IP Library › Granted Patent US 12,411,888
Granted Patent B2
US 12,411,888 · App. 18/458,408 · Granted Sep 9, 2025

System and method for managing user accessibility based on data in a data management system

Inventors: Prem Pradeep Motgi (Austin, TX); Dharmesh M. Patel (Round Rock, TX); Manpreet Singh Sokhi (Santa Clara, CA)
Assignee: Dell Products L.P.
G06F16/65G06F3/167
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 12,411,888
App. No.
18/458,408
Granted
Sep 9, 2025
Kind
B2
Abstract

Methods and systems for managing user interactions between a user and at least one user device are disclosed. To manage user interactions, data management system may obtain an interaction model to deploy to the at least one user device in order to establish an interface. The interaction model may define how the at least one user device communicates information to the user and/or obtained user input from the user. To obtain the interaction model relevant to a user, data management system may identify at least one condition impacting an ability of the user to interact with the at least one user device and the extent of the condition limiting the user's ability to interact with the at least one user device.

Claims (60)

1. A method for managing user interactions between a user and at least one user device, the method comprising:

obtaining topic classifications and topic rankings for the topic classifications, the topic classifications and the topic rankings being used by a data management system to manage data relevant to the user;

performing an interaction management process to generate an interaction model that is customized solely for the user using:

a sensory impairment of the user that limits an ability of the user to interact with the at least one user device,

the topic classifications, and

the topic rankings, wherein the topic rankings are based at least on a magnitude of the sensory impairment of the user and are used to determine a rank order the topic classifications, the magnitude of the sensory impairment being determined based at least on detection of one or more polarity shifts between positive and negative sentiments towards one or more topics related to the sensory impairment discussed within a conversation between the user and a second individual; and

deploying the interaction model to the at least one user device with instructions for the at least one user device to implement the interaction model, wherein implementation of the interaction model by the at least one user device causes the at least one user device to adjust how the at least one user device communicates information to the user and obtains user input from the user in a manner that improves the ability of the user to interact with the at least one user device in view of the sensory impairment, the adjusting by the at least one user device of how the at least one user device communicates information to the user is based on the magnitude of the sensory impairment.

2. The method of claim 1 , wherein the topic classifications and the topic rankings are based at least in part on an audio transcript, the audio transcript being based on an audio file, and the audio file comprising audio data of the conversation.

3. The method of claim 2 , wherein the topic classifications comprise an enumeration of each unique topic of topics discussed within the conversation, the topics comprise the one or more topics related to the sensory impairment, and the second individual provides at least one service to the user.

4. The method of claim 1 , wherein the performing of the interaction management process comprises:

identifying the sensory impairment for the user using the topic classifications, the sensory impairment limiting the ability of the user to interact with the at least one user device using a default interface;

obtaining an accessibility quantification for the user using the topic rankings, the accessibility quantification indicating an extent to which the user is limited in their ability to interact with the at least one user device using the default interface;

identifying at least one accessibility feature of the at least one user device based on the sensory impairment;

selecting an extent of change for use of the at least one accessibility feature based on the accessibility quantification; and

populating the interaction model at least in part using the at least one accessibility feature and the extent of the change.

5. The method of claim 1 , wherein the deploying of the interaction model comprises:

establishing, using the interaction model, an interface of the at least one user device for the user that is customized to at least one condition associated with the sensory impairment that impacts the ability of the user to interact with the at least one user device.

6. The method of claim 5 , further comprising:

communicating information from the at least one user device to the user via the interface, the interface being a medium to translate the information between two different systems of representation, the two different systems of representation comprising different forms of communicating the information.

7. The method of claim 6 , wherein the communicating of the information to the user comprises:

providing a portion of data, using the interface, from the at least one user device to the user, the interface being a graphical user interface to communicate the portion of data through a visual interaction with the user.

8. The method of claim 7 , wherein the communicating of the information to the user further comprises:

selecting a characteristic of characteristics of the graphical user interface based on the topic classifications, the characteristics of the graphical user interface comprising font size, display regions, display icons, color palettes, and/or any other characteristics of the graphical user interface; and

adjusting the selected characteristic of the graphical user interface based on the topic rankings to improve the visual interaction between the at least one user device and the user.

