IP Library Granted Patent US 12,413,506
Granted Patent B2
US 12,413,506 · App. 17/947,009 · Granted Sep 9, 2025

Systems, apparatus, articles of manufacture, and methods for proactive data routing

Inventors: Rita Wouhaybi (Portland, OR); Stanley Mo (Portland, OR); Hassnaa Moustafa (San Jose, CA); Greeshma Pisharody (Portland, OR)
Assignee: Intel Corporation
H04L45/22G06F16/9024G06F16/908G06F21/6209H04L45/16
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 12,413,506
App. No.
17/947,009
Granted
Sep 9, 2025
Kind
B2
Abstract

Methods, apparatus, systems, and articles of manufacture are disclosed for proactive data routing. An example apparatus includes at least one memory, machine-readable instructions, and processor circuitry to execute the machine-readable instructions to at least execute a machine-learning model to output a first data routing path in a network environment based on metadata associated with an event in the network environment. The processor circuitry is further to, after a detection of a change of the first data routing path to a second data routing path, retrain the machine-learning model to output a third data routing path based on the second data routing path. The processor circuitry is additionally to cause transmission of a second message to a first node based on the third data routing path after an identification of the event.

Claims (54)

1. An apparatus comprising:

at least one memory;

machine-readable instructions; and

at least one processor circuit to utilize the machine-readable instructions to at least:

execute a machine-learning model to output a first data routing path in a network environment based on metadata associated with an event in the network environment, a first message based on the event to be transmitted to a first node based on the first data routing path, the first data routing path representative of transmission of the first message to the first node via one or more second nodes, the first data routing path to have a first strength of association with at least one of the metadata or the event;

detect a change of the first data routing path to a second data routing path, the second data routing path representative of transmission of the first message to the first node via one or more third nodes;

after detection of the change, retrain the machine-learning model to output a third data routing path based on the second data routing path, the third data routing path to have a second strength of association with the at least one of the metadata or the event, the second strength of association to be greater than the first strength of association; and

cause transmission of a second message to the first node based on the third data routing path after an identification of the event.

2. The apparatus of claim 1 , wherein one or more of the at least one processor circuit is to be instantiated after receiving the machine-readable instructions.

3. The apparatus of claim 1 , wherein the event is a first event, the metadata is first metadata, the identification is a first identification, and one or more of the at least one processor circuit is to cause transmission of a third message after a second identification of a second event, the second event associated with second metadata, the second metadata to include a portion of the first metadata.

4. The apparatus of claim 1 , wherein the first data routing path is representative of predicted transmission of the first message to the first node via the one or more second nodes, and the second data routing path is representative of actual transmission of the first message to the first node via the one or more third nodes.

5. The apparatus of claim 1 , wherein one or more of the at least one processor circuit is to multicast the second message to the first node and one or more fourth nodes, the one or more fourth nodes associated with the metadata.

6. An apparatus comprising:

at least one memory;

machine-readable instructions; and

at least one processor circuit to utilize the machine-readable instruction to at least:

execute a machine-learning model to output a first data routing path in a network environment based on metadata associated with an event in the network environment, a first message based on the event to be transmitted to a first node based on the first data routing path, the first data routing path to have a first strength of association with at least one of the metadata or the event;

after a detection of a change of the first data routing path to a second data routing path, retrain the machine-learning model to output a third data routing path based on the second data routing path, the third data routing path to have a second strength of association with the at least one of the metadata or the event, the second strength of association to be greater than the first strength of association;

cause transmission of a second message to the first node based on the third data routing path after an identification of the event; and

after a determination that the first node is associated with a first network interface and a second network interface, cause transmission of a first portion of the second message to the first network interface and a second portion of the second message to the second network interface.

7. The apparatus of claim 6 , wherein the first network interface is a Wi-Fi network interface and the second network interface is a cellular network interface.

8. At least one non-transitory computer readable storage medium comprising instructions to cause at least one processor circuit to at least:

execute a machine-learning model to output a first data routing path in a network environment based on metadata associated with an event in the network environment, a first message based on the event to be transmitted to a first node based on the first data routing path, the first data routing path to have a first strength of association with at least one of the metadata or the event;

after a detection of a change of the first data routing path to a second data routing path, retrain the machine-learning model to output a third data routing path based on the second data routing path, the third data routing path to have a second strength of association with the at least one of the metadata or the event, the second strength of association to be greater than the first strength of association; and

cause transmission of a second message to the first node based on the third data routing path after an identification of the event, the third data routing path representative of transmission of the second message to the first node via one or more second nodes.

9. The at least one non-transitory computer readable storage medium of claim 8 , wherein the first data routing path is representative of transmission of the first message to the first node via one or more third nodes, and the instructions cause one or more of the at least one processor circuit to detect the change to be representative of transmission of the first message to the first node via one or more fourth nodes.

