IP Library › Granted Patent US 12,602,435
Granted Patent B1
US 12,602,435 · App. 18/962,807 · Granted Apr 14, 2026

Providing customized services to users of data processing systems

Inventors: Tsehsin Jason Liu (Wellesley, MA); Amihai Savir (Newton, MA); Ofir Ezrielev (Be'er Sheva, IL)
Assignee: Dell Products L.P.
G06F16/90335
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 12,602,435
App. No.
18/962,807
Granted
Apr 14, 2026
Kind
B1
Abstract

Methods and systems for providing customized services to users of data processing systems are disclosed. To provide the customized services, a query may be obtained from a user. Contextual information for the query may be attempted to be obtained from a first data source associated with the user. If at least a first portion of the contextual information is unable to be obtained from the first data source, at least one other user may be identified based on the user. A second data source may be identified that is associated with the at least one other user. The at least the first portion of the contextual information may be attempted to be obtained from the second data source. The query may be serviced using at least the first portion of the contextual information and any other information obtained from the first data source.

Claims (91)

1 . A method for providing customized services to users of data processing systems, the method comprising:

obtaining a query from a user of the users;

attempting, based on the query, to obtain contextual information for the query from a first data source associated with the user, the first data source comprising first content ascribed a predetermined level of importance by the user;

in a first instance of the attempting where at least a first portion of the contextual information is unable to be obtained from the first data source:

identifying at least one other user based on the user;

identifying a second data source associated with the at least one other user, the second data source comprising second content ascribed the predetermined level of the importance by the at least one other user;

attempting, based on the at least the first portion of the contextual information, to obtain the at least the first portion of the contextual information for the query from the second data source; and

servicing the query using the at least the first portion of the contextual information and any other information obtained from the first data source during the attempting to obtain the contextual information for the query from the first data source.

2 . The method of claim 1 , wherein attempting to obtain the contextual information for the query from the first data source comprises:

comparing information obtained from the first data source to criteria, the criteria comprising a level of enhancement threshold to allow the query to be serviced in a manner that is acceptable to the user;

in a first instance of the comparing in which the information meets the criteria:

concluding that the contextual information is able to be obtained from the first data source;

servicing the query using the contextual information; and

in a second instance of the comparing in which the information does not meet the criteria:

concluding that the at least the first portion of the contextual information is unable to be obtained from the first data source.

3 . The method of claim 1 , wherein identifying the at least one other user based on the user comprises:

obtaining first characteristics for the user; and

performing, using the first characteristics and similarity criteria, a user matching process to identify the at least one other user, the at least one other user having second characteristics that meet the similarity criteria.

4 . The method of claim 3 , wherein the first characteristics comprise at least one type of characteristic selected from a list of types of characteristics consisting of:

a job title for the user;

job duties for the user;

a job division for the user; and

a job ranking for the user.

5 . The method of claim 1 , wherein the first data source is managed by a first personal agent assigned to the user, and the second data source is managed by a second personal agent assigned to the at least one other user.

6 . The method of claim 5 , wherein attempting to obtain the at least the first portion of the contextual information for the query from the second data source comprises:

initiating interactions, by the first personal agent, with the second personal agent to attempt to obtain the at least the first portion of the contextual information; and

in an instance of the attempting to obtain the at least the first portion of the contextual information for the query from the second data source in which the at least the first portion of the contextual information is unable to be obtained from the second data source:

providing the query to a second user that is likely to have a knowledge base usable to service the query.

7 . The method of claim 1 , wherein servicing the query comprises:

obtaining, using the query, the at least the first portion of the contextual information, and the any other information, an ingest data package for an inference model;

initiating generation of a response by the inference model using the ingest data package; and

providing the response to the user as a customized service.

8 . The method of claim 7 , wherein the ingest data package is a retrieval-augmented generation (RAG) output from a RAG pipeline process, and the inference model is a large language model (LLM).

9 . A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations for providing customized services to users of data processing systems, the operations comprising:

obtaining a query from a user of the users;

attempting, based on the query, to obtain contextual information for the query from a first data source associated with the user, the first data source comprising first content ascribed a predetermined level of importance by the user;

in a first instance of the attempting where at least a first portion of the contextual information is unable to be obtained from the first data source:

identifying at least one other user based on the user;

identifying a second data source associated with the at least one other user, the second data source comprising second content ascribed the predetermined level of the importance by the at least one other user;

attempting, based on the at least the first portion of the contextual information, to obtain the at least the first portion of the contextual information for the query from the second data source; and

servicing the query using the at least the first portion of the contextual information and any other information obtained from the first data source during the attempting to obtain the contextual information for the query from the first data source.

