IP Library Granted Patent US 12,657,405
Granted Patent B2
US 12,657,405 · App. 18/807,751 · Granted Jun 16, 2026

Systems for controllable summarization of content

Inventors: Richard Gardner (Scottsdale, AZ); John Jozwiak (Cave Creek, AZ)
Assignee: Modulus AI, Inc.
G06F40/56G06F16/345
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 12,657,405
App. No.
18/807,751
Granted
Jun 16, 2026
Kind
B2
Abstract

A method of generating summaries of content items using one or more large language models (LLMs) is disclosed. A first content item is identified. The first content item includes a set of sub-content items. A level of abstraction is determined for the content item. A prompt is automatically engineered for providing to the one or more LLMs. The prompt includes a reference to the first content item and the level of the abstraction for the first content item. A response to the prompt is received from the LLM. The response includes a second content item. The second content item includes a representation of the first content item that is generated by the LLM. The representation omits or simplifies one or more of the set of sub-content items based on the level of abstraction. The representation is used to control an output that is communicated to a target device.

Claims (35)

1 . A system comprising:

one or more computer processors;

one or more computer memories;

a set of instructions stored in the one or more computer memories, the set of instructions configuring the one or more computer processors to perform operations, the operations comprising:

receiving a content corpus to be summarized;

generating a first summarized content by applying a large language model (LLM) or an appropriate processing model to the content corpus to create an initial summary at a first predefined abstraction level;

recursively generating subsequent summarized content by applying the large language model or the appropriate processing model to previously summarized content at progressively greater abstraction levels, wherein each subsequent summary is derived from last summarized content without reprocessing the content corpus; and

storing each of the subsequent summarized content at a plurality of abstraction levels, thereby facilitating efficient retrieval and use based on user-defined summarization needs.

2 . The system of claim 1 , wherein the content corpus comprises one or more of text, audio, video, and image content.

3 . The system of claim 1 , wherein the recursive generating of the subsequent summarized content utilizes previously summarized outputs to perform further summarizations.

4 . The system of claim 1 , wherein the plurality of abstraction levels for generating subsequent summarized content includes a plurality of specific percentages to support a tiered approach to content reduction.

5 . The system of claim 1 , the operations further comprising calculating a cost savings of the recursive generating of the subsequent summarized content compared to a technique where the content corpus is reprocessed for each summarization.

6 . The system of claim 1 , wherein the LLM or the appropriate processing model is configured to adjust a depth of summarization dynamically based on a complexity or length of the content corpus.

7 . The system of claim 1 , wherein the storing of each of the subsequent summarized content comprises indexing each of the subsequent summarized content based on its abstraction level to increase a speed of retrieval in one or more applications that require different levels of content detail.

8 . A method comprising:

receiving a content corpus to be summarized;

generating a first summarized content by applying a large language model (LLM) or an appropriate processing model to the content corpus to create an initial summary at a first predefined abstraction level;

recursively generating subsequent summarized content by applying the large language model or the appropriate processing model to previously summarized content at progressively greater abstraction levels, wherein each subsequent summary is derived from last summarized content without reprocessing the content corpus; and

storing each of the subsequent summarized content at a plurality of abstraction levels, thereby facilitating efficient retrieval and use based on user-defined summarization needs.

9 . The method of claim 8 , wherein the content corpus comprises one or more of text, audio, video, and image content.

10 . The method of claim 8 , wherein the recursive generating of the subsequent summarized content utilizes previously summarized outputs to perform further summarizations.

11 . The method of claim 8 , wherein the plurality of abstraction levels for generating subsequent summarized content includes a plurality of specific percentages to support a tiered approach to content reduction.

12 . The method of claim 8 , further comprising calculating a cost savings of the recursive generating of the subsequent summarized content compared to a technique where the content corpus is reprocessed for each summarization.

13 . The method of claim 8 , wherein the LLM or the appropriate processing model is configured to adjust a depth of summarization dynamically based on a complexity or length of the content corpus.

14 . The method of claim 8 , wherein the storing of each of the subsequent summarized content comprises indexing each of the subsequent summarized content based on its abstraction level to increase a speed of retrieval in one or more applications that require different levels of content detail.

15 . A non-transitory computer-readable storage medium storing a set of instructions that, when executed by one or more computer processors, causes the one or more computer processors to perform operations, the operations comprising:

receiving a content corpus to be summarized;

generating a first summarized content by applying a large language model (LLM) or an appropriate processing model to the content corpus to create an initial summary at a first predefined abstraction level;

recursively generating subsequent summarized content by applying the large language model or the appropriate processing model to previously summarized content at progressively greater abstraction levels, wherein each subsequent summary is derived from last summarized content without reprocessing the content corpus; and

storing each of the subsequent summarized content at a plurality of abstraction levels, thereby facilitating efficient retrieval and use based on user-defined summarization needs.

16 . The non-transitory computer-readable storage medium of claim 15 , wherein the content corpus comprises one or more of text, audio, video, and image content.

17 . The non-transitory computer-readable storage medium of claim 15 , wherein the recursive generating of the subsequent summarized content utilizes previously summarized outputs to perform further summarizations.

18 . The non-transitory computer-readable storage medium of claim 15 , wherein the plurality of abstraction levels for generating subsequent summarized content includes a plurality of specific percentages to support a tiered approach to content reduction.

19 . The non-transitory computer-readable storage medium of claim 15 , further comprising calculating a cost savings of the recursive generating of the subsequent summarized content compared to a technique where the content corpus is reprocessed for each summarization.

