US 12,243,130 B2
Data interpolation platform for generating predictive and interpolated pricing data
Olga Ponomarenko, San Francisco, CA (US); Javier Avalos, San Francisco, CA (US); Justin Moore, San Francisco, CA (US); and Marc Perkins, San Francisco, CA (US)
Assigned to Caplight Technologies, Inc., San Francisco, CA (US)
Filed by Caplight Technologies, Inc., San Francisco, CA (US)
Filed on Aug. 15, 2024, as Appl. No. 18/806,361.
Application 18/806,361 is a continuation of application No. 18/597,110, filed on Mar. 6, 2024.
Claims priority of provisional application 63/490,832, filed on Mar. 17, 2023.
Prior Publication US 2024/0404137 A1, Dec. 5, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 11/20 (2006.01)
CPC G06T 11/206 (2013.01) 18 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
in a system comprising a data interpolation platform, the data interpolation platform comprising:
a data collector configured to collect, from among one or more data sources, data and information (“collected data”),
a pre-processor,
an artificial intelligence (AI) engine configured to at least one of generate, train, validate, test and execute multiple AI models, the multiple AI models including at least one AI pricing model configured to generate predictive or interpolated pricing data;
an interactive graphical user interface (GUI) engine configured to generate and dynamically update an interactive GUI,
a data monitor, and
one or more servers comprising a memory, computer-readable instructions, and one or more processors executing the computer-readable instructions, thereby causing the data interpolation platform to perform operations, the operations comprising:
receiving, by the data collector, the collected data;
executing, by the AI engine, at least one AI model from among the multiple AI models to identify outlier data from among the collected data, wherein the outlier data is determined using predetermined quality control parameters;
removing the determined outlier data from the collected data;
grouping and weighting, by the pre-processor, the collected data to create pre-processed data;
generating, from among the pre-processed data, one or more datasets;
executing, by the AI engine, the at least one AI pricing model from among the multiple AI models, said at least one AI pricing model using the one or more datasets as input and generating the predictive or interpolated pricing data as output;
generating, by the interactive GUI engine, one or more graphical price visualizations based on the predictive or interpolated pricing data;
displaying, via the interactive GUI, the one or more graphical price visualizations;
detecting, by the data monitor, at least one of a change to the collected data and a presence of new data from among the one or more data sources (collectively, “detected data”), the new data comprising data that is different from the collected data;
updating the one or more datasets responsive to the detected data;
re-executing, by the AI engine, the at least one AI pricing model, using the one or more updated datasets as input, to generate updated predictive or interpolated pricing data;
generating one or more updated graphical price visualizations based on the updated predictive or interpolated pricing data; and
dynamically updating the interactive GUI to display the one or more updated graphical price visualizations.