IP Library › Granted Patent US 12,572,830
Granted Patent B1
US 12,572,830 · App. 19/315,849 · Granted Mar 10, 2026

System and method for enterprise hierarchical persistent cognitive machines with organizational hierarchy awareness and compliance integration

Inventors: Brian Galvin (Silverdale, WA); Alan McCord (Forney, TX)
Assignee: AtomBeam Technologies Inc.
G06N5/04G06Q10/067
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 12,572,830
App. No.
19/315,849
Granted
Mar 10, 2026
Kind
B1
Abstract

A system and methods for enterprise hierarchical persistent cognitive machines (PCMs) that extends mobile-optimized multi-stage language model processing with organizational hierarchy awareness and enterprise-specific adaptations. The system comprises a CEO-PCM at the executive level coordinating multiple functional domain PCMs corresponding to organizational departments. A supervisory network layer dynamically adapts underlying language models to enterprise-specific dialect, terminology, and communication patterns through automated analysis of organizational knowledge sources. User prompts are routed through enterprise hierarchical pathways based on authority levels and sensitivity classification, enabling appropriate escalation and cross-functional coordination. The CEO-PCM synthesizes insights from multiple domain PCMs to generate enterprise-wide strategic intelligence while domain-specific compliance modules enforce regulatory requirements during cognitive processing. The system automatically adapts to organizational changes by redistributing knowledge and reconfiguring PCM architecture, while maintaining persistent cognitive state across enterprise operations through comprehensive state preservation and restoration mechanisms that ensure organizational knowledge continuity.

Claims (72)

1 . A computing system for enterprise hierarchical cognitive processing, the computing system comprising:

one or more hardware processors configured for:

initializing an enterprise hierarchical persistent cognitive machine architecture comprising a chief executive officer personal cognitive machine (CEO-PCM) and a plurality of functional domain persistent cognitive machines (PCMs) corresponding to organizational departments;

implementing a supervisory network layer that adapts underlying language model processing to enterprise-specific dialect and organizational communication patterns;

routing user prompts through the enterprise hierarchical architecture based on user authority level and prompt sensitivity classification;

synthesizing cross-functional insights by collecting domain-specific knowledge from the plurality of functional domain PCMs and integrating the knowledge into the CEO-PCM;

enforcing domain-specific compliance requirements during cognitive processing through compliance modules associated with the plurality of functional domain PCMs;

automatically adapting the enterprise hierarchical architecture in response to detected organizational changes by redistributing knowledge between the plurality of functional domain PCMs; and

maintaining persistent cognitive states across the enterprise hierarchical architecture including thought cache contents and organizational relationship models.

2 . The computing system of claim 1 , wherein the one or more hardware processors are further configured for:

generating thoughts representing intermediate reasoning steps using the functional domain PCMs; and

caching the generated thoughts in a multi-tier thought cache hierarchy comprising local user caches, domain-specific branch caches, and enterprise collective caches.

3 . The computing system of claim 2 , wherein the multi-tier thought cache hierarchy implements:

graduated access controls between cache tiers based on information sensitivity; and

privacy protection mechanisms that prevent unauthorized cross-domain knowledge access.

4 . The computing system of claim 1 , wherein routing user prompts comprises:

analyzing prompt content to determine required functional domain expertise; and

escalating prompts to supervisory levels when user authority is insufficient for direct processing.

5 . The computing system of claim 1 , wherein the supervisory network layer comprises:

an enterprise dialect processor that adapts vocabulary and communication styles; and

an organizational context manager that injects hierarchy-aware information into cognitive processing.

6 . The computing system of claim 1 , wherein synthesizing cross-functional insights comprises:

detecting conflicts between domain-specific knowledge from different functional domain PCMs; and

resolving the conflicts using enterprise priority frameworks.

7 . The computing system of claim 1 , wherein the one or more hardware processors are further configured for:

entering sleep states during periods of reduced user activity; and

performing memory consolidation and cross-domain insight generation during the sleep states.