9. The method of claim 6 , wherein the communicating of the information to the user comprises:

providing a portion of data, using the interface, from the at least one user device to the user, the interface being an auditory interface to communicate the portion of data through an auditory interaction with the user.

10. The method of claim 9 , wherein the communicating of the information to the user further comprises:

selecting a characteristic of characteristics of the auditory interface based on the topic classifications, the characteristics of the auditory interface comprising speech recognition, non-speech audio cues, audio volume, text-to-speech, and/or any other characteristics of the auditory interface; and

adjusting the selected characteristic of the auditory interface based on the topic rankings to improve the auditory interaction between the at least one user device and the user.

11. A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations for managing user interactions between a user and at least one user device, the operations comprising:

obtaining topic classifications and topic rankings for the topic classifications, the topic classifications and the topic rankings being used by a data management system to manage data relevant to the user;

performing an interaction management process to generate an interaction model that is customized solely for the user using:

a sensory impairment of the user that limits an ability of the user to interact with the at least one user device,

the topic classifications, and

the topic rankings, wherein the topic rankings are based at least on a magnitude of the sensory impairment of the user and are used to determine a rank order the topic classifications, the magnitude of the sensory impairment being determined based at least on detection of one or more polarity shifts between positive and negative sentiments towards one or more topics related to the sensory impairment discussed within a conversation between the user and a second individual; and

deploying the interaction model to the at least one user device with instructions for the at least one user device to implement the interaction model, wherein implementation of the interaction model by the at least one user device causes the at least one user device to adjust how the at least one user device communicates information to the user and obtains user input from the user in a manner that improves the ability of the user to interact with the at least one user device in view of the sensory impairment, the adjusting by the at least one user device of how the at least one user device communicates information to the user is based on the magnitude of the sensory impairment.

12. The non-transitory machine-readable medium of claim 11 , wherein the topic classifications and the topic rankings are based at least in part on an audio transcript, the audio transcript being based on an audio file, and the audio file comprising audio data of the conversation.

13. The non-transitory machine-readable medium of claim 12 , wherein the topic classifications comprise an enumeration of each unique topic of topics discussed within the conversation, the topics comprise the one or more topics related to the sensory impairment, and the second individual provides at least one service to the user.

14. The non-transitory machine-readable medium of claim 11 , wherein the performing of the interaction management process comprises:

identifying sensory impairment for the user using the topic classifications, the sensory impairment limiting an ability of the user to interact with the at least one user device using a default interface;

obtaining an accessibility quantification for the user using the topic rankings, the accessibility quantification indicating an extent to which the user is limited in their ability to interact with the at least one user device using the default interface;

identifying at least one accessibility feature of the at least one user device based on the sensory impairment;

selecting an extent of change for use of the at least one accessibility feature based on the accessibility quantification; and

populating the interaction model at least in part using the at least one accessibility feature and the extent of the change.

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 managing user interactions between a user and at least one user device, the operations comprising:

obtaining topic classifications and topic rankings for the topic classifications, the topic classifications and the topic rankings being used by a data management system to manage data relevant to the user;

performing an interaction management process to generate an interaction model that is customized solely for the user using:

a sensory impairment of the user that limits an ability of the user to interact with the at least one user device,

the topic classifications, and

the topic rankings, wherein the topic rankings are based at least on a magnitude of the sensory impairment of the user and are used to determine a rank order the topic classifications, the magnitude of the sensory impairment being determined based at least on detection of one or more polarity shifts between positive and negative sentiments towards one or more topics related to the sensory impairment discussed within a conversation between the user and a second individual; and

deploying the interaction model to the at least one user device with instructions for the at least one user device to implement the interaction model, wherein implementation of the interaction model by the at least one user device causes the at least one user device to adjust how the at least one user device communicates information to the user and obtains user input from the user in a manner that improves the ability of the user to interact with the at least one user device in view of the sensory impairment, the adjusting by the at least one user device of how the at least one user device communicates information to the user is based on the magnitude of the sensory impairment.

16. The data processing system of claim 15 , wherein the topic classifications and the topic rankings are based at least in part on an audio transcript, the audio transcript being based on an audio file, and the audio file comprising audio data of the conversation.

17. The data processing system of claim 16 , wherein the topic classifications comprise an enumeration of each unique topic of topics discussed within the conversation, the topics comprise the one or more topics related to the sensory impairment, and the second individual provides at least one service to the user.

