Client
Our client is a Martech company that sells and implements an out-of-the-box web traffic tracking system that helps businesses to monitor user behavior, traffic sources, and conversion metrics to optimize online presence.
Challenge
The client needed a custom software solution for internal use that would simplify, accelerate, and automate employee operations with meetings and vacays, namely: scheduling/booking a slot, or getting reference on the status. The solution was to be integrated with the HRIS system and meeting scheduling software as well as be simple to learn and use for predominantly non-tech employees.
Project Description
We suggested developing a voice recognition solution to enable fast and hands-free operation, and that suggestion was accepted by the client’s team with great enthusiasm. To ensure the ease of installation and usage as well as to prevent employees from cluttering their app stack, it was decided to develop a telegram bot, based on language model, that would recognize not just fixed commands, but spoken, conversational language in English and German (as the client team is bilingual).
The voice-powered chatbot allows employees to solve the following tasks:
- schedule a meeting with the specification of the meeting day, time, duration, title, and participants
- reschedule the meeting or adjust its title and participants
- cancel the meeting
- get information on the meeting: available slots for a certain day, planned meetings for a certain day, and their details (time, participants, title)
- book vacation of any type (paid, unpaid, sick leave, special day-off, etc).
- reschedule or cancel vacation
- get information on the vacation: how many days are available, how many days are booked and when.
To enable automatic spoken language recognition instead of rigidly fixed voice commands, our data scientist developed a range of data clusters, where each cluster was associated with a certain possible query from the above mentioned use cases.
Another task was to ensure the accuracy of voice command recognition. To attain this objective, our team implemented various spoken language and word recognition strategies and thoroughly trained the language model in different sound conditions – where volume, intonation, accent, and other characteristics varied.
Let’s get an overview of a user flow:
- Аfter the activation of a telegram bot, a user can say a meeting- or vacation-related phrase in English or German.
- The bot identifies the language automatically, then identifies primary and contextual keywords in the user’s phrase. Based on these keywords, the bot determines the complete user query. The query may be either action-based (e.g. cancel a meeting, book a day off), or information-based (e.g. provide available amount of paid vacation days next month).
- The bot passes the user query to the HRIS system and meeting scheduling software. If the query is action-based, the target tasks get completed, while if the query is information-based, the target information gets back from the source systems.
- The bot informs the user one’s the query is completed (if action-based), or provides the requested data (for information-based queries).
Thanks to the integration with the client’s HRIS and meeting scheduling systems, all changes are applied and all data is updated in real time, preventing irrelevant results and collisions of meetings and vacations of different employees.
Key Features
Voice-driven, instant booking of meetings and vacations as well as getting reference on them
Automatic spoken language recognition to enable conversational experience and eliminate necessity to learn fixed commands
Automatic identification of language – English and German – for bilingual team support
Integration with HRIS system and meeting scheduling system for instant request execution and real-time data communication
Team & Time Frame
We delivered the project in 3 months, with the team of three members:
Project Manager
Data Scientist
QA Engineer
Major Tech Stack
NVIDIA AI, QuartzNet, Conformer-CTC, Telegram BotFather
Results
A voice-driven telegram bot that we delivered streamlined and accelerated meeting and vacation booking process as well as obtaining information on them for each employee. That offloaded employees from manual manipulations in distributed software systems (HRIS and app scheduling ones in particular) and minimized manual query processing for HR specialists, enabling them to focus on more essential working tasks as well as enhancing employee experience.