Evaluating Human-Machine Translation with Attention Mechanisms for Industry 4.0 Environment SQL-Based Systems
NLP, Attention, Industry, IoT, Measurement, SQL, Deep Learning.
The use of relational databases is increasingly present in the industry. Applications in medicine, IoT and Industry 4.0 are examples of this. Despite the great capacity and efficiency in data storage and retrieval, this type of database requires technical knowledge in specific query languages to access this information, which distances these types of applications from the non-specialized public. In this work, we propose an application of recent models in natural language processing that uses mechanisms to translate natural language into English into SQL applied to a database that stores sensor data, focusing on the concept of Industry 4.0. Paired examples of natural language phrases were generated with their corresponding SQL query to be used for training and validation. The model was agnostic in relation to the database schema, so that it only handles the input and output sequences regardless of the database structure. The data comes from historians of the typical process used in industrial settings. When training the deep neural network, we obtained a language model with an accuracy of approximately 99 \% in the validation set.