A Fortune 500 retailer wanted to use AI and natural language processing (NLP) to enhance their ordering and customer service systems. The goal was to use natural language to interact with multiple backend systems of an enterprise organization, including order management, inventory management, and package tracking systems and customer service interfaces.
consumer goods
2 years
NLP models, AI, speech-to-text, Arduino/Raspberry Pi
The vision was to say
Hey, System, order me more blue pens!
Or
Hey, System, where is my order?
and have the system answer accordingly.
To accomplish this, the system had to interpret spoken or written language, interact with backend enterprise systems, and respond naturally and accurately. We used hardware interfaces for speech input, speech-to-text translation, and natural language models to do so. To fulfill requests for message meaning, most of the backend enterprise systems, some of them legacy, also required integration.
Additionally, the language taxonomy of customer SKU database with over a million entries presented an extreme challenge. Most natural language models and processes use words, not alphanumeric codes. We developed a specialized NLP configuration for our language model so that system could understand the customer product catalog.
We also created a natural language orchestration engine that takes human language from a variety of channels (phone, custom hardware, web chat, call center recordings, etc.) and passes it to a natural language processing model. The system then deciphers the message’s meaning through a series of complex dialogue flows, which KIS configured and engineered in a conversation decision tree.
When required, the orchestration engine interfaces with backend enterprise systems to look up products or orders. The system interprets the enterprise API’s responses and formulates and returns a response to the end user over the appropriate channel.
This system currently automates thousands of chat conversations daily as well as auto-classifies call center contacts for an over 3,000-person operation.
Like many of our projects, this one was an absolute pleasure to work on!
This was a truly once in a lifetime project and one of the most challenging and interesting initiatives that we have worked on.
tech strategy & consulting.
We empower companies, invest in IT, provide tech training, create scalable squads, and deliver the right value.
data
management.
We handle data migration, conversion, analysis and integration, and database consolidation and management.
machine learning models.
We use AI algorithms and data to improve the accuracy of your analyses and help you make better predictions that guide decision-making processes.
web services development.
From discovery to delivery, we solve every issue, not just the basic ones.
