US 11,636,169 B2Granted

Adaptive data collection optimization

AssigneeOxylabs, UAB

InventorsMartynas Juravicius, Erikas Bulba, Mantas Briliauskas

Life of this patent

Estimating the term…

Loading patent…

Abstract

Systems and methods to intelligently optimize data collection requests are disclosed. In one embodiment, systems are configured to identify and select a complete set of suitable parameters to execute the data collection requests. In another embodiment, systems are configured to identify and select a partial set of suitable parameters to execute the data collection requests. The present embodiments can implement machine learning algorithms to identify and select the suitable parameters according to the nature of the data collection requests and the targets. Moreover, the embodiments provide systems and methods to generate feedback data based upon the effectiveness of the data collection parameters. Furthermore, the embodiments provide systems and methods to score the set of suitable parameters based on the feedback data and the overall cost, which are then stored in an internal database.

Claims20

Dependent claims

A system for optimizing a data collection request by identifying a set of parameters for executing the data collection request against a target, the system comprising:

a processor;
an extractor, operable with the processor to generate feedback data based on a classification decision received from a block detector, wherein the feedback data comprises information regarding an effectiveness of the set of parameters in executing a previous data collection request;
a valuation unit, operable with the processor to:
receive the feedback data from the extractor and calculate an overall cost to implement the set of parameters;
assign a score to the set of parameters according to the feedback data and the overall cost;
send the score assigned to the set of parameters to an optimizer, wherein the optimizer stores the score coupled with the set of parameters in a database;
the optimizer, operable with the processor to:
identify the set of parameters suitable for a subsequent data collection request by employing a machine learning algorithm, wherein the optimizer retrieves the score coupled with the set of parameters from the database and, wherein the optimizer subjects the score coupled with the set of parameters to the machine learning algorithm;
and
select the set of parameters and forward the set of parameters to the extractor through a gateway.

7 more elements

Dependencies are inferred from the claim text.

Facts

Application: 17/823,660Filed 31 Aug 2022 · continuation
Priority: 24 Aug 2021
Published: US 2023/0066328 A12 Mar 2023
Granted: 25 Apr 2023
Term ends: Not estimatedThe source records don’t support an estimate.

Classification10 codes

G06F 16/955
Retrieval from the web: using information identifiers, e.g. uniform resource locators [URL]
G06F 11/3409
Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of…:…
G06F 16/906
Details of database functions independent of the retrieved data types: clustering; Classification
G06F 16/951
Retrieval from the web: indexing; Web crawling techniques

Family

Application63/260,530Us provisional application · filed 24 Aug 2021
Application17/454,074Parent of this continuation · filed 9 Nov 2021
Application17/655,932Parent of this continuation · filed 22 Mar 2022
US 11,314,833 B1Parent of this continuation · filed 26 Apr 2022
US 2023/0066328 A1Pre-grant publication · published 2 Mar 2023
US 11,468,137 B1Parent of this continuation
US 11,636,169 B2This patent

From the US filing history. Foreign family members aren’t listed.