Back to the portfolio

Per-user chart and dashboard personalization engine

Computing, Software & AIHealth & Safety TechSensors & InstrumentationLab validated

PRIME is a recommendation engine that learns which data visualizations work best for each individual user by analyzing physiological signals — things like eye tracking, brain activity, or skin response — captured while users interact with different charts and dashboards. It builds a personalized model that predicts which visualization design will help a specific person extract insights most effectively in a given context (task type, device, environment). The system uses a matrix-completion optimization technique to fill in gaps in sparse user-performance data, similar to how Netflix predicts movie ratings you haven't given yet. The result is a system that automatically surfaces the right chart type or interface layout for each user rather than applying one-size-fits-all defaults.

What you could build

An analytics platform plugin or enterprise BI tool feature that automatically personalizes dashboard layouts and chart types per user, purchased by enterprise software vendors (Tableau, Power BI, Salesforce) or large organizations running internal analytics platforms where decision quality matters at scale.

Who in Virginia should care

Northern Virginia's dense concentration of federal agencies, defense contractors, and intelligence community data analysts represents a natural early market for tools that improve human understanding of complex datasets.

Readiness: Lab validated

Concept — described but not yet demonstrated. Lab validated — supported by experimental results in the patent. Prototype likely — the text describes a built, working embodiment.

Readiness is inferred from the patent text, not from a lab visit.

The record

Inventors
Ran JIN, Xiaoyu CHEN, Nathan LAU
Granted
December 23, 2025
Status
Granted patent
Patent number
12504980

Ready to talk?

Virginia Tech Intellectual Properties handles licensing for this technology.

VTIP contact coming shortly

Prosim summaries are generated from public patent text and are not legal advice.