| CPC G06F 16/285 (2019.01) [G06F 18/214 (2023.01); G06F 18/2321 (2023.01); G06F 18/23213 (2023.01); G06F 18/24137 (2023.01); G06F 18/2433 (2023.01)] | 20 Claims |

|
1. A method comprising:
determining a plurality of representative points of input data using different data techniques;
upon identifying deviations between clusters of the plurality of representative points, modifying a defined segment size as a modified segment size, the defined segment size and the modified segment size being used to segment the input data;
obtaining a plurality of new representative points corresponding to new segments of the input data using the modified segment size;
clustering the new representative points using at least two different data clustering techniques, the clustering obtaining multiple sets of new clusters of the plurality of new representative points;
eliminating deviations between the multiple sets of the new clusters;
repeating the obtaining, the clustering, and the eliminating until the plurality of new representative points is within a threshold; and
training a data model using the input data with the plurality of new representative points.
|