18. The method of claim 1 , wherein the performing of the interaction management process comprises, at least, using only the topic classifications to automatically identify the sensory impairment of the user without direct input of the sensory impairment and information related to the sensory impairment by the user and without direct input of the sensory impairment and the information related to the sensory impairment by another individual on behalf of the user.

19. The non-transitory machine-readable medium of claim 11 , wherein the deploying of the interaction model comprises:

establishing, using the interaction model, an interface of the at least one user device for the user that is customized to at least one condition associated with the sensory impairment that impacts the ability of the user to interact with the at least one user device.

20. The data processing system of claim 15 , wherein the deploying of the interaction model comprises:

establishing, using the interaction model, an interface of the at least one user device for the user that is customized to at least one condition associated with the sensory impairment that impacts the ability of the user to interact with the at least one user device.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 8, 2023
From: MOTGI, PREM PRADEEP; PATEL, DHARMESH M.; SOKHI, MANPREET SINGH
To: DELL PRODUCTS L.P.
Reel/Frame 064844/0900 →
Continuity (1)
Related Publication 20250077575A1 · Mar 6, 2025
References Cited (107)
US 5649060A · Ellozy et al. · 1997 [cited by applicant]
US 6606620B1 · Sundaresan · 2003 [cited by applicant]
US 8117235B1 · Barta · 2012 [cited by applicant]
US 8255386B1 · Annau et al. · 2012 [cited by applicant]
US 8255948B1 · Black et al. · 2012 [cited by applicant]
US 8335688B2 · Yegnanarayanan et al. · 2012 [cited by applicant]
US 8412521B2 · Mathias et al. · 2013 [cited by applicant]
US 8495720B2 · Counterman · 2013 [cited by applicant]
US 9031839B2 · Thorsen et al. · 2015 [cited by applicant]
US 9361428B2 · Bessette · 2016 [cited by applicant]
US 9571890B1 · Diamondstein · 2017 [cited by applicant]
US 9781097B2 · Grajek et al. · 2017 [cited by applicant]
US 10042993B2 · Beigi · 2018 [cited by applicant]
US 10073948B2 · Cohen et al. · 2018 [cited by applicant]
US 10157275B1 · Venkatasamy et al. · 2018 [cited by applicant]
US 10462142B2 · Pattar et al. · 2019 [cited by applicant]
US 10701056B2 · Murthy · 2020 [cited by applicant]
US 10896681B2 · Aleksic et al. · 2021 [cited by applicant]
US 10904237B2 · Murthy et al. · 2021 [cited by applicant]
US 11010392B1 · Hirsch et al. · 2021 [cited by applicant]
US 11094402B2 · Brown et al. · 2021 [cited by applicant]
US 11217331B2 · Vishnubhatla et al. · 2022 [cited by applicant]
US 11405189B1 · Bennison · 2022 [cited by applicant]
US 11631401B1 · Nudd · 2023 [cited by examiner]
US 11763821B1 · McNair · 2023 [cited by examiner]
US 11849069B1 · Can · 2023 [cited by examiner]
US 12135708B2 · Chermside · 2024 [cited by applicant]
US 20030046401A1 · Abbott · 2003 [cited by examiner]
US 20050160166A1 · Kraenzel · 2005 [cited by applicant]
US 20080154961A1 · Dougall · 2008 [cited by applicant]
US 20080275701A1 · Wu et al. · 2008 [cited by applicant]
US 20090171692A1 · Zilberman · 2009 [cited by examiner]
US 20100169304A1 · Hendricksen et al. · 2010 [cited by applicant]
US 20110131174A1 · Birch et al. · 2011 [cited by applicant]
US 20120265771A1 · Suh · 2012 [cited by applicant]
US 20140181673A1 · Work · 2014 [cited by examiner]
US 20140201199A1 · Hajaj · 2014 [cited by applicant]
US 20140207885A1 · Baker et al. · 2014 [cited by applicant]
US 20140344288A1 · Evans · 2014 [cited by applicant]
US 20150169574A1 · Bau et al. · 2015 [cited by applicant]
