Multi-platform integration for classification of web content

Patent metadata

Field	Value
Publication number	US-12579557-B2
Application number	US-202418926279-A
Country	US
Kind code	B2
Filing date	Oct 24, 2024
Priority date	Dec 28, 2020
Publication date	Mar 17, 2026
Grant date	Mar 17, 2026

Abstract

In some examples, a system comprises at least one programmable processor; and a machine-readable medium having instructions stored thereon which, when executed by the at least one programmable processor, cause the at least one programmable processor to execute operations comprising: receiving a first request from at least one user device to execute an instance of an application; transmitting a graphical user interface (GUI) to the at least one user device to be rendered on a display of the at least one user device; receiving a second request, via the GUI, from the at least one user device, to deploy a digital advertisement, the second request including a set of platforms of a plurality of platforms of a multi-platform integration system, a set of settings, a set of parameters, and a set of allocation data; interfacing with each one of the platforms in the set of platforms; and integrating a digital advertisement directly with each one of the platforms in the set of platforms based on the set of settings, the set of parameters and the set of allocation data.

First claim

What is claimed is:

1 . A system comprising:
at least one programmable processor; and a machine-readable medium having processor-executable instructions stored thereon which, when executed by the at least one programmable processor, cause the at least one programmable processor to: access a request to deploy a digital advertisement, the request including a set of platforms of a plurality of platforms and a set of allocation data; determine a webpage classification for a website of at least one platform of the set of platforms, the webpage classification determined by: running an in-browser script to crawl data associated with one or more sub-URL webpages of the website to create a cascading analysis of the website using one or more of a URL parsing, HTML metadata, and text classification; and executing, by the in-browser script, in real-time a machine learning model to categorize the crawled data associated with the one or more sub-URL webpages to generate the webpage classification for the website, wherein the machine learning model used by the in-browser script parses elements of the one or more sub-URL webpages, the elements including one or more of a placement of images, a text, and comments on the one or more sub-URL webpages, and wherein the machine learning model used by the in-browser script further learns or uses contextual queues to parse a meaning of the text or the comments; adjust the set of allocation data based on the webpage classification; and integrate the digital advertisement directly with at least one platform of the set of platforms based on the adjusted set of allocation data.

2 . The system of claim 1 , wherein the set of allocation data is associated with a number of units of the digital advertisement to be deployed to each platform in the set of platforms.

3 . The system of claim 1 , wherein, when executed by the at least one programmable processor, the processor-executable instructions cause the at least one processor to:
update the adjusted set of allocation data after the digital advertisement is integrated with the at least one platform of the set of platforms.

4 . The system of claim 1 , wherein the request includes a configuration of a line associated with a campaign shell for a corresponding campaign including the digital advertisement, the line corresponding to a customized placement of the digital advertisement configured based on a screen type of a user device.

5 . The system of claim 1 , wherein when executed by the at least one programmable processor, the processor-executable instructions cause the at least one processor to:
interface with one or more of the set of platforms to adjust a number of units of the digital advertisement to be deployed on a particular platform, based on the adjusted set of allocation data.

6 . The system of claim 1 , wherein the machine learning model is a pre-trained model that is further trained in a browser running the in-browser script.

7 . The system of claim 1 , wherein the machine learning model categorizes the crawled data associated with the one or more sub-URL webpages to generate a webpage classification for one or more webpages of a website of one or more of the set of platforms.

8 . The system of claim 1 , wherein, when executed by the at least one programmable processor, the processor-executable instructions cause the at least one processor to:
collect the crawled data using URL crawler that builds an index of the crawled data using at least one of one or more content categories and keyword counts per document.

9 . The system of claim 1 , wherein, when executed by the at least one programmable processor, the processor-executable instructions cause the at least one processor to:
collect the crawled data using a wrapper that invokes executable links repeatedly and a thread-safe queue that ensures only a fixed number of linked downloads are running concurrently.

10 . The system of claim 9 , wherein, when executed by the at least one programmable processor, the processor-executable instructions cause the at least one processor to:
use the thread-safe queue to stop a linked download that exceeds a specified limit; and give a slot in the queue previously filled by the stopped download to a new linked download process.

11 . A method comprising:
accessing a request to deploy a digital advertisement, the request including a set of platforms of a plurality of platforms and a set of allocation data; determining a webpage classification for a website of at least one platform of the set of platforms, the webpage classification determined by: running an in-browser script to crawl data associated with one or more sub-URL webpages of the website to create a cascading analysis of the website using one or more of a URL parsing, HTML metadata, and text classification; and executing, by the in-browser script, in real-time a machine learning model to categorize the crawled data associated with the one or more sub-URL webpages to generate the webpage classification for the website, wherein the machine learning model used by the in-browser script parses elements of the one or more sub-URL webpages, the elements including one or more of a placement of images, a text, and comments on the one or more sub-URL webpages, and wherein the machine learning model used by the in-browser script further learns or uses contextual queues to parse a meaning of the text or the comments; adjusting the set of allocation data based on the webpage classification; and integrating the digital advertisement directly with at least one platform of the set of platforms based on the adjusted set of allocation data.

12 . The method of claim 11 , wherein the set of allocation data is associated with a number of units of the digital advertisement to be deployed to each platform in the set of platforms.

13 . The method of claim 11 , further comprising updating the adjusted set of allocation data after the digital advertisement is integrated with the at least one platform of the set of platforms.

14 . The method of claim 11 , wherein the request includes a configuration of a line associated with a campaign shell for a corresponding campaign including the digital advertisement, the line corresponding to a customized placement of the digital advertisement configured based on a screen type of a user device.

15 . The method of claim 11 , further comprising interfacing with one or more of the set of platforms to adjust a number of units of the digital advertisement to be deployed on a particular platform, based on the adjusted set of allocation data.

16 . The method of claim 11 , wherein the machine learning model is a pre-trained model that is further trained in a browser running the in-browser script.

17 . The method of claim 11 , wherein the machine learning model categorizes the crawled data associated with the one or more sub-URL webpages to generate a webpage classification for one or more webpages of a website of one or more of the set of platforms.

18 . The method of claim 11 , further comprising collecting the crawled data using URL crawler that builds an index of the crawled data using at least one of one or more content categories and keyword counts per document.

19 . The method of claim 11 , further comprising collecting the crawled data using a wrapper that invokes executable links repeatedly and a thread-safe queue that ensures only a fixed number of linked downloads are running concurrently.

20 . The method of claim 19 , furth

Assignees

• Zeta Global Corp

Inventors

• Rose David
• Portman Danny

Classifications

• G06F16/958

  Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking · CPC title

• G06Q30/0275

  Auctions · CPC title

• G06Q30/0277 Primary

  Online advertisement · CPC title