Our client is a leading commercial auto manufacturer headquartered in Europe operating in over 40 locations across the world. They’re committed to improving the mobility of the world with state-of-the-art commercial vehicles.
A truck has close to 30000 parts. The combination of which axle type is used in which model type together with what suspension makes it too many. It becomes humanly impossible for the shop floor engineer to use the right one without the right data where the system can give reliable information on this based on existing successful truck models. There could be information on how many trucks needed fans on time in locations where the temperature is higher.
Senior executives want to know how the sales are performing with each customer having different models with a combination of which parts. They would want to know how the sales were with the same type with a combination of a different set of parts. Timeline adds to the confusion of the sales trend. So, without a proper data insights system, executives may not get the right data.
The salesperson has the responsibility to balance both the client expectations and organizational revenue requirements. However, many times they will be trying to convince the client why the mid-range truck is a better option than the regular 6-wheeler for the tonnage and power output.
All three are stuck at one level simply because they are unable to derive trustworthy actionable information at a moment’s notice. This was exactly the case with our client as they had to empower their frontline employees with the right information at the right time to create a striking impact.
They required a solution that enables their employees.
The client wanted to create a seamless data experience for its employees across functions. We suggested a voice powered data analytics platform connected to the enterprise database. A true hands-free solution for data users which is omnichannel in nature and database agnostic. But then we cannot always “talk” to the system. On such occasions, the text acts as a secondary input format.
However, it was not smooth sailing throughout the project. The system needed to understand complex industry terminologies to fetch the right data. We achieved a 90%+ accuracy level on voice recognition and Natural Language Understanding (NLU) of automobile manufacturing terminologies along with their appropriate hierarchy with rigorous training of the ML models on entity recognition and intent identification. We also trained the models on an extensive corpus of user utterances, including industry-specific vocabulary such as “Take Rate”, “Power Train”, “Axle Model”, “Front Suspension”, etc. to name a few. This helped us manage the challenges around accuracy.
And we proved it right with our
purpleSlate offers a host of technology service offerings, with AI and NLP as the crux of its solutions, to solve complex business problems. As machines become increasingly proficient in natural language, conversations, in voice and text will transform into the primary mode of providing and consuming services.