transcription of the command it heard and gives a response by reading what has been marked as the answer to the question it understood using a voice simulator. However, designing a textual and voice conversation presents different challenges – in chatbots, difficulties may arise in understanding the speaker’s intention resulting from logical, grammatical, or spelling errors, while in voice communication, problems with call quality, understanding a person who speaks unclearly, or is in a noisy environment may occur. However, a large volume of conversations can minimize these difficulties.
Finally, in order for the conversation to take place, bridges needed to be built between the systems involved in the entire process, which are:
Integrations
FME System
A database that collects information about network availability in specific locations where NEXERA is present
Salesforce
CRM, where customer contact information is stored and information about network availability and development status changes can be sent to them
Teryt & Google Maps
Solutions that aggregate a database of addresses in Poland, which must be provided by the user and correctly recognized by the bot to perform further actions in both processes
KODA Platform
Its components allowing the creation of a textual and voice conversation scenario using Voice AI Connect – a product of Audiocodes, one of the market leaders in telecommunication solutions
Solution
The process of creating a multichannel bot proceeded in two ways. After the workshops with the client and suppliers of all systems involved in the project, we started integration work and work on the scenario, which was prepared immediately with two communication channels in mind (chat and phone), assuming that other text channels – messengers – may also appear in the future.
The conversation flow in both cases is not complicated:
- Need (check availability or report lack of access)
- Location (entered or spoken with all possible errors)
- Information (returned from NEXERA’s systems textually or vocally)
- Saving to CRM (contact with information on availability).
From the beginning, the KODA platform has been developed as a comprehensive tool that, thanks to easy integration, accepts and transmits data to systems in which our clients’ important processes are implemented
We also decided to look for ways to enrich our interlocutor’s experience and minimize the risk of errors in understanding what they want to convey, wherever possible. Therefore, for phone conversations, we decided to speed up the reading of the informational obligation regarding personal data, and when the bot is waiting for feedback from connected systems, sound effects appear in the conversation. It was also important to check how the speech recognition mechanism (ASR) and voice simulator (TTS) would cope with the names of places that are already or will soon be appearing in conversations. And these are not simple names, just mention, for example, Gietrzwałd, Gierzwałd, Rąbity, Wąbrzeźno, Szwarcenowo or Zawidz Kościelny, and many others. We tested the components available on the market, and decided to go with the Google Speech solution.
In the text version of the chatbot, we also decided to add an interactive Google Maps map, on which the user can place a pin, which reduces the probability of incorrectly interpreting the entered address to zero.
Introducing chatbot and voicebot made it possible to quickly obtain information about network availability in NEXERA’s regions for interested parties. It has also reduced the number of messages that have to be handled manually. In addition, it shortened the time it takes to pass on reports of irregularities to technical services, streamlining our operations.
Results
The chatbot and voicebot effectively help the NEXERA’s team in their daily work. Since its premiere, they have exchanged over 1,000,000 messages with their interlocutors and conducted 40,000 conversations with 30,000 clients and residents of NEXERA’s regions.
Voicebot
16K
number of conversations
370K
number of messages
65%
address recognition rate
Chatbot
30K
number of conversations
710K
number of messages
80%
address recognition rate
As you can see, the chatbot handles considerably more conversations, and 70% of them are about network availability. In turn, voicebots are more often used to report irregularities. This shows that voicebots are used more interventionally.
We also noticed that over 80% of people who click on the chatbot icon on the Nexera.pl website engage in conversation with it – almost three times more than we observe in other chatbots. The percentage of people who go through the entire conversation path with the voicebot is even higher – as much as 99%.
A multi-channel bot for NEXERA is a project that responds to our client’s specific needs. Together, we have developed a virtual assistant that is available 24 hours a day and can be developed to support further topics, languages, and introduced into additional communication channels.
And to top it all off – the solution we implemented was recognized by the organizers of the Titans of Hyperautomation (Mocarze Hiperautomatyzacji) competition, who acknowledged the world-class implementation of the project and awarded it with the 2nd prize in the “Intelligent Assistants” category. The Titans of Hyperautomation competition is the first initiative of this kind in Poland. Its main goal is to identify and reward the most effective hyperautomation implementations, whose effectiveness is measured by comparing the business goals set for the implementation with the results achieved after its completion. The event is organized by the Centre for Studies on Digital Government Foundation.