| CPC G06F 16/24544 (2019.01) [G06N 3/092 (2023.01)] | 20 Claims |

|
1. A method comprising:
receiving a request to combine data from a plurality of data collections based on one or more constraints;
analyzing the request using one or more machine learning algorithms to determine an order by which respective ones of the plurality of data collections are to be searched;
searching the respective ones of the plurality of data collections according to the determined order, wherein the searching comprises using one or more parameters from a previous one of the plurality of data collections in the determined order when searching a next one of the plurality of data collections in the determined order, wherein a maximum time to search the respective ones of the plurality of data collections is designated, and wherein one or more search actions exceeding the maximum time are discarded; and
generating an output of combined data from the searching in response to the request;
wherein the one or machine learning algorithms are iteratively trained based on backpropagation from a loss function; and
wherein the steps of the method are executed by a processing device operatively coupled to a memory.
|