10. The at least one non-transitory computer readable storage medium of claim 8 , wherein the instructions cause one or more of the at least one processor circuit to, after a determination that a user associated with the first node is unable to view video data, generate the second message to include audio data to be output to the user.

11. The at least one non-transitory computer readable storage medium of claim 8 , wherein the instructions cause one or more of the at least one processor circuit to, after a determination that the first node has a bandwidth less than a threshold, generate the second message to include at least one of audio data or text data.

12. At least one non-transitory computer readable storage medium comprising instructions to cause at least one processor circuit to at least:

execute a machine-learning model to output a first data routing path in a network environment based on metadata associated with an event in the network environment, a first message based on the event to be transmitted to a first node based on the first data routing path, the first data routing path to have a first strength of association with at least one of the metadata or the event;

after a detection of a change of the first data routing path to a second data routing path, retrain the machine-learning model to output a third data routing path based on the second data routing path, the third data routing path to have a second strength of association with the at least one of the metadata or the event, the second strength of association to be greater than the first strength of association;

after a determination that the first node has a bandwidth that satisfies a threshold, generate a second message to include at least one of audio data, text data, or video data; and

cause transmission of the second message to the first node based on the third data routing path after an identification of the event.

13. The at least one non-transitory computer readable storage medium of claim 8 , wherein the metadata is first metadata, the instructions cause one or more of the at least one processor circuit to generate the second message to include first data, second data, and second metadata, the first data associated with a time duration, and the second metadata to cause the first node to access the second data after the time duration has elapsed.

14. The at least one non-transitory computer readable storage medium of claim 8 , wherein the instructions cause one or more of the at least one processor circuit to:

generate the second message to include first data and second data, the first data associated with a time duration; and

after transmission of the first data to the first node, cause the transmission of the second data to the first node after the time duration has elapsed.

15. A method comprising:

executing a machine-learning model to output a first data routing path in a network environment based on first metadata associated with event data in the network environment, a first message based on the event data to be transmitted to a first node based on the first data routing path, the first data routing path to have a first strength of association with at least one of the first metadata or the event data;

after detecting a change of the first data routing path to a second data routing path, retraining the machine-learning model to output a third data routing path based on the second data routing path, the third data routing path to have a second strength of association with the at least one of the first metadata or the event data, the second strength of association to be greater than the first strength of association;

generating a second message to include first data, second data, and second metadata, the first data associated with a time duration; and

transmitting the second message to the first node based on the third data routing path after an identification of the event data, the second metadata to cause the first node to access the second data after the time duration has elapsed.

16. The method of claim 15 , wherein the event data is first event data, the identification is a first identification, and the method includes transmitting a third message after a second identification of second event data, the second event data associated with third metadata, the third metadata to include a portion of the first metadata.

17. The method of claim 16 , wherein the third message includes at least one of data or the third metadata directly associated with the data.

18. The method of claim 15 , including, after a determination that the first node is associated with a first network interface and a second network interface, transmitting a first portion of the second message to the first network interface and a second portion of the second message to the second network interface.

19. The method of claim 15 , including executing a machine-learning microservice to cause execution of the machine-learning model.

20. The method of claim 15 , wherein the machine-learning model is a digital twin associated with the network environment.

21. A method comprising:

executing a machine-learning model to predict a first data routing path in a network environment based on metadata associated with event data in the network environment, the machine-learning model being a digital twin associated with the network environment, a first message based on the event data to be transmitted to a first node based on the first data routing path, prediction of the first data routing path based on simulating transmission of the first message in the network environment, the simulating based on the digital twin, the first data routing path to have a first strength of association with at least one of the metadata or the event data;

after detecting a change of the first data routing path to a second data routing path, retraining the machine-learning model to output a third data routing path based on the second data routing path, the third data routing path to have a second strength of association with the at least one of the metadata or the event data, the second strength of association to be greater than the first strength of association; and

transmitting a second message to the first node based on the third data routing path after an identification of the event data.

22. The method of claim 21 , wherein the metadata is first metadata, the first node is a first device, the network environment includes a second device and a third device, and including generating the second message to include second metadata, the first device is not associated with an operation indicated by the second metadata, and the first device is to cause at least one of the second device or the third device to perform the operation based on the second metadata.

23. The apparatus of claim 6 , wherein the determination is a first determination, and one or more of the at least one processor circuit is to, after a second determination that the first node has a bandwidth that satisfies a threshold, generate the second message to include at least one of audio data, text data, or video data.