10 . The non-transitory machine-readable medium of claim 9 , wherein attempting to obtain the contextual information for the query from the first data source comprises:

comparing information obtained from the first data source to criteria, the criteria comprising a level of enhancement threshold to allow the query to be serviced in a manner that is acceptable to the user;

in a first instance of the comparing in which the information meets the criteria:

concluding that the contextual information is able to be obtained from the first data source;

servicing the query using the contextual information; and

in a second instance of the comparing in which the information does not meet the criteria:

concluding that the at least the first portion of the contextual information is unable to be obtained from the first data source.

11 . The non-transitory machine-readable medium of claim 9 , wherein identifying the at least one other user based on the user comprises:

obtaining first characteristics for the user; and

performing, using the first characteristics and similarity criteria, a user matching process to identify the at least one other user, the at least one other user having second characteristics that meet the similarity criteria.

12 . The non-transitory machine-readable medium of claim 11 , wherein the first characteristics comprise at least one type of characteristic selected from a list of types of characteristics consisting of:

a job title for the user;

job duties for the user;

a job division for the user; and

a job ranking for the user.

13 . The non-transitory machine-readable medium of claim 9 , wherein the first data source is managed by a first personal agent assigned to the user, and the second data source is managed by a second personal agent assigned to the at least one other user.

14 . The non-transitory machine-readable medium of claim 13 , wherein attempting to obtain the at least the first portion of the contextual information for the query from the second data source comprises:

initiating interactions, by the first personal agent, with the second personal agent to attempt to obtain the at least the first portion of the contextual information; and

in an instance of the attempting to obtain the at least the first portion of the contextual information for the query from the second data source in which the at least the first portion of the contextual information is unable to be obtained from the second data source:

providing the query to a second user that is likely to have a knowledge base usable to service the query.

15 . A data processing system, comprising:

a processor; and

a memory coupled to the processor to store instructions, which when executed by the processor, cause the processor to perform operations for providing customized services to users of data processing systems, the operations comprising:

obtaining a query from a user of the users;

attempting, based on the query, to obtain contextual information for the query from a first data source associated with the user, the first data source comprising first content ascribed a predetermined level of importance by the user;

in a first instance of the attempting where at least a first portion of the contextual information is unable to be obtained from the first data source:

identifying at least one other user based on the user;

identifying a second data source associated with the at least one other user, the second data source comprising second content ascribed the predetermined level of the importance by the at least one other user;

attempting, based on the at least the first portion of the contextual information, to obtain the at least the first portion of the contextual information for the query from the second data source; and

servicing the query using the at least the first portion of the contextual information and any other information obtained from the first data source during the attempting to obtain the contextual information for the query from the first data source.

16 . The data processing system of claim 15 , wherein attempting to obtain the contextual information for the query from the first data source comprises:

comparing information obtained from the first data source to criteria, the criteria comprising a level of enhancement threshold to allow the query to be serviced in a manner that is acceptable to the user;

in a first instance of the comparing in which the information meets the criteria:

concluding that the contextual information is able to be obtained from the first data source;

servicing the query using the contextual information; and

in a second instance of the comparing in which the information does not meet the criteria:

concluding that the at least the first portion of the contextual information is unable to be obtained from the first data source.

17 . The data processing system of claim 15 , wherein identifying the at least one other user based on the user comprises:

obtaining first characteristics for the user; and

performing, using the first characteristics and similarity criteria, a user matching process to identify the at least one other user, the at least one other user having second characteristics that meet the similarity criteria.

18 . The data processing system of claim 17 , wherein the first characteristics comprise at least one type of characteristic selected from a list of types of characteristics consisting of:

a job title for the user;

job duties for the user;

a job division for the user; and

a job ranking for the user.

19 . The data processing system of claim 15 , wherein the first data source is managed by a first personal agent assigned to the user, and the second data source is managed by a second personal agent assigned to the at least one other user.

