IP Library Granted Patent US 12,724,837
Granted Patent B2
US 12,724,837 · App. 19/425,193 · Granted Sep 1, 2026

Combined wide and deep machine learning models for automated database element processing systems, methods and apparatuses

Inventors: Bing Song (La Canada, CA); Jeffrey Michael Balbien (Los Angeles, CA); Hao Lu (Los Angeles, CA); Phillip Yang (Los Angeles, CA); Patrick Soon-Shiong (Los Angeles, CA)
Assignee: NantMedia Holdings, LLC
G06F16/9535G06F40/284G06F40/40G06N3/045
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 12,724,837
App. No.
19/425,193
Granted
Sep 1, 2026
Kind
B2
Abstract

A method of automated database element processing includes training a wide machine learning model with historical feature vector inputs to generate a wide ranked element output. The method includes training a deep machine learning model with the historical feature vector inputs to generate a deep ranked element output. The method includes generating a set of inputs specific to an individual entity, obtaining a set of current article database elements, and creating a feature vector input according to the set of inputs and the set of current article database elements. The method includes processing the feature vector input with the wide machine learning model to generate a wide ranked element list, processing the feature vector input with the deep machine learning model to generate a deep ranked element list, and merging database elements of the wide and deep ranked element lists to generate a ranked element recommendation output.

Claims (29)

1 . A computer-implemented method of dynamic machine learning model retraining in a content recommendation system, the method comprising:

receiving, by at least one processor, a plurality of article elements published by at least one content provider over a time period;

determining, by the at least one processor, an article publication count associated with the plurality of article elements published by the at least one content provider during the time period;

comparing, by the at least one processor, the article publication count to a training criteria;

in response to determining that the article publication count satisfies the training criteria based on the comparison, automatically adjusting a model retraining frequency for at least one machine learning model used for article recommendations;

obtaining, by the at least one processor, updated article elements published since a last model training;

obtaining, by the at least one processor, updated user interaction data associated with the updated article elements;

retraining, by the at least one processor, the at least one machine learning model using the updated article elements and the updated user interaction data;

generating, by the at least one processor and using the retrained machine learning model, personalized article recommendations for at least one user based on user-specific input data; and

providing the personalized article recommendations to a user device for display.

2 . The method of claim 1 , wherein the time period comprises a sliding time window.

3 . The method of claim 2 , wherein the sliding time window has a duration of at least one week.

4 . The method of claim 1 , wherein the article publication count is calculated based on a number of article elements published in the time period.

5 . The method of claim 1 , wherein the training criteria comprises an elapsed time threshold.

6 . The method of claim 5 , wherein automatically adjusting the model retraining frequency comprises increasing the model retraining frequency in response to the elapsed time threshold being exceeded.

7 . The method of claim 1 , further comprising obtaining a new click history since the last model training.

8 . The method of claim 7 , further comprising retraining the at least one machine learning model using the new click history.

9 . The method of claim 1 , wherein the at least one machine learning model comprises a wide machine learning model and a deep machine learning model.

10 . The method of claim 9 , wherein retraining comprises jointly retraining both the wide machine learning model and the deep machine learning model.

11 . The method of claim 9 , wherein the wide machine learning model comprises a term frequency inverse document frequency (TFIDF) model or a best matching (BM25) model.

12 . The method of claim 9 , wherein the deep machine learning model comprises a Doc2Vec model or a deep contrastive learning (DECLUTR) model.

13 . The method of claim 1 , wherein the at least one machine learning model comprises a supervised trained model.

14 . The method of claim 1 , wherein the at least one machine learning model comprises an unsupervised model.

15 . The method of claim 1 , wherein the updated article elements comprise articles published within at least the last six months.

16 . The method of claim 1 , wherein the updated user interaction data comprises user click history from at least the last forty-five days.

17 . The method of claim 1 , wherein the article elements comprise news articles having temporal relevance windows of a week.

18 . The method of claim 1 , wherein determining the article publication count comprises analyzing publication timestamps of the plurality of article elements.

19 . The method of claim 1 , wherein the model retraining frequency is adjusted to a frequency based on a time scale selected from the group consisting of: an hour, a five minute period, a day, a week, and a month.

20 . The method of claim 1 , wherein the method is implemented using a scalable serverless compute engine.