8 . The computing system of claim 1 , wherein automatically adapting the enterprise hierarchical architecture comprises:

monitoring organizational announcements for structural changes;

creating adaptation plans for PCM architecture modifications; and

validating adapted architecture through systematic testing.

9 . The computing system of claim 1 , wherein the CEO-PCM comprises:

an executive cognitive core that provides strategic decision support; and

an enterprise thought cache that maintains strategic knowledge and cross-functional patterns.

10 . The computing system of claim 1 , wherein maintaining persistent cognitive state comprises:

serializing cognitive states including thought cache contents and relationship models; and

restoring complete cognitive state upon system restart to preserve enterprise knowledge continuity.

11 . A computer-implemented method for enterprise hierarchical cognitive processing, the method comprising the steps of:

initializing an enterprise hierarchical persistent cognitive machine architecture comprising a chief executive officer personal cognitive machine (CEO-PCM) and a plurality of functional domain persistent cognitive machines (PCMs) corresponding to organizational departments;

implementing a supervisory network layer that adapts underlying language model processing to enterprise-specific dialect and organizational communication patterns;

routing user prompts through the enterprise hierarchical architecture based on user authority level and prompt sensitivity classification;

synthesizing cross-functional insights by collecting domain-specific knowledge from the plurality of functional domain PCMs and integrating the knowledge into the CEO-PCM;

enforcing domain-specific compliance requirements during cognitive processing through compliance modules associated with the plurality of functional domain PCMs;

automatically adapting the enterprise hierarchical architecture in response to detected organizational changes by redistributing knowledge between the plurality of functional domain PCMs; and

maintaining persistent cognitive states across the enterprise hierarchical architecture including thought cache contents and organizational relationship models.

12 . The method of claim 11 , further comprising:

generating thoughts representing intermediate reasoning steps using the functional domain PCMs; and

caching the generated thoughts in a multi-tier thought cache hierarchy comprising local user caches, domain-specific branch caches, and enterprise collective caches.

13 . The method of claim 12 , wherein the multi-tier thought cache hierarchy implements:

applying graduated access controls between cache tiers based on information sensitivity; and

preventing unauthorized cross-domain knowledge access through privacy protection mechanisms.

14 . The method of claim 11 , wherein routing user prompts comprises:

analyzing prompt content to determine required functional domain expertise; and

escalating prompts to supervisory levels when user authority is insufficient for direct processing.

15 . The method of claim 11 , wherein the supervisory network layer comprises:

adapting vocabulary and communication styles through an enterprise dialect processor; and

injecting hierarchy-aware information into cognitive processing through an organizational context manager.

16 . The method of claim 11 , wherein synthesizing cross-functional insights comprises:

detecting conflicts between domain-specific knowledge from different functional domain PCMs; and

resolving the conflicts using enterprise priority frameworks.

17 . The method of claim 11 , further comprising the steps of:

entering sleep states during periods of reduced user activity; and

performing memory consolidation and cross-domain insight generation during the sleep states.

18 . The method of claim 11 , wherein automatically adapting the enterprise hierarchical architecture comprises:

monitoring organizational announcements for structural changes;

creating adaptation plans for PCM architecture modifications; and

validating adapted architecture through systematic testing.

19 . The method of claim 11 , wherein the CEO-PCM provides:

strategic decision support through an executive cognitive core; and

strategic knowledge storage through an enterprise thought cache that maintains cross-functional patterns.