US 20150199268A1 · Davis et al. · 2015 [cited by applicant]
US 20150356127A1 · Pierre et al. · 2015 [cited by applicant]
US 20160006839A1 · Sawazaki · 2016 [cited by applicant]
US 20160164813A1 · Anderson · 2016 [cited by examiner]
US 20160231928A1 · Lewis et al. · 2016 [cited by applicant]
US 20160232159A1 · Parikh · 2016 [cited by applicant]
US 20160306812A1 · McHenry et al. · 2016 [cited by applicant]
US 20160378760A1 · Braz · 2016 [cited by applicant]
US 20170013047A1 · Hubbard · 2017 [cited by applicant]
US 20170262164A1 · Jain · 2017 [cited by examiner]
US 20170365101A1 · Samec · 2017 [cited by examiner]
US 20180024845A1 · Card · 2018 [cited by examiner]
US 20180121502A1 · Prieur · 2018 [cited by applicant]
US 20180189352A1 · Ghafourifar · 2018 [cited by examiner]
US 20180203612A1 · Kats et al. · 2018 [cited by applicant]
US 20190012931A1 · Candelore · 2019 [cited by examiner]
US 20190279744A1 · Howley et al. · 2019 [cited by applicant]
US 20190297035A1 · Fox et al. · 2019 [cited by applicant]
US 20190325036A1 · Edge · 2019 [cited by applicant]
US 20200110882A1 · Ripolles Mateu et al. · 2020 [cited by applicant]
US 20200226216A1 · Marin et al. · 2020 [cited by applicant]
US 20200258516A1 · Khaleghi · 2020 [cited by examiner]
US 20210056131A1 · Ackermann et al. · 2021 [cited by applicant]
US 20210065203A1 · Billigmeier et al. · 2021 [cited by applicant]
US 20210256534A1 · An · 2021 [cited by applicant]
US 20210390196A1 · Lavine et al. · 2021 [cited by applicant]
US 20220027859A1 · Daga · 2022 [cited by applicant]
US 20220261152A1 · Jude et al. · 2022 [cited by applicant]
US 20220293087A1 · Kumar · 2022 [cited by applicant]
US 20220334719A1 · Thrane · 2022 [cited by applicant]
US 20220366131A1 · Ekron · 2022 [cited by examiner]
US 20230058470A1 · Chandrashekar et al. · 2023 [cited by applicant]
US 20230061725A1 · Khan · 2023 [cited by applicant]
US 20230068099A1 · Abramenko · 2023 [cited by examiner]
US 20230137931A1 · Song · 2023 [cited by applicant]
US 20230221911A1 · Bandameedipalli · 2023 [cited by examiner]
US 20240112597A1 · Kim · 2024 [cited by examiner]
US 20240248592A1 · Zerhusen · 2024 [cited by examiner]
CN 202058147U · 2011 [cited by applicant]
CN 115292285A · 2022 [cited by applicant]
JP 4808173B2 · 2011 [cited by applicant]
JP 2015106406A · 2015 [cited by applicant]
WO 2023220948A1 · 2023 [cited by applicant]
D. Fedasyuk and I. Lutsyk, “Tools for adaptation of a mobile application to the needs of users with cognitive impairments,” 2021 IEEE 16th International Conference on Computer Sciences and Information Technologies (CSIT… [cited by examiner]
Balaskas, Georgios, et al., “An end-to-end system for transcription, translation, and summarization to support the co-creation process. A Health Cascade Study”, ACM Petra '23, published Aug. 10, 2023, pp. 625-631. (Year… [cited by applicant]
“FollowMyHealth®,” Allscripts Healthcare Solutions Inc, Google Play Store, Web Page <https://play.google.com/store/apps/details?id=com.jardogs.fmhmobile&hl=en_US&gl=US> accesed on Jan. 8, 2023 (4 Pages). [cited by applicant]
Page, Sébastien, “How to move your Health data from one iPhone to another,” iDB, Web Page <https://www.idownloadblog.com/2016/10/13/health-data-importer-makes-moving-your-health-data-from-one-iphone-to-another-a-breeze/… [cited by applicant]
“MyChart,” Web Page <https://www.mychart.org/> accessed on Oct. 30, 2022 (6 Pages). [cited by applicant]
Xu, Jie et al., “Federated learning for healthcare informatics,” Journal of Healthcare Informatics Research 5 (2021): 1-19. (19 Pages). [cited by applicant]
Naz, Sadaf et al., “A comprehensive review of federated learning for COVID-19 detection,” International Journal of Intelligent Systems 37.3 (2022):2371-2392. (22 Pages). [cited by applicant]
