© 2022, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.Artificial intelligence (AI) and machine learning (ML) have begun to include promising methods for solving real-world problems. However, the power of these methods is limited by the CPU capabilities of the current computers. Quantum computing (QC) appears to be not only an alternative route for more powerful computers but also the introduction of a new computing paradigm. Much more powerful AI protocols are predicted to be developed by the QC implementations. In this study, we present a binary classification of quantum data implemented by superconducting quantum circuits. Binary classification of data is a subroutine of both AI and ML. Therefore, much effort has been spent on the development of AI and ML strategies to be implemented on quantum computers. In our framework, we adopt a dissipative protocol for the classification of quantum information. The dissipative model of quantum computing has already been proven to be well-matched to the circuit model of quantum computing. More specifically, we introduce repeated interactions-based model with distinct quantum reservoirs as strings of pure qubits representing the quantum data. In the scenario, a probe qubit repeatedly interacts with the reservoir units and the binary classification is encoded in the steady quantum state of the probe qubit. We also present analytical results including system and reservoir parameters. We use realistic parameters for the implementation of the proposal with superconducting quantum circuits which are the leading platform for building universal quantum computers.