The Client
A car manufacturer benefits from being able to catalog problems and solutions into a document management system. This way they can quickly identify problems and solutions based on past experiences. This task requires being able to sift through large amounts of customer service records and internal memos, and then sorting them into relevant groups for the catalog. While sorting is usually no problem for AI, the prevalence of different text jargon from wildly different sources causes major issues.
The Solution
Text data with varying syntaxes poses a serious challenge for AI. A mechanic and a customer may describe the same problem in a different way, so being able to know that those two accounts belong in the same class is paramount. OneClick.ai tackles this problem through the use of Deep Learning. Because our platform has been pre-trained using a large corpus of knowledge, it is capable of looking beyond syntax through a variety of techniques. Techniques like using word embeddings, Word2Vec, Char-level CNN, and analyzing textual features (e.g. editing distance, BM25, etc) helps our AI find common concepts between different syntaxes. All these tools are then put together in Meta-learning to produce a highly optimized and accurate model. The actual model created performed with an accuracy of 98%.
The Benefits
An increasingly accurate catalog also leads to increased productivity as customer cases are handled faster, and a centralized source of info allows accurate statistics to be gathered, providing insights into customer issues and quality control.
Additionally, when it comes time to update the system, the platform nature of OneClick.ai allows a new classification model to be made in moments without needing any of the original development team.
OneClick.ai 