20 . The data processing system of claim 19 , wherein attempting to obtain the at least the first portion of the contextual information for the query from the second data source comprises:

initiating interactions, by the first personal agent, with the second personal agent to attempt to obtain the at least the first portion of the contextual information; and

in an instance of the attempting to obtain the at least the first portion of the contextual information for the query from the second data source in which the at least the first portion of the contextual information is unable to be obtained from the second data source:

providing the query to a second user that is likely to have a knowledge base usable to service the query.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 9, 2024
From: LIU, TSEHSIN JASON; SAVIR, AMIHAI; EZRIELEV, OFIR
To: DELL PRODUCTS L.P.
Reel/Frame 069526/0456 →
References Cited (33)
US 12406013B1 · Nadig · 2025 [cited by examiner]
US 20050060417A1 · Rose · 2005 [cited by applicant]
US 20090276419A1 · Jones · 2009 [cited by examiner]
US 20160378941A1 · Pastuszak · 2016 [cited by applicant]
US 20180052925A1 · Cohn · 2018 [cited by examiner]
US 20200192928A1 · Arar · 2020 [cited by applicant]
US 20200218770A1 · Tu · 2020 [cited by examiner]
US 20200272664A1 · Aggour · 2020 [cited by applicant]
US 20210182709A1 · Manchanda · 2021 [cited by applicant]
US 20240029262A1 · Ezrielev · 2024 [cited by applicant]
US 20240143545A1 · Brenner · 2024 [cited by applicant]
US 20250111246A1 · Casini · 2025 [cited by applicant]
US 20250117412A1 · Jalagam · 2025 [cited by applicant]
US 20250118417A1 · Chong · 2025 [cited by applicant]
US 20250342168A1 · Masih · 2025 [cited by applicant]
WO 2024015321A1 · 2024 [cited by applicant]
Guo, Xudong, et al. “Embodied llm agents learn to cooperate in organized teams.” arXiv preprint arXiv:2403.12482 (2024). [cited by applicant]
Sinha, Pallavi, “Understanding LLM-Based Agents and their Multi-Agent Architecture,” Medium, May 1, 2024, Web Page <https://medium.com/@pallavisinha12/understanding-llm-based-agents-and-their-multi-agent-architecture-29… [cited by applicant]
Liu, Jiawen, et al. “PeerGPT: Probing the Roles of LLM-based Peer Agents as Team Moderators and Participants in Children's Collaborative Learning.” Extended Abstracts of the CHI Conference on Human Factors in Computing … [cited by applicant]
Chuang, Yun-Shiuan, et al. “Beyond demographics: aligning role-playing LLM-based agents using human belief networks.” arXiv preprint arXiv:2406.17232 (2024). [cited by applicant]
Wang, Lei, et al. “A survey on large language model based autonomous agents.” Frontiers of Computer Science 18.6 (2024): 186345. [cited by applicant]
Zong, Chang, et al. “Triad: A Framework Leveraging a Multi-Role LLM-based Agent to Solve Knowledge Base Question Answering.” arXiv preprint arXiv:2402.14320 (2024). [cited by applicant]
Cheng, Yuheng, et al. “Exploring large language model based intelligent agents: Definitions, methods, and prospects.” arXiv preprint arXiv:2401.03428 (2024). [cited by applicant]
“Azure Storage redundancy,” Microsoft, Jan. 19, 2024, Web Page <https://learn.microsoft.com/en-us/azure/storage/common/storage-redundancy> accessed on Nov. 26, 2024. [cited by applicant]
Chen, Jou-An, et al. “Survey: Exploiting data redundancy for optimization of deep learning.” ACM Computing Surveys 55.10 (2023): 1-38. [cited by applicant]
Mayr, Philipp, and Vivien Petras. “Cross-concordances: terminology mapping and its effectiveness for information retrieval.” arXiv preprint arXiv:0806.3765 (2008). [cited by applicant]
Mayr, Philipp, and Vivien Petras. “Building a Terminology Network for Search: The KoMoHe Project.” Dublin Core Conference. 2008. [cited by applicant]
Schlangen, David. “LLMs as Function Approximators: Terminology, Taxonomy, and Questions for Evaluation.” arXiv preprint arXiv:2407.13744 (2024). [cited by applicant]
Purpura, Alberto, et al. “Automatic Mapping of Terminology Items with Transformers.” AMIA Annual Symposium Proceedings. vol. 2023. American Medical Informatics Association, 2023. [cited by applicant]
Zhang, Zhang, et al. “Intention recognition for multiple agents.” Information Sciences 628 (2023): 360-376. [cited by applicant]
Besta, Maciej, et al. “Graph of thoughts: Solving elaborate problems with large language models.” Proceedings of the AAAI Conference on Artificial Intelligence. vol. 38. No. 16. 2024. [cited by applicant]
“Record desktop flows,” Microsoft, Feb. 23, 2023, Web Page <https://learn.microsoft.com/en-us/power-automate/desktop-flows/recording-flow> accessed on Nov. 26, 2024. [cited by applicant]
Xi, Zhiheng, et al. “The rise and potential of large language model based agents: A survey.” arXiv preprint arXiv:2309.07864 (2023). [cited by applicant]