IP Library › Granted Patent US 12,737,424
Granted Patent B2
US 12,737,424 · App. 18/745,655 · Granted Sep 15, 2026

Media intelligence system for advisory recommendation

Inventor: Sabal Almadi (Dhahran, SA)
Assignee: SAUDI ARABIAN OIL COMPANY
G06F16/9535G06F40/279
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,737,424
App. No.
18/745,655
Granted
Sep 15, 2026
Kind
B2
Abstract

System and methods are disclosed relating media intelligence for a company relating to a topic and/or theme. In some examples, media intelligence parameter data and company historical data can be received, which can be used to generate a subject search parameter. The subject search parameter can include one or more phrases, words, sentences, and/or categories for the topic and/or theme. Data for the topic and/or theme from a number of private and/or media data sources can be queried based on the subject search parameter. The queried data can be aggregated to provide aggregated data. The aggregated data can be filtered to provide filtered data. The filtered data can indicate a position of the private and/or media data sources on the topic and/or theme. A recommendation can be provided for the topic and/or theme using a machine learning model.

Claims (47)

1 . A computer-implemented method for providing media intelligence for a company relating to a topic and/or theme comprising:

receiving media intelligence parameter data and company historical data;

generating a subject search parameter based on the media intelligence parameter data and the company historical data, the subject search parameter including one or more phrases, words, sentences, and/or categories for the topic and/or theme;

establishing a baseline media trend for the topic and/or theme from historical media data from a prior time period, the baseline media trend representing sentiment patterns over the prior time period;

querying data for the topic and/or theme from a number of private and/or media data sources based on the subject search parameter;

aggregating the queried data to provide aggregated data;

filtering the aggregated data to provide filtered data, the filtered data representing current media coverage indicating a position of the private and/or media data sources on the topic and/or theme;

comparing the filtered data against the baseline media trend to identify deviations; and

providing a recommendation for the topic and/or theme in response to processing the filtered data and the identified deviations through a machine learning (ML) model, wherein the recommendation is based on a magnitude and direction of the identified deviations and specifies a responsive action proportional to the magnitude of the identified deviations.

2 . The computer-implemented method of claim 1 , wherein the media intelligence parameter data identifies one or more parameters for controlling a type of recommendation that is provided as the recommendation by the ML model.

3 . The computer-implemented method of claim 1 , wherein the company historical data comprises past advisories, reports, strategic documents white papers, and/or other publications related to the theme and/or topic.

4 . The computer-implemented method of claim 3 , wherein said generating comprises using text mining techniques to extract keywords, phrases, and/or sentences from the company historical data.

5 . The computer-implemented method of claim 4 , wherein the text mining techniques uses a natural language processing (NLP) model trained to identify the keywords, phrases, and/or sentences from the company historical data relevant to the theme and/or topic.

6 . The computer-implemented method of claim 5 , wherein the NLP model is a first model, and said filtering comprises using a second NLP to process the aggregated data to provide the filtered data.

7 . The computer-implemented method of claim 6 , wherein filtered data 132 comprises information characterizing a view point, facts, statistics, regulation, share of voice (SOV), and media sentiment relating to the topic and/or theme.

8 . The computer-implemented method of claim 1 , further comprising validating using an external system the filtered data to confirm whether the filtered data is valid.

9 . The computer-implemented method of claim 8 , wherein said validating comprising checking a context, a source credibility, and relevance of the filtered data.

10 . The computer-implemented method of claim 1 , further comprising storing the filtered data in a database and the ML is to retrieve the filtered data from the database for processing to provide the recommendation.

11 . The computer-implemented method of claim 10 , further comprising receiving user data for the topic and/or theme, the user data being provided via an input device and being stored as part of the filtered data.

12 . The computer-implemented method of claim 1 , wherein said providing comprises generating a report with the recommendation and information from the filtered data.

13 . The computer-implemented method of claim 1 , further comprising receiving data indicative of the theme and/or topic from a user.