20 . The method of claim 11 , wherein maintaining persistent cognitive state comprises:

serializing cognitive states including thought cache contents and relationship models; and restoring complete cognitive state upon system restart to preserve enterprise knowledge continuity.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 22, 2026
From: GALVIN, BRIAN; MCCORD, ALAN
To: ATOMBEAM TECHNOLOGIES INC.
Reel/Frame 073556/0885 →
Continuity (15)
Continuation In Part 19294125 · Aug 7, 2025
Continuation In Part 19203069 · Jun 3, 2025
Continuation In Part 19205960 · May 12, 2025
Continuation In Part 19178873 · Apr 15, 2025
Continuation In Part 19177611 · Apr 13, 2025
Continuation In Part 19060794 · Feb 24, 2025
Continuation In Part 19051193 · Feb 12, 2025
Continuation In Part 19044546 · Feb 3, 2025
Continuation In Part 19026276 · Jan 16, 2025
Continuation In Part 18928022 · Oct 26, 2024
Continuation In Part 18919417 · Oct 17, 2024
Continuation In Part 18918077 · Oct 17, 2024
Continuation In Part 18737906 · Jun 7, 2024
Continuation In Part 18736498 · Jun 6, 2024
Provisional Application 63651359 · May 23, 2024
References Cited (56)
US 4780718A · Hudson et al. · 1988 [cited by applicant]
US 5708436A · Loiz et al. · 1998 [cited by applicant]
US 7411540B1 · Lopez et al. · 2008 [cited by applicant]
US 7629922B2 · Winstead et al. · 2009 [cited by applicant]
US 7876257B2 · Vetro et al. · 2011 [cited by applicant]
US 9524392B2 · Naehrig et al. · 2016 [cited by applicant]
US 11451242B2 · Choi et al. · 2022 [cited by applicant]
US 11656353B2 · Li et al. · 2023 [cited by applicant]
US 11972333B1 · Horesh · 2024 [cited by examiner]
US 12387050B1 · Galvin · 2025 [cited by examiner]
US 12481688B1 · Galvin · 2025 [cited by examiner]
US 20040017307A1 · Cirillo et al. · 2004 [cited by applicant]
US 20040160353A1 · Cirillo et al. · 2004 [cited by applicant]
US 20080231504A1 · Sartor et al. · 2008 [cited by applicant]
US 20110012778A1 · Nguyen et al. · 2011 [cited by applicant]
US 20150054678A1 · Wakayama · 2015 [cited by applicant]
US 20170048537A1 · Boufounos et al. · 2017 [cited by applicant]
US 20180196609A1 · Niesen · 2018 [cited by applicant]
US 20200258296A1 · Pennings et al. · 2020 [cited by applicant]
US 20220156631A1 · Kanso et al. · 2022 [cited by applicant]
US 20220404490A1 · Evans et al. · 2022 [cited by applicant]
US 20230131694A1 · Saber et al. · 2023 [cited by applicant]
US 20230169623A1 · Chen et al. · 2023 [cited by applicant]
US 20230184927A1 · Chen et al. · 2023 [cited by applicant]
US 20230316006A1 · Tunstall-Pedoe · 2023 [cited by examiner]
US 20240104391A1 · Higgins · 2024 [cited by examiner]
US 20240185037A1 · Park et al. · 2024 [cited by applicant]
US 20240195438A1 · Isik et al. · 2024 [cited by applicant]
US 20240354320A1 · Procter · 2024 [cited by examiner]
US 20240362476A1 · Grenader · 2024 [cited by examiner]
US 20240420491A1 · Park · 2024 [cited by examiner]
US 20250259085A1 · Crabtree · 2025 [cited by examiner]
US 20250291866A1 · Park · 2025 [cited by examiner]
US 20250371004A1 · Chen · 2025 [cited by examiner]
EP 3364212A1 · 2018 [cited by applicant]
GB 2620921A · 2024 [cited by applicant]
WO 2020104416A1 · 2020 [cited by applicant]
RamÃ-rez, Guillem, et al. “Cache & distil: Optimising api calls to large language models.” arXiv preprint arXiv:2310.13561 (2023). (Year: 2023). [cited by examiner]
