AI Program: discover NEO Schedule!

How to have better automatic scheduling and better dispatching optimization for technical resources? Discover Axians' solution, NEO Schedule, one of the twelve projects resulting from Leonard's Artificial Intelligence program (cohort 2021). Its objective? Help VINCI teams become more autonomous by implementing AI use cases, with a high business impact.

“A wizard is never late, nor is he early, he arrives precisely when he means to” Gandalf, The Fellowship of the Ring. As we are not all wizards, it comes as no surprise that scheduling is quite paramount when it comes to deploying the right resource at the right place, at the right time. That is what Axians’ NEO Schedule is all about.

A promising market

Resource allocation is an ever-growing market with ever-harsher competition. A 2020 report by Gartner* hinted towards a 12% CAGR for the global scheduling market, making it grow from 3 USD billion in 2020 to 5 USD billion in 2025. In addition to the figures, Gartner also points out that scheduling solutions should focus on features improving the dispatchers’ efficiency and the technicians’ utilization rate. In order to tackle this new paradigm, Axians NEO decided to build an AI-powered solution to complete and augment its current solution NEO Schedule. In that regard, Axians joined the AI Program run by Leonard in order to first enhance the skills of its team regarding the AI technology and second to be autonomous allowing for easy maintenance and evolution of the solution.

NEO Schedule is Axians’ solution for the automatic optimization of the scheduling and dispatching of technical resources. This solution is two-fold, and the first part of it focuses on scheduling.

Scheduling is a complex problem to be solved

Scheduling consists in allocating a list of tasks/assignments to the right resources, e.g., a set of maintenance intervention among a team of technicians, in order to build the most rational intervention plan. Specific resources called dispatchers are in charge of factoring in all of the constraints associated with such a problem and propose the most rational plan. Locations, availabilities, service level agreements (SLA), local regulations and working agreements are all taken into account when setting up such a schedule. This makes for quite the optimized result, but in turn is time-consuming and iteration-heavy as it is all done manually. On average, estimations hint towards a 10-hour process per day for the dispatching of 90 resources on 400 assignments.

AI to the rescue

The New AI-augmented NEO Schedule provides an overhaul of the solution as it reduces this time to less than 10 minutes per day for a similar configuration. Not only does this reduce the time required to plan the day for a given number of resources but it also provides the dispatchers with an opportunity to manage more resources and spend more time on more added-value tasks. One of these tasks would be the marginal alteration of a given schedule as information flows in from the field. This is called dispatching.

The dispatching process boils down to processing real-time information from the technicians on the field. This information can amount to a resource being ill and not able to work for a given day, having a flat tire and having to work with a small delay, or simply a job that would have taken more time than expected to complete. These field-insights are crucial to the dispatchers as they are to be used to marginally shift the schedule to factor it in and ensure the most optimal schedule is still provided.

The current norm, which is manual dispatching, relies on the dispatchers’ expertise and knowledge, which is good, but tends to be suboptimal at times given the high volume of updates getting in, the great volume of interdependencies to factor in the schedule, and the very short reaction time that is expected from the dispatchers. AI-augmented NEO Schedule takes care of these problems as it completely automates the whole process and marginally adapts the schedule as live updates come from the field.

Towards a new solution that faces the future and the need for efficiency

The new AI-augmented NEO Schedule meets the new markets demands and ensures the solution’s survival and thriving in the future. AI-augmented NEO Schedule proves to be more efficient than the competitors’ solutions when it comes to factoring in real life constraints as such constraints are directly embedded within the underlying optimization algorithms. In addition to this, AI-augmented NEO Schedule is built on tailor-made methods and functionalities, never resorting to any open-source solution for its optimization process. In a nutshell, AI-augmented NEO Schedule is an efficient scheduling solution built by dispatchers and for dispatchers.

By Alexander Wassiltschenko, Axians

This article is part of a series involving the participants of the AI program by Leonard, the VINCI Group’s foresight and innovation platform. The program has been specifically designed to accelerate the adoption of AI technologies within VINCI. It consists in a five-month incubation period where selected VINCI collaborators follow a learning by doing process where they codevelop an AI-based use case under the coaching and mentoring of Leonard’s team and consultants from Eleven Strategy.

> More about Leonard’s AI program

*Gartner: Magic Quadrant for Field Service Management –ID: G003992502

What do we do?

The VINCI Group created Leonard to tackle the challenges posed by the transformation of regions and lifestyles. Our goal is to unite a community of key stakeholders in order to build the city of the future together.