CNIPA.AI
검색으로 돌아가기
기록

METHODS AND SYSTEMS FOR ADAPTIVE DATA TREND PREDICTION AND VISUALIZATION

발명심사 중
20청구항 · 3 독립항
§ Ⅰ

개요

발명자

John Sciacchitano; Dustin Helquist; Abhii Parakh; Lauren Mattison; Joe Portella; Rossana Bandyopadhyay; Jason Kapel; Harsha Vanjani; Kahang Ngau; Amborish Baruah; Nga Than

IPC 분류

G6Q 10/639G6N 20/

CPC 분류

G6Q10/6393G6N20/

This application is directed to adaptively predicting and visualizing a trend of a large set of complex data (e.g., process data, performance data). A computer system executes an application for tracking a plurality of metrics that are associated with a project and include a set of process metrics and a set of performance metrics. Historical data of the plurality of metrics include a temporal series of historical metric indicators of each metric, and are applied to train a performance projection model. Current data include a temporal series of current metric indicators of each of the plurality of metrics. At a first time, while collecting the current data, the computer system applies the performance projection model to process a subset of current metric indicators and generate a predicted performance trend for a target projection length. The predicted performance trend is visualized jointly with the subset of current metric indicators.

원문 (중국어)

This application is directed to adaptively predicting and visualizing a trend of a large set of complex data (e.g., process data, performance data). A computer system executes an application for tracking a plurality of metrics that are associated with a project and include a set of process metrics and a set of performance metrics. Historical data of the plurality of metrics include a temporal series of historical metric indicators of each metric, and are applied to train a performance projection model. Current data include a temporal series of current metric indicators of each of the plurality of metrics. At a first time, while collecting the current data, the computer system applies the performance projection model to process a subset of current metric indicators and generate a predicted performance trend for a target projection length. The predicted performance trend is visualized jointly with the subset of current metric indicators.