Sikurayer Registers Patent for GUI-Based Artificial Intelligence Technology... Implementation of Codeless AI

Sikurayer (CEO Jeon Joo-ho) has registered a patent for no-code AI technology, marking a significant step in enhancing its artificial intelligence competitiveness. On the 28th, Sikurayer announced that it has registered a patent containing artificial intelligence technology that allows non-experts to develop AI models using a no-code approach. The patent includes core technologies that recommend the most suitable AI models for data, data preprocessing, hyperparameters, etc., thereby reducing the difficulty of AI development and shortening development time. Previously, to develop an AI detection model, it was necessary to establish a total of more than seven processes, including △data preparation △data analysis (EDA, Exploratory Data Analysis) △feature selection (Feature Engineering) △algorithm selection △Hyper Parameter Optimization △model evaluation/validation ▲deployment. Sikurayer has applied for a patent that implements AI models based on a GUI (Graphical User Interface), reducing the existing AI development process to three steps. In particular, Sikurayer has advanced hyperparameter optimization technology to enable non-engineers to easily develop AI models using no-code AI technology, according to the company. To this end, Sikurayer has built the HPRS (Hyper-Parameter Recommend Server) and implemented a hyperparameter optimization module. The core of HPRS is to select all clusters that can be tested, automatically test all possible cases, and provide the hyperparameters that showed the best performance among the test results. Sikurayer's team leader Kim Jin stated, “We are working to lower the barrier to artificial intelligence by implementing AI technology in a user-friendly manner,” and emphasized, “We will use this patent as a stepping stone to alleviate the shortage of experts in the field of artificial intelligence and contribute to the advancement of domestic AI technology.” Meanwhile, this patent was applied for and registered as part of the 'SW Computing Industry Source Technology Development Project (2020-0-00107)' supported by the Institute for Information & Communications Technology Planning & Evaluation (IITP).