24. The at least one non-transitory computer readable storage medium of claim 12 , wherein the instructions cause one or more of the at least one processor circuit to multicast the second message to the first node and one or more second nodes associated with the metadata.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 28, 2023
From: WOUHAYBI, RITA; MO, STANLEY; MOUSTAFA, HASSNAA; PISHARODY, GREESHMA
To: INTEL CORPORATION
Reel/Frame 062539/0441 →
Continuity (3)
Continuation In Part PCTUS2021065156 · Dec 23, 2021
Provisional Application 63248312 · Sep 24, 2021
Related Publication 20230016946A1 · Jan 19, 2023
References Cited (36)
US 20080226046A1 · Shaffer et al. · 2008 [cited by applicant]
US 20150186635A1 · Nakhjiri et al. · 2015 [cited by applicant]
US 20180300124A1 · Malladi et al. · 2018 [cited by applicant]
US 20190364130A1 · Rogynskyy · 2019 [cited by applicant]
US 20190370089A1 · Patton · 2019 [cited by examiner]
US 20200134423A1 · Shinde et al. · 2020 [cited by applicant]
US 20200167205A1 · Guim Bernat et al. · 2020 [cited by applicant]
US 20200267110A1 · Nolan et al. · 2020 [cited by applicant]
US 20200372016A1 · Rogynskyy · 2020 [cited by examiner]
US 20210004265A1 · Guim Bernat et al. · 2021 [cited by applicant]
US 20210011765A1 · Doshi et al. · 2021 [cited by applicant]
US 20210014113A1 · Guim Bernat et al. · 2021 [cited by applicant]
US 20210125083A1 · Ogawa et al. · 2021 [cited by applicant]
US 20210203739A1 · Calegari et al. · 2021 [cited by applicant]
US 20220198562A1 · Cella · 2022 [cited by examiner]
US 20220303828A1 · Gamage et al. · 2022 [cited by applicant]
US 20220335340A1 · Moustafa et al. · 2022 [cited by applicant]
US 20240386054A1 · Wouhaybi et al. · 2024 [cited by applicant]
US 20240386442A1 · Mo et al. · 2024 [cited by applicant]
WO 2017035536A1 · 2017 [cited by applicant]
WO 2023048770A1 · 2023 [cited by applicant]
International Searching Authority, “International Search Report and Written Opinion,” issued in connection with International Application No. PCT/US2021/065156, Jul. 1, 2022, 16 pages. [cited by applicant]
Song et al., “Practical Techniques for Searches on Encrypted Data,” In the Proceedings of the IEEE Symposium on Security and Privacy, May 14-17, 2000, 12 pages. [cited by applicant]
Gentry, “Fully Homomorphic Encryption Using Ideal Lattices,” In Proceedings of the Annual ACM Symposium on Theory of Computing, May 31 through Jun. 2, 2009, 10 pages. [cited by applicant]
Kamara et al., “Dynamic Searchable Symmetric Encryption,” Proceedings of the 2012 ACM Conference on Computer and Communications Security, Oct. 2012, 24 pages. [cited by applicant]
Garg et al., “Candidate Indistinguishability Obfuscation and Functional Encryption for all circuits,” In the Proceedings of the IEEE Symposium on Theory of Computing Science, Oct. 2013, 46 pages. [cited by applicant]
International Searching Authority, “Written Opinion,” issued in connection with International Application No. PCT/US2022/023107, Jul. 1, 2022, 7 pages. [cited by applicant]
International Searching Authority, “International Search Report,” issued in connection with International Application No. PCT/US2022/023107, Jul. 1, 2022, 3 pages. [cited by applicant]
Netherlands Patent Office, “Search Report,” issued in connection with Netherlands Application No. NL2032844, Jun. 5, 2023, 28 pages, with machine English translation. [cited by applicant]
Netherlands Patent Office, “Notice of Grant,” issued in connection with Netherlands Application No. NL2032844, Aug. 11, 2023, 4 pages, with machine English translation. [cited by applicant]
International Searching Authority, “International Preliminary Report on Patentability,” issued in connection with International Application No. PCT/US2021/065156, Mar. 26, 2024, 11 pages. [cited by applicant]
International Searching Authority, “International Preliminary Report on Patentability,” issued in connection with International Application No. PCT/US2022/023107, Mar. 26, 2024, 8 pages. [cited by applicant]
United States Patent and Trademark Office, “Requirement for Restriction/Election,” issued in connection with U.S. Appl. No. 18/571,142, dated Sep. 29, 2024, 10 pages. [cited by applicant]
United States Patent and Trademark Office, “Non-Final Office Action,” issued in connection with U.S. Appl. No. 18/571,142, dated Mar. 21, 2025, 33 pages. [cited by applicant]
Ismail, “A Machine Learning Approach for Energy-Efficient IoT Systems,” Journal of Intelligent Systems and Internet of Things (JISIoT), vol. 01, No. 02, 2020, 10 pages. [cited by applicant]
United States Patent and Trademark Office, “Non-Final Office Action,” issued in connection with U.S. Appl. No. 18/571,149, dated Jun. 5, 2025, 18 pages. [cited by applicant]