The challenge
Energy & Utilities are living critical and extremely complex times. Changes taking place on the geopolitical and social scenario, on competition, customer demand, expectations, attitudes, and climate are at the heart of an epoch-making revolution: the energy transition.
To accelerate this transition, Utilities are enabling the digital transformation within their organizations, developing innovation, and creating sustainable organizations.
In this context, Utilities need to rethink their business processes. Among these, one is related to the meter reading. Companies carry out a huge number of readings every day, scheduling volatile appointments, and dispatching multiple technicians per day. Moreover, some types of meters could be hard to be read by technicians because they display values without common information or are located in places not easy to reach (such as water meter, that are very often located underground).
Could technicians manually fill in the value of meters while in the field? No, as this could lead to mistakes, inefficiency, and incorrect billing, minimizing customers’ satisfaction.
With an eye toward a highly digitized and faster future, Utilities are looking for ways to upgrade this process, improving operations, maintaining reliability, safety, and 100% service continuity.
The solution
A new era of meter readings has now begun. Relying on powerful ML algorithms based on Computer Vision techniques, the new Computer Vision meter-reading assistant feature allows companies to automatically recognize, read, and collect data for water, gas, heating, and electric utilities (both digital and analogic, for those who have not replaced it yet). Capturing the area of interest with the camera, via mobile device (smartphone and tablet), the system automatically reads and identifies the data, even offline. The technician receives complete information about the reading (not only the value number, but its description too), and about the meter (such as the type of model and the obsolescence of the asset).
In the second stage, data is collected and directly reported both on the mobile and back-end side. Each field of the data forms is automatically filled in and transmitted to the system, allowing operators to efficiently manage readings, avoiding the dispersion of information.
Impact & KPIs
• Improving and automating processes in mobility
• Expediting the execution of tasks
• Creating more efficient and sustainable enterprises
• Enhancing the accuracy of data collected in the field