December 19, 2022

ONCE partners with Ibermatica for its first project in Quantum Computing

ONCE and Ibermática Join Forces for a Quantum Computing Project to Enhance Sales Outlet Allocation

The project encompasses the utilization of a cutting-edge quantum machine learning solution. This advanced technology enables the modeling of subjective manual assignments of sales outlets, leveraging historical data to automatically replicate these assignments in various contexts such as day, month, and products. Notably, the quantum solution offers significant advantages by excelling in problem-solving capabilities at a much faster pace when compared to conventional methods.

Due to the distinctive characteristics of ONCE employees and with presence throughout Spain, regular staff assignments to sales outlets are necessary due to various unforeseen circumstances. While there is already some level of automation through RPA (Robotic Process Automation) for employee assignment, the complexity arises from the consideration of multiple variables required to ensure efficient sales outlet allocation. Consequently, this intricate task must be performed each morning, emphasizing the importance of streamlining the process.

The coordination of products sold by over a hundred staff members based on regional considerations adds another layer of complexity to the employee assignment process. It becomes crucial to take into account the productivity of each sales outlet, especially those with high sales volumes, while also respecting the individual limitations, preferences, unique circumstances, and profile of each employee. This ensures that an optimal solution is achieved, allowing for efficient and effective operations within the organization.

Traditional solutions for optimizing complex combination problems have been computationally expensive and often fail to guarantee an optimal outcome due to their limited consideration of all possible scenarios. However, with recent advancements in quantum hardware and software, it is now possible to find optimal solutions to these problems in real-world settings. In the coming years, as quantum technologies are exponentially scaled up, they are expected to complement existing artificial intelligence systems and optimization solvers. One of the key advantages of these quantum systems is their ability to explore all viable solutions within a significantly shorter timeframe.

The project incorporates a quantum machine learning (QML) solution that effectively models the subjective manual assignment of employees using historical data and replicates it automatically based on various contextual factors such as day, month, and products. One significant advantage of this solution is its remarkable time efficiency compared to traditional methods, enabling the process to be repeated multiple times if required. This not only saves time but also enhances the overall effectiveness of the assignment process.

Recognizing the potential of quantum computing as a groundbreaking technology, ONCE is strongly committed to exploring its applications beyond this project. Once the proof of concept for the optimization solution, developed in collaboration with Ibermática, is successfully completed, ONCE plans to expand its utilization to other areas within the organization. This forward-thinking approach highlights ONCE’s intention to leverage the benefits of quantum computing and extend its impact throughout the organization, opening up new possibilities for innovation and optimization.

This project serves as compelling evidence that quantum computing can provide practical solutions to real-world problems. As its impact continues to unfold in the coming months, it is expected to generate significant attention and discussions within the industry. The successful implementation of this project showcases the potential of quantum computing to address complex challenges and reinforces its position as a viable and promising technology.

We support your projects

We are here for you, to advise you personally and offer you the product you need.