Assignments (6)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 19, 2025
From: YANG, PHILLIP; SOON-SHIONG, PATRICK
To: NANTWORKS, LLC
Reel/Frame 073269/0364 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 19, 2025
From: BALBIEN, JEFFREY MICHAEL; LU, HAO
To: LOS ANGELES TIMES COMMUNICATIONS, LLC
Reel/Frame 073269/0383 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 19, 2025
From: SONG, BING
To: IMMUNITYBIO, INC.
Reel/Frame 073269/0411 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 19, 2025
From: LOS ANGELES TIMES COMMUNICATIONS, LLC
To: NANTMEDIA HOLDINGS, LLC
Reel/Frame 073269/0467 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 19, 2025
From: NANTWORKS, LLC
To: NANTMEDIA HOLDINGS, LLC
Reel/Frame 073269/0542 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 19, 2025
From: IMMUNITYBIO, INC.
To: NANTMEDIA HOLDINGS, LLC
Reel/Frame 073269/0551 →
Continuity (6)
Continuation 19195181 · Apr 30, 2025
Continuation 18988223 · Dec 19, 2024
Continuation 18807634 · Aug 16, 2024
Continuation 17643881 · Dec 13, 2021
Provisional Application 63125570 · Dec 15, 2020
Related Publication 20260111501A1 · Apr 23, 2026
References Cited (41)
US 8255385B1 · Sun · 2012 [cited by examiner]
US 8868541B2 · Lin · 2014 [cited by examiner]
US 10938979B1 · Dave et al. · 2021 [cited by applicant]
US 11210583B2 · Mathew et al. · 2021 [cited by applicant]
US 11393036B2 · Wang et al. · 2022 [cited by applicant]
US 11716400B2 · Harish et al. · 2023 [cited by applicant]
US 20130179424A1 · Xu · 2013 [cited by examiner]
US 20140317105A1 · Jain et al. · 2014 [cited by applicant]
US 20150088888A1 · Brennan et al. · 2015 [cited by applicant]
US 20150293897A1 · Myslinski · 2015 [cited by applicant]
US 20170300814A1 · Shaked et al. · 2017 [cited by applicant]
US 20180158004A1 · Davar et al. · 2018 [cited by applicant]
US 20180276305A1 · Liu et al. · 2018 [cited by applicant]
US 20190050750A1 · Le et al. · 2019 [cited by applicant]
US 20190139092A1 · Nomula · 2019 [cited by applicant]
US 20200026769A1 · Tripodi et al. · 2020 [cited by applicant]
US 20210042374A1 · Davis et al. · 2021 [cited by applicant]
US 20210097367A1 · Zhang et al. · 2021 [cited by applicant]
US 20220188366A1 · Song et al. · 2022 [cited by applicant]
US 20220197248A1 · Weinberg · 2022 [cited by applicant]
US 20220222289A1 · Srinivasan et al. · 2022 [cited by applicant]
US 20220230226A1 · Shahrasbi et al. · 2022 [cited by applicant]
US 20220398643A1 · Sivakumar et al. · 2022 [cited by applicant]
US 20230093756A1 · Banerjee et al. · 2023 [cited by applicant]
US 20230315781A1 · Huang et al. · 2023 [cited by applicant]
US 20240411827A1 · Song et al. · 2024 [cited by applicant]
US 20250272346A1 · Song et al. · 2025 [cited by applicant]
Gundogan, E., Kaya, M. & Daud, A. Deep learning for journal recommendation system of research papers. Scientometrics 128, 461-481 (2023). (Year: 2022). [cited by examiner]
A. Nawrocka, A. Kot and M. Nawrocki, “Application of machine learning in recommendation systems,” 2018 19th International Carpathian Control Conference (ICCC), Szilvasvarad, Hungary, 2018, pp. 328-331. (Year: 2018). [cited by examiner]
Wu, F., et al., “Mind: A Large-scale Dataset for News Recommendation,” p. 1-10 (2020). [cited by applicant]
Cheng, H., et al., “Wide & Deep Learning for Recommender Systems,” Jun. 24, 2016, p. 1-4. [cited by applicant]
Le, Q., & Mikolov, T., “Distributed Representations of Sentences and Documents,” Google Inc., May 22, 2014, p. 1-9. [cited by applicant]
Wikipedia, “tf-idf” Aug. 25, 2020, https://en.wikipedia.org/wiki/Tf-idf. [cited by applicant]
Wikipedia, “Okapi BM25”, Aug. 25, 2020, http://en.wikipedia.org/wiki/Okapi_BM25. [cited by applicant]
Reimers, N., & Gurevych, I., “Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks,” Aug. 27, 2019, p. 1-11. [cited by applicant]
Vaswani, A., et al., “Attention is all you Need,” Dec. 6, 2017, p. 1-15. [cited by applicant]
Giorgi, J.M., et al., “DeCLUTR: Deep Contrastive Learing for Unsupervised Textual Representations,” Jun. 11, 2020, pp. 1-22. [cited by applicant]
W. Jing and Y. Bailong (2021). News Text Classification and Recommendation Technology Based on Wide & Deep-Bert Model. IEEE International Conference on Information Communication and Software Engineering (ICICSE), 209-21… [cited by applicant]
Non-Final Office Action from U.S. Appl. No. 18/988,223 dated Feb. 12, 2025. [cited by applicant]
Non-Final Office Action from U.S. Appl. No. 19/195,181 dated Jul. 9, 2025. [cited by applicant]
Final Office Action from U.S. Appl. No. 19/195,181 dated Sep. 17, 2025. [cited by applicant]