Zhang, Dawen, et al. “A layered architecture for developing and enhancing capabilities in large language model-based software systems.” arXiv preprint arXiv:2411.12357 (2024). (Year: 2024). [cited by examiner]
Zhou, Hao, et al. “Large Language Model (LLM) for Telecommunications: A Comprehensive Survey on Principles, Key Techniques, and Opportunities.” arXiv preprint arXiv:2405.10825 v2 (2024). (Year: 2024). [cited by examiner]
Bai, Guangji, et al. “Beyond efficiency: A systematic survey of resource-efficient large language models.” arXiv preprint arXiv:2401.00625 (2024). (Year: 2024). [cited by examiner]
Yin, Wangsong, et al. “Llm as a system service on mobile devices.” arXiv preprint arXiv:2403.11805 (2024). (Year: 2024). [cited by examiner]
Chen, Daihang, et al. “LLM for Mobile: An Initial Roadmap.” arXiv preprint arXiv:2407.06573 (2024). (Year: 2024). [cited by examiner]
Fungwacharakorn, Wachara, et al. “Layer-of-Thoughts Prompting (LoT): Leveraging LLM-Based Retrieval with Constraint Hierarchies.” arXiv preprint arXiv:2410.12153 (2024). (Year: 2024). [cited by examiner]
Spivack, Nova, et al. “Cognition is All You Need—The Next Layer of Al Above Large Language Models.” arXiv preprint arXiv:2403.02164 (2024). (Year: 2024). [cited by examiner]
Hu, Pengbo, and Xiang Ying. “Unified mind model: Reimagining autonomous agents in the llm era.” arXiv preprint arXiv:2503.03459 v2 (Mar. 2025). (Year: 2025). [cited by examiner]
Aviss, Thea. “State Stream Transformer (SST): Emergent Metacognitive Behaviours Through Latent State Persistence.” arXiv preprint arXiv:2501.18356 (Jan. 2025). (Year: 2025). [cited by examiner]
Shan, Lianlei, et al. “Cognitive memory in large language models.” arXiv preprint arXiv:2504.02441 (Apr. 2025). (Year: 2025). [cited by examiner]
Balaneshin-Kordan, Saeid et al; “Deep Neural Architecture for Multi-Modal Retrieval based on Joint Embedding Space for Text and Images”, Association for Computing Machinery, Feb. 5-9, 2018, pp. 1-9, Marina Del Rey, CA, … [cited by applicant]
Gim, In, et al; “Prompt Cache: Modular Attention Reuse for Low-Latency Inference”, arXiv:2311.04934v2, Apr. 2024. [cited by applicant]
Khan, Abdul Rafae, et al; “Coding Textual Inputs Boosts the Accuracy of Neural Networks”, 2020 Conference on Empirical Methods in Natural Language Processing, Nov. 16-20, 2020, pp. 1350-1360. [cited by applicant]
Messina, Nicola et al; “Towards Efficient Cross-Modal Visual Textual Retrieval using Transformer-Encoder Deep Features”, 2021 International Conference on Content-Based Multimedia Indexing, 2021, pp. 1-6, United States. [cited by applicant]
Seo, Beomsoek et al; “How Does A Transformer Learn Compression? An Attention Study on Huffman and LZ4”, Department of Electronic and Electrical Engineering, Dec. 12, 2023, vol. 11, Seoul, South Korea. [cited by applicant]
Vaswani, Ashish, et al; “Attention is All You Need”, arXiv:1706.03762v7, Aug. 2023. [cited by applicant]
Wang, Tianming, & Wan, Xiaojun; “T-CVAE: Transformer-based conditioned variational autoencoder for story completion”, Proceedings of the Twenty-Eighth Joint Conference on Artificial Intelligence, pp. 5233-5239, 2019. [cited by applicant]
Wieting, John et al; “A Bilingual Generative Transformer for Semantic Sentence Embedding”, arXiv:1911.03895v2, Nov. 2020. [cited by applicant]