Issue tagging in Asseti

by Asseti Insights

Asseti’s value is best experienced where the data – primarily imagery at this time – is enriched in a way that enables faster/stronger/better work at an operational asset management level and at an asset network performance optimization level. Issue tagging is foundational to both of these.

Issue tagging in Asseti is done manually, through intelligent AI/ML-enabled automation, and hybrid AI/ML-assisted specialists.

Issues are tagged with rectification cost and issue details, plus risk and likelihood. The combination of these primary dimensions helps to expedite and improve operational decision making at a site level – managers instantaneously know the priority of the pending MRO (maintenance and repair operations) backlog.

The power of this functionality is exponentially greater at a network level, which makes sense given many of the challenges of asset network management derive directly from the scale of operations. Asseti issue functionality enables portfolio managers to understand carried risk in real-time, and drill into the numbers as easily as scrolling with their mouse.

HubSpot Video

This effective set of dimensions, detail, cost, risk and likelihood, provides the insight to optimize and evaluate asset network performance. A configurable ‘priority’ setting is included to accommodate needs on the ground. This setting is used by our manual issue tagging users.

Automated or machine-enabled issue tagging is available to Enterprise level Asseti subscribers. Automated issue tagging relies on our trained AI/ML algorithm to identify, tag, estimate and set the risk/likelihood level. Asseti arranged a huge volume of historical datasets to be used in the algorithm’s training, encompassing multiple countries, currency zones and asset types. The algorithm is highly effective and accurate – however, is it true that humans possess the very best multi-dimensional computational capability!

Hybrid AI/ML-assisted issue tagging by specialist business analysts combines the best of both capabilities – the blunt force capacity of high compute power systems to plow through gigabytes of data and laboriously search for minuscule evidence of defects or issues is superior to human operators. And, the capability of specialists operators to synthesize numerous disconnected inputs, correctly identify circumstances and diagnose the appropriate response is (and will remain for a long time) far superior to that of computers. Asseti’s centralized team of BAs have extensive experience with issue detection, and their efficiency expanded massively once our trained algorithm was set free!

Whether generated manually, through AI/ML or a hybrid model with AI/ML-assisted analysts, issue detail and risk aggregates feed the Asseti Analytics engine to populate pre-configured or custom dashboards to enable faster, better decision making and asset network optimization.

A-Issue-3List of Asseti issues logged to a specific site