20 . The non-transitory computer-readable storage medium of claim 15 , wherein the LLM or the appropriate processing model is configured to adjust a depth of summarization dynamically based on a complexity or length of the content corpus.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 31, 2025
From: GARDNER, RICHARD; JOZWIAK, JOHN
To: ANZER, INC.
Reel/Frame 071894/0822 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 5, 2025
From: ANZER, INC.
To: MODULUS AI, INC.
Reel/Frame 071324/0193 →
Continuity (3)
Continuation In Part 18582262 · Feb 20, 2024
Continuation 18452496 · Aug 18, 2023
Related Publication 20250061291A1 · Feb 20, 2025
References Cited (45)
US 11663404B2 · Wang et al. · 2023 [cited by applicant]
US 11769017B1 · Gray · 2023 [cited by examiner]
US 12008332B1 · Gardner et al. · 2024 [cited by applicant]
US 12380287B2 · Gardner et al. · 2025 [cited by applicant]
US 20130014169A1 · Sansom et al. · 2013 [cited by applicant]
US 20190114308A1 · Hancock · 2019 [cited by applicant]
US 20200250223A1 · Gultekin et al. · 2020 [cited by applicant]
US 20210084145A1 · Pham et al. · 2021 [cited by applicant]
US 20210326646A1 · Gultekin et al. · 2021 [cited by applicant]
US 20220300551A1 · Gultekin et al. · 2022 [cited by applicant]
US 20220391591A1 · Ronen et al. · 2022 [cited by applicant]
US 20230252233A1 · Gutierrez · 2023 [cited by examiner]
US 20230252244A1 · Yang et al. · 2023 [cited by applicant]
US 20230259705A1 · Tunstall-Pedoe · 2023 [cited by examiner]
US 20230274086A1 · Tunstall-Pedoe · 2023 [cited by examiner]
US 20230298589A1 · Madan · 2023 [cited by examiner]
US 20230316006A1 · Tunstall-Pedoe · 2023 [cited by examiner]
US 20230367960A1 · Smus et al. · 2023 [cited by applicant]
US 20230419051A1 · Sabapathy et al. · 2023 [cited by applicant]
CN 107526718 · 2017 [cited by applicant]
CN 109657053 · 2019 [cited by applicant]
CN 110188349 · 2019 [cited by applicant]
CN 110807312 · 2020 [cited by applicant]
CN 112507711 · 2021 [cited by applicant]
CN 113822514 · 2021 [cited by applicant]
CN 113918708 · 2022 [cited by applicant]
WO 2023220198 · 2023 [cited by applicant]
“International Application Serial No. PCT US2024 042803, International Preliminary Report on Patentability mailed Jul. 18, 2025”, 4 pages. [cited by applicant]
“U.S. Appl. No. 19/263,111, Preliminary Amendment Filed Sep. 29, 2025”, 6 pages. [cited by applicant]
“U.S. Appl. No. 18/582,262, Notice of Allowance mailed Apr. 9, 2025”, 10 pages. [cited by applicant]
“U.S. Appl. No. 18/582,262, Notice of Allowance mailed Nov. 27, 2024”, 11 pgs. [cited by applicant]
“[2211.01910] Large Language Models Are Human-Level Prompt Engineers”, arXivLabs, [Online]. Retrieved from the Internet: URL: https: arxiv.org abs 2211.01910, (2022), 4 pgs. [cited by applicant]
Kollar, Jan, “Data-driven Executable Language Model”, Proceedings of the International Multiconference on Computer Science and Information Techology. Technical University of Ko″sice Department of Computers and Informati… [cited by applicant]
Zhou, Yongchao, “Large Language Models Are Human-Level Prompt Engineers”, ICLR. arXiv:2211.01910v2, (2023), 43 pgs. [cited by applicant]
“U.S. Appl. No. 18/452,496, Notice of Allowance mailed Nov. 1, 2023”, 11 pgs. [cited by applicant]
“U.S. Appl. No. 18/452,496, Notice of Allowance mailed Feb. 15, 2024”, 11 pgs. [cited by applicant]
“U.S. Appl. No. 18/452,496, 312 Amendment filed Feb. 20, 2024”, 6 pgs. [cited by applicant]
“U.S. Appl. No. 18/452,496, PTO Response to Rule 312 Communication mailed Mar. 5, 2024”, 2 pgs. [cited by applicant]
“International Application Serial No. PCT US2024 042803, International Search Report mailed Sep. 10, 2024”, 2 pgs. [cited by applicant]
“International Application Serial No. PCT US2024 042803, Written Opinion mailed Sep. 10, 2024”, 3 pgs. [cited by applicant]
Genesys, “How Generative Al is used in Genesys Agent Assist”, Retrieved Online. URL: https: developer.genesys.cloud blog 2023-05-08-generative-AI-in-agent-assist , (May 8, 2023), 3 pgs. [cited by applicant]
Liane, Makatura, “How Can Large Language Models Help Humans in Design And Manufacturing?”, Michael Foshey, (2023), 100 pgs. [cited by applicant]
Munro, Jillian, “Effortlessly Summarize Phone Conversations with AmazonChime SDK Call Analytics: Step-by-Step Guide”, Retrieved online. URL: https: aws.amazon.com blogs business-productivity effortlessly-summarize-phone… [cited by applicant]
Suleiman, Dima, “Deep Learning Based Abstractive Text Summarization: Approaches, Datasets, Evaluation Measures, and Challenges”, Mathematical Problems in Engineering, vol. 2020, Article ID 9365340, (Aug. 24, 2020), 29 p… [cited by applicant]
Wiens, Vitalis, “Semantic Zooming for Ontology Graph Visualizations”, K-CAP '17: Proceedings of the 9th Knowledge Capture Conference, Article No. 4, (Dec. 2017), 8 pgs. [cited by applicant]