Prasser, Fabian, et al., “Efficient and effective pruning strategies for health data de-identification,” BMC medical informatics and decision making 16.1 (2016): 1-14. (14 Pages). [cited by applicant]
“Speech Recognition,” Web Accessibility Initiative. Web Page <https://www.w3.org/WAI/perspective-videos/voice/> accessed on Aug. 30, 2023 (6 Pages). [cited by applicant]
“Text Size,” Web Accessibility Initiative. Web Page <https://www.w3.org/WAI/GL/low-vision-a11y-tf/wiki/Text_Size> accessed on Aug. 30, 2023 (5 Pages). [cited by applicant]
Mesko, Bertlan, “The Top 10 Health Chatbots,” The Medical Futurist, Aug. 1, 2023, Web Page <https://medicalfuturist.com/top-10-health-chatbots/> accessed on Aug. 30, 2023 (11 Pages). [cited by applicant]
Longoni, Chiara et al., “AI Can Outperform Doctors. So Why Don't Patients Trust It?” Harvard Business Review, Oct. 30, 2019, Web Page <https://hbr.org/2019/10/ai-can-outperform-doctors-so-why-dont-patients-trust-it> acc… [cited by applicant]
“Doctor Ai,” DDXRX, Web Page <https://www.ddxrx.com/> accessed on Aug. 30, 2023 (7 Pages). [cited by applicant]
“Multi-Factor Authentication and Voice Biometrics,” Voice Biometrics Group, Feb. 2021, Web Page <https://www.voicebiogroup.com/starting/multi-factor-authentication-and-voice-biometrics.html> accessed on Aug. 30, 2023 (6… [cited by applicant]
Wallace, Byron C et al. “Automatically annotating topics in transcripts of patient-provider interactions via machine learning.” Medical decision making : an international journal of the Society for Medical Decision Maki… [cited by applicant]
“Medical Transcription Analysis with Machine Learning—Doctor/Patient Conversation Demo,”Amazon Web Services, Jun. 16, 2021, Web Page <https://www.youtube.com/watch?v=f5HVIALG5g4> accessed on Aug. 30, 2023 (2 Pages). [cited by applicant]
Baxendale, Simran et al., “Performing medical transcription analysis with Amazon Transcribe Medical and Amazon Comprehend Medical,” Amazon Web Services, May 8, 2020, Web Page <https://aws.amazon.com/blogs/machine-learni… [cited by applicant]
Sullivan, Todd et al., “Speaker Identification and Geographical Region Prediction in Audio Reviews,” Department of Computer Science, Stanford University, 2023 (4 Pages). [cited by applicant]
“Finding Local Destinations with Siri's Regionally Specific Language Models for Speech Recognition,” Apple Machine Learning Research, Aug. 2018, Web Page <https://machinelearning.apple.com/research/regionally-specific-l… [cited by applicant]
Tyagi, Nemika et al., “Demystifying the Role of Natural Language Processing (NLP) in Smart City Applications: Background, Motivation, Recent Advances, and Future Research Directions.” Wireless Personal Communications 13… [cited by applicant]
Alozie, Emeka, “The AI Surgeon's Assistant: How Generative AI is Revolutionizing the Operating Room,” Apr. 20, 2023, Web Page <https://intuitivex.com/tpost/p7bhza9611-the-ai-surgeons-assistant-how-generative> accessed o… [cited by applicant]
Gaitan, Michelle, “Researchers at UTSA use artificial intelligence to improve cancer treatment,” University of Texas at San Antonio, Apr. 18, 2023, Web Page <https://www.utsa.edu/today/2023/04/story/researchers-use-arti… [cited by applicant]
Bohr, Adam et al., “The rise of artificial intelligence in healthcare applications.” Artificial Intelligence in Healthcare (2020): 25-60. doi:10.1016/B978-0-12-818438-7.00002-2 (37 Pages). [cited by applicant]
“Introducing Healthcare-Specific Large Language Models from John Snow Labs,” KDnuggets, Apr. 28, 2023, Web Page <https://www.kdnuggets.com/2023/04/john-snow-introducing-healthcare-specific-large-language-models-john-sno… [cited by applicant]