14 . A system for providing media intelligence for a company for a topic and/or theme comprising:

one or more computing platforms each comprising:

memory to store machine-readable instructions;

one or more processors to access the memory and execute the machine-readable instructions, the machine readable instructions configured to:

receive media data from a media data source based on subject search parameter and private data from a private data source, the subject search parameter including one or more phrases, words, sentences, and/or categories for the topic and/or theme;

establishing a baseline media trend for the topic and/or theme from historical media data from a prior time period, the baseline media trend representing sentiment patterns over the prior time period;

aggregate the media data and the private data to provide aggregated data;

filter the aggregated data to provide filtered data, the filtered data representing current media coverage indicating a position of the media data sources and the private data source on the topic and/or theme;

comparing the filtered data against the baseline media trend to identify deviations;

provide a recommendation relating to the media intelligence for the topic and/or theme by processing the filtered data and the identified deviations through a machine learning (ML) model, wherein the recommendation is based on a magnitude and direction of the identified deviations and specifies a responsive action proportional to the magnitude of the identified deviations; and

cause a process and/or system of a company to be adjusted based on the provided recommendation to adjust a hydrocarbon production.

15 . The system of claim 14 , wherein the one or more computing platforms are configured to generate the subject search parameter based on media intelligence parameter data and company historical data.

16 . The system of claim 14 , wherein the one or more computing platforms are configured to validate using an external system the filtered data to confirm whether the filtered data is valid.

17 . The system of claim 14 , wherein the ML model is a supervised ML model trained based on labelled data and historical data.

18 . A system for providing media intelligence for a company for a topic and/or theme comprising:

memory to store machine-readable instructions;

one or more processors to access the memory and execute the machine-readable instructions, the machine readable instructions comprising:

a first natural language processing (NLP) model to provide a subject search parameter, the subject search parameter identifying one or more phrases, words, sentences, and/or categories for the topic and/or theme associated with a sector;

a system interface to aggregate data for the topic and/or theme from a number of different of media data sources and private data sources to provide aggregated data;

a second NLP model to filter the aggregated data to provide filtered data, the filtered data representing current media coverage indicating a position of the private and media data sources on the topic and/or theme;

an analytics engine to:

establish a baseline media trend for the topic and/or theme from historical media data from a prior time period, the baseline media trend representing sentiment patterns over the prior time period; and

compare the filtered data against the baseline media trend to identify deviations; and

a machine learning (ML) model to process the filtered data and the identified deviations to provide a recommendation relating to the media intelligence for the topic and/or theme, wherein the recommendation is based on the magnitude and direction of the identified deviations and specifies a responsive action proportional to the magnitude of the identified deviations.

19 . The system of claim 18 , wherein the machine readable instructions further comprise a user interface to receive user data for the topic and/or theme, the user data being stored as part of the filtered data.

20 . The system of claim 18 , wherein the machine readable instructions further comprise a report generator to provide a report with the recommendation and information from the filtered data.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 17, 2024
From: ALMADI, SABAL
To: SAUDI ARABIAN OIL COMPANY
Reel/Frame 067748/0443 →
Continuity (1)
Related Publication 20250384094A1 · Dec 18, 2025
References Cited (21)
US 9367590B1 · Chun · 2016 [cited by applicant]
US 10262283B2 · Leidner · 2019 [cited by examiner]
US 10360193B2 · Sarkar et al. · 2019 [cited by applicant]
US 10437871B2 · Yi · 2019 [cited by examiner]
US 10565214B2 · Pidaparthi et al. · 2020 [cited by applicant]
US 11257161B2 · Sisk · 2022 [cited by examiner]
US 11321327B2 · Stennett et al. · 2022 [cited by applicant]
US 11334949B2 · Kim · 2022 [cited by examiner]
US 11348125B2 · Rao et al. · 2022 [cited by applicant]
US 11595202B1 · Stewart et al. · 2023 [cited by applicant]
US 20120185544A1 · Chang et al. · 2012 [cited by applicant]
US 20140046879A1 · Maclennan et al. · 2014 [cited by applicant]
US 20180165604A1 · Minkin et al. · 2018 [cited by applicant]
US 20210281569A1 · Soon-Shiong · 2021 [cited by examiner]
US 20230132532A1 · Rangachar · 2023 [cited by applicant]
US 20240054135A1 · Furlaneto · 2024 [cited by examiner]
CN 112420147A · 2021 [cited by applicant]
CN 114119251A · 2021 [cited by applicant]
CN 115907837A · 2023 [cited by applicant]
EP 4182879A1 · 2023 [cited by applicant]
WO 2022133210A2 · 2022 [cited by applicant]